Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The method for predicting the new energy generation power region of the intelligent fusion of the multiple stations, provided by the embodiment of the application, can be applied to a new energy generation power region prediction system of the intelligent fusion of the multiple stations as shown in fig. 1. The new energy power generation power region prediction system with intelligent fusion of multiple stations comprises a power prediction demand end and a server; wherein the power forecast demand side 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process, such as geographic coordinates of each new energy station in the target area. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. Specifically, when detecting that the operation and maintenance party has a power prediction requirement, the power prediction requirement end may generate a power prediction request, and send the power prediction request to the server 104; the server 104 is configured with a power prediction system, and after receiving a power prediction request sent by a power prediction demand end, the power prediction system can be used for acquiring target prediction power generated by each new energy station in a target area corresponding to a future period; further, the server predicts the new energy power generation of the target area in the future period by combining the obtained target predicted power generation of each new energy station, the contribution weight of each new energy station to the target area, the historical actual total power generation of the target area in the historical period and the geographic coordinates of each new energy station. Optionally, after predicting the new energy generated power of the target area in the future period, the server 104 may interact with the power prediction demand end 102 through the network, and feed back the prediction result to the power prediction demand end 102, so that the staff can better manage each new energy station of the target area according to the prediction result.
The power prediction demand end 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a method for predicting a new energy generated power area by intelligent fusion of multiple stations is provided, and the method is applied to the server 104 in fig. 1 for illustration, and includes the following steps:
s201, obtaining target prediction power generation power corresponding to each new energy station in the target area in a future period.
In this embodiment, the target area is the area to be predicted where the new energy generated power prediction needs. The new energy station is the station which utilizes new energy to generate power in the target area. Wherein, the target area can comprise a plurality of new energy stations. The future time period is a period of time after the current time when the new energy generated power needs to be predicted. The target predicted power is the power of each new energy station obtained through prediction in future time period. Each new energy station corresponds to a target predicted power.
Specifically, when detecting that the operation and maintenance side has a power prediction requirement, the power prediction requirement end can generate a power prediction request and send the generated power prediction request to the server. After the server receives the power prediction request, the data acquisition module in the server can acquire historical power generation data and station data of each new energy station in the target area and predicted meteorological data of the target area in a future period. Further, according to the collected historical power generation data and station data (such as station equipment state, station electricity limiting time period and the like) of each new energy station and the predicted meteorological data of a target area in a future time period, the power generation power of each new energy station in the future time period is predicted through a preset power prediction system, and the target predicted power generation power corresponding to each new energy station in the future time period is obtained.
S202, determining a first predicted total power generation of the target area according to the predicted power generation of each target and the contribution weight of each new energy station to the target area.
In this embodiment, the contribution weight of each new energy station to the target area is the weight of the contribution of the generated power of each new energy station to the total generated power of the target area. The first predicted total power is the predicted total power of the target area in the future period under the condition of considering the contribution degree of each new energy station to the target area.
Specifically, after determining each target predicted power and the weight of each new energy station to the target area, the obtained target predicted power corresponding to each new energy station may be multiplied by the contribution weight of the new energy station to the target area; further, the products are added to obtain a final calculation result, and the calculation result is used as the first predicted total power of the target area.
S203, determining a second predicted total power of the target area according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station.
In this embodiment, the historical actual total power generated is the total power generated in the actual measured target area in the historical period. The geographic coordinates of each new energy station are coordinates determined according to the position of each new energy station. The second predicted total power is the predicted total power of the target area in the future period under the condition of considering the synergistic effect among the new energy stations.
Optionally, the historical actual total power generation power of the target area in the historical period can be obtained, and the geographic coordinates of each new energy station can be determined according to the position of each new energy station; further, the historical actual total power generated by the target area in the historical period and the geographic coordinates of each new energy station can be analyzed through a preset power prediction model, so that the second predicted total power generated by the target area is determined.
S204, predicting the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power.
Optionally, after the first predicted total power and the second predicted total power of the target area are obtained, the first predicted total power and the second predicted total power may be added, and the addition result is divided by 2, so as to obtain a simple average value of the first predicted total power and the second predicted total power, and the simple average value is used as the target predicted total power of the target area in the future period, so as to realize the prediction of the new energy power of the target area in the future period.
Optionally, after determining the target predicted total power of the target area in the future period, the server may interact with the power prediction demand end through the network, and feed back the determined target predicted total power to the power prediction demand end, so that the operation and maintenance party can better manage the target area according to the target predicted total power.
Further, in order to improve the accuracy of predicting the new energy generated power of the target area in the future period, the calculated average value between the first predicted total generated power and the second predicted total generated power can be used as the target predicted total generated power of the target area in the future period by calculating the calculated average value between the first predicted total generated power and the second predicted total generated power, so as to realize the prediction of the new energy generated power of the target area in the future period.
Specifically, after the first predicted total power and the second predicted total power of the target area are obtained, an arithmetic average value between the first predicted total power and the second predicted total power may be calculated by the following formula (1); and further predicting the total generated power with the arithmetic average value as a target of the target region in a future period.
（1）
wherein ,the first predicted total power of the target area; />The second predicted total power of the target area; />And predicting the total power for the target.
It can be understood that by calculating an arithmetic average value between the first predicted total power generation and the second predicted total power generation of the target area, and using the arithmetic average value as the target predicted total power generation of the target area in the future period, the accuracy of determining the target predicted total power generation can be improved, and further, the effect of predicting the new energy power generation of the target area in the future period can be more comprehensively and accurately realized.
According to the intelligent fusion new energy power generation power region prediction method for the multiple stations, the target prediction power generation power corresponding to each new energy station in the target region in the future period is obtained, and the first prediction total power generation power is determined by combining the contribution weight of each new energy station to the target region; determining a second predicted total power according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station; further, the first predicted total power generation power and the second predicted total power generation power are combined, and the new energy power generation power of the target area in a future period is predicted. According to the scheme, the cooperative action among the plurality of new energy stations in the area and the contribution degree of each new energy station to the area are considered, and in the process of predicting the new energy generation power of the area, the contribution weight of each new energy station to the target area and the data such as the geographic coordinates of each new energy station are introduced, so that the comprehensiveness and the accuracy of predicting the new energy generation power of the target area are improved.
In order to ensure the accuracy of the target predicted power for each new energy station in the future period, in one embodiment, as shown in fig. 3, the step of further refining S201 may include the following steps:
s301, selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models.
In this embodiment, there may be a plurality of power prediction models for predicting the power generated by each new energy station among the candidate power prediction models; the power prediction model includes, but is not limited to, a statistical-based model, a machine learning model, a deep learning model, and the like. Optionally, in this embodiment, each new energy station corresponds to a target power prediction model.
Specifically, each new energy station can be analyzed, and the required data for predicting the generated power of each new energy station can be determined; and selecting a power prediction model containing the required data from candidate power prediction models according to the required data required by the power generation prediction of the new energy station for each new energy station, and taking the power prediction model as a target power prediction model corresponding to the new energy station.
For example, if a new energy station is analyzed, it is determined that the required data required for predicting the power of the new energy station is weather data, that is, weather data needs to be input in the process of predicting the power of the new energy station; and selecting a power prediction model containing the demand data from the candidate power prediction models, and taking the power prediction model as a target power prediction model corresponding to the new energy station.
Alternatively, the present embodiment provides another implementation manner, where the target power prediction model corresponding to each new energy station may be selected from the candidate power prediction models according to the station type of each new energy station in the target area. In this embodiment, the station type is the type to which each new energy station belongs in the target area.
Specifically, station data of each new energy station in the target area can be combined, and the like, so that each new energy station in the target area can be analyzed, and the station type of each new energy station is determined; further, according to the station type corresponding to each new energy station, the target power prediction model corresponding to each new energy station can be selected from the candidate power prediction models through a preset mapping relation between the station type and the candidate power prediction models.
Optionally, for each power prediction model in the candidate power prediction models, the power prediction model may be analyzed to determine a station type corresponding to the power prediction model; inputting station data of each new energy station under the station type, historical actual power generation power in each historical period and historical meteorological data of a target area in the historical period into the power prediction model to obtain a data result of the power prediction model; further, according to the reliability of the data result of the power prediction model, the model parameters of the power prediction model are adjusted, and then the trained power prediction model corresponding to the power prediction model is obtained. And taking each trained power prediction model as a candidate power prediction model for later determining the target predicted power generation power of each new energy station in a future period.
S302, based on a target power prediction model corresponding to each new energy station, determining target predicted power corresponding to each new energy station in a future period according to historical actual power generated by each new energy station in the historical period and future meteorological data of a target area in the future period.
In this embodiment, the historical actual power generated by each new energy station is the actual measured power generated by the new energy station in the historical period; because noise data may exist in the collected historical power generation data of each new energy station in the data collection process, in order to ensure the accuracy of the target predicted power generation power of each new energy station, the collected historical power generation data of each new energy station may be preprocessed, such as data cleaning, so as to obtain more accurate historical actual power generation power. The future meteorological data is the meteorological data of the predicted target area in the future period, such as wind speed, temperature, irradiance, pressure, humidity and the like.
Specifically, for each new energy station in the target area, the collected historical actual power of the new energy station and future meteorological data of the target area in a future period are input into a target power prediction model corresponding to the new energy station; and analyzing the historical actual power generated by the new energy station and the future meteorological data of the target area in the future period through a target power prediction model corresponding to the new energy station, so as to determine the target predicted power generated by the new energy station in the future period.
It can be understood that, due to the difference between the new energy stations, for each new energy station, by selecting a corresponding target power prediction model for the new energy station, according to the collected historical actual power of the new energy station and the future meteorological data of the target area in the future period, based on the target power prediction model, the more accurate target predicted power of the new energy station corresponding to the future period can be obtained, and the effect of improving the accuracy of power prediction of each new energy station is further achieved.
In order to improve the accuracy of the first predicted total generated power of the target area in the future period, in one embodiment, as shown in fig. 4, the step of further refining S202 may include the following steps:
s401, determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data.
In this embodiment, the historical weather data is the weather data of the target area in the historical period.
Specifically, the historical actual power generation power of each new energy station in the historical period, the historical actual total power generation power of the target area in the historical period and the historical meteorological data can be obtained; further, through a pre-trained contribution weight determining model, the historical actual power generation power of each new energy station in the historical period and the historical actual total power generation power of the target area in the historical period are analyzed, and the contribution weight of each new energy station to the target area is determined.
Optionally, after the historical actual power, the historical actual total power and the historical meteorological data are obtained, a reinforcement learning algorithm may be adopted to determine the contribution weight of each new energy station to the target area according to the historical actual power of each new energy station in the historical period, the historical actual total power and the historical meteorological data of the target area in the historical period.
Specifically, after the historical actual power generation, the historical actual total power generation and the historical meteorological data are obtained, the contribution weight of each new energy station ground target area can be determined through the expression of the reinforcement learning algorithm shown in the following formula (2).
（2）
Wherein s is the contribution weight of each new energy station. a is learning action, which is the variation value of the contribution weight of each new energy station iterated in each step; the next state can be simply represented asIndicating that the next state is corrected by the last state superposition correction; the superscripts l, p and k respectively represent the first real code for reinforcement learning, the p search and the k iteration; />For immediate rewards, it can be generally converted from the optimization objective, where it can be calculated by weighting and accumulating the historical actual power according to the historical actual power of each new energy station, and the root mean square error value of the historical actual total power of the objective area; / > and />The knowledge matrix and the increment thereof are represented in the current state, and are necessary for knowledge iteration in iteration; />Is a random value in the unified probability distribution;εis a local greedy search parameter, is a custom constant parameter>Representing a global random search action. />，The learning parameters are all adjustable parameters.
Optionally, to prevent overfitting, a certain degree of relaxation may be performed on the reinforcement learning model, that is, in the environment evaluation function, the convergence condition is moderately relaxed, and the convergence condition is set as follows:
（3）
wherein ,for the historical actual total power of the target area at time t +.>For the historical actual power generated by the ith new energy station at time t, +.>The total number of stations in the area; />The relaxation coefficients can be custom.
Further, the historical actual power generated by each new energy station, the historical actual total power generated by the target area and the historical meteorological data may be input into the reinforcement learning model (i.e., formula (2)), and the contribution weight of each new energy station to the target area may be determined in combination with the convergence condition (i.e., formula (3)).
S402, adding products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain first predicted total power of the target area.
Specifically, after determining the contribution weights of the new energy stations to the target area, the obtained target prediction power corresponding to the new energy stations can be multiplied by the contribution weights of the new energy stations to the target area; further, the products are added to obtain a final calculation result, and the calculation result is used as the first predicted total power of the target area.
For example, if 3 new energy stations exist in the target area, acquiring target predicted power generated corresponding to each new energy station as a, b and c respectively; determining that the contribution weights of the new energy stations to the target area are 0.5, 0.3 and 0.2 respectively; further, the product of the target predicted power and the contribution weight corresponding to each new energy station is added to obtain the first predicted total power of the target area, namely, 0.5a+0.3b+0.2c.
It can be understood that by introducing the contribution weight of each new energy station to the target area, the first predicted total power of the target area is determined according to the target predicted power of each new energy station and the contribution weight of each new energy station to the target area, and the difference of the contribution amounts of each new energy station to the total power of the target area is considered, so that the accuracy of determining the first predicted total power of the target area is improved, and the effect of improving the comprehensiveness and accuracy of predicting the new energy power of the target area is further realized.
Further, in order to improve the accuracy of the second predicted total generated power of the target area in the future period, in one embodiment, as shown in fig. 5, the step S203 may be further refined, and may specifically include the following steps:
s501, based on a space-time regression statistical algorithm, constructing a space-time regression model of the target area according to the historical actual total power generated by the target area at each historical moment in the historical period and the geographic coordinates of each new energy station.
In this embodiment, a Space-time series Auto-Regressive and Moving Average Model (STARMA) algorithm is a modeling algorithm for analyzing a sequence according to the time correlation and the Space correlation of a Space-time sequence. The space-time regression model is a model corresponding to the target area constructed based on a space-time regression statistical algorithm.
Specifically, after the historical actual total power generated at each historical moment in the historical period and the geographic coordinates of each new energy station in the target area are obtained, a geographic matrix of the target area can be constructed according to the obtained geographic coordinates of each new energy station; further, substituting the historical actual total power generated by the target area at each historical moment in the historical period and the geographic matrix of the target area into a space-time regression statistical algorithm of the following formula (4) to form an equation set, and further adopting a least square method to obtain a time sequence parameter、/>Fitting and determining the time sequence parameter +.>、/>Is a numerical value of (2).
（4）
Wherein t is a history period;the historical actual total power generated for the target area; n is the nth historical time in the historical period; />The historical actual total power generated by the target area at the nth historical moment; p, q are the autoregressive and sliding orders, respectively,>is a white noise sequence; />White noise sequence of the target area at the nth historical moment;lis the order of the spatial matrix; />、/>Time sequence parameters in a space-time regression model; />The geographic matrix, which reflects the geographic relevance of each station, can be obtained by the following equation (5).
（5）
Wherein k and k' are numbers of each geographic coordinate.
Further, the time series parameters to be determined、/>Substituting the model into a space-time regression statistical algorithm to obtain a space-time regression model.
S502, based on a space-time regression model of the target area, predicting second predicted total power of the target area in a future period according to geographic coordinates of each new energy station.
Specifically, the second predicted total generated power of the target area in the future period can be predicted based on the constructed space-time regression model of the target area according to the geographic matrix of the target area determined by the geographic coordinates of each new energy station.
It can be understood that by introducing a space-time regression statistical algorithm, a space-time regression model is constructed according to the historical actual total power generated by the target area in the historical period and the geographic coordinates of each new energy station; and the second predicted total power generation power of the target area is further based on the constructed space-time regression model, the cooperative effect among the new energy stations in the target area is considered, the accuracy of determining the second predicted total power generation power of the target area is improved, and the effects of improving the comprehensiveness and accuracy of predicting the new energy power generation power of the target area are further achieved.
In one embodiment, as shown in fig. 6, an alternative example of a new energy generated power region prediction method for intelligent fusion of multiple stations is provided. The specific process is as follows:
s601, selecting a target power prediction model corresponding to each new energy station from candidate power prediction models according to the station type of each new energy station in the target area.
S602, based on the target power prediction model corresponding to each new energy station, determining the target predicted power corresponding to each new energy station in the future period according to the historical actual power generated by each new energy station in the historical period and the future meteorological data of the target area in the future period.
S603, determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data by adopting a reinforcement learning algorithm.
S604, adding products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain the first predicted total power of the target area.
S605, based on a space-time regression statistical algorithm, constructing a space-time regression model of the target area according to the historical actual total power generated by the target area at each historical moment in the historical period and the geographic coordinates of each new energy station.
S606, based on the space-time regression model of the target area, predicting second predicted total power of the target area in a future period according to the geographic coordinates of each new energy station.
S607, taking the arithmetic average value between the first predicted total generated power and the second predicted total generated power as the target predicted total generated power of the target region in the future period.
The specific process of S601 to S607 may refer to the description of the above method embodiment, and its implementation principle and technical effect are similar, and will not be described herein.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a multi-station intelligent fusion new energy power generation power region prediction system for realizing the multi-station intelligent fusion new energy power generation power region prediction method. The implementation scheme of the system for solving the problem is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the system for predicting the new energy generation power area by intelligent fusion of one or more multiple stations can be referred to the limitation of the method for predicting the new energy generation power area by intelligent fusion of multiple stations in the above description, and the description is omitted here.
In one embodiment, a new energy generated power region prediction system for intelligent fusion of multiple stations is provided, including: a power prediction demand end and a server; wherein,
the power prediction demand end is used for sending a power prediction request for the target area to the server under the condition that the power prediction demand for the new energy generated power of the target area exists;
the server responds to the power prediction request to obtain target prediction power generation power corresponding to each new energy station in the target area in a future period; determining a first predicted total power generation of the target area according to the predicted power generation of each target and the contribution weight of each new energy station to the target area; determining a second predicted total power of the target area according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station; and predicting the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power, and feeding back a prediction result to the power prediction demand end.
Furthermore, based on the same inventive concept, the embodiment of the application also provides a multi-station intelligent fusion new energy generation power region prediction device for realizing the multi-station intelligent fusion new energy generation power region prediction method. The implementation scheme of the device for solving the problems is similar to the implementation scheme recorded in the method, so the specific limitation in the embodiment of the device for predicting the new energy generation power area of intelligent fusion of one or more multiple stations provided below can be referred to the limitation of the method for predicting the new energy generation power area of intelligent fusion of multiple stations in the above description, and the description is omitted here.
In one embodiment, as shown in fig. 7, there is provided a new energy generated power region prediction apparatus 1 for intelligent fusion of multiple stations, including: a power acquisition module 10, a first determination module 20, a second determination module 30, and a power prediction module 40, wherein:
the power acquisition module 10 is configured to acquire target predicted generated power corresponding to each new energy station in the target area in a future period.
The first determining module 20 is configured to determine a first predicted total generated power of the target area according to each target predicted generated power and a contribution weight of each new energy station to the target area.
The second determining module 30 is configured to determine a second predicted total power of the target area according to the historical actual total power of the target area during the historical period and the geographic coordinates of each new energy station.
The power prediction module 40 is configured to predict the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power.
In one embodiment, on the basis of fig. 7, as shown in fig. 8, the first determining module 20 may include:
the weight determining unit 21 is configured to determine a contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period, and the historical meteorological data.
The first determining unit 22 is configured to add products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain a first predicted total power of the target area.
In one embodiment, the weight determining unit 21 may be configured to:
and determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data by adopting a reinforcement learning algorithm.
In one embodiment, based on the above fig. 7 or fig. 8, as shown in fig. 9, the above second determining module 30 may include:
the model construction unit 31 is configured to construct a spatiotemporal regression model of the target area based on the spatiotemporal regression statistical algorithm and according to the historical actual total power generated by the target area at each historical time in the historical period and the geographic coordinates of each new energy station.
And a second determining unit 32 for predicting a second predicted total generated power of the target area in a future period according to the geographical coordinates of each new energy station based on the spatiotemporal regression model of the target area.
In one embodiment, the power prediction module 40 may be configured to:
And taking an arithmetic average value between the first predicted total generated power and the second predicted total generated power as a target predicted total generated power of the target area in a future period.
In one embodiment, on the basis of fig. 7, 8 or 9, as shown in fig. 10, the power acquisition module 10 may include:
the model selecting unit 11 is configured to select a target power prediction model corresponding to each new energy station from the candidate power prediction models.
The power determining unit 12 is configured to determine, based on the target power prediction model corresponding to each new energy station, a target predicted power corresponding to each new energy station in a future period according to the historical actual power generated by each new energy station in the historical period and future weather data of the target area in the future period.
In one embodiment, the model selection unit 11 may be configured to:
and selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models according to the station type of each new energy station in the target area.
All or part of each module in the intelligent fusion new energy power generation region prediction device of the multiple stations can be realized by software, hardware and combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 11. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing data such as geographic coordinates of each new energy station in the target area. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a new energy generation power region prediction method of intelligent fusion of multiple stations.
It will be appreciated by those skilled in the art that the structure shown in FIG. 11 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
obtaining target prediction power generation power corresponding to each new energy station in the target area in a future period;
determining a first predicted total power generation of the target area according to the predicted power generation of each target and the contribution weight of each new energy station to the target area;
determining a second predicted total power of the target area according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station;
and predicting the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power.
In one embodiment, when the processor executes the logic of determining the first predicted total generated power for the target area based on the predicted generated power for each target and the contribution weight of each new energy station to the target area, the processor further performs the steps of:
determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data; and adding products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain the first predicted total power of the target area.
In one embodiment, when the processor executes the logic for determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data, the following steps are further implemented:
and determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data by adopting a reinforcement learning algorithm.
In one embodiment, when the processor executes the logic for determining the second predicted total generated power for the target area based on the historical actual total generated power for the target area over the historical period and the geographic coordinates of each new energy station, the processor further performs the steps of:
based on a space-time regression statistical algorithm, constructing a space-time regression model of the target area according to the historical actual total power generated by the target area at each historical moment in a historical period and the geographic coordinates of each new energy station; and predicting the second predicted total power of the target area in the future period according to the geographic coordinates of each new energy station based on the space-time regression model of the target area.
In one embodiment, when the processor executes logic for predicting the new energy generated power of the target area in a future time period based on the first predicted total generated power and the second predicted total generated power, the processor further performs the steps of:
and taking an arithmetic average value between the first predicted total generated power and the second predicted total generated power as a target predicted total generated power of the target area in a future period.
In one embodiment, when the processor executes the logic of the computer program to obtain the target predicted generated power corresponding to the future time period for each new energy station in the target area, the following steps are further implemented:
selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models; and determining the target predicted power generation power corresponding to each new energy station in the future period according to the historical actual power generation power of each new energy station in the historical period and the future meteorological data of the target area in the future period based on the target power prediction model corresponding to each new energy station.
In one embodiment, when the processor executes logic for selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models, the processor further performs the steps of:
And selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models according to the station type of each new energy station in the target area.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
obtaining target prediction power generation power corresponding to each new energy station in the target area in a future period;
determining a first predicted total power generation of the target area according to the predicted power generation of each target and the contribution weight of each new energy station to the target area;
determining a second predicted total power of the target area according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station;
and predicting the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power.
In one embodiment, the computer program further performs the following steps when the logic for determining the first predicted total generated power for the target area is executed by the processor, based on the predicted generated power for each target and the contribution weight of each new energy station to the target area:
Determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data; and adding products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain the first predicted total power of the target area.
In one embodiment, the computer program further implements the following steps when the logic for determining the contribution weight of each new energy station to the target area is executed by the processor, based on the historical actual power generated by each new energy station during the historical period, the historical actual total power generated by the target area during the historical period, and the historical meteorological data:
and determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data by adopting a reinforcement learning algorithm.
In one embodiment, the logic for determining the second predicted total generated power for the target area based on the historical actual total generated power for the target area over the historical period and the geographic coordinates of each new energy station further performs the steps of:
Based on a space-time regression statistical algorithm, constructing a space-time regression model of the target area according to the historical actual total power generated by the target area at each historical moment in a historical period and the geographic coordinates of each new energy station; and predicting the second predicted total power of the target area in the future period according to the geographic coordinates of each new energy station based on the space-time regression model of the target area.
In one embodiment, the computer program further performs the following steps when the logic for predicting the new energy generated power of the target area in the future time period is executed by the processor based on the first predicted total generated power and the second predicted total generated power:
and taking an arithmetic average value between the first predicted total generated power and the second predicted total generated power as a target predicted total generated power of the target area in a future period.
In one embodiment, the logic for obtaining the target predicted generated power for each new energy station in the target area corresponding to the future time period by the computer program is executed by the processor, and further implements the steps of:
selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models; and determining the target predicted power generation power corresponding to each new energy station in the future period according to the historical actual power generation power of each new energy station in the historical period and the future meteorological data of the target area in the future period based on the target power prediction model corresponding to each new energy station.
In one embodiment, the logic of the computer program selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models is executed by the processor and further performs the steps of:
and selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models according to the station type of each new energy station in the target area.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
obtaining target prediction power generation power corresponding to each new energy station in the target area in a future period;
determining a first predicted total power generation of the target area according to the predicted power generation of each target and the contribution weight of each new energy station to the target area;
determining a second predicted total power of the target area according to the historical actual total power of the target area in the historical period and the geographic coordinates of each new energy station;
and predicting the new energy generated power of the target area in a future period according to the first predicted total generated power and the second predicted total generated power.
In one embodiment, the computer program further performs the following steps when the logic for determining the first predicted total generated power for the target area is executed by the processor, based on the predicted generated power for each target and the contribution weight of each new energy station to the target area:
Determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data; and adding products of the target predicted power and the contribution weights corresponding to the new energy stations to obtain the first predicted total power of the target area.
In one embodiment, the computer program further implements the following steps when the logic for determining the contribution weight of each new energy station to the target area is executed by the processor, based on the historical actual power generated by each new energy station during the historical period, the historical actual total power generated by the target area during the historical period, and the historical meteorological data:
and determining the contribution weight of each new energy station to the target area according to the historical actual power generated by each new energy station in the historical period, the historical actual total power generated by the target area in the historical period and the historical meteorological data by adopting a reinforcement learning algorithm.
In one embodiment, the logic for determining the second predicted total generated power for the target area based on the historical actual total generated power for the target area over the historical period and the geographic coordinates of each new energy station further performs the steps of:
Based on a space-time regression statistical algorithm, constructing a space-time regression model of the target area according to the historical actual total power generated by the target area at each historical moment in a historical period and the geographic coordinates of each new energy station; and predicting the second predicted total power of the target area in the future period according to the geographic coordinates of each new energy station based on the space-time regression model of the target area.
In one embodiment, the computer program further performs the following steps when the logic for predicting the new energy generated power of the target area in the future time period is executed by the processor based on the first predicted total generated power and the second predicted total generated power:
and taking an arithmetic average value between the first predicted total generated power and the second predicted total generated power as a target predicted total generated power of the target area in a future period.
In one embodiment, the logic for obtaining the target predicted generated power for each new energy station in the target area corresponding to the future time period by the computer program is executed by the processor, and further implements the steps of:
selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models; and determining the target predicted power generation power corresponding to each new energy station in the future period according to the historical actual power generation power of each new energy station in the historical period and the future meteorological data of the target area in the future period based on the target power prediction model corresponding to each new energy station.
In one embodiment, the logic of the computer program selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models is executed by the processor and further performs the steps of:
and selecting a target power prediction model corresponding to each new energy station from the candidate power prediction models according to the station type of each new energy station in the target area.
The data related to the present application (including but not limited to the data such as the geographic coordinates of each new energy station) is information and data authorized by the user or fully authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.