技术领域technical field
本发明涉及电力自动化领域，特别涉及一种基于大数据的线路台区异常分析方法。The invention relates to the field of electric power automation, in particular to a big data-based abnormality analysis method for line station areas.
背景技术Background technique
在构建国家电网公司一体化电量与线损管理平台的背景下，电网线损异常分析与决策系统作为高级应用模块被提出。该应用模块的主要功能是通过对电网生产数据进行定性与定量分析，对各类线损异常的成因进行解析，找出问题的关键点，提出初步的处理建议，从而使整个数据分析过程具有现实意义。Under the background of building an integrated electricity and line loss management platform of the State Grid Corporation of China, the power grid line loss anomaly analysis and decision-making system is proposed as an advanced application module. The main function of this application module is to analyze the causes of various line loss anomalies through qualitative and quantitative analysis of the power grid production data, find out the key points of the problem, and put forward preliminary processing suggestions, so that the whole data analysis process is realistic. significance.
对全网线损异常进行分析，是一个非常复杂的系统工程，分析的着眼点可以分为宏观和微观两个方面。宏观分析具体落实的是对线损单元数据进行考核，它主要关心“线”和“面”的问题。通过对变电站、线路、台区等数据的变化情况的观察和分析，定位出有问题的计量点，是从宏观到微观的过程；微观分析具体落实的是对计量点数据进行考核，它关心的是“点”的问题。通过对计量点数据的分析，发现存在问题的关口、专变用户和低压用户。Analyzing the abnormal line loss of the entire network is a very complex system engineering, and the focus of analysis can be divided into two aspects: macroscopic and microscopic. The specific implementation of the macro analysis is to assess the data of the line loss unit, which is mainly concerned with the issues of "line" and "surface". Through the observation and analysis of data changes in substations, lines, and station areas, it is a process from macro to micro to locate problematic metering points; the specific implementation of microscopic analysis is to assess the data of metering points. It's a matter of "point". Through the analysis of metering point data, it is found that there are problematic gateways, special transformer users and low-voltage users.
面对海量的电力数据，传统的计算框架己无法胜任如此繁杂的计算工作。因此，利用大数据技术就成为了行之有效的解决方法。In the face of massive power data, traditional computing frameworks are no longer capable of such complicated computing tasks. Therefore, using big data technology has become an effective solution.
发明内容Contents of the invention
本发明为解决上述问题，提供了一种大数据的线路台区异常分析方法，其特征在于，包括：In order to solve the above-mentioned problems, the present invention provides a method for analyzing the abnormality of a large data line platform area, which is characterized in that it includes:
步骤100：从海量平台及线损数据库中抽取表底及档案数据，存入数据库；Step 100: extract table bottom and file data from massive platforms and line loss databases, and store them in the database;
步骤200：根据所述数据库中所述表底及档案数据，计算低压用户、专变用户和台区售电量；Step 200: According to the table bottom and file data in the database, calculate the electricity sales of low-voltage users, special transformer users and station districts;
步骤300：在国网省公司计算完成低压用户、专变用户和台区售电量后，将计算结果及高压通过数据中心的非结构化传输通道上传到国网总部非结构化数据库中；Step 300: After the State Grid Provincial Corporation completes the calculation of the low-voltage users, special transformer users, and power sales in the station area, upload the calculation results and high voltage to the unstructured database of the State Grid Headquarters through the unstructured transmission channel of the data center;
步骤400：抽取所述国网总部非结构化数据库的数据，将表底、档案和计算模型存入总部分布式文件系统中；Step 400: Extract the data of the unstructured database of the State Grid headquarters, and store the table bottom, files and calculation models in the distributed file system of the headquarters;
步骤500：根据步骤400获取的所述表底、档案和计算模型，计算线路、台区的供电量及线损率；Step 500: Calculate the power supply and line loss rate of the line and station area according to the table bottom, file and calculation model obtained in step 400;
步骤600，选择至少一种线损分析模式，进行线损分析；根据一种或多种线损分析模式结果，生成诊断报告。Step 600, select at least one line loss analysis mode, and perform line loss analysis; generate a diagnosis report according to the results of one or more line loss analysis modes.
本发明可以解决线损所涉各专业数据横向融合，同时响应千万级数据量并发计算需求,在此基础上对国家电网的线路和台区异常作出准确分析，辅助领导者进行决策，提高了工作效率，创造了极大的经济和社会价值。The invention can solve the horizontal fusion of various professional data involved in line loss, and at the same time respond to the concurrent calculation requirements of tens of millions of data volumes. On this basis, it can accurately analyze the abnormalities of the national grid lines and station areas, assist the leader in making decisions, and improve the efficiency. Work efficiency has created great economic and social value.
附图说明Description of drawings
图1是本发明的基于大数据的线路台区异常分析的方法的流程图。Fig. 1 is a flow chart of the method for abnormal analysis of line station area based on big data in the present invention.
图2是以5个用户为例的线路累计电量占比图；Figure 2 is a diagram of the proportion of line cumulative power for 5 users as an example;
图3是以6个用户为例的台区累计电量占比图；Figure 3 is a diagram of the proportion of cumulative electricity in the station area for 6 users as an example;
图4本发明的基于随机森林的线路台区异常分析的方法的示意图。FIG. 4 is a schematic diagram of the method for analyzing anomalies in line station areas based on random forests in the present invention.
具体实施方式detailed description
为使本发明的目的、技术方案和优点更加清楚，下面将对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. example. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
在本发明的描述中，需要理解的是，术语“纵向”、“横向”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本发明，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本发明的限制。In describing the present invention, it should be understood that the terms "longitudinal", "transverse", "upper", "lower", "front", "rear", "left", "right", "vertical", The orientations or positional relationships indicated by "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention, rather than indicating or It should not be construed as limiting the invention by implying that a referenced device or element must have a particular orientation, be constructed, and operate in a particular orientation.
在本发明中，涉及以下基本概念：In the present invention, the following basic concepts are involved:
供电量：供电量指供电企业生产活动的全部投入电量，它包括以下电量：(1)发电厂上网电量：指本地区统调电厂(独立发电公司、直属电厂、地方电厂)记录的上网电量。(2)外购电量：指各供电公司从本公司供电区域外的电网购买的电量。(3)邻网输入输出电量：指地区电网之间的互供电量。Power supply volume: Power supply volume refers to the total input power of power supply enterprises in production activities, which includes the following power quantities: (1) On-grid electricity of power plants: refers to the on-grid electricity recorded by the unified control power plants (independent power companies, directly affiliated power plants, and local power plants) in the region. (2) Purchased electricity: refers to the electricity purchased by each power supply company from the power grid outside the power supply area of the company. (3) Neighboring network input and output power: refers to the mutual power supply between regional power grids.
供电量计算公式为：The formula for calculating power supply is:
供电量＝发电厂上网电量+外购电量+邻网输入电量－邻网输出电量。Power supply = on-grid electricity of power plant + purchased electricity + input electricity of adjacent network - output electricity of adjacent network.
售电量：指电力企业卖给用户的电量和电力企业供给本企业非电力生产用的电量。Electricity sales: Refers to the electricity sold by electric power enterprises to users and the electricity supplied by electric power enterprises for non-power production purposes.
线损：线损或网损指的是以热能形式散发的能量损失，即为电阻、电导消耗的有功功率。电力系统线损主要由两部分构成，管理线损和技术线损。管理线损又称可控线损，主要是由于电网结构、电网运行、电网管理不善造成的。本发明重点讨论技术线损，技术线损又称理论线损，线损的大小主要由电网负荷情况、供电设备、供电线路参数决定的，理论上无法避免，只能采取措施降低损耗，因此这样的损耗又称不可控损耗，是正常合理的电能消耗。Line loss: Line loss or network loss refers to the energy loss in the form of heat energy, that is, the active power consumed by resistance and conductance. Power system line loss is mainly composed of two parts, management line loss and technical line loss. Managed line loss, also known as controllable line loss, is mainly caused by poor grid structure, grid operation, and grid management. The present invention focuses on technical line loss, which is also called theoretical line loss. The size of line loss is mainly determined by the grid load, power supply equipment, and power supply line parameters. It cannot be avoided in theory, and measures can only be taken to reduce the loss. Therefore, The loss is also called uncontrollable loss, which is a normal and reasonable power consumption.
线损率：电力网线损率是指线损电量占供电量的百分比，简称线损率，其计算公式为Line loss rate: The line loss rate of the power network refers to the percentage of line loss electricity in the power supply, referred to as the line loss rate, and its calculation formula is
线损率＝(线损电量÷供电量)×100％Line loss rate = (line loss power ÷ power supply) × 100%
＝(供电量－售电量)÷供电量×100％= (power supply - electricity sales) ÷ power supply x 100%
在线损异常定性分析业务活动中，线损异常主要为分：电量异常，线损异常，档案异常，运行异常，采集异常。Qualitative analysis of line loss anomalies In business activities, line loss anomalies are mainly divided into: power anomalies, line loss anomalies, file anomalies, operation anomalies, and collection anomalies.
电量异常主要是通过连续考查计量点的表计数值，分析该计量点电量的变化情况，以确定其是否存在电量突增、突减或占比突变的情况。The abnormality of electricity is mainly to continuously check the meter count value of the metering point and analyze the change of the electricity at the metering point to determine whether there is a sudden increase, decrease or sudden change in the proportion of electricity.
线损异常主要是通过计算考核客体(线路、台区等)的线损指标，结合一些关联信息和参考数据，分析出该线损异常的可能成因，进而作出定性判断。The abnormal line loss is mainly through the calculation of the line loss index of the assessment object (line, station area, etc.), combined with some related information and reference data, to analyze the possible cause of the abnormal line loss, and then make a qualitative judgment.
档案异常主要暴露的是管理方面的问题，具体表现为一些考核客体的档案信息与生产环境的真实信息不符。The file anomaly mainly exposes management problems, which are specifically manifested as the discrepancy between the file information of some assessment objects and the real information of the production environment.
运行异常主要是通过对采集系统反馈的数据信息进行对比分析，发现运行状态与正常水平发生偏离的考核客体，比如：关口失压断相、关口表计电流过载。Abnormal operation is mainly through the comparison and analysis of the data information fed back by the acquisition system to find the assessment objects whose operating status deviates from the normal level, such as: loss of voltage and phase failure at the gate, current overload of the gate meter.
采集异常主要是通过对考核客体的运行时数据采集成功率的分析，发现采集通讯系统的问题。Abnormal collection is mainly through the analysis of the success rate of data collection during the operation of the assessment object, and the problem of the collection communication system is found.
相关系数:Correlation coefficient:
相关系数是用以反映变量之间相关关系密切程度及其相关方向的统计指标，利用相关系数的性质，可以找出线损波动与那个台区电量波动的相关程度及其相关方向，从而提高了降损效率。相关系数性质:The correlation coefficient is a statistical index used to reflect the closeness of the correlation between variables and the direction of the correlation. Using the nature of the correlation coefficient, the correlation degree and direction of the line loss fluctuation and the power fluctuation of the station can be found out, thereby improving the Loss reduction efficiency. Correlation coefficient properties:
相关系数ρXY取值在-1到1之间；The correlation coefficient ρXY takes a value between -1 and 1;
当ρXY＝0时，称X,Y不相关；When ρXY = 0, X and Y are said to be irrelevant;
当|ρXY|＝1时，称X,Y完全相关，此时，X,Y之间具有线性函数关系；When |ρXY |=1, it is said that X and Y are completely correlated, and at this time, there is a linear functional relationship between X and Y;
当|ρXY|<1时，X的变动引起Y的部分变动，ρXY的绝对值越大，X的变动引起Y的变动就越大，|ρXY|>0.8时称为高度相关，当0.5<|ρXY|<0.8时称为显著相关，当0.3<| ρXY|<0.5时，成为低度相关，当|ρXY|<0.3时，称为无相关。When |ρXY |<1, the change of X causes a partial change of Y. The larger the absolute value of ρXY , the greater the change of Y caused by the change of X. When |ρXY |>0.8, it is called high correlation. When When 0.5<|ρXY |<0.8, it is called significant correlation, when 0.3<|ρXY |<0.5, it becomes low correlation, when |ρXY |<0.3, it is called no correlation.
如附图1所示，本发明实施例一公开了一种基于大数据的线路、台区线损率计算方法，其特征在于，包括：As shown in Figure 1, Embodiment 1 of the present invention discloses a method for calculating line loss rate based on big data, which is characterized in that it includes:
步骤100：从海量平台及线损数据库中抽取表底及档案数据，存入数据库；Step 100: extract table bottom and file data from massive platforms and line loss databases, and store them in the database;
步骤200：根据所述数据库中所述表底及档案数据，计算低压用户、专变用户和台区售电量；Step 200: According to the table bottom and file data in the database, calculate the electricity sales of low-voltage users, special transformer users and station districts;
步骤300：在国网省公司计算完成低压用户、专变用户和台区售电量后，将计算结果及高压通过数据中心的非结构化传输通道上传到国网总部非结构化数据库中；Step 300: After the State Grid Provincial Corporation completes the calculation of the low-voltage users, special transformer users, and power sales in the station area, upload the calculation results and high voltage to the unstructured database of the State Grid Headquarters through the unstructured transmission channel of the data center;
步骤400：抽取所述国网总部非结构化数据库的数据，将表底、档案和计算模型存入总部分布式文件系统中；Step 400: Extract the data of the unstructured database of the State Grid headquarters, and store the table bottom, files and calculation models in the distributed file system of the headquarters;
步骤500：根据步骤400获取的所述表底、档案和计算模型，计算线路、台区的供电量及线损率；Step 500: Calculate the power supply and line loss rate of the line and station area according to the table bottom, file and calculation model obtained in step 400;
步骤600，选择至少一种线损分析模式，进行线损分析，所述线损分析模式包括第一线损分析模式，第二线损分析模式和第三线损分析模式；根据一种或多种线损分析模式结果，生成诊断报告。如果选择了一种线损分析模式，那么直接将线损分析结果作为诊断报告；如果选择了多种线损分析模式，那么根据各种分析模式权重，重新生成诊断报告。Step 600, select at least one line loss analysis mode to perform line loss analysis, the line loss analysis mode includes a first line loss analysis mode, a second line loss analysis mode and a third line loss analysis mode; according to one or more line loss analysis modes Damage analysis mode results and generate diagnostic reports. If a line loss analysis mode is selected, the line loss analysis result is directly used as a diagnosis report; if multiple line loss analysis modes are selected, the diagnosis report is regenerated according to the weights of various analysis modes.
进一步的，所述第一线损分析模式为零供电量的线路和台区诊断模式，包括Further, the first line loss analysis mode is a line and station area diagnosis mode with zero power supply, including
步骤A100，获取所有供电量为零的线路和台区数据；Step A100, obtaining data of all lines and stations whose power supply is zero;
步骤A200，检测所述线路和台区供电侧表计是否采集失败；Step A200, detecting whether the meter on the power supply side of the line and station area fails to collect;
具体的，检测所述线路和台区的供电侧表计的数值，如果出现下述情况的一种或几种：上表底为空、下表底为空、上下表底为空、下表底小于上表底、有表底无电量，那么认为供电侧表计采集失败。Specifically, detect the value of the meter on the power supply side of the line and station area. If one or more of the following situations occur: the bottom of the upper meter is empty, the bottom of the lower meter is empty, the bottom of the upper and lower meters is empty, and the bottom of the lower meter is empty. If the bottom of the meter is smaller than the bottom of the upper meter, and there is a meter with a bottom but no electricity, then it is considered that the meter collection on the power supply side has failed.
步骤A300，检测供电侧表计是否没走电；Step A300, detecting whether the meter on the power supply side is not powered off;
具体的，检测所述线路和台区的供电侧表计上下表底的数值，如果上下表底数值一样，则没走电。Specifically, detect the values at the bottom of the upper and lower meters of the meter on the power supply side of the line and station area, if the values at the bottom of the upper and lower meters are the same, then there is no electricity.
步骤A400，检测所述线路和台区档案模型的配置情况；Step A400, detecting the configuration of the line and station area file models;
具体的，检测所述线路档案模型的配置情况的方法为：诊断所述线路的线路档案模型的配置情况，如果出现下述情况的一种或几种：开关与测点关系缺失、计量点与电能表关系缺失、供电计量点倍率为空、供电计量点抄表例日为空、供电计量点数据来源为空、电能表生效日期为空，那么认为所述线路档案模型配置错误；Specifically, the method for detecting the configuration of the line file model is: diagnosing the configuration of the line file model of the line, if one or more of the following situations occur: the relationship between the switch and the measuring point is missing, the metering point and If the energy meter relationship is missing, the scale of the power supply metering point is empty, the meter reading at the power supply metering point is empty, the data source of the power metering point is empty, and the effective date of the electric energy meter is empty, then the configuration of the line file model is considered to be wrong;
检测所述台区档案模型的配置情况的方法为：诊断台区档案模型的配置情况，如果台区档案计量点信息与台区模型计量点信息不一致，那么认为所述台区档案模型配置错误。The method for detecting the configuration of the station area file model is: diagnosing the configuration of the station area file model, if the metering point information of the station area file is inconsistent with the metering point information of the station area model, then it is considered that the configuration of the station area file model is wrong.
步骤A500，生成所述线路和台区零供电量诊断报告。Step A500, generating a diagnosis report of the zero power supply of the line and station area.
进一步的，所述第二线损分析模式为零售电量的线路和台区诊断模式，包括Further, the second line loss analysis mode is a line and station area diagnosis mode of retail electricity, including
步骤B100，获取所有售电量为零的线路和台区数据；Step B100, obtaining data of all lines and station areas whose electricity sales are zero;
步骤B200，检测所述线路的线变关系和所述台区的营配变关系；Step B200, detecting the line change relationship of the line and the distribution change relationship of the station area;
具体的，检测所述线路的线变关系的方法为：如果所述线路下无公专变，那么所述线路为空；Specifically, the method for detecting the line-change relationship of the line is: if there is no public-specific change under the line, then the line is empty;
检测所述台区的营配变关系的方法为：如果所述台区下无低压用户，那么所述台区为空；The method for detecting the distribution relationship of the station area is as follows: if there is no low-voltage user under the station area, then the station area is empty;
步骤B300，检测所述线路的公专变和所述台区的用户表计是否采集失败；Step B300, detecting whether the collection of the public transformer of the line and the user meter of the station area fails;
具体的，检测所述线路的公专变是否采集失败的方法为：检测公专变表计的数值，如果出现以下一种或几种情况：台区无总表、高压用户无总表、零度户、有表计无数值(包括上表底为空、下表底为空、上下表底为空、下表底小于上表底、有表底无电量)，那么认为所述线路的公专变采集失败；Specifically, the method for detecting whether the public substation of the line fails to collect is as follows: to detect the value of the public substation meter, if one or more of the following situations occur: there is no master meter in the station area, no master meter for high-voltage users, zero temperature If there is a meter with no value (including the bottom of the upper meter is empty, the bottom of the lower meter is empty, the bottom of the upper and lower meter is empty, the bottom of the lower meter is smaller than the bottom of the upper meter, and the bottom of the meter has no power), then it is considered that the public private meter of the line in question Change collection failed;
检测所述台区的用户表计是否采集失败的方法为：检测用户表计的数值，如果出现以下一种或几种情况：用户无总表、用户有表计无数值(包括上表底为空、下表底为空、上下表底为空、下表底小于上表底、有表底无电量)、零度户，那么认为所述台区的用户表计采集失败；The method for detecting whether the collection of the user meters in the station area fails is: to detect the value of the user meters, if one or more of the following situations occur: the user has no total meter, the user has a meter but no value (including the bottom of the upper table is empty, the bottom of the lower table is empty, the bottom of the upper and lower tables is empty, the bottom of the lower table is smaller than the bottom of the upper table, there is a bottom of the table and no electricity), zero degree households, then it is considered that the collection of user meters in the station area has failed;
步骤B400，检测所述线路的公专变和所述台区的用户表计是否没走电；Step B400, detecting whether the public substation of the line and the user meter in the station area are not powered;
检测所述线路的公专变是否没走电的方法为：检测公专变表计上下表底的数值，上下表底数值一样，则没走电；The method for detecting whether the public transformer of the line has no electricity is as follows: detect the values at the bottom of the upper and lower meters of the meter of the public transformer, if the values at the bottom of the upper and lower meters are the same, then there is no electricity;
检测所述台区的用户表计是否没走电的方法为：检测用户表计上下表底的数值，上下表底数值一样，则没走电。The method for detecting whether the user meters in the station area have no electricity is as follows: detect the values at the bottom of the upper and lower meters of the user meters, if the values at the bottom of the upper and lower meters are the same, then there is no electricity.
步骤B500，生成所述线路和台区零售电量诊断报告。Step B500, generating a diagnosis report of the retail electric quantity of the line and station area.
进一步的，所述第三线损分析模式为高损与负损的线路和台区诊断模式，包括Further, the third line loss analysis mode is a high loss and negative loss line and station area diagnosis mode, including
步骤C100，获取所有负损和高损的线路和台区的数据；Step C100, obtaining data of all negative-loss and high-loss lines and station areas;
步骤C200，检测所述线路和台区供电侧计量是否有误；Step C200, detecting whether the metering of the line and the power supply side of the station area is wrong;
具体的，如果所述线路为高损，所述线路所在母线为负损，或者所述线路为负损，所述线路所在母线为高损，那么所述线路供电侧计量有误；Specifically, if the line is high loss and the bus bar where the line is located is negative loss, or if the line is negative loss and the bus bar where the line is located is high loss, then the measurement on the power supply side of the line is wrong;
所述台区为高损，所述台区所在线路为负损，或者所述台区为负损，所述台区所在线路为高损，那么所述台区供电侧计量有误；If the station area is high loss and the line where the station area is located is negative loss, or if the station area is negative loss and the line where the station area is located is high loss, then the metering of the power supply side of the station area is wrong;
母线和线路的高损、负损定义为：母线或线路的不平衡率大于2％为高损，小于-2％为负损；High loss and negative loss of busbar and line are defined as: if the unbalance rate of busbar or line is greater than 2%, it is high loss, and if it is less than -2%, it is negative loss;
步骤C300，检测所述线路和台区下是否下挂电量异常用户；Step C300, detecting whether the user with abnormal power is connected to the line and station area;
检测所述线路是否下挂电量异常用户的方法为：The method for detecting whether the line is connected to a user with abnormal power is as follows:
线路所在母线平衡，下挂公专变总表电量从大到小排序，累积电量和刚好大于等于线路供电量的用户为可疑用户。The busbar where the line is located is balanced, and the electric quantity of the main meter of the public substation connected below is sorted from large to small. Users whose cumulative electric quantity is just greater than or equal to the power supply of the line are suspicious users.
假设某条线路下共有n个用户，按照电量由大到小顺序排列，计算所有用户累计电量，如果计算结果大于或等于(≥)线路供电量，则截取该线路下用户，用户分别设为：x1,x2,x3……xn，各用户对应电量分别为：y1,y2,y3……yn。Assuming that there are n users in a certain line, they are arranged according to the order of power consumption from large to small, and the accumulated power of all users is calculated. If the calculation result is greater than or equal to (≥) the power supply of the line, the users under the line are intercepted, and the users are respectively set as: x1 , x2 , x3 ... xn , the corresponding electric power of each user is: y1 , y2 , y3 ... yn .
累计电量为The accumulated power is
各用户电量占比分别为：y1/Y、(y1+y2)/Y、(y1+y2+y3)/Y、……(y1+y2+y3+…+ yn)/Y。The power consumption ratio of each user is: y1 /Y, (y1 +y2 )/Y, (y1 +y2 +y3 )/Y, ...(y1 +y2 +y3 +...+ yn )/Y.
以线路下有5个用户为例，累计电量占比图形如附图2所示。Taking 5 users under the line as an example, the graph of the cumulative power ratio is shown in Figure 2.
台区所在线路线损率正常，下挂用户总表电量从大到小排序，累积电量和刚好大于等于台区供电量的用户为可疑用户，求出可疑用户的累积占比，并画出占比折线图。The loss rate of the online line of the station area is normal, and the power of the total meter of the connected users is sorted from large to small. The users whose cumulative power is just greater than or equal to the power supply of the station area are suspicious users. Find the cumulative proportion of suspicious users, and draw the proportion than a line chart.
假设某台区下共有n个用户，按照电量由大到小顺序排列，计算所有用户累计电量，如果计算结果大于或等于(≥)台区供电量，则截取该台区下用户，用户分别设为：x1,x2,x3……xn，各用户对应电量分别为：y1,y2,y3……yn。Assuming that there are n users in a station area, they are arranged according to the order of power consumption from large to small, and the accumulated power of all users is calculated. If the calculation result is greater than or equal to (≥) the power supply of the station area, the users in the station area are intercepted, and the users respectively set It is: x1 , x2 , x3 ... xn , and the power corresponding to each user is: y1 , y2 , y3 ... yn .
累计电量为The accumulated power is
各用户电量占比分别为：y1/Y、(y1+y2)/Y、(y1+y2+y3)/Y、……(y1+y2+y3+…+ yn)/Y。The power consumption ratio of each user is: y1 /Y, (y1 +y2 )/Y, (y1 +y2 +y3 )/Y, ...(y1 +y2 +y3 +...+ yn )/Y.
以线路下有6个用户为例，累计电量占比图形如附图3所示。Taking 6 users under the line as an example, the cumulative power ratio graph is shown in Figure 3.
步骤C400，检测所述线路线变和所述台区营配变关系；Step C400, detecting the relationship between the route change of the line and the distribution change of the station area;
所述线路线变关系的检测方法为：The detection method of the line linear relationship is:
计算线路线损率波动与每一个下挂公专变电量波动的相关系数，若相关，则该公专变线变关系有误。Calculate the correlation coefficient between the line loss rate fluctuation and the power fluctuation of each connected public transformer. If there is a correlation, the relationship between the public transformer and the transformer is wrong.
线变关系排查过程如下：The line change relationship investigation process is as follows:
相关系数求取：计算线路线损率变化量与每个下挂公专变电量变化量的相关系数，如果相关，则该公专变线变关系有误。Calculation of the correlation coefficient: calculate the correlation coefficient between the line loss rate change and the power change of each connected public-private substation. If there is a correlation, the public-private line-to-substation relationship is wrong.
1)获取该线路下每台配变最近5个月的电量变化量，设为A＝{A1、A2、A3、A4、A5}；1) Obtain the power variation of each distribution transformer under the line in the last 5 months, set A={A1 , A2 , A3 , A4 , A5 };
2)获取该线路最近5个月线损率的变化量，设为B＝{B1、B2、B3、B4、B5}；2) Obtain the variation of the line loss rate of the line in the last 5 months, set B={B1 , B2 , B3 , B4 , B5 };
3)求A、B的相关系数ρAB3) Find the correlation coefficient ρAB of A and B
4)如果|ρAB|>0.8，则强相关；|ρAB|<0.3则低度相关，其它为中度相关。4) If |ρAB |>0.8, it means strong correlation; |ρAB |<0.3 means low correlation, and others are moderate correlation.
所述台区营配变关系的检测方法为：The detection method of the distribution and distribution relationship in the station area is as follows:
计算台区线损率波动与每一个下挂用户电量的相关系数，若相关，则该用户的营配变关系有误。Calculate the correlation coefficient between the fluctuation of the line loss rate in the station area and the power of each connected user. If there is a correlation, the relationship between the distribution and distribution of the user is wrong.
营配变关系排查过程如下：The investigation process of the relationship between the distribution and distribution is as follows:
相关系数求取：计算台区线损率变化量与每个下挂用户电量的相关系数，如果相关，则该用户的营配变关系有误。Calculation of the correlation coefficient: calculate the correlation coefficient between the change of the line loss rate in the station area and the power of each connected user. If there is a correlation, the relationship between the distribution and distribution of the user is wrong.
①获取该台区下每个用户最近5个月的电量，设为C＝{C1、C2、C3、C4、C5}；① Obtain the power of each user in the station area in the last 5 months, set C = {C1 , C2 , C3 , C4 , C5 };
②获取该台区最近5个月线损率的变化量，设为D＝{D1、D2、D3、D4、D5}② Obtain the variation of the line loss rate in the station area in the last 5 months, set D={D1 , D2 , D3 , D4 , D5 }
③求C、D的相关系数ρCD③ Calculate the correlation coefficient ρCD of C and D
其中in
④如果|ρCD|>0.8，则强相关；|ρCD|<0.3则低度相关；其它为中度相关。|ρCD|>0.3则相关。④ If |ρCD |>0.8, it means strong correlation; |ρCD |<0.3 means low correlation; others are moderate correlation. |ρCD |>0.3 is relevant.
步骤C500，检测公专变、台区总表是否采集失败；Step C500, detecting whether the collection of the public-specific variable and the general table of the station district has failed;
具体的，如果有以下情况的一种或几种：线路下挂公专变无表计、有表计无数据(包括上表底为空、下表底为空、上下表底为空、下表底小于上表底、有表底无电量)、存在零度户，那么所述线路采集失败；Specifically, if there are one or more of the following situations: the line connected to the public private line has no meter, there is a meter but no data (including the bottom of the upper meter is empty, the bottom of the lower meter is empty, the bottom of the upper and lower meters is empty, and the bottom of the lower meter is empty. The bottom of the meter is smaller than the bottom of the upper meter, there is a bottom of the meter but no electricity), and there is a zero-degree household, then the line acquisition fails;
具体的，如果有以下情况的一种或几种：台区下挂用户无表计、有表计无数据(包括上表底为空、下表底为空、上下表底为空、下表底小于上表底、有表底无电量)、存在零度户，那么所述台区总表采集失败；Specifically, if there are one or more of the following situations: the user connected to the platform area has no meter, there is a meter but no data (including the bottom of the upper table is empty, the bottom of the lower table is empty, the bottom of the upper and lower tables is empty, and the bottom of the lower table is empty. The bottom is smaller than the bottom of the upper table, there is no electricity at the bottom of the table), and there is a zero-degree household, then the collection of the general table of the station area fails;
步骤C600，检测所述线路和台区是否存在用户电量突减；Step C600, detecting whether there is a sudden drop in user power in the line and station area;
检测所述线路是否存在用户电量突减的方法为：所述线路的当月公专变电量与上月电量相比，减少20％以上，即为所述线路用户电量突减；The method for detecting whether there is a sudden drop in user power on the line is as follows: the current month’s public-private power conversion power of the line is reduced by more than 20% compared with the previous month’s power, which means that the user’s power on the line has suddenly dropped;
检测所述台区是否存在用户电量突减的方法为：所述台区的当月下挂用户电量与上月电量相比，减少20％以上，即为所述台区用户电量突减；The method for detecting whether there is a sudden decrease in user power in the station area is as follows: the power consumption of the users connected to the station in the current month is reduced by more than 20% compared with the power in the previous month, which means that the user power in the station area has suddenly decreased;
步骤C700，生成所述线路和台区负损和高损诊断报告。Step C700, generating a negative loss and high loss diagnosis report for the line and station area.
在使用上述方法分析线路和台区线损异常之前，只能依靠人工核对来判断的方法，每个线路和台区，根据其规模，大致要花两分钟到二十分钟左右的时间，使用本发明方法之后，可以批量导入线路和台区的线损数据，每个线路和台区只需要花费50ms的时间，由此可见，本发明的方法极大的提高了分析效率，可以较为快捷的确定线路和台区的线损异常原因，从而及时进行整改，增强电网服务社会的能力。Before using the above method to analyze the abnormal line loss of the line and station area, it can only be judged by manual checking. Each line and station area will take about two minutes to twenty minutes according to its scale. After inventing the method, the line loss data of lines and stations can be imported in batches, and it only takes 50ms for each line and station. It can be seen that the method of the present invention greatly improves the analysis efficiency and can be determined more quickly The cause of abnormal line loss in the line and station area, so as to make timely rectification and enhance the ability of the power grid to serve the society.
一种对步骤600的改进方法为：使用随机森林算法，确定线路和台区的线损分析模型，生成诊断报告；An improved method to step 600 is: use random forest algorithm to determine the line loss analysis model of the line and station area, and generate a diagnosis report;
如附图4所示，进一步包括：As shown in accompanying drawing 4, further include:
步骤S606：将所述线路和台区线损数据整理成训练集，并进行线损分析特征选择，确定训练集使用的特征；Step S606: Arranging the line loss data of the line and station area into a training set, and performing line loss analysis feature selection to determine the features used in the training set;
步骤S610：对于给定的处理后的线路和台区线损数据训练集S和其特征维数F，设定随机森林的相关参数：使用到的分类树的数量g，每棵树的最大深度d，每个节点使用到的特征数量f；并制定终止条件：节点上最少样本数s，节点上最少的信息增益m；Step S610: For a given training set S of processed line and station area line loss data and its feature dimension F, set the relevant parameters of the random forest: the number g of classification trees used, the maximum depth of each tree d, the number of features f used by each node; and formulate termination conditions: the minimum number of samples s on the node, the minimum information gain m on the node;
步骤S620：有放回地从S中随机抽取大小和S一样的训练集S(i)，并将其作为根节点的样本，从根节点开始训练；Step S620: Randomly extract a training set S(i) with the same size as S from S with replacement, and use it as a sample of the root node, and start training from the root node;
步骤S630：若当前节点满足终止条件，则设置当前节点为叶子节点，该叶子节点的预测输出为当前节点样本集合中数量最多的那一类c(j)，定义概率p为c(j)占当前样本集的比例。然后继续训练其他节点。如果当前节点没有达到终止条件，则从F维特征中无放回地随机选取f维特征。利用这f维特征，寻找分类效果最好的一维特征k及其阈值th，当前节点上样本第k维特征小于th的样本被划分到左节点，其余的被划分到右节点。继续训练其他节点；Step S630: If the current node satisfies the termination condition, then set the current node as a leaf node, the predicted output of the leaf node is the type c(j) with the largest number in the sample set of the current node, and define the probability p as c(j) accounts for The proportion of the current sample set. Then continue training other nodes. If the current node does not meet the termination condition, f-dimensional features are randomly selected from the F-dimensional features without replacement. Use this f-dimensional feature to find the one-dimensional feature k with the best classification effect and its threshold value th. The samples whose k-th dimensional feature is smaller than th on the current node are divided into the left node, and the rest are divided into the right node. Continue to train other nodes;
步骤S640：如果重复所有节点都训练过了或者被标记为叶子节点，那么转入步骤S650；否则转入步骤S620；Step S640: If all nodes have been trained or marked as leaf nodes, then go to step S650; otherwise, go to step S620;
步骤S650：如果所有分类树都被训练过，那么结束；否则转入步骤S620。Step S650: If all classification trees have been trained, then end; otherwise, go to step S620.
构造线路和台区的线损分析的随机森林的具体实施方式为:The specific implementation of the random forest of the line loss analysis of construction line and platform area is:
假设线损分析特征选择之后确定的特征为供电侧表计、供电量计量和线路为高损或负损，训练集如下表所示：Assuming that the features determined after line loss analysis feature selection are power supply side meters, power supply metering, and lines are high loss or negative loss, the training set is shown in the following table:
对于给定的处理后的用电信息数据训练集S如上表，第一列表示线路或台区供电侧表计，正常为1，异常为0；第二列表示线路或台区供电量计量，正常为1，异常为0；第三列表示线路或台区为高损或负损，高损为1，负损为0；第四列表示线路异常原因，分别以1,2,3代替具体原因；其特征维数F＝3，设定随机森林的相关参数：使用到的分类树的数量g＝3，每棵树的最大深度d＝4，每个节点使用到的特征数量f＝1；并制定终止条件：节点上最少样本数s＝1，节点上最少的信息增益m＝0.001；For the given processed power consumption information data training set S as shown in the above table, the first column indicates the meter on the power supply side of the line or station area, which is 1 for normal and 0 for abnormality; the second column indicates the power supply measurement of the line or station area, Normal is 1, abnormal is 0; the third column indicates that the line or station area is high loss or negative loss, high loss is 1, and negative loss is 0; the fourth column indicates the cause of line abnormality, and the specific ones are replaced by 1, 2, and 3 respectively. Reason; its feature dimension F=3, set the relevant parameters of the random forest: the number of classification trees used g=3, the maximum depth of each tree d=4, the number of features used by each node f=1 ; And formulate the termination conditions: the minimum number of samples on the node s = 1, the minimum information gain on the node m = 0.001;
有放回地从S中随机抽取大小和S一样的训练集S(i)，并将其作为根节点的样本，从根节点开始训练；分别取{(1,1,1,1)，(1,1,0,2)，(1,1,1,1)}，{(1,1,0,2)，(1,1,0,2)，(1,1,1,1)}，{(0,1,0,3)， (1,1,0,2)，(0,1,0,3)}，按照所述步骤630～650的方法，可以得到如图4所示的三棵分类树，从而完成了线路和台区的线损分析的随机森林的构造。Randomly select a training set S(i) of the same size as S from S with replacement, and use it as a sample of the root node, and start training from the root node; respectively take {(1,1,1,1), ( 1,1,0,2), (1,1,1,1)}, {(1,1,0,2), (1,1,0,2), (1,1,1,1) }, {(0,1,0,3), (1,1,0,2), (0,1,0,3)}, according to the method of steps 630-650, can get as shown in Figure 4 The three classification trees shown, thus completing the construction of the random forest for the line loss analysis of the line and station area.
步骤S600：输入待预测的线路或台区线损情况表，作为测试集；Step S600: Input the line loss table to be predicted or station area, as a test set;
步骤S700：对测试集进行预处理；Step S700: Preprocessing the test set;
步骤S800：利用信息熵算法对测试集进行特征选择；Step S800: Using the information entropy algorithm to perform feature selection on the test set;
步骤S900：分析线路和台区的线损异常原因，具体方法为：获取所有g棵树的预测值；将 g棵树中数量最多的线损异常原因，作为最终的线损异常原因，生成诊断报告；或者按照线损异常原因的个数从大到小排列，由用户选择诊断报告中线损异常原因呈现的个数，生成诊断报告；或者由用户设定异常原因所占百分比的阈值，百分比超出该阈值的异常原因，将被呈现在诊断报告中。Step S900: Analyze the causes of abnormal line loss in the line and station area, the specific method is: obtain the predicted values of all g trees; use the cause of abnormal line loss with the largest number in g trees as the final cause of abnormal line loss, and generate a diagnosis report; or according to the number of abnormal line loss causes in descending order, the user selects the number of abnormal line loss causes in the diagnostic report to generate a diagnostic report; or the user sets the threshold for the percentage of abnormal reasons, and the percentage exceeds The reason for the abnormality of this threshold will be presented in the diagnosis report.
将本发明中步骤600原方法和改进方法做对比，同样数据量下考察二者的准确率，由上表可以看出，步骤600原方法大致在0.8左右，并且随着数据的增加呈缓慢下降趋势；步骤600 改进方法准确率大致在0.9左右，并且随着数据的增加基本保持稳定。数据表明，步骤600的改进方法准确率更高，从而与现有技术相比取得了良好的效果，具有显著的进步。Comparing the original method of step 600 and the improved method in the present invention, and investigating the accuracy of the two under the same amount of data, it can be seen from the above table that the original method of step 600 is roughly around 0.8, and slowly decreases with the increase of data Trend; Step 600 The accuracy of the improved method is roughly around 0.9, and remains basically stable with the increase of data. The data shows that the improved method in step 600 has a higher accuracy rate, thereby achieving good results compared with the prior art, and has a significant progress.
使用步骤600原方法，虽然数据处理速度得到了提高，但是只能串行处理数据，数据量增加的情况下，处理时间呈线性增长；使用步骤600改进方法，构造随机森林，可以将数据批量处理，极大的提高了处理效率，节省了人力物力。Using the original method of step 600, although the data processing speed has been improved, the data can only be processed serially. When the amount of data increases, the processing time increases linearly; using the improved method of step 600 to construct a random forest, the data can be processed in batches , which greatly improves the processing efficiency and saves manpower and material resources.
本发明实施例可以在线路和台区发生异常的情况下，准确地判别发生异常的原因，迅速的作出相应措施进行整改，提高电网的健壮性和容错性，保障了社会和人民用电，提升了电网正面形象，扩大了影响力。The embodiment of the present invention can accurately determine the cause of the abnormality when the line and the station area are abnormal, and quickly take corresponding measures to rectify it, improve the robustness and fault tolerance of the power grid, ensure the society and people's electricity consumption, and improve It strengthened the positive image of the power grid and expanded its influence.
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，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发明各实施例技术方案的精神和范围。Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710675256.6ACN107527114B (en) | 2017-08-09 | 2017-08-09 | An abnormal analysis method of line station area based on big data |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710675256.6ACN107527114B (en) | 2017-08-09 | 2017-08-09 | An abnormal analysis method of line station area based on big data |
| Publication Number | Publication Date |
|---|---|
| CN107527114Atrue CN107527114A (en) | 2017-12-29 |
| CN107527114B CN107527114B (en) | 2019-04-23 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710675256.6AActiveCN107527114B (en) | 2017-08-09 | 2017-08-09 | An abnormal analysis method of line station area based on big data |
| Country | Link |
|---|---|
| CN (1) | CN107527114B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086950A (en)* | 2018-10-11 | 2018-12-25 | 国网上海市电力公司 | A kind of user's coulometric analysis prediction technique based on big data analysis |
| CN109767349A (en)* | 2018-10-23 | 2019-05-17 | 中国电力科学研究院有限公司 | A method and system for verifying and correcting line loss data in a distribution network |
| CN109919425A (en)* | 2019-01-23 | 2019-06-21 | 国网浙江省电力有限公司 | An error correction method based on correlation analysis for user relationship in station area |
| CN110134708A (en)* | 2019-03-03 | 2019-08-16 | 云南电网有限责任公司信息中心 | Electric net platform region line loss abnormal cause diagnostic method, device, computer equipment and storage medium |
| CN110276511A (en)* | 2019-04-16 | 2019-09-24 | 国网浙江海盐县供电有限公司 | A Discrimination Method for Abnormality of Line Change Relationship Based on Correlation Between Electricity and Line Loss |
| CN110472871A (en)* | 2019-08-16 | 2019-11-19 | 广东电网有限责任公司 | A kind of investigation method for management line loss abnormal cause |
| CN110749784A (en)* | 2019-08-05 | 2020-02-04 | 上海大学 | A method for detecting power theft based on wavelet analysis of power data |
| CN111461577A (en)* | 2020-04-28 | 2020-07-28 | 广东电网有限责任公司惠州供电局 | Line loss calculation method, device, equipment and storage medium |
| CN111579928A (en)* | 2020-05-25 | 2020-08-25 | 国网江苏省电力有限公司无锡供电分公司 | Distribution line line loss analysis method and analysis device |
| CN111598380A (en)* | 2020-04-01 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | A method for judging the causes of negative losses in distribution lines |
| CN111695600A (en)* | 2020-05-13 | 2020-09-22 | 国网湖北省电力有限公司电力科学研究院 | Multi-threshold and KNN-based distribution room classification method |
| CN111985524A (en)* | 2020-07-01 | 2020-11-24 | 佳源科技有限公司 | Improved low-voltage transformer area line loss calculation method |
| CN112035544A (en)* | 2020-08-29 | 2020-12-04 | 国网信通亿力科技有限责任公司 | A method for monitoring and diagnosing abnormal data in distribution network |
| CN112308437A (en)* | 2020-11-04 | 2021-02-02 | 国网北京市电力公司 | Line loss management method, system, device and storage medium based on big data analysis |
| CN113655308A (en)* | 2021-07-30 | 2021-11-16 | 国网天津市电力公司 | A Synchronous Line Loss Monitoring and Governance System Based on Intelligent Perception |
| CN114236283A (en)* | 2021-12-15 | 2022-03-25 | 广东电网有限责任公司 | Method and device for determining line loss reason of power supply network |
| CN114565324A (en)* | 2022-04-02 | 2022-05-31 | 广东电网有限责任公司 | Transformer area line loss evaluation method and device, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102545213A (en)* | 2012-01-11 | 2012-07-04 | 藁城市供电公司 | System and method for managing line loss of power grid in real time |
| CN102637288A (en)* | 2012-03-31 | 2012-08-15 | 上海市电力公司 | Method for analysis of line loss in distribution-room area of power supply enterprise |
| US20140148963A1 (en)* | 2009-01-14 | 2014-05-29 | Integral Analytics, Inc. | Optimization of microgrid energy use and distribution |
| US20150088583A1 (en)* | 2010-01-29 | 2015-03-26 | Enginuity Worldwide, LLC | Sustainability campus of co-located facilities |
| CN106570778A (en)* | 2016-10-14 | 2017-04-19 | 国网信通亿力科技有限责任公司 | A method of data integration and line loss analysis and calculation based on big data |
| CN106932639A (en)* | 2017-03-22 | 2017-07-07 | 深圳市均方根科技有限公司 | A kind of platform area line loss analyzing management system |
| CN106950440A (en)* | 2017-02-14 | 2017-07-14 | 国网新疆电力公司伊犁供电公司 | Transformer station's metering critical point quickly judges alarm method extremely |
| CN107024641A (en)* | 2017-03-29 | 2017-08-08 | 国网上海市电力公司 | A kind of platform area line loss per unit exception monitoring system |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140148963A1 (en)* | 2009-01-14 | 2014-05-29 | Integral Analytics, Inc. | Optimization of microgrid energy use and distribution |
| US20150088583A1 (en)* | 2010-01-29 | 2015-03-26 | Enginuity Worldwide, LLC | Sustainability campus of co-located facilities |
| CN102545213A (en)* | 2012-01-11 | 2012-07-04 | 藁城市供电公司 | System and method for managing line loss of power grid in real time |
| CN102637288A (en)* | 2012-03-31 | 2012-08-15 | 上海市电力公司 | Method for analysis of line loss in distribution-room area of power supply enterprise |
| CN106570778A (en)* | 2016-10-14 | 2017-04-19 | 国网信通亿力科技有限责任公司 | A method of data integration and line loss analysis and calculation based on big data |
| CN106950440A (en)* | 2017-02-14 | 2017-07-14 | 国网新疆电力公司伊犁供电公司 | Transformer station's metering critical point quickly judges alarm method extremely |
| CN106932639A (en)* | 2017-03-22 | 2017-07-07 | 深圳市均方根科技有限公司 | A kind of platform area line loss analyzing management system |
| CN107024641A (en)* | 2017-03-29 | 2017-08-08 | 国网上海市电力公司 | A kind of platform area line loss per unit exception monitoring system |
| Title |
|---|
| 施文: "台区线损异常成因分析及解决方法", 《电力需求侧管理》* |
| 肖建红: "低压台区线损异常的监测与分析", 《电力需求侧管理》* |
| 蔡晓燕: "基于智能用电大数据分析的台区线损管理初探", 《科技创新与应用》* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109086950A (en)* | 2018-10-11 | 2018-12-25 | 国网上海市电力公司 | A kind of user's coulometric analysis prediction technique based on big data analysis |
| CN109767349A (en)* | 2018-10-23 | 2019-05-17 | 中国电力科学研究院有限公司 | A method and system for verifying and correcting line loss data in a distribution network |
| CN109919425A (en)* | 2019-01-23 | 2019-06-21 | 国网浙江省电力有限公司 | An error correction method based on correlation analysis for user relationship in station area |
| CN110134708A (en)* | 2019-03-03 | 2019-08-16 | 云南电网有限责任公司信息中心 | Electric net platform region line loss abnormal cause diagnostic method, device, computer equipment and storage medium |
| CN110276511A (en)* | 2019-04-16 | 2019-09-24 | 国网浙江海盐县供电有限公司 | A Discrimination Method for Abnormality of Line Change Relationship Based on Correlation Between Electricity and Line Loss |
| CN110749784A (en)* | 2019-08-05 | 2020-02-04 | 上海大学 | A method for detecting power theft based on wavelet analysis of power data |
| CN110749784B (en)* | 2019-08-05 | 2022-07-08 | 上海大学 | Line electricity stealing detection method based on electric power data wavelet analysis |
| CN110472871A (en)* | 2019-08-16 | 2019-11-19 | 广东电网有限责任公司 | A kind of investigation method for management line loss abnormal cause |
| CN110472871B (en)* | 2019-08-16 | 2023-07-07 | 广东电网有限责任公司 | Investigation method for managing line loss abnormal reasons |
| CN111598380A (en)* | 2020-04-01 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | A method for judging the causes of negative losses in distribution lines |
| CN111598380B (en)* | 2020-04-01 | 2022-08-16 | 国网江西省电力有限公司电力科学研究院 | Distribution line negative loss reason distinguishing method |
| CN111461577A (en)* | 2020-04-28 | 2020-07-28 | 广东电网有限责任公司惠州供电局 | Line loss calculation method, device, equipment and storage medium |
| CN111695600A (en)* | 2020-05-13 | 2020-09-22 | 国网湖北省电力有限公司电力科学研究院 | Multi-threshold and KNN-based distribution room classification method |
| CN111695600B (en)* | 2020-05-13 | 2023-08-18 | 国网湖北省电力有限公司电力科学研究院 | Multi-threshold and KNN-based station classification method |
| CN111579928A (en)* | 2020-05-25 | 2020-08-25 | 国网江苏省电力有限公司无锡供电分公司 | Distribution line line loss analysis method and analysis device |
| CN111579928B (en)* | 2020-05-25 | 2022-03-15 | 国网江苏省电力有限公司无锡供电分公司 | Distribution line loss analysis method and analysis device |
| CN111985524A (en)* | 2020-07-01 | 2020-11-24 | 佳源科技有限公司 | Improved low-voltage transformer area line loss calculation method |
| CN112035544A (en)* | 2020-08-29 | 2020-12-04 | 国网信通亿力科技有限责任公司 | A method for monitoring and diagnosing abnormal data in distribution network |
| CN112035544B (en)* | 2020-08-29 | 2022-05-17 | 国网信通亿力科技有限责任公司 | Power distribution network data anomaly monitoring and diagnosis method |
| CN112308437A (en)* | 2020-11-04 | 2021-02-02 | 国网北京市电力公司 | Line loss management method, system, device and storage medium based on big data analysis |
| CN113655308A (en)* | 2021-07-30 | 2021-11-16 | 国网天津市电力公司 | A Synchronous Line Loss Monitoring and Governance System Based on Intelligent Perception |
| CN114236283A (en)* | 2021-12-15 | 2022-03-25 | 广东电网有限责任公司 | Method and device for determining line loss reason of power supply network |
| CN114236283B (en)* | 2021-12-15 | 2024-02-13 | 广东电网有限责任公司 | Method and device for determining line loss reason of power supply network |
| CN114565324A (en)* | 2022-04-02 | 2022-05-31 | 广东电网有限责任公司 | Transformer area line loss evaluation method and device, electronic equipment and storage medium |
| Publication number | Publication date |
|---|---|
| CN107527114B (en) | 2019-04-23 |
| Publication | Publication Date | Title |
|---|---|---|
| CN107527114A (en) | A kind of circuit taiwan area exception analysis method based on big data | |
| CN113159339B (en) | One-area one-index line loss management method and system based on big data | |
| CN114862139B (en) | Data-driven-based abnormal diagnosis method for line loss rate of transformer area | |
| CN104700321B (en) | A kind of power transmission and transformation equipment state operation trend analysis method | |
| CN115018139B (en) | Method and system for online identifying error state of current transformer based on interphase characteristics | |
| CN112035544B (en) | Power distribution network data anomaly monitoring and diagnosis method | |
| CN106154209A (en) | Electrical energy meter fault Forecasting Methodology based on decision Tree algorithms | |
| CN111507013A (en) | Line loss fault positioning implementation method for power system | |
| CN101859409A (en) | Condition-based maintenance system for power transmission and transformation equipment based on risk assessment | |
| CN106570784A (en) | Integrated model for voltage monitoring | |
| CN110659273A (en) | Data abnormality monitoring and repair method of distributed big data acquisition platform | |
| CN109034461A (en) | A kind of voltage dip Stochastic prediction method based on actual electric network monitoring information | |
| CN111552686B (en) | A method and device for evaluating power data quality | |
| CN113487447A (en) | Power distribution network load prediction and line loss cause analysis method based on big data | |
| CN115545514A (en) | Health degree evaluation-based differentiated operation and maintenance method and device for power distribution fusion equipment | |
| CN113111955A (en) | Line loss abnormal data expert system and detection method | |
| CN110910026B (en) | Cross-provincial power transmission line loss intelligent management and decision method and system | |
| CN111724060A (en) | An integrated analysis and monitoring system for line loss in Taiwan area and its analysis method | |
| CN106779267A (en) | A kind of electric power system model based on multi-layer Fuzzy method and quality testing method | |
| CN116128467A (en) | Power utilization system maintenance method, device, computer equipment and storage medium | |
| CN111340337A (en) | Evaluation method of high-penetration distributed power grid connection to distribution network operation risk | |
| JP2024015999A (en) | Big data screening system for abnormal capacity of distribution transformers | |
| CN115833387A (en) | Automatic state inspection method for energy storage power station | |
| CN111861256A (en) | An active distribution network reconfiguration decision-making method and system | |
| CN115375073A (en) | A decision-making method for distribution station operation and maintenance based on multi-dimensional data fusion evaluation |
| 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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information | Address after:No. 8 Huanglong Road, Hangzhou, Zhejiang Province Applicant after:State Grid Zhejiang Electric Power Company Applicant after:State Grid Inforamtion & Telecommunication Great Power Science and Technology Co., Ltd. Address before:361009 402, room 36, two day watching day, Xiamen Software Park, Siming District, Xiamen, Fujian. Applicant before:State Grid Inforamtion & Telecommunication Great Power Science and Technology Co., Ltd. Applicant before:State Grid Zhejiang Electric Power Company | |
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information | Address after:Room 402, No. 36 Guanri Road, Phase II Software Park, Siming District, Xiamen City, Fujian Province Applicant after:State Grid Inforamtion & Telecommunication Great Power Science and Technology Co., Ltd. Applicant after:State Grid Zhejiang Electric Power Company Address before:No. 8 Huanglong Road, Hangzhou, Zhejiang Province Applicant before:State Grid Zhejiang Electric Power Company Applicant before:State Grid Inforamtion & Telecommunication Great Power Science and Technology Co., Ltd. | |
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder | Address after:Room 402, No. 36 Guanri Road, Phase II Software Park, Siming District, Xiamen City, Fujian Province Patentee after:STATE GRID INFO-TELECOM GREAT POWER SCIENCE AND TECHNOLOGY Co.,Ltd. Patentee after:STATE GRID ZHEJIANG ELECTRIC POWER Co.,Ltd. Address before:Room 402, No. 36 Guanri Road, Phase II Software Park, Siming District, Xiamen City, Fujian Province Patentee before:STATE GRID INFO-TELECOM GREAT POWER SCIENCE AND TECHNOLOGY Co.,Ltd. Patentee before:STATE GRID ZHEJIANG ELECTRIC POWER Co. |