技术领域Technical Field
本申请涉及电路板功耗监控技术领域，尤其涉及一种蓝牙电路板自适应功耗管理方法及系统。The present application relates to the technical field of circuit board power consumption monitoring, and in particular to a method and system for adaptive power consumption management of a Bluetooth circuit board.
背景技术Background technique
随着便携式设备和可穿戴设备的普及，如何有效管理电路板上的能耗以延长设备的使用时间和优化性能成为了设计者面临的主要挑战之一。蓝牙技术作为一种广泛应用于各种便携设备的无线通讯技术，其电路板的功耗管理尤为关键，因为它直接影响到设备的运行效率和用户的使用体验。With the popularity of portable devices and wearable devices, how to effectively manage the energy consumption on the circuit board to extend the use time of the device and optimize the performance has become one of the main challenges faced by designers. As a wireless communication technology widely used in various portable devices, Bluetooth technology is particularly critical for the power consumption management of its circuit board, because it directly affects the operating efficiency of the device and the user experience.
传统的蓝牙电路板功耗管理多依赖于静态的电源管理策略，这些策略通常在设计时就已确定，并不根据设备的实际运行状态进行调整。这种方法在实际应用中往往无法应对动态变化的使用环境和操作需求，导致电能浪费严重或设备性能受限。例如，当设备处于低负载或待机状态时，传统的管理系统可能仍旧按照高负载状态供电，从而造成能源的不必要消耗。Traditional Bluetooth circuit board power management relies on static power management strategies, which are usually determined at design time and are not adjusted according to the actual operating status of the device. This approach often cannot cope with dynamically changing usage environments and operating requirements in actual applications, resulting in serious waste of power or limited device performance. For example, when the device is in low load or standby state, the traditional management system may still supply power according to the high load state, resulting in unnecessary energy consumption.
发明内容Summary of the invention
本申请提供了一种蓝牙电路板自适应功耗管理方法及系统，本申请实现了蓝牙电路板自适应功耗管理并且提高了多层电路板的功耗优化效果。The present application provides a method and system for adaptive power consumption management of a Bluetooth circuit board, which implements adaptive power consumption management of a Bluetooth circuit board and improves the power consumption optimization effect of a multi-layer circuit board.
第一方面，本申请提供了一种蓝牙电路板自适应功耗管理方法，所述蓝牙电路板自适应功耗管理方法包括：In a first aspect, the present application provides a method for adaptive power consumption management of a Bluetooth circuit board, the method comprising:
在多层电路板的不同层级设置功率转换器并进行实时功耗监测，得到第一功率转换器的第一功率数据集和第二功率转换器的第二功率数据集；Power converters are arranged at different levels of the multi-layer circuit board and real-time power consumption monitoring is performed to obtain a first power data set of the first power converter and a second power data set of the second power converter;
分别对所述第一功率数据集和所述第二功率数据集进行功率特征提取，得到第一功率特征集合和第二功率特征集合；Performing power feature extraction on the first power data set and the second power data set respectively to obtain a first power feature set and a second power feature set;
通过双重Q网络和PSO算法根据所述第一功率特征集合和所述第二功率特征集合创建所述多层电路板的全局功耗优化参数。A global power consumption optimization parameter of the multi-layer circuit board is created according to the first power feature set and the second power feature set by using a dual Q network and a PSO algorithm.
第二方面，本申请提供了一种蓝牙电路板自适应功耗管理系统，所述蓝牙电路板自适应功耗管理系统包括：In a second aspect, the present application provides a Bluetooth circuit board adaptive power consumption management system, the Bluetooth circuit board adaptive power consumption management system comprising:
监测模块，用于在多层电路板的不同层级设置功率转换器并进行实时功耗监测，得到第一功率转换器的第一功率数据集和第二功率转换器的第二功率数据集；A monitoring module, configured to set power converters at different levels of the multi-layer circuit board and perform real-time power consumption monitoring to obtain a first power data set of the first power converter and a second power data set of the second power converter;
提取模块，用于分别对所述第一功率数据集和所述第二功率数据集进行功率特征提取，得到第一功率特征集合和第二功率特征集合；An extraction module, configured to extract power features from the first power data set and the second power data set respectively to obtain a first power feature set and a second power feature set;
创建模块，用于通过双重Q网络和PSO算法根据所述第一功率特征集合和所述第二功率特征集合创建所述多层电路板的全局功耗优化参数。A creation module is used to create global power consumption optimization parameters of the multi-layer circuit board according to the first power feature set and the second power feature set through a dual Q network and a PSO algorithm.
本申请第三方面提供了一种计算机设备，包括：存储器和至少一个处理器，所述存储器中存储有指令；所述至少一个处理器调用所述存储器中的所述指令，以使得所述计算机设备执行上述的蓝牙电路板自适应功耗管理方法。The third aspect of the present application provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned Bluetooth circuit board adaptive power consumption management method.
本申请的第四方面提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述的蓝牙电路板自适应功耗管理方法。A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned Bluetooth circuit board adaptive power consumption management method.
本申请提供的技术方案中，通过在多层电路板的不同层级设置功率转换器并进行实时监测，能够精确地获取各层电路板的功耗数据。这种实时监测确保了能源利用的最大化效率，使设备能够根据当前的运行状态动态调整功率输出，从而降低无效的能耗和延长设备的电池寿命。应用主成分分析特征提取技术，有效地从原始电流和电压数据中提取关键特征。这种深入的数据分析方法帮助更准确地理解电路板在不同工作条件下的行为，为后续的功耗优化提供了数据支持。利用双重Q网络和PSO算法，此方法不仅能够创建高效的全局功耗优化参数，还可以通过算法动态调整和优化电路板的功耗配置。这种智能化的决策过程显著提高了电路板的能效，减少了因固定或过时的功耗配置引起的能源浪费。结合奖励反馈参数的计算与策略更新，此方法实现了一种自学习的功耗管理系统。通过持续的学习和调整，电路板可以不断地优化其功耗策略以适应环境变化和设备需求，提升整体的性能和效率。通过综合考虑各层电路板的功耗特征和优化执行策略，该方法能够在整个电路板级别上实施功耗管理，从而实现更为统一和协调的能源管理。这种全局视角的管理不仅提高了能效，还有助于保持设备的稳定性和可靠性，进而实现了蓝牙电路板自适应功耗管理并且提高了多层电路板的功耗优化效果。In the technical solution provided by the present application, by setting power converters at different levels of a multi-layer circuit board and performing real-time monitoring, the power consumption data of each layer of the circuit board can be accurately obtained. This real-time monitoring ensures the maximum efficiency of energy utilization, enabling the device to dynamically adjust the power output according to the current operating state, thereby reducing ineffective energy consumption and extending the battery life of the device. The principal component analysis feature extraction technology is applied to effectively extract key features from the original current and voltage data. This in-depth data analysis method helps to more accurately understand the behavior of the circuit board under different working conditions and provides data support for subsequent power consumption optimization. Using the dual Q network and PSO algorithm, this method can not only create efficient global power consumption optimization parameters, but also dynamically adjust and optimize the power consumption configuration of the circuit board through the algorithm. This intelligent decision-making process significantly improves the energy efficiency of the circuit board and reduces the energy waste caused by fixed or outdated power consumption configuration. Combined with the calculation of reward feedback parameters and strategy updates, this method implements a self-learning power consumption management system. Through continuous learning and adjustment, the circuit board can continuously optimize its power consumption strategy to adapt to environmental changes and equipment requirements, and improve overall performance and efficiency. By comprehensively considering the power consumption characteristics of each layer of the circuit board and optimizing the execution strategy, this method can implement power consumption management at the level of the entire circuit board, thereby achieving more unified and coordinated energy management. This global perspective management not only improves energy efficiency, but also helps maintain the stability and reliability of the device, thereby achieving adaptive power consumption management of the Bluetooth circuit board and improving the power consumption optimization effect of multi-layer circuit boards.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以基于这些附图获得其他的附图。In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.
图1为本申请实施例中蓝牙电路板自适应功耗管理方法的一个实施例示意图；FIG1 is a schematic diagram of an embodiment of a method for adaptive power consumption management of a Bluetooth circuit board in an embodiment of the present application;
图2为本申请实施例中蓝牙电路板自适应功耗管理系统的一个实施例示意图。FIG. 2 is a schematic diagram of an embodiment of a Bluetooth circuit board adaptive power consumption management system in an embodiment of the present application.
具体实施方式Detailed ways
本申请实施例提供了一种蓝牙电路板自适应功耗管理方法及系统。本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包括”或“具有”及其任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。The embodiment of the present application provides a method and system for adaptive power consumption management of a Bluetooth circuit board. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
为便于理解，下面对本申请实施例的具体流程进行描述，请参阅图1，本申请实施例中蓝牙电路板自适应功耗管理方法的一个实施例包括：For ease of understanding, the specific process of the embodiment of the present application is described below. Please refer to Figure 1. An embodiment of the Bluetooth circuit board adaptive power consumption management method in the embodiment of the present application includes:
步骤101、在多层电路板的不同层级设置功率转换器并进行实时功耗监测，得到第一功率转换器的第一功率数据集和第二功率转换器的第二功率数据集；Step 101, power converters are arranged at different levels of the multi-layer circuit board and real-time power consumption monitoring is performed to obtain a first power data set of a first power converter and a second power data set of a second power converter;
可以理解的是，本申请的执行主体可以为蓝牙电路板自适应功耗管理系统，还可以是终端或者服务器，具体此处不做限定。本申请实施例以服务器为执行主体为例进行说明。It is understandable that the execution subject of the present application can be a Bluetooth circuit board adaptive power consumption management system, or a terminal or a server, which is not limited here. The present application embodiment is described by taking a server as the execution subject as an example.
具体的，获取多层电路板中的顶层电路板、中层电路板和底层电路板，多层电路板用于蓝牙通信。为了有效管理这些层级的电源需求，在顶层电路板和中层电路板之间设置第一功率转换器，同时在中层电路板和底层电路板之间设置第二功率转换器，使得电源能够更精确地按需分配，优化整个系统的能效。进行实时的电流和电压监控。对于第一功率转换器，通过监控设备收集电流和电压的初始数据，得到第一初始电流数据和第一初始电压数据。通过第二功率转换器的监控得到第二初始电流数据和第二初始电压数据。为了从初始数据中提取有用的信息，采用主成分分析技术处理第一和第二的初始电流及电压数据。主成分分析能有效地从大量数据中提取主要特征，降低数据的复杂性同时保留最关键的信息。通过分析，得到更具有代表性的数据集，即第一目标电流数据和第一目标电压数据，以及第二目标电流数据和第二目标电压数据。基于提取出的目标数据计算功率数据集。使用第一目标电流数据和第一目标电压数据，计算第一功率转换器的第一功率数据集，这个数据集直接反映顶层和中层电路板之间在实际运行中的功耗情况。同样，使用第二目标电流数据和第二目标电压数据计算第二功率数据集，得到中层和底层电路板间的功耗状况。Specifically, a top circuit board, a middle circuit board and a bottom circuit board in a multi-layer circuit board are obtained, and the multi-layer circuit board is used for Bluetooth communication. In order to effectively manage the power requirements of these levels, a first power converter is set between the top circuit board and the middle circuit board, and a second power converter is set between the middle circuit board and the bottom circuit board, so that the power can be more accurately distributed on demand, and the energy efficiency of the entire system is optimized. Real-time current and voltage monitoring is performed. For the first power converter, the initial data of current and voltage are collected by a monitoring device to obtain the first initial current data and the first initial voltage data. The second initial current data and the second initial voltage data are obtained by monitoring the second power converter. In order to extract useful information from the initial data, the principal component analysis technology is used to process the first and second initial current and voltage data. Principal component analysis can effectively extract the main features from a large amount of data, reduce the complexity of the data while retaining the most critical information. Through analysis, a more representative data set is obtained, namely the first target current data and the first target voltage data, as well as the second target current data and the second target voltage data. The power data set is calculated based on the extracted target data. The first target current data and the first target voltage data are used to calculate the first power data set of the first power converter, which directly reflects the power consumption between the top and middle circuit boards in actual operation. Similarly, the second target current data and the second target voltage data are used to calculate the second power data set to obtain the power consumption between the middle and bottom circuit boards.
对第一和第二功率转换器监测到的初始电流数据和电压数据进行特征提取。从原始监测数据中提炼出关键的特征信息，如电流的峰值、谷值、平均值和波动率，电压的峰值、谷值、平均值和波动率。通过采用数据处理技术，例如信号处理算法，可以有效地从噪声中分离出有用的信号，确保所提取的特征具有代表性和实用性。对提取出的电流和电压特征进行线性特征变换，将多维数据转换为主要成分，简化后续的处理和分析。线性特征变换通常采用主成分分析方法，通过构建数据的协方差矩阵，提取出能够代表数据最大方差的成分，这些成分即为数据的主要特征向量。完成线性特征变换后，分别构建第一和第二电流以及电压的协方差矩阵。协方差矩阵的构建是为了分析不同特征之间的相关性，特征之间的相互关系可以提供如何优化和调整电路板性能的重要信息。通过计算特征向量的协方差，了解哪些特征是相关的，哪些是独立的。进行特征相关性计算，利用协方差矩阵评估各特征之间的相关性。通过计算，确定哪些特征对电流和电压的变化具有更大的影响。在特征相关性分析的基础上，计算出每个特征的权重，这些权重反映了各特征在电路功耗管理中的重要性。利用计算得到的特征权重对初步提取的电流和电压特征进行特征融合。通过加权平均的方式，将所有特征整合成一个综合的电流和电压数据，得到目标电流数据和目标电压数据。Feature extraction is performed on the initial current data and voltage data monitored by the first and second power converters. Key feature information is extracted from the original monitoring data, such as the peak value, valley value, average value and fluctuation rate of the current, and the peak value, valley value, average value and fluctuation rate of the voltage. By adopting data processing technology, such as signal processing algorithm, useful signals can be effectively separated from noise to ensure that the extracted features are representative and practical. Linear feature transformation is performed on the extracted current and voltage features to convert the multidimensional data into main components to simplify subsequent processing and analysis. Linear feature transformation usually adopts the principal component analysis method. By constructing the covariance matrix of the data, the components that can represent the maximum variance of the data are extracted. These components are the main eigenvectors of the data. After completing the linear feature transformation, the covariance matrices of the first and second currents and voltages are constructed respectively. The covariance matrix is constructed to analyze the correlation between different features. The relationship between the features can provide important information on how to optimize and adjust the performance of the circuit board. By calculating the covariance of the eigenvectors, it is understood which features are related and which are independent. Feature correlation calculation is performed, and the correlation between the features is evaluated using the covariance matrix. By calculation, determine which features have a greater impact on the changes in current and voltage. Based on the feature correlation analysis, calculate the weight of each feature, which reflects the importance of each feature in circuit power management. Use the calculated feature weights to perform feature fusion on the initially extracted current and voltage features. By weighted averaging, integrate all features into a comprehensive current and voltage data to obtain the target current data and target voltage data.
步骤102、分别对第一功率数据集和第二功率数据集进行功率特征提取，得到第一功率特征集合和第二功率特征集合；Step 102: extract power features from the first power data set and the second power data set respectively to obtain a first power feature set and a second power feature set;
具体的，对第一和第二功率数据集分别进行曲线拟合，得到描述电路板功耗随时间变化的第一功率曲线和第二功率曲线。采用数学模型如多项式回归或者非线性模型，确保曲线能够尽可能精确地反映实际的功耗数据。基于得到的功率曲线进行特征提取，从简化后的曲线中识别出关键的功率特征，例如峰值、平均功耗、波动幅度等。对第一功率曲线和第二功率曲线进行特征分析，得到第一初始功率特征和第二初始功率特征，这些特征反映了电路板各部分在能耗管理上的具体情况。对多个第一初始功率特征进行特征分类，得到多个第一高频功率特征和多个第一低频功率特征，并对多个第二初始功率特征进行特征分类，得到多个第二高频功率特征和多个第二低频功率特征。高频特征可能与电路板的瞬时反应和短期变化相关，而低频特征则可能反映更长期的能耗趋势和模式。分类帮助系统针对不同的功耗需求和性能预期，进行更有针对性的管理和优化。通过计算各个特征的权重，评估它们在整体功耗管理中的重要性，评估基于特征对电路板性能的影响程度。利用权重对高频和低频功率特征进行综合，形成最终的第一功率特征集合和第二功率特征集合。Specifically, the first and second power data sets are respectively subjected to curve fitting to obtain a first power curve and a second power curve describing the change of the power consumption of the circuit board over time. A mathematical model such as polynomial regression or a nonlinear model is used to ensure that the curve can reflect the actual power consumption data as accurately as possible. Feature extraction is performed based on the obtained power curve, and key power features such as peak value, average power consumption, fluctuation amplitude, etc. are identified from the simplified curve. Feature analysis is performed on the first power curve and the second power curve to obtain a first initial power feature and a second initial power feature, which reflect the specific situation of energy consumption management of each part of the circuit board. Feature classification is performed on multiple first initial power features to obtain multiple first high-frequency power features and multiple first low-frequency power features, and feature classification is performed on multiple second initial power features to obtain multiple second high-frequency power features and multiple second low-frequency power features. High-frequency features may be related to the instantaneous response and short-term changes of the circuit board, while low-frequency features may reflect longer-term energy consumption trends and patterns. Classification helps the system to perform more targeted management and optimization for different power consumption requirements and performance expectations. By calculating the weight of each feature, their importance in the overall power consumption management is evaluated, and the degree of influence of the feature on the performance of the circuit board is evaluated. The high-frequency and low-frequency power features are integrated using weights to form a final first power feature set and a second power feature set.
对第一高频功率特征和第一低频功率特征进行皮尔逊相关系数计算，明确不同特征之间的线性关系强度。皮尔逊相关系数提供了一种衡量两个变量线性相关程度的方法，其值介于-1和1之间，其中1表示完全正相关，-1表示完全负相关，0则意味着没有线性相关。类似地，对第二组高频和低频功率特征进行皮尔逊相关系数计算，得到第二皮尔逊相关系数。根据得到的皮尔逊相关系数设定各特征的权重值。高相关性的特征得到较高的权重值，因为这些特征在描述电路板的功耗行为时更为重要，确保特征集合的构建能够真实反映电路板在不同工作状态下的实际表现。使用所设定的特征权重对第一和第二组的高频和低频功率特征进行加权。每个特征将根据其权重值进行调整，以强化那些对电路板性能影响更大的特征的作用。将加权后的高频和低频功率特征合并，形成综合的第一功率特征集合和第二功率特征集合。这些特征集合包括了所有经过筛选和加权的关键功率特征，确保电路板的功耗优化策略既精确又适应性强，能够根据实际需求动态调整，以达到最优的能效。The Pearson correlation coefficient is calculated for the first high-frequency power feature and the first low-frequency power feature to clarify the strength of the linear relationship between different features. The Pearson correlation coefficient provides a method to measure the degree of linear correlation between two variables, and its value is between -1 and 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 means no linear correlation. Similarly, the Pearson correlation coefficient is calculated for the second set of high-frequency and low-frequency power features to obtain a second Pearson correlation coefficient. The weight value of each feature is set according to the obtained Pearson correlation coefficient. Features with high correlation receive higher weight values because these features are more important in describing the power consumption behavior of the circuit board, ensuring that the construction of the feature set can truly reflect the actual performance of the circuit board under different working conditions. The high-frequency and low-frequency power features of the first and second groups are weighted using the set feature weights. Each feature will be adjusted according to its weight value to strengthen the role of those features that have a greater impact on the performance of the circuit board. The weighted high-frequency and low-frequency power features are merged to form a comprehensive first power feature set and a second power feature set. These feature sets include all the key power features that have been screened and weighted, ensuring that the power consumption optimization strategy of the circuit board is both accurate and adaptable, and can be dynamically adjusted according to actual needs to achieve optimal energy efficiency.
步骤103、通过双重Q网络和PSO算法根据第一功率特征集合和第二功率特征集合创建多层电路板的全局功耗优化参数。Step 103: Create global power consumption optimization parameters of the multi-layer circuit board according to the first power feature set and the second power feature set by using a dual Q network and a PSO algorithm.
具体的，分别对第一功率特征集合和第二功率特征集合进行特征编码，得到第一功率特征向量和第二功率特征向量，将复杂的功率数据简化为更易于计算和分析的数学表达形式。通过双重Q网络分别对第一功率特征向量和第二功率特征向量进行功率优化执行策略分析。双重Q网络是一种强化学习算法，能够在保持学习过程中稳定性的同时，通过两个独立的学习路径避免过度估计。在这个过程中，双重Q网络通过学习和模拟不同的功耗管理策略，输出第一和第二功率转换器的初始功耗优化执行策略。这些策略基于实时数据和预先设定的目标，制定出最佳的功率调整方案。为了优化这些策略并确保它们在实际应用中的有效性，引入奖励反馈参数计算。通过对第一和第二功率转换器的操作结果进行评估，计算得到奖励反馈参数，这些参数反映了每种策略执行的效果和功耗节约的成效。根据这些反馈参数，双重Q网络可以更新其初始功耗优化执行策略，使之更加精准和高效。通过PSO算法，根据第一目标功耗优化执行策略和第二目标功耗优化执行策略对多层电路板进行功耗参数计算。PSO算法通过模拟鸟群的搜索行为，寻找最优解决方案，能够在全局参数空间中有效搜索，快速收敛到最优功耗管理策略。结合第一和第二目标功耗优化执行策略，PSO算法计算出多层电路板的全局功耗优化参数。这些参数考虑了各层电路板的独立需求，并通过全局优化确保整个系统的能效最大化。Specifically, the first power feature set and the second power feature set are feature encoded respectively to obtain the first power feature vector and the second power feature vector, and the complex power data is simplified into a mathematical expression form that is easier to calculate and analyze. The power optimization execution strategy analysis is performed on the first power feature vector and the second power feature vector respectively through the dual Q network. The dual Q network is a reinforcement learning algorithm that can avoid overestimation through two independent learning paths while maintaining stability during the learning process. In this process, the dual Q network outputs the initial power optimization execution strategy of the first and second power converters by learning and simulating different power management strategies. These strategies are based on real-time data and pre-set goals to formulate the best power adjustment plan. In order to optimize these strategies and ensure their effectiveness in practical applications, reward feedback parameter calculation is introduced. By evaluating the operation results of the first and second power converters, reward feedback parameters are calculated, which reflect the effect of each strategy execution and the effect of power saving. According to these feedback parameters, the dual Q network can update its initial power optimization execution strategy to make it more accurate and efficient. Through the PSO algorithm, the power consumption parameters of the multilayer circuit board are calculated according to the first target power optimization execution strategy and the second target power optimization execution strategy. The PSO algorithm simulates the search behavior of a flock of birds to find the optimal solution. It can effectively search in the global parameter space and quickly converge to the optimal power management strategy. Combining the first and second target power optimization execution strategies, the PSO algorithm calculates the global power optimization parameters of the multi-layer circuit board. These parameters take into account the independent needs of each layer of the circuit board and ensure the maximum energy efficiency of the entire system through global optimization.
通过PSO算法，根据第一目标功耗优化执行策略对第一功率转换器进行随机初始值生成，得到第一随机初始值集合，并根据第二目标功耗优化执行策略对第二功率转换器进行随机初始值生成，得到第二随机初始值集合。随机初始值集合为粒子群优化提供了必要的多样性基础，确保算法能探索到参数空间的广泛区域，从而避免局部最优解而错失更优的全局解。通过反向粒子传播算法，根据随机初始值集合构建第一和第二粒子种群。反向粒子传播算法起到了优化粒子位置和速度的作用，确保粒子群能够有效地朝向潜在的最优解区域迁移。每个粒子都代表一个可能的解决方案，而整个粒子种群则构成了解决方案的搜索空间。对第一和第二粒子种群进行种群分割，形成多个子粒子种群。细化搜索过程，提高搜索效率，使每个子种群能够在参数空间的特定区域进行更深入的探索。种群分割有助于精细管理资源，使得各子种群可以在不同的方向上自适应地调整搜索策略，从而更有效地找到优化参数。对每个子粒子种群进行适应度计算，评估各个粒子代表的解决方案对于功耗优化的效果。适应度计算基于如功耗减少程度、系统稳定性和性能效率等因素，确保只有最适合的解决方案才会被选作最终的优化策略，得到第一粒子适应度集合和第二粒子适应度集合。根据适应度集合，生成第一和第二功率转换器的功耗优化参数。这些参数基于之前计算得到的最优解决方案，旨在将整个电路板的功耗降到最低，同时保持系统的运行效率和稳定性。对第一功耗优化参数和第二功耗优化参数进行全局优化，整合所有优化得到的参数，形成多层电路板的全局功耗优化参数。Through the PSO algorithm, random initial values are generated for the first power converter according to the first target power consumption optimization execution strategy to obtain a first random initial value set, and random initial values are generated for the second power converter according to the second target power consumption optimization execution strategy to obtain a second random initial value set. The random initial value set provides the necessary diversity basis for particle swarm optimization, ensuring that the algorithm can explore a wide area of the parameter space, thereby avoiding the local optimal solution and missing the better global solution. Through the reverse particle propagation algorithm, the first and second particle populations are constructed according to the random initial value set. The reverse particle propagation algorithm plays a role in optimizing the position and speed of particles, ensuring that the particle swarm can effectively migrate toward the potential optimal solution area. Each particle represents a possible solution, and the entire particle population constitutes the search space for the solution. The first and second particle populations are divided into populations to form multiple sub-particle populations. The search process is refined, the search efficiency is improved, and each sub-population can conduct a deeper exploration in a specific area of the parameter space. Population division helps to finely manage resources, so that each sub-population can adaptively adjust the search strategy in different directions, so as to more effectively find the optimization parameters. The fitness of each sub-particle population is calculated to evaluate the effect of the solution represented by each particle on power consumption optimization. The fitness calculation is based on factors such as the degree of power consumption reduction, system stability, and performance efficiency to ensure that only the most suitable solution is selected as the final optimization strategy, and the first particle fitness set and the second particle fitness set are obtained. Based on the fitness set, the power consumption optimization parameters of the first and second power converters are generated. These parameters are based on the optimal solution calculated previously, and are intended to minimize the power consumption of the entire circuit board while maintaining the operating efficiency and stability of the system. The first power consumption optimization parameters and the second power consumption optimization parameters are globally optimized, and all optimized parameters are integrated to form the global power consumption optimization parameters of the multi-layer circuit board.
本申请实施例中，通过在多层电路板的不同层级设置功率转换器并进行实时监测，能够精确地获取各层电路板的功耗数据。这种实时监测确保了能源利用的最大化效率，使设备能够根据当前的运行状态动态调整功率输出，从而降低无效的能耗和延长设备的电池寿命。应用主成分分析特征提取技术，有效地从原始电流和电压数据中提取关键特征。这种深入的数据分析方法帮助更准确地理解电路板在不同工作条件下的行为，为后续的功耗优化提供了数据支持。利用双重Q网络和PSO算法，此方法不仅能够创建高效的全局功耗优化参数，还可以通过算法动态调整和优化电路板的功耗配置。这种智能化的决策过程显著提高了电路板的能效，减少了因固定或过时的功耗配置引起的能源浪费。结合奖励反馈参数的计算与策略更新，此方法实现了一种自学习的功耗管理系统。通过持续的学习和调整，电路板可以不断地优化其功耗策略以适应环境变化和设备需求，提升整体的性能和效率。通过综合考虑各层电路板的功耗特征和优化执行策略，该方法能够在整个电路板级别上实施功耗管理，从而实现更为统一和协调的能源管理。这种全局视角的管理不仅提高了能效，还有助于保持设备的稳定性和可靠性，进而实现了蓝牙电路板自适应功耗管理并且提高了多层电路板的功耗优化效果。In the embodiment of the present application, by setting power converters at different levels of a multi-layer circuit board and performing real-time monitoring, the power consumption data of each layer of the circuit board can be accurately obtained. This real-time monitoring ensures the maximum efficiency of energy utilization, enabling the device to dynamically adjust the power output according to the current operating state, thereby reducing ineffective energy consumption and extending the battery life of the device. The principal component analysis feature extraction technology is applied to effectively extract key features from the original current and voltage data. This in-depth data analysis method helps to more accurately understand the behavior of the circuit board under different working conditions and provides data support for subsequent power consumption optimization. Using the dual Q network and PSO algorithm, this method can not only create efficient global power consumption optimization parameters, but also dynamically adjust and optimize the power consumption configuration of the circuit board through the algorithm. This intelligent decision-making process significantly improves the energy efficiency of the circuit board and reduces the energy waste caused by fixed or outdated power consumption configuration. Combined with the calculation of reward feedback parameters and strategy updates, this method implements a self-learning power consumption management system. Through continuous learning and adjustment, the circuit board can continuously optimize its power consumption strategy to adapt to environmental changes and equipment requirements, and improve overall performance and efficiency. By comprehensively considering the power consumption characteristics of each layer of the circuit board and optimizing the execution strategy, this method can implement power consumption management at the level of the entire circuit board, thereby achieving more unified and coordinated energy management. This global perspective management not only improves energy efficiency, but also helps maintain the stability and reliability of the device, thereby achieving adaptive power consumption management of the Bluetooth circuit board and improving the power consumption optimization effect of multi-layer circuit boards.
在一具体实施例中，执行步骤101的过程可以具体包括如下步骤：In a specific embodiment, the process of executing step 101 may specifically include the following steps:
(1)获取多层电路板中的顶层电路板、中层电路板和底层电路板，多层电路板用于蓝牙通信；(1) obtaining a top-layer circuit board, a middle-layer circuit board, and a bottom-layer circuit board in a multi-layer circuit board, where the multi-layer circuit board is used for Bluetooth communication;
(2)在顶层电路板和中层电路板之间设置第一功率转换器，同时，在中层电路板和底层电路板之间设置第二功率转换器；(2) a first power converter is arranged between the top circuit board and the middle circuit board, and a second power converter is arranged between the middle circuit board and the bottom circuit board;
(3)对第一功率转换器进行电流和电压监控，得到第一初始电流数据和第一初始电压数据，并对第二功率转换器进行电流和电压监控，得到第二初始电流数据和第二初始电压数据；(3) monitoring the current and voltage of the first power converter to obtain first initial current data and first initial voltage data, and monitoring the current and voltage of the second power converter to obtain second initial current data and second initial voltage data;
(4)分别对第一初始电流数据和第一初始电压数据进行主成分特征解析，得到第一目标电流数据和第一目标电压数据，并分别对第二初始电流数据和第二初始电压数据进行主成分特征解析，得到第二目标电流数据和第二目标电压数据；(4) performing principal component feature analysis on the first initial current data and the first initial voltage data respectively to obtain first target current data and first target voltage data, and performing principal component feature analysis on the second initial current data and the second initial voltage data respectively to obtain second target current data and second target voltage data;
(5)基于第一目标电流数据和第一目标电压数据计算第一功率转换器的第一功率数据集，并基于第二目标电流数据和第二目标电压数据计算第二功率转换器的第二功率数据集。(5) Calculating a first power data set of the first power converter based on the first target current data and the first target voltage data, and calculating a second power data set of the second power converter based on the second target current data and the second target voltage data.
具体的，获取多层电路板中的顶层电路板、中层电路板和底层电路板，多层电路板用于蓝牙通信。顶层电路板通常负责接收和发送信号，而中层和底层电路板则处理更多的数据处理和电源管理功能。为了有效地管理电力分配和消耗，在顶层电路板和中层电路板之间以及中层电路板和底层电路板之间分别设置第一和第二功率转换器。每个电路板根据实际需求调整电力供应，从而优化整个系统的功耗。对第一功率转换器进行电流和电压监控，得到第一初始电流数据和第一初始电压数据，并对第二功率转换器进行电流和电压监控，得到第二初始电流数据和第二初始电压数据。对第一和第二功率转换器进行监控，帮助系统及时发现任何异常或效率下降的迹象。对初始数据进行主成分分析，提取有用信息和简化数据处理过程。主成分分析通过识别数据中的主要变量和模式，减少数据的复杂性，从而更准确地识别出影响电路板性能的关键因素。例如，通过主成分分析，可能会发现某些特定的电流和电压模式与系统性能下降直接相关，这些发现可以用来调整功率转换器的工作方式，以提高效率。在完成主成分特征解析后，基于分析结果，得到第一目标电流数据和第一目标电压数据，以及第二目标电流数据和第二目标电压数据。利用这些数据，计算第一和第二功率转换器的功率数据集，这些数据集反映了在特定工作条件下，每个功率转换器的功耗特性。例如，假设顶层电路板在进行蓝牙通信时，因应用的增多，其功耗需求上升。第一功率转换器在接收到增加的电流和电压需求信号后，根据第一目标电流和电压数据进行调整，以满足顶层的功耗需求而不至于过载。类似地，如果中层电路板处理更多的数据，第二功率转换器也会根据第二目标电流和电压数据进行调整，确保电力供应既满足需求又最大程度地节能。Specifically, a top circuit board, a middle circuit board and a bottom circuit board in a multi-layer circuit board are obtained, and the multi-layer circuit board is used for Bluetooth communication. The top circuit board is usually responsible for receiving and sending signals, while the middle and bottom circuit boards handle more data processing and power management functions. In order to effectively manage power distribution and consumption, a first and a second power converter are respectively set between the top circuit board and the middle circuit board and between the middle circuit board and the bottom circuit board. Each circuit board adjusts the power supply according to actual needs, thereby optimizing the power consumption of the entire system. The current and voltage of the first power converter are monitored to obtain first initial current data and first initial voltage data, and the current and voltage of the second power converter are monitored to obtain second initial current data and second initial voltage data. The first and second power converters are monitored to help the system detect any abnormality or signs of efficiency decline in a timely manner. The initial data is subjected to principal component analysis to extract useful information and simplify the data processing process. Principal component analysis reduces the complexity of the data by identifying the main variables and patterns in the data, thereby more accurately identifying the key factors affecting the performance of the circuit board. For example, through principal component analysis, it may be found that certain specific current and voltage patterns are directly related to the decline in system performance, and these findings can be used to adjust the working mode of the power converter to improve efficiency. After completing the principal component feature analysis, the first target current data and the first target voltage data, as well as the second target current data and the second target voltage data are obtained based on the analysis results. Using these data, the power data sets of the first and second power converters are calculated, which reflect the power consumption characteristics of each power converter under specific working conditions. For example, suppose that when the top-level circuit board is performing Bluetooth communication, its power consumption demand increases due to the increase in applications. After receiving the increased current and voltage demand signal, the first power converter adjusts according to the first target current and voltage data to meet the power consumption demand of the top layer without overloading. Similarly, if the middle-level circuit board processes more data, the second power converter will also adjust according to the second target current and voltage data to ensure that the power supply meets the demand and saves energy to the greatest extent.
在一具体实施例中，执行步骤分别对第一初始电流数据和第一初始电压数据进行主成分特征解析，得到第一目标电流数据和第一目标电压数据，并分别对第二初始电流数据和第二初始电压数据进行主成分特征解析，得到第二目标电流数据和第二目标电压数据的过程可以具体包括如下步骤：In a specific embodiment, the execution step performs principal component feature analysis on the first initial current data and the first initial voltage data to obtain the first target current data and the first target voltage data, and performs principal component feature analysis on the second initial current data and the second initial voltage data to obtain the second target current data and the second target voltage data, which may specifically include the following steps:
(1)分别对第一初始电流数据和第一初始电压数据进行特征提取，得到多个第一初始电流特征和多个第一初始电压特征，并分别对第二初始电流数据和第二初始电压数据进行特征提取，得到多个第二初始电流特征和多个第二初始电压特征；(1) performing feature extraction on the first initial current data and the first initial voltage data respectively to obtain a plurality of first initial current features and a plurality of first initial voltage features, and performing feature extraction on the second initial current data and the second initial voltage data respectively to obtain a plurality of second initial current features and a plurality of second initial voltage features;
(2)分别对多个第一初始电流特征和多个第一初始电压特征进行线性特征变换，得到第一电流线性特征集合和第一电压线性特征集合，并分别对多个第二初始电流特征和多个第二初始电压特征进行线性特征变换，得到第二电流线性特征集合和第二电压线性特征集合；(2) performing linear feature transformation on the plurality of first initial current features and the plurality of first initial voltage features respectively to obtain a first current linear feature set and a first voltage linear feature set, and performing linear feature transformation on the plurality of second initial current features and the plurality of second initial voltage features respectively to obtain a second current linear feature set and a second voltage linear feature set;
(3)基于第一电流线性特征集合和第一电压线性特征集合构建对应的第一电流协方差矩阵和第一电压协方差矩阵，并基于第二电流线性特征集合和第二电压线性特征集合构建对应的第二电流协方差矩阵和第二电压协方差矩阵；(3) constructing a corresponding first current covariance matrix and a first voltage covariance matrix based on the first current linear feature set and the first voltage linear feature set, and constructing a corresponding second current covariance matrix and a second voltage covariance matrix based on the second current linear feature set and the second voltage linear feature set;
(4)对第一电流协方差矩阵和第一电压协方差矩阵进行特征相关性计算，得到第一电流特征相关性和第一电压特征相关性，并对第二电流协方差矩阵和第二电压协方差矩阵进行特征相关性计算，得到第二电流特征相关性和第二电压特征相关性；(4) performing feature correlation calculation on the first current covariance matrix and the first voltage covariance matrix to obtain a first current feature correlation and a first voltage feature correlation, and performing feature correlation calculation on the second current covariance matrix and the second voltage covariance matrix to obtain a second current feature correlation and a second voltage feature correlation;
(5)根据第一电流特征相关性和第一电压特征相关性分别计算第一电流线性特征集合和第一电压线性特征集合对应的第一电流主成分特征权重和第一电压主成分特征权重，并根据第二电流特征相关性和第二电压特征相关性分别计算第二电流线性特征集合和第二电压线性特征集合对应的第二电流主成分特征权重和第二电压主成分特征权重；(5) calculating the first current principal component feature weight and the first voltage principal component feature weight corresponding to the first current linear feature set and the first voltage linear feature set respectively according to the first current feature correlation and the first voltage feature correlation, and calculating the second current principal component feature weight and the second voltage principal component feature weight corresponding to the second current linear feature set and the second voltage linear feature set respectively according to the second current feature correlation and the second voltage feature correlation;
(6)根据第一电流主成分特征权重和第一电压主成分特征权重对多个第一初始电流特征和多个第一初始电压特征进行特征融合，得到第一目标电流数据和第一目标电压数据，并根据第二电流主成分特征权重和第二电压主成分特征权重对多个第二初始电流特征和多个第二初始电压特征进行特征融合，得到第二目标电流数据和第二目标电压数据。(6) Feature fusion is performed on multiple first initial current features and multiple first initial voltage features according to the first current principal component feature weight and the first voltage principal component feature weight to obtain first target current data and first target voltage data, and feature fusion is performed on multiple second initial current features and multiple second initial voltage features according to the second current principal component feature weight and the second voltage principal component feature weight to obtain second target current data and second target voltage data.
具体的，对第一功率转换器和第二功率转换器收集的初始电流和电压数据进行特征提取。测量每个转换器的电流和电压值，以捕捉其运行状态下的具体表现，例如电流和电压的峰值、平均值、波动和最小值等。对初始特征进行线性特征变换，通常采用主成分分析(PCA)等方法。从多个相关的原始特征中提取出主要的特征，以减少数据集的维度同时保留最重要的信息。例如，如果原始数据显示电流和电压特征之间存在高度相关性，主成分分析可以帮助识别出影响系统性能的关键因素，从而简化整个特征集。构建电流和电压的协方差矩阵。协方差矩阵帮助理解不同特征之间的线性关系，即哪些特征与其他特征有较强的相关性。通过计算协方差矩阵的特征值和特征向量，得到每个特征的相关性。特征相关性的高低代表每个特征对于电路板功耗行为的重要性。高相关性的特征将被赋予更高的权重。根据特征的相关性计算得出的权重，对所有特征进行加权融合，形成最终的目标电流数据和目标电压数据。融合确保了最重要的特征被突出表示，而不那么关键的特征则相对降低其影响力。例如，如果主成分分析显示第一功率转换器的某一特定电流变化模式与系统性能下降高度相关，那么这一特征在最终融合时将被赋予较高的权重。Specifically, feature extraction is performed on the initial current and voltage data collected from the first power converter and the second power converter. The current and voltage values of each converter are measured to capture the specific performance of the converter under the operating state, such as the peak value, average value, fluctuation and minimum value of the current and voltage. Linear feature transformation is performed on the initial features, usually using methods such as principal component analysis (PCA). The main features are extracted from multiple related original features to reduce the dimension of the data set while retaining the most important information. For example, if the original data shows that there is a high correlation between the current and voltage features, principal component analysis can help identify the key factors affecting the system performance, thereby simplifying the entire feature set. The covariance matrix of current and voltage is constructed. The covariance matrix helps understand the linear relationship between different features, that is, which features have a strong correlation with other features. The correlation of each feature is obtained by calculating the eigenvalues and eigenvectors of the covariance matrix. The high or low correlation of the features represents the importance of each feature to the power consumption behavior of the circuit board. Features with high correlation will be given higher weights. According to the weights calculated based on the correlation of the features, all features are weighted fused to form the final target current data and target voltage data. The fusion ensures that the most important features are highlighted, while the less critical features are relatively reduced in influence. For example, if the principal component analysis shows that a specific current variation pattern of the first power converter is highly correlated with system performance degradation, then this feature will be given a higher weight in the final fusion.
在一具体实施例中，执行步骤102的过程可以具体包括如下步骤：In a specific embodiment, the process of executing step 102 may specifically include the following steps:
(1)对第一功率数据集进行曲线拟合，得到第一功率曲线，并对第二功率数据集进行曲线拟合，得到第二功率曲线；(1) performing curve fitting on the first power data set to obtain a first power curve, and performing curve fitting on the second power data set to obtain a second power curve;
(2)对第一功率曲线进行特征提取，得到多个第一初始功率特征，并对第二功率曲线进行特征提取，得到多个第二初始功率特征；(2) performing feature extraction on the first power curve to obtain a plurality of first initial power features, and performing feature extraction on the second power curve to obtain a plurality of second initial power features;
(3)对多个第一初始功率特征进行特征分类，得到多个第一高频功率特征和多个第一低频功率特征，并对多个第二初始功率特征进行特征分类，得到多个第二高频功率特征和多个第二低频功率特征；(3) performing feature classification on the plurality of first initial power features to obtain a plurality of first high-frequency power features and a plurality of first low-frequency power features, and performing feature classification on the plurality of second initial power features to obtain a plurality of second high-frequency power features and a plurality of second low-frequency power features;
(4)对多个第一高频功率特征和多个第一低频功率特征进行特征权重计算和特征集合转换，得到第一功率特征集合，并对多个第二高频功率特征和多个第二低频功率特征进行特征权重计算和特征集合转换，得到第二功率特征集合。(4) Performing feature weight calculation and feature set conversion on multiple first high-frequency power features and multiple first low-frequency power features to obtain a first power feature set, and performing feature weight calculation and feature set conversion on multiple second high-frequency power features and multiple second low-frequency power features to obtain a second power feature set.
具体的，对第一和第二功率数据集进行曲线拟合。使用数学模型，如多项式回归或非线性回归模型，逼近实际观察到的数据点。曲线拟合的目的是创建一个数学表达式，能够描述功率数据随时间或其他变量变化的趋势。例如，如果第一功率数据集显示随着时间增加功耗逐渐增加，曲线拟合可能揭示一个线性增长或更复杂的指数增长模式。同理，第二功率数据集的拟合可能揭示不同的模式，这取决于电路板的不同部分或不同功能模块的具体功耗行为。对第一功率曲线进行特征提取，得到多个第一初始功率特征，并对第二功率曲线进行特征提取，得到多个第二初始功率特征。从拟合得到的曲线中识别出有意义的特征，如峰值、谷值、平均值、波动性等。这些特征有助于更深入地理解电路板的功耗动态。例如，第一功率曲线可能显示在特定条件下功耗突增，这可以被提取为一个关键特征；而第二功率曲线可能揭示了功耗的周期性变化。特征提取后，将这些特征进行分类，通常分为高频和低频功率特征。高频特征关注于功耗变化迅速的瞬态行为，而低频特征则关注较长时间尺度上的变化趋势。进行特征权重计算和特征集合转换。通过分析每个特征对总体功耗影响的重要性来分配权重。高影响力的特征将获得更高的权重，反映其在功耗优化中的重要性。例如，如果某一高频电流特征与系统性能下降紧密相关，则这个特征在第一功率特征集合中的权重将被提高。通过权重，将初步提取的特征转换为更综合、更具影响力的功率特征集合，得到第一和第二功率特征集合，指导功率转换器的调整和优化，从而实现电路板功耗的整体优化。Specifically, curve fitting is performed on the first and second power data sets. A mathematical model, such as a polynomial regression or nonlinear regression model, is used to approximate the actual observed data points. The purpose of curve fitting is to create a mathematical expression that can describe the trend of power data over time or other variables. For example, if the first power data set shows that power consumption gradually increases over time, curve fitting may reveal a linear growth or a more complex exponential growth pattern. Similarly, the fitting of the second power data set may reveal different patterns, depending on the specific power consumption behavior of different parts or different functional modules of the circuit board. Feature extraction is performed on the first power curve to obtain multiple first initial power features, and feature extraction is performed on the second power curve to obtain multiple second initial power features. Meaningful features, such as peaks, valleys, averages, fluctuations, etc., are identified from the fitted curves. These features help to gain a deeper understanding of the power consumption dynamics of the circuit board. For example, the first power curve may show a sudden increase in power consumption under certain conditions, which can be extracted as a key feature; while the second power curve may reveal a periodic change in power consumption. After feature extraction, these features are classified, usually into high-frequency and low-frequency power features. High-frequency features focus on transient behaviors where power consumption changes rapidly, while low-frequency features focus on changing trends over longer time scales. Perform feature weight calculation and feature set conversion. Weights are assigned by analyzing the importance of each feature’s impact on overall power consumption. High-impact features will receive higher weights, reflecting their importance in power consumption optimization. For example, if a high-frequency current feature is closely related to system performance degradation, the weight of this feature in the first power feature set will be increased. Through weights, the initially extracted features are converted into a more comprehensive and influential power feature set, resulting in the first and second power feature sets, which guide the adjustment and optimization of the power converter, thereby achieving overall optimization of the circuit board power consumption.
在一具体实施例中，执行步骤对多个第一高频功率特征和多个第一低频功率特征进行特征权重计算和特征集合转换，得到第一功率特征集合，并对多个第二高频功率特征和多个第二低频功率特征进行特征权重计算和特征集合转换，得到第二功率特征集合的过程可以具体包括如下步骤：In a specific embodiment, the execution step performs feature weight calculation and feature set conversion on multiple first high-frequency power features and multiple first low-frequency power features to obtain a first power feature set, and performs feature weight calculation and feature set conversion on multiple second high-frequency power features and multiple second low-frequency power features to obtain a second power feature set. The process may specifically include the following steps:
(1)对多个第一高频功率特征和多个第一低频功率特征进行皮尔逊相关系数计算，得到第一皮尔逊相关系数，并对多个第二高频功率特征和多个第二低频功率特征进行皮尔逊相关系数计算，得到第二皮尔逊相关系数；(1) calculating a Pearson correlation coefficient for a plurality of first high-frequency power features and a plurality of first low-frequency power features to obtain a first Pearson correlation coefficient, and calculating a Pearson correlation coefficient for a plurality of second high-frequency power features and a plurality of second low-frequency power features to obtain a second Pearson correlation coefficient;
(2)根据第一皮尔逊相关系数设置多个第一高频功率特征和多个第一低频功率特征的第一特征权重值，并根据第二皮尔逊相关系数设置多个第二高频功率特征和多个第二低频功率特征的第二特征权重值；(2) setting first feature weight values of the plurality of first high-frequency power features and the plurality of first low-frequency power features according to the first Pearson correlation coefficient, and setting second feature weight values of the plurality of second high-frequency power features and the plurality of second low-frequency power features according to the second Pearson correlation coefficient;
(3)根据第一特征权重值对多个第一高频功率特征和多个第一低频功率特征进行特征加权，得到多个第一高频加权特征和多个第一低频加权特征，并根据第二特征权重值对多个第二高频功率特征和多个第二低频功率特征进行特征加权，得到多个第二高频加权特征和多个第二低频加权特征；(3) performing feature weighting on the plurality of first high-frequency power features and the plurality of first low-frequency power features according to the first feature weight value to obtain a plurality of first high-frequency weighted features and a plurality of first low-frequency weighted features, and performing feature weighting on the plurality of second high-frequency power features and the plurality of second low-frequency power features according to the second feature weight value to obtain a plurality of second high-frequency weighted features and a plurality of second low-frequency weighted features;
(4)根据多个第一高频加权特征和多个第一低频加权特征生成对应的第一功率特征集合，并根据多个第二高频加权特征和多个第二低频加权特征生成对应的第二功率特征集合。(4) Generate a corresponding first power feature set based on the plurality of first high-frequency weighted features and the plurality of first low-frequency weighted features, and generate a corresponding second power feature set based on the plurality of second high-frequency weighted features and the plurality of second low-frequency weighted features.
具体的，对第一和第二功率数据集中的高频和低频功率特征进行皮尔逊相关系数计算。皮尔逊相关系数是衡量两个变量之间线性关系强度的统计指标，其值范围从-1到1，其中1表示完全正相关，-1表示完全负相关，而0则表示没有线性关联。例如，对于第一功率数据集，假设观察到在高功耗模式下，电流的快速变化(高频特征)与电压的稳定性(低频特征)高度相关。这种相关性可能表明在高功耗状态下电路的稳定电压对于维持设备性能至关重要。通过计算出的皮尔逊相关系数，为每个高频和低频功率特征设定相应的权重。这些权重反映了各特征在电路整体功耗行为中的重要性。例如，如果某一高频电流变化特征与电路性能下降高度相关，则可能给予较高的权重，因为这种特征有助于预测和避免潜在的性能问题。根据设定的权重对第一和第二功率特征进行加权处理。通过将每个特征乘以其相应的权重，强调对电路性能影响更大的特征，而减少那些较不重要特征的影响，得到加权后的第一和第二高频加权特征以及低频加权特征。将加权特征合并成综合的功率特征集合。将所有加权特征整合，形成代表第一和第二功率转换器的全面功率特征集合。例如，将第一功率特征集合中的高频加权特征和低频加权特征合并，提供一个全面的视图，说明在不同操作条件下，第一功率转换器的性能如何受到各个因素的影响。同样，第二功率特征集合也通过相似的方式构建，以确保每个功率转换器的操作都能达到最优的能效和性能。Specifically, the Pearson correlation coefficient is calculated for the high-frequency and low-frequency power features in the first and second power data sets. The Pearson correlation coefficient is a statistical indicator that measures the strength of the linear relationship between two variables, and its value ranges from -1 to 1, where 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no linear correlation. For example, for the first power data set, it is assumed that the rapid change of current (high-frequency feature) is observed to be highly correlated with the stability of voltage (low-frequency feature) in the high power consumption mode. This correlation may indicate that the stable voltage of the circuit in the high power consumption state is essential to maintain the performance of the device. Through the calculated Pearson correlation coefficient, a corresponding weight is set for each high-frequency and low-frequency power feature. These weights reflect the importance of each feature in the overall power consumption behavior of the circuit. For example, if a high-frequency current change feature is highly correlated with the degradation of circuit performance, it may be given a higher weight because such a feature helps predict and avoid potential performance problems. The first and second power features are weighted according to the set weights. By multiplying each feature by its corresponding weight, the features that have a greater impact on circuit performance are emphasized, while the impact of those less important features is reduced, and the weighted first and second high-frequency weighted features and low-frequency weighted features are obtained. The weighted features are combined into a comprehensive power feature set. All weighted features are integrated to form a comprehensive power feature set representing the first and second power converters. For example, the high-frequency weighted features and the low-frequency weighted features in the first power feature set are combined to provide a comprehensive view of how the performance of the first power converter is affected by various factors under different operating conditions. Similarly, the second power feature set is constructed in a similar manner to ensure that each power converter operates at optimal energy efficiency and performance.
在一具体实施例中，执行步骤103的过程可以具体包括如下步骤：In a specific embodiment, the process of executing step 103 may specifically include the following steps:
(1)分别对第一功率特征集合和第二功率特征集合进行特征编码，得到第一功率特征向量和第二功率特征向量；(1) performing feature encoding on the first power feature set and the second power feature set respectively to obtain a first power feature vector and a second power feature vector;
(2)通过双重Q网络分别对第一功率特征向量和第二功率特征向量进行功率优化执行策略分析，得到第一功率转换器的第一初始功耗优化执行策略和第二功率转换器的第二初始功耗优化执行策略；(2) performing power optimization execution strategy analysis on the first power characteristic vector and the second power characteristic vector respectively through a dual Q network to obtain a first initial power consumption optimization execution strategy for the first power converter and a second initial power consumption optimization execution strategy for the second power converter;
(3)对第一功率转换器和第二功率转换器进行奖励反馈参数计算，得到第一功率转换器的第一奖励反馈参数和第二功率转换器的第二奖励反馈参数；(3) calculating reward feedback parameters for the first power converter and the second power converter to obtain a first reward feedback parameter for the first power converter and a second reward feedback parameter for the second power converter;
(4)根据第一奖励反馈参数对第一初始功耗优化执行策略进行策略更新，得到第一目标功耗优化执行策略，并根据第二奖励反馈参数对第二初始功耗优化执行策略进行策略更新，得到第二目标功耗优化执行策略；(4) updating the first initial power consumption optimization execution strategy according to the first reward feedback parameter to obtain a first target power consumption optimization execution strategy, and updating the second initial power consumption optimization execution strategy according to the second reward feedback parameter to obtain a second target power consumption optimization execution strategy;
(5)通过PSO算法，根据第一目标功耗优化执行策略和第二目标功耗优化执行策略对多层电路板进行功耗参数计算，得到多层电路板的全局功耗优化参数。(5) Using the PSO algorithm, the power consumption parameters of the multi-layer circuit board are calculated according to the first target power consumption optimization execution strategy and the second target power consumption optimization execution strategy, so as to obtain the global power consumption optimization parameters of the multi-layer circuit board.
具体的，分别对第一功率特征集合和第二功率特征集合进行特征编码，得到第一功率特征向量和第二功率特征向量。例如，将功耗峰值、平均功耗、波动性等数据转换为一系列数值，这些数值能够准确描述功率转换器的运行状态。如果第一功率转换器在高负载时表现出功耗峰值，这一信息将被编码到第一功率特征向量中。通过双重Q网络对编码后的功率特征向量进行分析，形成初始的功耗优化执行策略。双重Q网络是一种强化学习算法，使用两个值函数评估器减少过度估计所带来的偏差，从而提供更稳定和准确的学习结果。分析每个功率特征向量，以预测不同的调整策略对功耗影响的大小，生成每个转换器的初始功耗优化执行策略。为了进一步提升策略的有效性，进行奖励反馈参数计算。根据实际运行数据与策略预测结果的比较评估每种策略的表现。例如，如果第一功率转换器在实施某一策略后，功耗明显降低且稳定性提高，则该策略会获得较高的奖励反馈参数。这些参数直接影响到后续策略的调整和优化。根据奖励反馈参数进行策略更新。双重Q网络根据获得的反馈调整其值函数评估器，优化原始的功耗优化执行策略。每个转换器的策略根据其实际表现被逐步调整，以确保在未来运行中能够达到更高的效率和更低的功耗。通过PSO算法，根据更新后的第一和第二目标功耗优化执行策略对整个多层电路板进行全局的功耗参数计算。PSO是一种群体智能算法，模拟鸟群的搜索行为找到最优解。在这一过程中，算法会在参数空间中寻找能够最小化整体功耗的最优参数组合。Specifically, feature encoding is performed on the first power feature set and the second power feature set respectively to obtain a first power feature vector and a second power feature vector. For example, data such as peak power consumption, average power consumption, and volatility are converted into a series of numerical values that can accurately describe the operating state of the power converter. If the first power converter exhibits a peak power consumption at high load, this information will be encoded into the first power feature vector. The encoded power feature vector is analyzed by a dual Q network to form an initial power consumption optimization execution strategy. The dual Q network is a reinforcement learning algorithm that uses two value function evaluators to reduce the deviation caused by overestimation, thereby providing more stable and accurate learning results. Each power feature vector is analyzed to predict the magnitude of the impact of different adjustment strategies on power consumption, and an initial power consumption optimization execution strategy for each converter is generated. In order to further improve the effectiveness of the strategy, reward feedback parameters are calculated. The performance of each strategy is evaluated by comparing the actual operating data with the strategy prediction results. For example, if the power consumption of the first power converter is significantly reduced and the stability is improved after implementing a certain strategy, the strategy will obtain a higher reward feedback parameter. These parameters directly affect the adjustment and optimization of subsequent strategies. The strategy is updated according to the reward feedback parameters. The dual Q network adjusts its value function evaluator based on the feedback obtained to optimize the original power optimization execution strategy. The strategy of each converter is gradually adjusted according to its actual performance to ensure higher efficiency and lower power consumption in future operations. Through the PSO algorithm, the power consumption parameters of the entire multi-layer circuit board are calculated globally according to the updated first and second target power optimization execution strategies. PSO is a swarm intelligence algorithm that simulates the search behavior of a flock of birds to find the optimal solution. In this process, the algorithm searches for the optimal parameter combination in the parameter space that minimizes the overall power consumption.
在一具体实施例中，执行步骤106的过程可以具体包括如下步骤：In a specific embodiment, the process of executing step 106 may specifically include the following steps:
(1)通过PSO算法，根据第一目标功耗优化执行策略对第一功率转换器进行随机初始值生成，得到第一随机初始值集合，并根据第二目标功耗优化执行策略对第二功率转换器进行随机初始值生成，得到第二随机初始值集合；(1) using a PSO algorithm, generating random initial values for a first power converter according to a first target power consumption optimization execution strategy to obtain a first random initial value set, and generating random initial values for a second power converter according to a second target power consumption optimization execution strategy to obtain a second random initial value set;
(2)通过反向粒子传播算法对第一随机初始值集合进行粒子种群构建，得到第一粒子种群，并通过反向粒子传播算法对第二随机初始值集合进行粒子种群构建，得到第二粒子种群；(2) constructing a particle population for the first random initial value set by using a reverse particle propagation algorithm to obtain a first particle population, and constructing a particle population for the second random initial value set by using a reverse particle propagation algorithm to obtain a second particle population;
(3)对第一粒子种群进行种群分割，得到多个第一子粒子种群，并对第二粒子种群进行种群分割，得到多个第二子粒子种群；(3) performing population segmentation on the first particle population to obtain a plurality of first sub-particle populations, and performing population segmentation on the second particle population to obtain a plurality of second sub-particle populations;
(4)分别对多个第一子粒子种群进行适应度计算，得到第一粒子种群对应的第一粒子适应度集合，并分别对多个第二子粒子种群进行适应度计算，得到第二粒子种群对应的第二粒子适应度集合；(4) performing fitness calculations on the plurality of first sub-particle populations respectively to obtain a first particle fitness set corresponding to the first particle population, and performing fitness calculations on the plurality of second sub-particle populations respectively to obtain a second particle fitness set corresponding to the second particle population;
(5)根据第一粒子适应度集合生成第一功率转换器的第一功耗优化参数，并根据第二粒子适应度集合生成第二功率转换器的第二功耗优化参数；(5) generating a first power consumption optimization parameter of the first power converter according to the first particle fitness set, and generating a second power consumption optimization parameter of the second power converter according to the second particle fitness set;
(6)对第一功耗优化参数和第二功耗优化参数进行全局优化，得到多层电路板的全局功耗优化参数。(6) Globally optimize the first power consumption optimization parameter and the second power consumption optimization parameter to obtain the global power consumption optimization parameter of the multi-layer circuit board.
具体的，通过PSO算法为第一和第二功率转换器生成随机初始值。PSO算法以一组随机解开始其搜索过程，这些解在算法的迭代过程中通过模拟鸟群的社会行为被优化。本实施例中，每个解代表了一套可能的功率转换器参数，如电流限制、电压设定等。例如，第一功率转换器可能在一定的功率范围内运行，而PSO算法生成的随机初始值集合将涵盖这一范围内的各种可能设定。使用反向粒子传播算法对随机生成的初始值进行粒子种群构建。每个初始值被视为一个粒子，整个集合形成了粒子种群。反向粒子传播是一个调整粒子位置和速度的过程，通过算法反复迭代找到更优的解决方案。例如，如果某个粒子代表的参数设置导致功耗降低而性能保持不变，那么这种设置会在后续的迭代中被推向更优的方向。进行粒子种群分割，以形成多个子粒子种群，每个子种群专注于搜索解空间的不同部分。种群分割增加了找到全局最优解的可能性，防止算法过早地聚焦于局部最优解。每个子种群都进行独立的搜索，但共享全局最优解的信息，以此来指导搜索过程。分别对多个第一子粒子种群进行适应度计算，得到第一粒子种群对应的第一粒子适应度集合，并分别对多个第二子粒子种群进行适应度计算，得到第二粒子种群对应的第二粒子适应度集合。适应度计算通常基于功耗降低的程度、系统稳定性的提高以及可能的性能增益。这些适应度值为每个粒子及其参数设置提供了一个量化的效益评估，用于指导最终的参数选择。基于每个粒子种群的适应度集合，生成第一和第二功率转换器的最优功耗参数。这些参数反映了在整个搜索过程中表现最好的设置。将这些参数应用于全局优化，整合所有最优解以形成多层电路板的综合功耗优化方案。全局优化考虑了所有相关的性能指标和操作限制，以确保电路板在所有操作条件下都能以最低的功耗运行。Specifically, random initial values are generated for the first and second power converters by the PSO algorithm. The PSO algorithm starts its search process with a set of random solutions, which are optimized by simulating the social behavior of bird flocks during the algorithm's iteration process. In this embodiment, each solution represents a set of possible power converter parameters, such as current limit, voltage setting, etc. For example, the first power converter may operate within a certain power range, and the set of random initial values generated by the PSO algorithm will cover various possible settings within this range. The reverse particle propagation algorithm is used to construct a particle population for the randomly generated initial values. Each initial value is regarded as a particle, and the entire set forms a particle population. Reverse particle propagation is a process of adjusting the position and velocity of particles, and a better solution is found through repeated iterations of the algorithm. For example, if the parameter setting represented by a particle leads to reduced power consumption while maintaining the same performance, then this setting will be pushed to a better direction in subsequent iterations. The particle population is divided to form multiple sub-particle populations, each of which focuses on searching different parts of the solution space. Population division increases the possibility of finding a global optimal solution and prevents the algorithm from focusing on a local optimal solution too early. Each sub-population performs an independent search, but shares information about the global optimal solution to guide the search process. Fitness calculations are performed on multiple first sub-particle populations to obtain first particle fitness sets corresponding to the first particle populations, and fitness calculations are performed on multiple second sub-particle populations to obtain second particle fitness sets corresponding to the second particle populations. Fitness calculations are usually based on the degree of power consumption reduction, improvement in system stability, and possible performance gains. These fitness values provide a quantitative benefit assessment for each particle and its parameter settings to guide the final parameter selection. Based on the fitness set of each particle population, optimal power consumption parameters for the first and second power converters are generated. These parameters reflect the settings that performed best during the entire search process. These parameters are applied to global optimization, and all optimal solutions are integrated to form a comprehensive power consumption optimization solution for the multi-layer circuit board. Global optimization takes into account all relevant performance indicators and operating constraints to ensure that the circuit board can operate with the lowest power consumption under all operating conditions.
上面对本申请实施例中蓝牙电路板自适应功耗管理方法进行了描述，下面对本申请实施例中蓝牙电路板自适应功耗管理系统进行描述，请参阅图2，本申请实施例中蓝牙电路板自适应功耗管理系统一个实施例包括：The above describes the adaptive power consumption management method of the Bluetooth circuit board in the embodiment of the present application. The following describes the adaptive power consumption management system of the Bluetooth circuit board in the embodiment of the present application. Please refer to Figure 2. An embodiment of the adaptive power consumption management system of the Bluetooth circuit board in the embodiment of the present application includes:
监测模块201，用于在多层电路板的不同层级设置功率转换器并进行实时功耗监测，得到第一功率转换器的第一功率数据集和第二功率转换器的第二功率数据集；A monitoring module 201, configured to set power converters at different levels of the multi-layer circuit board and perform real-time power consumption monitoring to obtain a first power data set of the first power converter and a second power data set of the second power converter;
提取模块202，用于分别对第一功率数据集和第二功率数据集进行功率特征提取，得到第一功率特征集合和第二功率特征集合；An extraction module 202 is used to extract power features from the first power data set and the second power data set respectively to obtain a first power feature set and a second power feature set;
创建模块203，用于通过双重Q网络和PSO算法根据第一功率特征集合和第二功率特征集合创建多层电路板的全局功耗优化参数。The creation module 203 is used to create global power consumption optimization parameters of the multi-layer circuit board according to the first power feature set and the second power feature set by using a dual Q network and a PSO algorithm.
通过上述各个组成部分的协同合作，通过在多层电路板的不同层级设置功率转换器并进行实时监测，能够精确地获取各层电路板的功耗数据。这种实时监测确保了能源利用的最大化效率，使设备能够根据当前的运行状态动态调整功率输出，从而降低无效的能耗和延长设备的电池寿命。应用主成分分析特征提取技术，有效地从原始电流和电压数据中提取关键特征。这种深入的数据分析方法帮助更准确地理解电路板在不同工作条件下的行为，为后续的功耗优化提供了数据支持。利用双重Q网络和PSO算法，此方法不仅能够创建高效的全局功耗优化参数，还可以通过算法动态调整和优化电路板的功耗配置。这种智能化的决策过程显著提高了电路板的能效，减少了因固定或过时的功耗配置引起的能源浪费。结合奖励反馈参数的计算与策略更新，此方法实现了一种自学习的功耗管理系统。通过持续的学习和调整，电路板可以不断地优化其功耗策略以适应环境变化和设备需求，提升整体的性能和效率。通过综合考虑各层电路板的功耗特征和优化执行策略，该方法能够在整个电路板级别上实施功耗管理，从而实现更为统一和协调的能源管理。这种全局视角的管理不仅提高了能效，还有助于保持设备的稳定性和可靠性，进而实现了蓝牙电路板自适应功耗管理并且提高了多层电路板的功耗优化效果。Through the synergy of the above components, by setting power converters at different levels of the multi-layer circuit board and performing real-time monitoring, the power consumption data of each layer of the circuit board can be accurately obtained. This real-time monitoring ensures the maximum efficiency of energy utilization, enabling the device to dynamically adjust the power output according to the current operating status, thereby reducing ineffective energy consumption and extending the battery life of the device. The principal component analysis feature extraction technology is applied to effectively extract key features from the original current and voltage data. This in-depth data analysis method helps to more accurately understand the behavior of the circuit board under different working conditions and provides data support for subsequent power consumption optimization. Using the dual Q network and PSO algorithm, this method can not only create efficient global power consumption optimization parameters, but also dynamically adjust and optimize the power consumption configuration of the circuit board through the algorithm. This intelligent decision-making process significantly improves the energy efficiency of the circuit board and reduces the energy waste caused by fixed or outdated power consumption configuration. Combined with the calculation of reward feedback parameters and strategy update, this method realizes a self-learning power management system. Through continuous learning and adjustment, the circuit board can continuously optimize its power consumption strategy to adapt to environmental changes and device requirements, improving overall performance and efficiency. By comprehensively considering the power consumption characteristics of each layer of the circuit board and optimizing the execution strategy, this method can implement power consumption management at the level of the entire circuit board, thereby achieving more unified and coordinated energy management. This global perspective management not only improves energy efficiency, but also helps maintain the stability and reliability of the device, thereby achieving adaptive power consumption management of the Bluetooth circuit board and improving the power consumption optimization effect of multi-layer circuit boards.
本申请还提供一种计算机设备，所述计算机设备包括存储器和处理器，存储器中存储有计算机可读指令，计算机可读指令被处理器执行时，使得处理器执行上述各实施例中的所述蓝牙电路板自适应功耗管理方法的步骤。The present application also provides a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the Bluetooth circuit board adaptive power consumption management method in the above-mentioned embodiments.
本申请还提供一种计算机可读存储介质，该计算机可读存储介质可以为非易失性计算机可读存储介质，该计算机可读存储介质也可以为易失性计算机可读存储介质，所述计算机可读存储介质中存储有指令，当所述指令在计算机上运行时，使得计算机执行所述蓝牙电路板自适应功耗管理方法的步骤。The present application also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the Bluetooth circuit board adaptive power consumption management method.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，系统和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-onlymemory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.
以上所述，以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410510708.5ACN118433835B (en) | 2024-04-26 | 2024-04-26 | Bluetooth circuit board self-adaptive power consumption management method and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410510708.5ACN118433835B (en) | 2024-04-26 | 2024-04-26 | Bluetooth circuit board self-adaptive power consumption management method and system |
| Publication Number | Publication Date |
|---|---|
| CN118433835Atrue CN118433835A (en) | 2024-08-02 |
| CN118433835B CN118433835B (en) | 2024-12-24 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410510708.5AActiveCN118433835B (en) | 2024-04-26 | 2024-04-26 | Bluetooth circuit board self-adaptive power consumption management method and system |
| Country | Link |
|---|---|
| CN (1) | CN118433835B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190228280A1 (en)* | 2016-07-12 | 2019-07-25 | Exteryo S.R.L | Multilayer electronic device and method for the construction and fixing of the device |
| CN216626118U (en)* | 2021-11-19 | 2022-05-27 | 江西嘉捷鑫源科技有限公司 | Current regulating circuit, power supply circuit, lamp and system for single live wire equipment |
| CN117556753A (en)* | 2024-01-11 | 2024-02-13 | 联和存储科技(江苏)有限公司 | Method, device, equipment and storage medium for analyzing energy consumption of storage chip |
| CN117709824A (en)* | 2024-02-06 | 2024-03-15 | 深圳市快金数据技术服务有限公司 | Logistics network layout optimization method, device, equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190228280A1 (en)* | 2016-07-12 | 2019-07-25 | Exteryo S.R.L | Multilayer electronic device and method for the construction and fixing of the device |
| CN216626118U (en)* | 2021-11-19 | 2022-05-27 | 江西嘉捷鑫源科技有限公司 | Current regulating circuit, power supply circuit, lamp and system for single live wire equipment |
| CN117556753A (en)* | 2024-01-11 | 2024-02-13 | 联和存储科技(江苏)有限公司 | Method, device, equipment and storage medium for analyzing energy consumption of storage chip |
| CN117709824A (en)* | 2024-02-06 | 2024-03-15 | 深圳市快金数据技术服务有限公司 | Logistics network layout optimization method, device, equipment and storage medium |
| Publication number | Publication date |
|---|---|
| CN118433835B (en) | 2024-12-24 |
| Publication | Publication Date | Title |
|---|---|---|
| CN117057517B (en) | Efficient power data processing method and system based on digital twins | |
| Moniz et al. | Smoteboost for regression: Improving the prediction of extreme values | |
| Simumba et al. | Multiple objective metaheuristics for feature selection based on stakeholder requirements in credit scoring | |
| CN118153516A (en) | Processor function simulation verification method and system | |
| CN117764637B (en) | A method and system for power trading based on multi-dimensional data analysis | |
| CN113712511B (en) | A Stable Pattern Discrimination Method for Brain Imaging Fusion Features | |
| CN119093337B (en) | A flexible and adjustable control method and device for a distributed photovoltaic system | |
| CN119578923B (en) | Intelligent load management-based power energy efficiency optimization method | |
| CN117807542A (en) | Power grid abnormal mode data identification method and system based on genetic LM algorithm | |
| CN117829054A (en) | Circuit layout optimization method and system based on programmable logic controller | |
| Yu | GDP economic forecasting model based on improved RBF neural network | |
| Mahlich et al. | From theory to practice: implementing and evaluating e-fold cross-validation | |
| CN108288093A (en) | BP neural network Weighting, system and prediction technique, system | |
| CN120049422A (en) | Power grid load optimization regulation and control method and system | |
| CN118433835A (en) | Bluetooth circuit board self-adaptive power consumption management method and system | |
| CN118228642B (en) | Parameter optimization design method and system for chip circuit | |
| CN114511078A (en) | BP neural network prediction method and device based on multi-strategy sparrow search algorithm | |
| CN118709058A (en) | Configuration method, device, equipment and storage medium of LED driver chip | |
| CN117691594B (en) | Energy saving and consumption reduction judging method and system for transformer | |
| Arunadevi et al. | Comparison of feature selection strategies for classification using rapid miner | |
| Eǧrioǧlu et al. | Comparison of feed forward and elman neural networks forecasting ability: Case study for IMKB | |
| CN119718855B (en) | Parameter determination method and device, storage medium and electronic equipment | |
| CN119675213B (en) | Control method of emergency mobile power supply and emergency mobile power supply | |
| CN120509331B (en) | A distributed energy storage device data generation method and system based on adaptive strategy optimization and long sequence dynamic enhancement network | |
| CN119398141B (en) | Big data analysis method and system based on ecological environment monitoring |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |