CN114186494A

CN114186494A - Load determination method, model training method and device and electronic equipment

Info

Publication number: CN114186494A
Application number: CN202111519479.6A
Authority: CN
Inventors: 杨海华; 田伦; 张硕; 杨敬
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-12-13
Filing date: 2021-12-13
Publication date: 2022-03-15

Abstract

The disclosure provides a load determination method, a model training device and electronic equipment, and relates to the technical field of artificial intelligence and computers, in particular to the field of industrial big data. The specific implementation scheme is as follows: determining a first load of a centralized photovoltaic in a preset area within a preset time period; and determining the target load of the distributed photovoltaic in the preset area within a preset time period according to the first load.

Description

Load determination method, model training method and device and electronic equipment

Technical Field

The present disclosure relates to the field of artificial intelligence and computer technologies, and in particular, to a load determination method, a model training method, an apparatus, and an electronic device.

Background

The distributed photovoltaic power generation is a photovoltaic power generation facility which is built near a user site, has an operation mode of self-service and self-use of a user side, is used for surfing the internet by redundant electric quantity and executes balance adjustment in a power distribution system. Distributed photovoltaic power generation refers to a distributed power generation system which directly converts solar energy into electric energy by adopting photovoltaic modules. Distributed photovoltaic power generation is a novel power generation and energy comprehensive utilization mode with wide development prospect, the generated energy of photovoltaic power stations with the same scale can be effectively improved, and the problem of loss of electric power in boosting and long-distance transportation can be effectively solved.

Disclosure of Invention

The disclosure provides a load determination method, a model training device and electronic equipment.

According to an aspect of the present disclosure, there is provided a load determination method including: determining a first load of a centralized photovoltaic in a preset area within a preset time period; and determining the target load of the distributed photovoltaic in the preset area within the preset time period according to the first load.

According to another aspect of the present disclosure, there is provided a model training method, including: acquiring a first historical load and a second historical load, wherein the first historical load represents the load of a centralized photovoltaic in a preset area in a historical time period, and the second historical load represents the load of a distributed photovoltaic in the preset area in the historical time period; inputting the first historical load into a prediction model to be trained to obtain a prediction load corresponding to the first historical load; and training the predictive model using the second historical load and the predicted load.

According to another aspect of the present disclosure, there is provided a load determination apparatus including: the first determining module is used for determining a first load of the centralized photovoltaic in a preset area within a preset time period; and the second determining module is used for determining the target load of the distributed photovoltaic in the preset area in the preset time period according to the first load.

According to another aspect of the present disclosure, there is provided a model training apparatus including: the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring a first historical load and a second historical load, the first historical load represents the load of a centralized photovoltaic in a preset area in a historical time period, and the second historical load represents the load of a distributed photovoltaic in the preset area in the historical time period; the input module is used for inputting the first historical load into a prediction model to be trained to obtain a prediction load corresponding to the first historical load; and a training module for training the predictive model using the second historical load and the predicted load.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a load determination method, a model training method, according to the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the load determination method, the model training method according to the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the load determination method, the model training method according to the present disclosure.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 schematically illustrates an exemplary system architecture to which the load determination method and apparatus or the model training method and apparatus may be applied, according to an embodiment of the disclosure;

FIG. 2 schematically illustrates a flow chart of a load determination method according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of a model training method according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates an exemplary application diagram of a load determination method according to an embodiment of the disclosure;

FIG. 5 schematically illustrates a block diagram of a load determination apparatus according to an embodiment of the present disclosure;

FIG. 6 schematically illustrates a block diagram of a model training apparatus according to an embodiment of the present disclosure; and

FIG. 7 illustrates a schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary security measures are taken, and the customs of the public order is not violated.

The photovoltaic is a solar photovoltaic power generation system for short, which is a power generation system for directly converting solar radiation energy into electric energy by using the photovoltaic effect of a solar cell semiconductor material and has two modes of independent operation and grid-connected operation. The photovoltaic can be divided into two categories, one is centralized photovoltaic, such as a large northwest ground photovoltaic power generation system; the other is distributed photovoltaic (demarcated with > 6 MW), such as a residential rooftop photovoltaic power generation system. In a bus load prediction system related to photovoltaic, a general bus load prediction process is to construct a model according to historical load data of a bus and combined with weather data, an overhaul plan and the like, and perform load prediction on the model. Modeling techniques are generally classified into expert experience methods, statistical methods, machine learning methods, and the like. The expert experience method means that an expert predicts future load influence according to weather forecast data, such as changes of temperature, illumination and the like; or the future load is correspondingly adjusted through the investigation of the electricity utilization unit and the electricity utilization plan, so that the purpose of prediction is achieved. The statistical method generally refers to statistical analysis of historical load data and external environment data through statistical knowledge, and then prediction of future load through techniques such as parameter estimation and regression, and the commonly used methods generally include Auto-Regressive and Moving Average (ARMA) and multiple linear regression. The application of the machine learning method in the power system is a popular application in recent years, and mainly aims at the characteristics of historical load, weather and the like of a certain bus, the modeling is carried out by using a tree model such as XGboost (XGBoost) or the like, or the modeling is carried out by using a recurrent neural network model such as LSTM (Long Short-Term Memory network) or the like.

The load data of a certain bus (for example, 220kv bus) is usually obtained by superimposing the load data of a plurality of lower-level buses (for example, 110kv bus, 35kv bus, etc.).

The inventor finds that due to the characteristic that distributed photovoltaic distribution is wide and scattered, the actual photovoltaic load workload of each household under a certain bus is large in household-by-household statistics, and therefore accurate load prediction is difficult to perform in actual bus load prediction. In addition, in the prediction of the actual bus load, only whether concentrated photovoltaic exists under a certain bus can be determined, and little mention is made of distributed photovoltaic. Therefore, during actual modeling, the factors of the distributed photovoltaic are not considered separately, and unified modeling is adopted. On the surface of actual data, the influence of distributed photovoltaic on the load prediction output of a certain bus is large, so that the prediction effect of directly modeling the bus is general.

The disclosure provides a load determination method, a model training device and electronic equipment. The load determination method comprises the following steps: determining a first load of a centralized photovoltaic in a preset area within a preset time period; and determining the target load of the distributed photovoltaic in the preset area within a preset time period according to the first load.

Fig. 1 schematically illustrates an exemplary system architecture to which the load determination method and apparatus or the model training method and apparatus may be applied, according to an embodiment of the present disclosure.

It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios. For example, in another embodiment, an exemplary system architecture to which the load determination method and apparatus or the model training method and apparatus may be applied may include a terminal device, but the terminal device may implement the load determination method and apparatus or the model training method and apparatus provided in the embodiments of the present disclosure without interacting with a server.

As shown in fig. 1, the system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a knowledge reading application, a web browser application, a search application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for content browsed by the user using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device. The Server may be a cloud Server, which is also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service extensibility in a traditional physical host and a VPS service ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be noted that the load determination method or the model training method provided by the embodiments of the present disclosure may be generally executed by the

terminal device

101, 102, or 103. Accordingly, the load determination device or the model training device provided by the embodiment of the present disclosure may also be disposed in the

terminal device

101, 102, or 103.

Alternatively, the load determination method or the model training method provided by the embodiments of the present disclosure may also be generally performed by the server 105. Accordingly, the load determination device or the model training device provided by the embodiments of the present disclosure may be generally disposed in the server 105. The load determination method or the model training method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the load determination apparatus or the model training apparatus provided in the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105.

For example, when the load needs to be determined, the

terminal devices

101, 102, and 103 may obtain a first load of the centralized photovoltaic in the preset area within a preset time period, then send the obtained first load to the server 105, and the server 105 determines, according to the first load, a target load of the distributed photovoltaic in the preset area within the preset time period. Or determining, by a server or a server cluster capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105, a target load of the distributed photovoltaic in the preset area for the preset time period according to the first load.

For example, when the model needs to be trained, the

terminal device

101, 102, 103 may obtain a first historical load and a second historical load, where the first historical load represents the load of the centralized photovoltaic in the preset area in the historical time period, and the second historical load represents the load of the distributed photovoltaic in the preset area in the historical time period. Then, the

terminal devices

101, 102, 103 may transmit the acquired first and second historical loads to the server 105, input the first historical load to a prediction model to be trained by the server 105, obtain a prediction load corresponding to the first historical load, and train the prediction model using the second historical load and the prediction load. Or by a server or server cluster capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105, and to process the first and second historical loads and to implement the trained predictive model.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically shows a flow chart of a load determination method according to an embodiment of the present disclosure.

As shown in fig. 2, the method includes operations S210 to S220.

In operation S210, a first load of a concentrated photovoltaic in a preset area for a preset time period is determined.

In operation S220, a target load of the distributed photovoltaic in the preset area within a preset time period is determined according to the first load.

According to the embodiment of the disclosure, the preset area may include areas adjacent or not adjacent to each other in geographic position and similar to each other or in environmental condition, and may also be an area occupied by the same bus-connected photovoltaic. The environmental condition may include, for example, at least one of weather, wind speed, temperature, etc., and is not limited herein. In the case that the similarity of the environmental conditions of the different regions is greater than a preset threshold, the environmental conditions may be characterized to be similar. For areas belonging to different geographical locations, the areas may be determined to be the same preset area as long as the environmental conditions are similar between the areas. The preset time period may include a future time period having a preset duration, such as a future day relative to the current time, a particular future day, and the like. The first load may be determined by acquiring loads of the respective concentrated photovoltaics in the preset area and then calculating a sum of the loads of all the concentrated photovoltaics in the preset area.

According to an embodiment of the present disclosure, a method of determining a target load of a distributed photovoltaic in a preset area for a preset time period according to a first load may include: and training a prediction model, inputting the first load of the centralized photovoltaic in the preset area in a preset time period into the prediction model, and obtaining the target load of the distributed photovoltaic in the preset area in the preset time period. And predefining a calculation formula with the first load as an independent variable and the target load as a dependent variable, and calculating the target load of the distributed photovoltaic in the preset area within a preset time period according to the first load of the centralized photovoltaic in the preset area within the preset time period by using the formula.

Through the embodiment of the disclosure, the load of the distributed photovoltaic can be determined according to the load of the centralized photovoltaic, and the load of the distributed photovoltaic can be determined reasonably, accurately and effectively under the condition of considering the distributed photovoltaic.

The method shown in fig. 2 is further described below with reference to specific embodiments.

According to an embodiment of the present disclosure, the method for determining the target load of the distributed photovoltaic system may further include: and determining the environmental information of the preset area in a preset time period. And determining the target load of the distributed photovoltaic in the preset area within a preset time period according to the environmental information and the first load.

According to an embodiment of the present disclosure, the environmental information may include at least one of weather, wind speed, temperature, and the like, and may not be limited thereto.

According to an embodiment of the present disclosure, a method for determining a target load of a distributed photovoltaic system in a preset area for a preset time period according to environmental information and a first load may include: training a prediction model, inputting a first load of a centralized photovoltaic in a preset area within a preset time period and environmental information of the preset area within the preset time period into the prediction model, and obtaining a target load of a distributed photovoltaic in the preset area within the preset time period. And predefining a calculation formula with the first load and the environmental information as independent variables and the target load as dependent variables, and calculating the target load of the distributed photovoltaic in the preset area within the preset time period by using the formula according to the first load of the centralized photovoltaic in the preset area within the preset time period and the environmental information of the preset area within the preset time period.

Through the above embodiments of the present disclosure, the load of the distributed photovoltaic can be determined in combination with the load of the centralized photovoltaic, and the accuracy of the determined load of the distributed photovoltaic can be improved in combination with the environment information in consideration of the distributed photovoltaic.

According to an embodiment of the present disclosure, determining, according to the first load, a target load of the distributed photovoltaic in the preset area over a preset time period may include: a second load for each of the concentrated photovoltaics is determined based on the first load and the number of photovoltaics of the concentrated photovoltaics. And determining the second load as a target load of the distributed photovoltaic in a preset time period.

According to embodiments of the present disclosure, the second load may characterize an average load of each photovoltaic in the concentrated photovoltaic. The load of each distributed photovoltaic may be determined accordingly based on the average load of each photovoltaic in the concentrated photovoltaic, i.e., the target load of each distributed photovoltaic may be determined based on the second load of each photovoltaic in the concentrated photovoltaic.

According to an embodiment of the present disclosure, the total load of all distributed photovoltaics in a preset area within a preset time period may be determined by product calculation of a target load of each distributed photovoltaic and the number of distributed photovoltaics included in the preset area.

For example, a certain bus bar is connected with a concentrated photovoltaic and 3 distributed photovoltaics. The concentrated photovoltaic includes 20 photovoltaics with a corresponding load of 100kw, and the load of each photovoltaic in the concentrated photovoltaic can be determined to be 5kw, and accordingly, the load of each distributed photovoltaic connected to the bus bar can be determined to be 5 kw. Accordingly, the total load of all distributed photovoltaics connected by the busbar can be determined to be 15 kw.

It should be noted that, when performing the product calculation, corresponding weights may also be configured for the process of product calculation according to the environmental information, the photovoltaic information, and the like, so as to obtain a calculation result with a higher accuracy.

Through the above embodiment of the present disclosure, a manner of calculating the load of the distributed photovoltaic according to the load of the centralized photovoltaic is realized, and the manner can be based on the statistical principle, is reasonable and effective, and can obtain a relatively accurate calculation result.

According to an embodiment of the present disclosure, the preset area includes a first number of distributed photovoltaics. Determining, according to the first load, a target load of the distributed photovoltaic in the preset area within a preset time period may include: and determining a third load of the distributed photovoltaics according to the first load for each distributed photovoltaic in case that the first number is less than or equal to a first preset threshold. And determining the third load as a target load of the distributed photovoltaic in a preset time period.

According to the embodiments of the present disclosure, in the case where the number of bus bar-connected distributed photovoltaics is small, a corresponding load, i.e., the above-described third load, may be calculated for each distributed photovoltaic, and a target load may be determined according to the third load. Whether the number of bus bar connected distributed photovoltaics is small or not may be defined by a preset first preset threshold.

According to the embodiment of the disclosure, the total load of all the distributed photovoltaics connected by the bus in the preset time period can be determined by summing the target loads of all the distributed photovoltaics.

It should be noted that, in the case of determining the third load of the distributed photovoltaic system according to the first load, corresponding adjustment parameters may also be configured for the determination process according to environmental information and the like, so as to obtain a calculation result with a higher accuracy.

Through the embodiment of the disclosure, the corresponding load can be calculated for each distributed photovoltaic under the condition that the number of the distributed photovoltaics is small, and the accuracy of the calculation result of each distributed photovoltaic is improved.

According to an embodiment of the present disclosure, the preset area includes a second number of distributed photovoltaics therein. Determining, according to the first load, a target load of the distributed photovoltaic in the preset area within a preset time period may include: and under the condition that the second number is larger than a second preset threshold value, dividing the second number of distributed photovoltaics into a plurality of distributed photovoltaic sets. For each distributed photovoltaic set, a fourth load for the distributed photovoltaic set is determined from the first load. Determining the fourth load as a target load of the distributed photovoltaic corresponding to the distributed photovoltaic set within a preset time period.

According to the embodiment of the disclosure, under the condition that the number of the distributed photovoltaics connected by the bus is large, a plurality of distributed photovoltaics can be clustered at first, and the distributed photovoltaics of the same class can be determined as a distributed photovoltaic set. Then, for each distributed photovoltaic set, a corresponding load, i.e. the fourth load described above, may be calculated, and the target loads of all distributed photovoltaics corresponding to the distributed photovoltaic set may be determined from this fourth load. Whether the number of bus bar connected distributed photovoltaics is large or not can be defined by a preset second preset threshold value.

According to an embodiment of the present disclosure, the clustering manner may include at least one of: clustering according to the distance of the geographical position of the distributed photovoltaic, clustering according to the use frequency of the distributed photovoltaic, clustering according to the similarity of the environmental information of the position of the distributed photovoltaic, and the like.

According to the embodiment of the disclosure, the total load of all the distributed photovoltaics connected by the bus in the preset time period can be determined by summing the target loads of all the distributed photovoltaic sets in all the distributed photovoltaics.

It should be noted that, in the case of determining the fourth load of the distributed photovoltaic set according to the first load, corresponding adjustment parameters may also be configured for the determination process according to environmental information and the like, so as to obtain a calculation result with a higher accuracy.

Through the embodiment of the disclosure, under the condition that the number of distributed photovoltaics is large, the distributed photovoltaics are firstly divided into the clusters, then the loads are calculated aiming at the clusters, the workload when the loads are independently calculated aiming at each distributed photovoltaic can be effectively reduced, and the accuracy of the calculation results of the distributed photovoltaics can be effectively improved.

According to an embodiment of the present disclosure, on the basis of calculating the target load of the distributed photovoltaic or the distributed photovoltaic set, the load determination method may further include: in a case where the photovoltaics associated with the target bus bar include at least one distributed photovoltaic, at least one target load corresponding to the at least one distributed photovoltaic is determined. And determining the load of the target bus according to the at least one target load.

According to embodiments of the present disclosure, the number of at least one target load may be less than or equal to the number of at least one distributed photovoltaic. For example, in case one target load corresponds to the load of one distributed photovoltaic cluster, the number of at least one target load is smaller than the number of at least one distributed photovoltaic.

According to the embodiment of the disclosure, in the case that the photovoltaic connected to the target bus only includes the distributed photovoltaic, the load of the target bus can be determined by counting the loads of all the distributed photovoltaics connected to the target bus.

Through the above embodiments of the present disclosure, in the case of calculating the load for the bus including the distributed photovoltaic, the influence of the distributed load may be considered, and the accuracy of the load calculated for the bus may be improved.

According to an embodiment of the present disclosure, on the basis of calculating the target load of the distributed photovoltaic or the distributed photovoltaic set, the load determination method may further include: in a case where the photovoltaics associated with the target bus bar include at least one distributed photovoltaic and at least one concentrated photovoltaic, at least one target load corresponding to the at least one distributed photovoltaic and at least one first load corresponding to the at least one concentrated photovoltaic are determined. And determining the load of the target bus according to the at least one target load and the at least one first load.

According to the embodiment of the disclosure, in the case that the photovoltaic connected to the target bus bar includes the distributed photovoltaic and the concentrated photovoltaic, the load of the target bus bar may be determined by counting the loads of all the distributed photovoltaics and all the concentrated photovoltaics connected to the target bus bar.

According to an embodiment of the present disclosure, the target load may be obtained by using a prediction model.

According to the embodiment of the present disclosure, the first load, the second load, the third load, the fourth load, and the load of the target bus may be obtained by using a prediction model.

According to the embodiment of the disclosure, the accuracy of the load calculation result of each step can be effectively improved in a model mode, so that the accuracy of the total load calculation result is improved.

FIG. 3 schematically shows a flow chart of a model training method according to an embodiment of the present disclosure.

As shown in fig. 3, the method includes operations S310 to S330.

In operation S310, a first historical load and a second historical load are obtained, where the first historical load represents a load of a centralized photovoltaic system in a preset area in a historical time period, and the second historical load represents a load of a distributed photovoltaic system in the preset area in the historical time period.

In operation S320, the first historical load is input to the prediction model to be trained, resulting in a predicted load corresponding to the first historical load.

In operation S330, a prediction model is trained using the second historical load and the predicted load.

According to an embodiment of the present disclosure, the trained model may be used in any of the above load determination methods. For example, the present invention can be applied to the above-described determination methods of the first load, the second load, the third load, the fourth load, and the load of the target bus.

It should be noted that, in the actual load prediction system construction, the area including the distributed photovoltaic may be determined first according to whether there is a negative number in the historical load data of the bus or according to the record of the local ledger data. For example, a set of busbars comprising distributed photovoltaics may be determined. Then, modeling can be done for all photovoltaics connected by the busbar. According to the application distribution condition of the photovoltaic, when modeling is carried out on the photovoltaic understood by the bus, the bus containing the distributed photovoltaic can be separated from the collected upper-level bus for independent modeling or modeling by taking a cluster as a unit, and when modeling is carried out on the upper-level bus, the separated bus can be subtracted for modeling. The upper-level bus bar may refer to a bus bar including all distributed photovoltaics and all concentrated photovoltaics. Then, the load of the concentrated photovoltaic in the same area or a nearby area can be used to predict the distributed photovoltaic load in the corresponding area. Or under the condition that the same region or a nearby region does not have the centralized photovoltaic, the load of the corresponding distributed photovoltaic is determined by clustering the distributed photovoltaic and then predicting the load of the clustered distributed photovoltaic. And the load of the corresponding bus can be determined according to the load of the distributed photovoltaic and/or the centralized photovoltaic.

According to the embodiment of the disclosure, a model training method is provided, and when the model is trained according to the method to perform load prediction, the prediction precision can be effectively improved.

Fig. 4 schematically illustrates an exemplary application diagram of a load determination method according to an embodiment of the present disclosure.

As shown in fig. 4,

lower buses

420, 430, 440, 450, 460, etc. are connected to the upper bus 410. The lower bus bar 420 is connected with a centralized photovoltaic 421, the lower bus bar 430 is connected with a distributed photovoltaic 431, the lower bus bar 440 is connected with a distributed photovoltaic 441, the lower bus bar 450 is connected with a centralized photovoltaic 451, and the lower bus bar 460 is connected with a distributed photovoltaic 461. The

photovoltaics

321, 431, 441, 451, 461, etc. connected under the busbar 410 may be positioned to the same preset area. The respective loads of the

concentrated photovoltaics

421, 451, etc. may be determined in advance. The respective photovoltaic of the distributed photovoltaic 431, 441, 461, etc. can be predicted by a prediction model trained for the respective distributed photovoltaic 431, 441, 461. At least two of the distributed

photovoltaics

431, 441, 461 may also be classified into the same class, determining one distributed photovoltaic set. For example, the distributed

photovoltaics

431, 441 may be determined as a distributed photovoltaic set whose load may be predicted using a predictive model trained for the distributed photovoltaic set. From the loads of all the

photovoltaics

321, 431, 441, 451, 461, the load of the busbar 410 can be determined.

Through the embodiment of the disclosure, the corresponding model can be trained, and the load prediction precision for every other distributed photovoltaic is improved. In addition, when the load of the bus is predicted, the prediction accuracy of the bus load can be improved by taking the distributed photovoltaic connected with the bus into consideration.

Fig. 5 schematically shows a block diagram of a load determining apparatus according to an embodiment of the present disclosure.

As shown in fig. 5, the load determination apparatus 500 includes a first determination module and a second determination module.

A first determining module 510, configured to determine a first load of the concentrated photovoltaic in the preset area within a preset time period.

A second determining module 520, configured to determine, according to the first load, a target load of the distributed photovoltaic in the preset area within a preset time period.

According to an embodiment of the present disclosure, the load determination apparatus further includes a third determination module and a fourth determination module.

And the third determining module is used for determining the environmental information of the preset area in the preset time period.

And the fourth determining module is used for determining the target load of the distributed photovoltaic in the preset area within a preset time period according to the environmental information and the first load.

According to an embodiment of the present disclosure, the second determination module includes a first determination unit and a second determination unit.

A first determination unit configured to determine a second load of each of the concentrated photovoltaics according to the first load and the number of the concentrated photovoltaics.

And the second determining unit is used for determining the second load as the target load of the distributed photovoltaic in the preset time period.

According to an embodiment of the present disclosure, a first number of distributed photovoltaics is included in the preset area. The second determination module includes a third determination unit and a fourth determination unit.

A third determining unit, configured to determine, for each distributed photovoltaic, a third load of the distributed photovoltaic according to the first load if the first number is less than or equal to a first preset threshold.

And the fourth determining unit is used for determining the third load as the target load of the distributed photovoltaic in the preset time period.

According to an embodiment of the present disclosure, the preset area includes a second number of distributed photovoltaics therein. The second determination module includes a dividing unit, a fifth determination unit, and a sixth determination unit.

And the dividing unit is used for dividing the second number of distributed photovoltaic sets into a plurality of distributed photovoltaic sets under the condition that the second number is greater than a second preset threshold value.

And a fifth determining unit, configured to determine, for each distributed photovoltaic set, a fourth load of the distributed photovoltaic set according to the first load.

A sixth determining unit, configured to determine the fourth load as a target load of the distributed photovoltaic corresponding to the distributed photovoltaic set within a preset time period.

According to an embodiment of the present disclosure, the load determination apparatus further includes a fifth determination module and a sixth determination module.

A fifth determining module for determining at least one target load corresponding to the at least one distributed photovoltaic if the photovoltaic associated with the target bus bar comprises the at least one distributed photovoltaic.

And the sixth determining module is used for determining the load of the target bus according to at least one target load.

According to an embodiment of the present disclosure, the load determination apparatus further includes a seventh determination module and an eighth determination module.

A seventh determining module for determining at least one target load corresponding to the at least one distributed photovoltaic and at least one first load corresponding to the at least one concentrated photovoltaic, if the photovoltaics associated with the target bus bar include at least one distributed photovoltaic and at least one concentrated photovoltaic.

And the eighth determining module is used for determining the load of the target bus according to the at least one target load and the at least one first load.

According to an embodiment of the present disclosure, the target load is obtained using a predictive model.

FIG. 6 schematically shows a block diagram of a model training apparatus according to an embodiment of the present disclosure.

As shown in FIG. 6, model training apparatus 600 includes an acquisition module, an input module, and a training module.

The obtaining module 610 is configured to obtain a first historical load and a second historical load, where the first historical load represents a load of a centralized photovoltaic in a preset area in a historical time period, and the second historical load represents a load of a distributed photovoltaic in the preset area in the historical time period.

And an input module 620, configured to input the first historical load into the prediction model to be trained, so as to obtain a predicted load corresponding to the first historical load.

A training module 630 for training the predictive model using the second historical load and the predicted load.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the load determination method, the model training method according to the present disclosure.

According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a load determination method, a model training method according to the present disclosure.

According to an embodiment of the disclosure, a computer program product comprising a computer program which, when executed by a processor, implements a load determination method, a model training method according to the disclosure.

FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

Computing unit 701 may be a variety of general purpose and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 701 performs the respective methods and processes described above, such as the load determination method, the model training method. For example, in some embodiments, the load determination method, the model training method, may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. When loaded into RAM 703 and executed by the computing unit 701, may perform one or more of the steps of the load determination method, the model training method described above. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the load determination method, the model training method, by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method of load determination, comprising:

determining a first load of a centralized photovoltaic in a preset area within a preset time period; and

and determining the target load of the distributed photovoltaic in the preset area within the preset time period according to the first load.

2. The method of claim 1, further comprising:

determining environmental information of the preset area in the preset time period; and

and determining the target load of the distributed photovoltaic in the preset area within the preset time period according to the environmental information and the first load.

3. The method of claim 1, wherein the determining, according to the first load, a target load of the distributed photovoltaic in the preset area for the preset time period comprises:

determining a second load for each of the concentrated photovoltaics as a function of the first load and the number of photovoltaics of the concentrated photovoltaics; and

determining the second load as a target load of the distributed photovoltaic within the preset time period.

4. The method of claim 1, wherein the preset area includes a first number of distributed photovoltaics;

the determining, according to the first load, a target load of the distributed photovoltaic in the preset area within the preset time period includes:

determining, for each of the distributed photovoltaics, a third load of the distributed photovoltaics according to the first load if the first number is less than or equal to a first preset threshold; and

determining the third load as a target load of the distributed photovoltaic within the preset time period.

5. The method of claim 1, wherein the preset area includes a second number of distributed photovoltaics;

under the condition that the second number is larger than a second preset threshold value, dividing the second number of distributed photovoltaics into a plurality of distributed photovoltaic sets;

for each distributed photovoltaic set, determining a fourth load for the distributed photovoltaic set from the first load; and

determining the fourth load as a target load of the distributed photovoltaic corresponding to the distributed photovoltaic set within the preset time period.

6. The method of any of claims 1 to 5, further comprising:

in the event that the photovoltaics associated with the target bus include at least one distributed photovoltaic, determining at least one target load corresponding to the at least one distributed photovoltaic; and

and determining the load of the target bus according to the at least one target load.

7. The method of any of claims 1 to 6, further comprising:

in the case where the photovoltaics associated with the target bus bar include at least one distributed photovoltaic and at least one concentrated photovoltaic, determining at least one target load corresponding to the at least one distributed photovoltaic and at least one first load corresponding to the at least one concentrated photovoltaic; and

and determining the load of the target bus according to the at least one target load and the at least one first load.

8. The method according to any one of claims 1 to 7, wherein the target load is obtained using a predictive model.

9. A model training method, comprising:

acquiring a first historical load and a second historical load, wherein the first historical load represents the load of a centralized photovoltaic in a preset area in a historical time period, and the second historical load represents the load of a distributed photovoltaic in the preset area in the historical time period;

inputting the first historical load into a prediction model to be trained to obtain a prediction load corresponding to the first historical load; and

training the predictive model using the second historical load and the predicted load.

10. A load determining apparatus comprising:

the first determining module is used for determining a first load of the centralized photovoltaic in a preset area within a preset time period; and

and the second determining module is used for determining the target load of the distributed photovoltaic in the preset area in the preset time period according to the first load.

11. The apparatus of claim 10, further comprising:

the third determining module is used for determining the environmental information of the preset area in the preset time period; and

and the fourth determining module is used for determining the target load of the distributed photovoltaic in the preset area in the preset time period according to the environment information and the first load.

12. The apparatus of claim 10, wherein the second determining means comprises:

a first determination unit configured to determine a second load of each of the concentrated photovoltaics according to the first load and the number of the concentrated photovoltaics; and

a second determining unit, configured to determine the second load as a target load of the distributed photovoltaic in the preset time period.

13. The apparatus of claim 10, wherein the preset area includes a first number of distributed photovoltaics;

the second determining module includes:

a third determining unit, configured to determine, for each of the distributed photovoltaics, a third load of the distributed photovoltaics according to the first load if the first number is less than or equal to a first preset threshold; and

a fourth determining unit, configured to determine the third load as a target load of the distributed photovoltaic in the preset time period.

14. The apparatus of claim 10, wherein the predetermined area includes a second number of distributed photovoltaics;

the second determining module includes:

the dividing unit is used for dividing the second number of distributed photovoltaics into a plurality of distributed photovoltaic sets under the condition that the second number is larger than a second preset threshold value;

a fifth determining unit, configured to determine, for each of the distributed photovoltaic sets, a fourth load of the distributed photovoltaic set according to the first load; and

a sixth determining unit, configured to determine the fourth load as a target load of the distributed photovoltaic corresponding to the distributed photovoltaic set within the preset time period.

15. The apparatus of any of claims 10 to 14, further comprising:

a fifth determining module for determining at least one target load corresponding to at least one distributed photovoltaic if the photovoltaic associated with the target bus bar comprises the at least one distributed photovoltaic; and

and the sixth determining module is used for determining the load of the target bus according to the at least one target load.

16. The apparatus of any of claims 10 to 15, further comprising:

a seventh determining module for determining, in the case where the photovoltaics associated with the target bus bar include at least one distributed photovoltaic and at least one concentrated photovoltaic, at least one target load corresponding to the at least one distributed photovoltaic and at least one first load corresponding to the at least one concentrated photovoltaic; and

an eighth determining module, configured to determine a load of the target bus according to the at least one target load and the at least one first load.

17. A model training apparatus comprising:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring a first historical load and a second historical load, the first historical load represents the load of a centralized photovoltaic in a preset area in a historical time period, and the second historical load represents the load of a distributed photovoltaic in the preset area in the historical time period;

the input module is used for inputting the first historical load into a prediction model to be trained to obtain a prediction load corresponding to the first historical load; and

a training module to train the predictive model using the second historical load and the predicted load.

18. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8 or 9.

19. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any of claims 1-8 or 9.

20. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-8 or claim 9.