Power control method, system and device based on source-grid-load-storage

Abstract

The present invention relates to the technical field of power control, and invents a power control method, system and device based on source-grid-load-storage, including: performing grid structure analysis and positioning modeling on historical grid data sets to obtain a grid structure model; performing geographic grid division and meteorological feature clustering mapping operations on historical meteorological data sets to obtain a meteorological grid model; performing time series meteorological training on the meteorological grid model using the historical meteorological data sets to obtain a meteorological analysis model; performing joint training on the grid structure model using the historical meteorological data sets and the historical grid data sets to obtain a grid analysis model; calculating analytical grid data using the meteorological analysis model, the grid analysis model, the real-time grid data and the real-time meteorological data, and performing power control on the target area according to the analytical grid data. The present invention can improve the efficiency of power control.

Description

Technical Field

[0001] The present invention relates to the field of power control technology, and in particular to a power control method, system and device based on source-grid-load-storage. Background Art

[0002] Source-grid-load-storage is a concept that integrates energy, power grid, load and energy storage. It aims to achieve efficient use of energy and sustainable development of the system. This concept integrates energy, power grid, load and energy storage to build a more flexible and intelligent energy system. In order to improve the energy utilization rate of the power grid and enhance the stability of the power system, it is necessary to control the power of the source-grid-load-storage power grid.

[0003] Most of the existing power control methods for power grids are based on mathematical models of power grids. They mainly achieve power control by modeling the power of various components of the source, grid, load and storage. In practical applications, the power control methods based on mathematical models of power grids are highly complex and require a large amount of computing resources and expertise to implement and adjust. They also give less consideration to the integrated energy system and fail to fully utilize the synergy between different energy sources. This may lead to poor economic efficiency of the power grid system and, in turn, low efficiency in power control. Summary of the invention

[0004] The present invention provides a power control method, system and device based on source-grid-load-storage, the main purpose of which is to solve the problem of low efficiency when performing power control.

[0005] To achieve the above object, the present invention provides a power control method based on source-grid-load-storage, comprising:

[0006] Acquire a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model;

[0007] Performing geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model;

[0008] The meteorological grid model is trained with time series meteorology using the historical meteorological data set to obtain a meteorological analysis model, wherein the training with the historical meteorological data set to obtain a meteorological analysis model includes: sorting the historical meteorological data set to obtain a historical meteorological data sequence; extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence; performing time series feature extraction and residual feature mapping operations on the meteorological feature group sequence using the meteorological grid model to obtain an analysis meteorological feature group sequence; performing sequence alignment on the meteorological feature group sequence using the analysis meteorological feature group sequence to obtain an aligned meteorological feature group sequence; and calculating the meteorological loss value of the meteorological analysis model according to the analysis meteorological feature group sequence and the aligned meteorological feature group sequence using the following meteorological loss value algorithm:

[0009]

[0010] Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h It refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol; the meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model;

[0011] The power grid structure model is jointly trained using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model;

[0012] Real-time power grid data and real-time meteorological data of the target area are obtained, analytical power grid data are calculated using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and power control of the target area is performed according to the analytical power grid data.

[0013] Optionally, performing grid structure analysis and positioning modeling on the historical grid data set to obtain a grid structure model includes:

[0014] Performing site detection on the historical power grid data set to obtain a power grid site set;

[0015] Performing site coordinate positioning on the historical power grid data set according to the power grid site set to obtain a site location set;

[0016] Performing a topological link analysis on the power grid site set according to the historical power grid data set to obtain a power grid connection structure;

[0017] The site location set is edge mapped according to the power grid connection structure to obtain a power grid structure model.

[0018] Optionally, the performing of geographic grid division and meteorological feature cluster mapping operations on the historical meteorological data set to obtain a meteorological grid model includes:

[0019] Extracting a historical meteorological map from the historical meteorological data set;

[0020] The historical meteorological map is sequentially subjected to geographic coordinate conversion and grid division to obtain a meteorological block group;

[0021] Using the historical meteorological data set to perform meteorological feature mapping on the meteorological block group, to obtain a block meteorological feature group set;

[0022] Perform block clustering and merging on the meteorological block group according to the block meteorological feature group set to obtain a standard meteorological block group;

[0023] Grid mapping and model initialization operations are performed on the standard meteorological block group to obtain a meteorological grid model.

[0024] Optionally, the performing block clustering and merging on the meteorological block groups according to the block meteorological feature group set to obtain a standard meteorological block group includes:

[0025] Selecting meteorological blocks in the meteorological block group one by one as target meteorological blocks, and gathering meteorological blocks in the meteorological block group that are adjacent to the target meteorological block into a neighboring block group;

[0026] The meteorological blocks in the neighboring block group are selected one by one as the target neighboring blocks, and the block distance between the target meteorological block and the target neighboring block is calculated using the following block distance algorithm and the block meteorological feature set:

[0027]

[0028] Wherein, C refers to the block distance, μ is the preset distance resistance coefficient, Q is the total number of features of each block meteorological feature set in the block meteorological feature set, and A qIt refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target meteorological block in the block meteorological feature set, B q It refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target adjacent block in the block meteorological feature set, · is the vector dot product symbol, A x It refers to the horizontal coordinate of the midpoint of the target meteorological block, B x A refers to the horizontal coordinate of the midpoint of the target neighboring block. y It refers to the ordinate of the midpoint of the target meteorological block, B y refers to the ordinate of the midpoint of the target adjacent block, || is the absolute value symbol, and || || is the modulus symbol;

[0029] Determining whether the block distance is less than a preset distance threshold;

[0030] If not, returning to the step of selecting the meteorological blocks in the neighboring block group one by one as the target neighboring blocks;

[0031] If yes, the target meteorological block and the target adjacent block are merged into a target merged block, the target merged block is used to update the meteorological blocks in the meteorological block group, and the step of selecting meteorological blocks in the meteorological block group as target meteorological blocks is returned to one by one;

[0032] When the target meteorological block is the last meteorological block in the meteorological block group, the meteorological block group is used as a standard meteorological block group.

[0033] Optionally, the using the historical meteorological data set and the historical power grid data set to jointly train the power grid structure model to obtain a power grid analysis model includes:

[0034] Extracting the site structure from the historical power grid data set to obtain the power grid distribution structure;

[0035] Using the power grid distribution structure to perform time sequence sorting and structure grouping operations on the historical meteorological data set to obtain a site meteorological data group sequence;

[0036] Using the power grid distribution structure, the historical power grid data set is subjected to time sequence sorting and structure grouping operations to obtain a historical power grid data set sequence;

[0037] Performing a jump feature fusion operation on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence;

[0038] The power grid meteorological feature group sequence and the historical power grid data group sequence are used to perform model training on the power grid structure model to obtain a power grid analysis model.

[0039] Optionally, performing a jump feature fusion operation on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence includes:

[0040] Extracting meteorological features from the site meteorological data group sequence to obtain a site meteorological feature group sequence;

[0041] Extracting power grid features from the historical power grid data group sequence to obtain a historical power grid feature group sequence;

[0042] The following jump fusion algorithm is used to perform feature fusion on the site meteorological feature group sequence and the historical power grid feature group sequence to obtain a power grid meteorological feature group sequence:

[0043]

[0044] Among them, Z i,j-1 refers to the i-th grid meteorological feature in the j-1-th grid meteorological feature group in the grid meteorological feature group sequence, i refers to the sequence number, I refers to the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence, and the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence is equal to the total number of historical grid features in each historical grid feature group in the historical grid feature group sequence, J refers to the sequence length of the site meteorological feature group sequence, and the sequence length of the site meteorological feature group sequence is equal to the sequence length of the historical grid feature group sequence, softmax is a normalization function, Q i,j-1 is the i-th historical power grid feature in the j-1-th historical power grid feature group in the historical power grid feature group sequence, R i,j is the i-th site meteorological feature in the j-th site meteorological feature group in the site meteorological feature group sequence, α, β, γ are preset attention coefficient matrices, w() is a dimensional function, and T is a transposition symbol.

[0045] Optionally, the using the power grid meteorological feature group sequence and the historical power grid data group sequence to perform model training on the power grid structure model to obtain a power grid analysis model includes:

[0046] Using the grid meteorological feature group sequence to perform feature mapping operation on the grid structure model to obtain an embedded grid model;

[0047] Performing recursive cyclic convolution and output mapping operations on the embedded power grid model to obtain a sequence of power grid feature groups for analysis;

[0048] Using the analyzed power grid feature group sequence to perform sequence alignment on the historical power grid data group sequence to obtain an aligned power grid data group sequence;

[0049] Extracting power grid features from the aligned power grid data group sequence to obtain an aligned power grid feature group sequence;

[0050] Calculating a power grid loss value between the aligned power grid feature group sequence and the analyzed power grid feature group sequence;

[0051] The embedded power grid model is iteratively updated with parameters according to the power grid loss value to obtain a power grid analysis model.

[0052] Optionally, the calculating and analyzing the power grid data by using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data includes:

[0053] Performing a block meteorological feature extraction operation on the real-time meteorological data to obtain a real-time meteorological feature group;

[0054] Performing meteorological analysis on the real-time meteorological feature group using the meteorological analysis model to obtain a target meteorological feature group;

[0055] Performing structure grouping and grid feature extraction operations on the real-time grid data to obtain a real-time grid feature group;

[0056] Performing a jump feature fusion operation on the real-time power grid feature group and the target meteorological feature group to obtain a target power grid meteorological feature group;

[0057] Calculating a target power grid feature group corresponding to the target power grid meteorological feature group using the power grid analysis model;

[0058] A feature inverse mapping operation is performed on the target power grid feature group to obtain analysis power grid data.

[0059] In order to solve the above problems, the present invention also provides a power control system based on source-grid-load-storage, the system comprising:

[0060] A structural modeling module is used to obtain a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model;

[0061] A grid modeling module is used to perform geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model;

[0062] A meteorological training module is used to perform time series meteorological training on the meteorological grid model using the historical meteorological data set to obtain a meteorological analysis model, wherein the use of the historical meteorological data set to perform time series meteorological training on the meteorological grid model to obtain a meteorological analysis model includes: sorting the historical meteorological data set to obtain a historical meteorological data sequence; extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence; using the meteorological grid model to perform time series feature extraction and residual feature mapping operations on the meteorological feature group sequence to obtain an analysis meteorological feature group sequence; using the analysis meteorological feature group sequence to perform sequence alignment on the meteorological feature group sequence to obtain an aligned meteorological feature group sequence; using the following meteorological loss value algorithm to calculate the meteorological loss value of the meteorological analysis model according to the analysis meteorological feature group sequence and the aligned meteorological feature group sequence:

[0063]

[0064] Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h It refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol; the meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model;

[0065] A joint training module, used for jointly training the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model;

[0066] A power control module is used to obtain real-time power grid data and real-time meteorological data of the target area, calculate analytical power grid data using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and perform power control on the target area according to the analytical power grid data.

[0067] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0068] at least one processor; and,

[0069] a memory communicatively connected to the at least one processor; wherein,

[0070] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power control method based on source, grid, load and storage as described above.

[0071] The present invention obtains a power grid structure model by performing power grid structure analysis and positioning modeling on the historical power grid data set, and can use graph neural networks to more accurately simulate the complex relationships and dynamic changes between power grid sites, thereby improving the accuracy of power grid power analysis. By generating a meteorological grid model based on the historical meteorological data set, the grid neural network can be used to achieve block simulation of meteorological data in the target area, and the spatial correlation of meteorological data can be retained to improve the generalization ability of the meteorological grid model. By using the historical meteorological data set to perform time-series meteorological training on the meteorological grid model, a meteorological analysis model is obtained, which can analyze meteorological data in subsequent time periods in combination with the positional relationship between regions and the time-series connection of meteorological data, thereby improving the accuracy of meteorological data analysis.

[0072] By using the historical meteorological data set and the historical power grid data set to jointly train the power grid structure model, a power grid analysis model is obtained, which can be combined with the real-time impact of meteorological data on power grid data and the periodic law of power grid data to analyze and predict the power grid data of the target area in subsequent time periods, thereby improving the accuracy of power grid data analysis. By controlling the power of the target area according to the analyzed power grid data, the power of the site can be adjusted in time according to the power grid data of each power grid site in the target area in the future time period obtained by analysis, thereby achieving accurate adjustment of power grid power, ensuring the matching of power supply and demand of electric energy, and thus improving the efficiency of power control. Therefore, the power control method, system and device based on source-grid-load-storage proposed in the present invention can solve the problem of low efficiency when performing power control. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic flow chart of a power control method based on source-grid-load-storage provided in one embodiment of the present invention;

[0074] Figure 2 A schematic diagram of a process for generating a power grid structure model provided by an embodiment of the present invention;

[0075] Figure 3 A schematic diagram of a process for generating a meteorological grid model provided by an embodiment of the present invention;

[0076] Figure 4 A functional module diagram of a power control system based on source, grid, load and storage provided in one embodiment of the present invention.

[0077] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0078] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0079] The embodiment of the present application provides a power control method based on source-grid-load-storage. The execution subject of the power control method based on source-grid-load-storage includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the power control method based on source-grid-load-storage can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0080] Reference Figure 1 FIG. 1 is a flow chart of a power control method based on source, grid, load and storage provided by an embodiment of the present invention. In this embodiment, the power control method based on source, grid, load and storage includes:

[0081] S1. Obtain a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model.

[0082] In an embodiment of the present invention, each historical power grid data in the historical power grid data set refers to the connectivity status, power generation data, load data and energy storage data of each node in the power grid of the target area recorded in the past period of time, and each historical meteorological data in the historical meteorological data set refers to the meteorological data of the target area recorded in the past period of time, such as temperature, humidity, wind speed, wind direction and weather data.

[0083] Specifically, the historical power grid data set and the historical meteorological data set can be obtained by data crawling by staff with corresponding permissions, and the power grid structure model is a graph neural network model composed of nodes and edges with a topological graph structure.

[0084] In the embodiment of the present invention, refer to Figure 2 As shown, the grid structure analysis and positioning modeling are performed on the historical grid data set to obtain a grid structure model, including:

[0085] S21, performing site detection on the historical power grid data set to obtain a power grid site set;

[0086] S22, performing site coordinate positioning on the historical power grid data set according to the power grid site set to obtain a site location set;

[0087] S23, performing a topological link analysis on the power grid site set according to the historical power grid data set to obtain a power grid connection structure;

[0088] S24. Perform edge mapping on the site location set according to the power grid connection structure to obtain a power grid structure model.

[0089] In detail, the site detection refers to using a keyword matching method to detect the names of each power grid site in the historical power grid data set and compile them into a power grid site set. The power grid site refers to an important node in the power grid system used for power generation, transmission, distribution and control, such as a wind power station, a distribution station, a residential power substation, an industrial power substation, a storage station, etc.

[0090] Specifically, the site coordinate positioning refers to matching the location coordinate data corresponding to each power grid site in the power grid site set from the historical power grid data set, and the topological link analysis refers to extracting the connection relationship between each site in the historical power grid data set, and using the topological analysis method to generate a power grid connection structure based on all site connection relationships.

[0091] In detail, the edge mapping refers to mapping the connection relationship between each site in the power grid connection structure to the nodes corresponding to the site location set to generate a power grid structure model with a graph structure.

[0092] Specifically, by performing grid structure analysis and positioning modeling on the historical grid data set to obtain a grid structure model, graph neural networks can be used to more accurately simulate the complex relationships and dynamic changes between grid sites, thereby improving the accuracy of grid power analysis.

[0093] S2. Perform geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model.

[0094] In an embodiment of the present invention, the meteorological grid model refers to a time series grid neural network model used for meteorological forecasting, the input of the meteorological grid model is the meteorological characteristics of each grid area of ​​the target area in the previous time period, and the output of the meteorological grid model is the meteorological characteristics of each grid area of ​​the target area in the next time period.

[0095] In the embodiment of the present invention, refer to Figure 3 As shown, the historical meteorological data set is subjected to geographic grid division and meteorological feature clustering mapping operations to obtain a meteorological grid model, including:

[0096] S31, extracting a historical meteorological map from the historical meteorological data set;

[0097] S32, sequentially performing geographic coordinate conversion and grid division on the historical meteorological map to obtain a meteorological block group;

[0098] S33, using the historical meteorological data set to perform meteorological feature mapping on the meteorological block group to obtain a block meteorological feature group set;

[0099] S34, performing block clustering and merging on the meteorological block group according to the block meteorological feature group set to obtain a standard meteorological block group;

[0100] S35, performing grid mapping and model initialization operations on the standard meteorological block group to obtain a meteorological grid model.

[0101] In detail, the historical meteorological map refers to the meteorological map of the target area, the geographic coordinate transformation refers to the transformation of the coordinates of the historical meteorological map according to the actual size scale and regional location coordinates of the target area, and the grid division refers to dividing the historical meteorological map after the coordinate transformation into multiple meteorological blocks of equal size according to a preset grid size, and aggregating all the meteorological blocks into a meteorological block group.

[0102] Specifically, using the historical meteorological data set to map the meteorological features of the meteorological block group to obtain a block meteorological feature group set refers to selecting meteorological blocks in the meteorological block group as target meteorological blocks one by one, screening out the block meteorological data set corresponding to the target meteorological block from the historical meteorological data set, vectorizing the block meteorological data set into a block meteorological feature set, and aggregating all the block meteorological feature sets into a block meteorological feature group set.

[0103] In detail, the block clustering and merging of the meteorological block groups according to the block meteorological feature group set to obtain a standard meteorological block group includes:

[0104] Selecting meteorological blocks in the meteorological block group one by one as target meteorological blocks, and gathering meteorological blocks in the meteorological block group that are adjacent to the target meteorological block into a neighboring block group;

[0105] The meteorological blocks in the neighboring block group are selected one by one as the target neighboring blocks, and the block distance between the target meteorological block and the target neighboring block is calculated using the following block distance algorithm and the block meteorological feature set:

[0106]

[0107] Wherein, C refers to the block distance, μ is the preset distance resistance coefficient, Q is the total number of features of each block meteorological feature set in the block meteorological feature set, and A q It refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target meteorological block in the block meteorological feature set, B q It refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target adjacent block in the block meteorological feature set, · is the vector dot product symbol, A x It refers to the horizontal coordinate of the midpoint of the target meteorological block, B x A refers to the horizontal coordinate of the midpoint of the target neighboring block. y It refers to the ordinate of the midpoint of the target meteorological block, B y refers to the ordinate of the midpoint of the target adjacent block, || is the absolute value symbol, and || || is the modulus symbol;

[0108] Determining whether the block distance is less than a preset distance threshold;

[0109] If not, returning to the step of selecting the meteorological blocks in the neighboring block group one by one as the target neighboring blocks;

[0110] If yes, the target meteorological block and the target adjacent block are merged into a target merged block, the target merged block is used to update the meteorological blocks in the meteorological block group, and the step of selecting meteorological blocks in the meteorological block group as target meteorological blocks is returned to one by one;

[0111] When the target meteorological block is the last meteorological block in the meteorological block group, the meteorological block group is used as a standard meteorological block group.

[0112] In detail, the block distance algorithm can combine the differences in meteorological characteristics and the distance differences between blocks to achieve the fusion of blocks with similar meteorology, thereby reducing the grid complexity of the meteorological grid model and retaining the spatial correlation of meteorological data.

[0113] Specifically, the grid mapping refers to extracting a block structure from the standard meteorological block group, performing grid mapping on the block structure to obtain an initial grid model, initializing a temporal neural structure layer for the initial grid model, and obtaining a meteorological grid model.

[0114] In an embodiment of the present invention, by generating a meteorological grid model based on the historical meteorological data set, a grid neural network can be used to implement block simulation of meteorological data in a target area, thereby retaining the spatial correlation of meteorological data and improving the generalization ability of the meteorological grid model.

[0115] S3. Using the historical meteorological data set to perform time series meteorological training on the meteorological grid model to obtain a meteorological analysis model.

[0116] In an embodiment of the present invention, the meteorological analysis model is a trained meteorological grid model, which can predict the meteorological characteristics of each grid area of ​​the target area in the next time period based on the meteorological characteristics of each grid area of ​​the target area in the previous time period.

[0117] In the embodiment of the present invention, the use of the historical meteorological data set to perform time series meteorological training on the meteorological grid model to obtain a meteorological analysis model includes:

[0118] Sorting the historical meteorological data set in time series to obtain a historical meteorological data sequence;

[0119] Extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence;

[0120] Using the meteorological grid model to perform time series feature extraction and residual feature mapping operations on the meteorological feature group sequence, to obtain an analysis meteorological feature group sequence;

[0121] Using the analyzed meteorological feature group sequence to perform sequence alignment on the meteorological feature group sequence to obtain an aligned meteorological feature group sequence;

[0122] The meteorological loss value of the meteorological analysis model is calculated according to the analyzed meteorological feature group sequence and the aligned meteorological feature group sequence using the following meteorological loss value algorithm:

[0123]

[0124] Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol;

[0125] The meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model.

[0126] In detail, the time series data sorting refers to sorting the historical meteorological data set according to a fixed time period length and time sequence, and aggregating the historical meteorological data within each period length into a historical meteorological data sequence.

[0127] Specifically, the block structure refers to the composition structure of each standard meteorological block in the standard meteorological block group corresponding to the meteorological grid model, the time series feature extraction refers to the use of the gating structure in the meteorological grid model to extract the time-dependent characteristics of the meteorological feature group sequence, and the residual feature mapping refers to the use of the fully connected layer and the residual connection layer in the meteorological grid model to map the time-dependent features.

[0128] Specifically, the meteorological loss value algorithm can determine the meteorological loss value of the model based on the difference in meteorological characteristics of each corresponding block in the target area within the corresponding time period according to the analysis of the meteorological feature group sequence and the aligned meteorological feature group sequence, thereby improving the accuracy of model training.

[0129] In detail, the sequence alignment refers to aggregating some meteorological feature groups in the meteorological feature group sequence that have the same timestamp as the analyzed meteorological feature group sequence into an aligned meteorological feature group sequence, and the iterative parameter updating method may be a gradient descent algorithm.

[0130] In an embodiment of the present invention, by using the historical meteorological data set to perform time-series meteorological training on the meteorological grid model, a meteorological analysis model is obtained, which can analyze the meteorological data of subsequent time periods in combination with the location relationship between regions and the time-series connection of meteorological data, thereby improving the accuracy of meteorological data analysis.

[0131] S4. Jointly train the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model.

[0132] In an embodiment of the present invention, the power grid analysis model is a graph recurrent neural network model whose input is the power grid characteristics of the previous time period and the meteorological characteristics of the next time period, and whose output is the power grid characteristics of the next time period.

[0133] In detail, since power grid data is greatly affected by usage habits, and peak electricity consumption and power generation data are greatly affected by meteorological data such as temperature, solar radiation intensity, wind force and wind direction, the power grid structure model can be jointly trained based on the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model.

[0134] In an embodiment of the present invention, the method of jointly training the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model includes:

[0135] Extracting the site structure from the historical power grid data set to obtain the power grid distribution structure;

[0136] Using the power grid distribution structure to perform time sequence sorting and structure grouping operations on the historical meteorological data set to obtain a site meteorological data group sequence;

[0137] Using the power grid distribution structure, the historical power grid data set is subjected to time sequence sorting and structure grouping operations to obtain a historical power grid data set sequence;

[0138] Performing a jump feature fusion operation on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence;

[0139] The power grid meteorological feature group sequence and the historical power grid data group sequence are used to perform model training on the power grid structure model to obtain a power grid analysis model.

[0140] In detail, the geographical distribution structure refers to the distribution position and distribution structure of each site in the target area corresponding to the historical power grid data set, and the site structure can be extracted by using a keyword search method.

[0141] Specifically, the structural grouping refers to grouping the time-series sorted historical meteorological data sets and the historical power grid data sets according to the interval positions corresponding to each power grid site in the power grid distribution structure, each site meteorological data group in the site meteorological data group sequence corresponds to the meteorological data of each site area in the target area within a time period, each site meteorological data in the site meteorological data group corresponds to the meteorological data of a site area, each historical power grid data group in the historical power grid data group sequence corresponds to the power grid data of each site area in the target area within a time period, and each historical power grid data in the historical power grid data group corresponds to the power grid data of a site area.

[0142] Specifically, the jump feature fusion operation is performed on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence, including:

[0143] Extracting meteorological features from the site meteorological data group sequence to obtain a site meteorological feature group sequence;

[0144] Extracting power grid features from the historical power grid data group sequence to obtain a historical power grid feature group sequence;

[0145] The following jump fusion algorithm is used to perform feature fusion on the site meteorological feature group sequence and the historical power grid feature group sequence to obtain a power grid meteorological feature group sequence:

[0146]

[0147] Among them, Z i,j-1 refers to the i-th grid meteorological feature in the j-1-th grid meteorological feature group in the grid meteorological feature group sequence, i refers to the sequence number, I refers to the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence, and the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence is equal to the total number of historical grid features in each historical grid feature group in the historical grid feature group sequence, J refers to the sequence length of the site meteorological feature group sequence, and the sequence length of the site meteorological feature group sequence is equal to the sequence length of the historical grid feature group sequence, softmax is a normalization function, Q i,j-1 is the i-th historical power grid feature in the j-1-th historical power grid feature group in the historical power grid feature group sequence, R i,j is the i-th site meteorological feature in the j-th site meteorological feature group in the site meteorological feature group sequence, α, β, γ are preset attention coefficient matrices, w() is a dimensional function, and T is a transposition symbol.

[0148] Specifically, the jump fusion algorithm can be combined with the attention feature fusion method to realize the fusion of the site meteorological feature group sequence and the historical power grid feature group sequence, while ensuring the time period difference between the power grid characteristics and the meteorological characteristics during fusion, thereby improving the representation of the power grid meteorological characteristics obtained after fusion.

[0149] In detail, the method of using the grid meteorological feature group sequence and the historical grid data group sequence to perform model training on the grid structure model to obtain a grid analysis model includes:

[0150] Using the grid meteorological feature group sequence to perform feature mapping operation on the grid structure model to obtain an embedded grid model;

[0151] Performing recursive cyclic convolution and output mapping operations on the embedded power grid model to obtain a sequence of power grid feature groups for analysis;

[0152] Using the analyzed power grid feature group sequence to perform sequence alignment on the historical power grid data group sequence to obtain an aligned power grid data group sequence;

[0153] Extracting power grid features from the aligned power grid data group sequence to obtain an aligned power grid feature group sequence;

[0154] Calculating a power grid loss value between the aligned power grid feature group sequence and the analyzed power grid feature group sequence;

[0155] The embedded power grid model is iteratively updated with parameters according to the power grid loss value to obtain a power grid analysis model.

[0156] In detail, the power grid meteorological feature group sequence is used to perform a feature embedding operation on the power grid structure model to obtain an embedded power grid model, which means that each power grid meteorological feature group in the power grid meteorological feature group sequence is embedded into the model nodes and model edges of the power grid structure model according to the time sequence and the correspondence between the power grid distribution structure.

[0157] In detail, a recurrent neural network or a long short-term memory network can be used to perform recursive circular convolution, so as to recursively calculate or iteratively update the representation of the node to capture the connection relationship and timing between the nodes. The output mapping can be implemented through a fully connected layer, and the power grid loss value can be calculated using a mean square error loss value algorithm.

[0158] In an embodiment of the present invention, the power grid structure model is jointly trained using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model. The power grid data of subsequent time periods in the target area can be analyzed and predicted in combination with the real-time impact of meteorological data on the power grid data and the periodic law of the power grid data, thereby improving the accuracy of the power grid data analysis.

[0159] S5. Acquire real-time power grid data and real-time meteorological data of the target area, calculate analytical power grid data using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and perform power control on the target area according to the analytical power grid data.

[0160] In the embodiment of the present invention, the real-time power grid data refers to the power grid data corresponding to each site in the target area within the current time period, and the real-time meteorological data refers to the meteorological data of the target area within the current time period.

[0161] In detail, the calculating and analyzing the power grid data by using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data includes:

[0162] Performing a block meteorological feature extraction operation on the real-time meteorological data to obtain a real-time meteorological feature group;

[0163] Performing meteorological analysis on the real-time meteorological feature group using the meteorological analysis model to obtain a target meteorological feature group;

[0164] Performing structure grouping and grid feature extraction operations on the real-time grid data to obtain a real-time grid feature group;

[0165] Performing a jump feature fusion operation on the real-time power grid feature group and the target meteorological feature group to obtain a target power grid meteorological feature group;

[0166] Calculating a target power grid feature group corresponding to the target power grid meteorological feature group using the power grid analysis model;

[0167] A feature inverse mapping operation is performed on the target power grid feature group to obtain analysis power grid data.

[0168] In detail, the block meteorological feature extraction operation is the same as the block meteorological feature extraction in the above step S3, and the feature inverse mapping operation refers to the inverse operation of the power grid feature extraction operation.

[0169] Specifically, the power control of the target area according to the analyzed power grid data refers to timely adjusting the power generation power and charging and discharging power of the corresponding site according to the power grid data such as the connectivity status of each site, power generation data, load data and energy storage data obtained from the analyzed power grid data, so as to achieve power balance of the power grid in the subsequent time period and ensure the matching of supply and demand of electric energy.

[0170] In an embodiment of the present invention, by performing power control on the target area according to the analyzed power grid data, the power of the site can be adjusted in a timely manner according to the power grid data of each power grid site in the target area in the future time period obtained by analysis, thereby achieving precise adjustment of the power grid, ensuring the matching of supply and demand of electric energy, and thereby improving the efficiency of power control.

[0171] The present invention obtains a power grid structure model by performing power grid structure analysis and positioning modeling on the historical power grid data set, and can use graph neural networks to more accurately simulate the complex relationships and dynamic changes between power grid sites, thereby improving the accuracy of power grid power analysis. By generating a meteorological grid model based on the historical meteorological data set, the grid neural network can be used to achieve block simulation of meteorological data in the target area, and the spatial correlation of meteorological data can be retained to improve the generalization ability of the meteorological grid model. By using the historical meteorological data set to perform time-series meteorological training on the meteorological grid model, a meteorological analysis model is obtained, which can analyze meteorological data in subsequent time periods in combination with the positional relationship between regions and the time-series connection of meteorological data, thereby improving the accuracy of meteorological data analysis.

[0172] By using the historical meteorological data set and the historical power grid data set to jointly train the power grid structure model, a power grid analysis model is obtained, which can be combined with the real-time impact of meteorological data on power grid data and the periodic law of power grid data to analyze and predict the power grid data of the target area in subsequent time periods, thereby improving the accuracy of power grid data analysis. By controlling the power of the target area according to the analyzed power grid data, the power of the site can be adjusted in time according to the power grid data of each power grid site in the target area in the future time period obtained by analysis, thereby achieving accurate adjustment of power grid power, ensuring the matching of power supply and demand of electric energy, and thus improving the efficiency of power control. Therefore, the power control method based on source-grid-load-storage proposed in the present invention can solve the problem of low efficiency when performing power control.

[0173] like Figure 4 , which is a functional module diagram of a power control system based on source, grid, load and storage provided in one embodiment of the present invention.

[0174] The power control system 100 based on source-grid-load-storage of the present invention can be installed in an electronic device. According to the functions to be implemented, the power control system 100 based on source-grid-load-storage can include a structural modeling module 101, a grid modeling module 102, a meteorological training module 103, a joint training module 104 and a power control module 105. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0175] In this embodiment, the functions of each module / unit are as follows:

[0176] The structural modeling module 101 is used to obtain a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model;

[0177] The grid modeling module 102 is used to perform geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model;

[0178] The meteorological training module 103 is used to perform time series meteorological training on the meteorological grid model using the historical meteorological data set to obtain a meteorological analysis model, wherein the use of the historical meteorological data set to perform time series meteorological training on the meteorological grid model to obtain a meteorological analysis model includes: sorting the historical meteorological data set to obtain a historical meteorological data sequence; extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence; using the meteorological grid model to perform time series feature extraction and residual feature mapping operations on the meteorological feature group sequence to obtain an analysis meteorological feature group sequence; using the analysis meteorological feature group sequence to perform sequence alignment on the meteorological feature group sequence to obtain an aligned meteorological feature group sequence; using the following meteorological loss value algorithm to calculate the meteorological loss value of the meteorological analysis model according to the analysis meteorological feature group sequence and the aligned meteorological feature group sequence:

[0179]

[0180] Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h It refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol; the meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model;

[0181] The joint training module 104 is used to jointly train the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model;

[0182] The power control module 105 is used to obtain real-time power grid data and real-time meteorological data of the target area, calculate analytical power grid data using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and perform power control on the target area according to the analytical power grid data.

[0183] In detail, each module described in the power control system 100 based on source, grid, load and storage in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The power control method based on source, grid, load and storage described in the present invention has the same technical means and can produce the same technical effects, so it will not be repeated here.

[0184] A schematic structural diagram of an electronic device for implementing a power control method based on source, grid, load and storage provided by an embodiment of the present invention.

[0185] The electronic device (not shown) may include a processor, a memory, a communication bus, and a communication interface, and may also include a computer program stored in the memory and executable on the processor, such as a power control program based on source, grid, load, and storage.

[0186] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory (for example, executing power control programs based on source, grid, load, and storage, etc.), and calls data stored in the memory to execute various functions of the electronic device and process data.

[0187] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory can also include both an internal storage unit of the electronic device and an external storage device. The memory can not only be used to store application software and various types of data installed in the electronic device, such as the code of the power control program based on the source network load storage, but also can be used to temporarily store data that has been output or is to be output.

[0188] The communication bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection communication between the memory and at least one processor, etc.

[0189] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0190] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0191] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0192] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0193] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0194] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0195] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0196] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0197] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0198] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0199] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system embodiment can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any specific order.

[0200] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A power control method based on source-grid-load-storage, characterized in that: The method comprises: Acquire a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model; Performing geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model; The meteorological grid model is trained with time series meteorology using the historical meteorological data set to obtain a meteorological analysis model, wherein the training with the historical meteorological data set to obtain a meteorological analysis model includes: sorting the historical meteorological data set to obtain a historical meteorological data sequence; extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence; performing time series feature extraction and residual feature mapping operations on the meteorological feature group sequence using the meteorological grid model to obtain an analysis meteorological feature group sequence; performing sequence alignment on the meteorological feature group sequence using the analysis meteorological feature group sequence to obtain an aligned meteorological feature group sequence; and calculating the meteorological loss value of the meteorological analysis model according to the analysis meteorological feature group sequence and the aligned meteorological feature group sequence using the following meteorological loss value algorithm: Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h It refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol; the meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model; The power grid structure model is jointly trained using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model; Real-time power grid data and real-time meteorological data of the target area are obtained, analytical power grid data are calculated using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and power control of the target area is performed according to the analytical power grid data.

2. The power control method based on source-grid-load-storage according to claim 1, characterized in that: The performing grid structure analysis and positioning modeling on the historical grid data set to obtain a grid structure model includes: Performing site detection on the historical power grid data set to obtain a power grid site set; Performing site coordinate positioning on the historical power grid data set according to the power grid site set to obtain a site location set; Performing a topological connection analysis on the power grid site set according to the historical power grid data set to obtain a power grid connection structure; The site location set is edge mapped according to the power grid connection structure to obtain a power grid structure model.

3. The power control method based on source-grid-load-storage according to claim 1, characterized in that: The historical meteorological data set is subjected to geographic grid division and meteorological feature cluster mapping operations to obtain a meteorological grid model, including: Extracting a historical meteorological map from the historical meteorological data set; The historical meteorological map is sequentially subjected to geographic coordinate conversion and grid division to obtain a meteorological block group; Using the historical meteorological data set to perform meteorological feature mapping on the meteorological block group, to obtain a block meteorological feature group set; Perform block clustering and merging on the meteorological block group according to the block meteorological feature group set to obtain a standard meteorological block group; Grid mapping and model initialization operations are performed on the standard meteorological block group to obtain a meteorological grid model.

4. The power control method based on source-grid-load-storage according to claim 3, characterized in that: The step of clustering and merging the meteorological block groups according to the block meteorological feature group set to obtain a standard meteorological block group includes: Selecting meteorological blocks in the meteorological block group one by one as target meteorological blocks, and gathering meteorological blocks in the meteorological block group that are adjacent to the target meteorological block into a neighboring block group; The meteorological blocks in the neighboring block group are selected one by one as the target neighboring blocks, and the block distance between the target meteorological block and the target neighboring block is calculated using the following block distance algorithm and the block meteorological feature set: Wherein, C refers to the block distance, μ is the preset distance resistance coefficient, Q is the total number of features of each block meteorological feature set in the block meteorological feature set, and A q It refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target meteorological block in the block meteorological feature set, B q It refers to the qth block meteorological feature in the block meteorological feature set corresponding to the target adjacent block in the block meteorological feature set, · is the vector dot product symbol, A x It refers to the horizontal coordinate of the midpoint of the target meteorological block, B x A refers to the horizontal coordinate of the midpoint of the target neighboring block. y It refers to the ordinate of the midpoint of the target meteorological block, B y It refers to the ordinate of the midpoint of the target adjacent block, || is the absolute value symbol, ‖‖ is the modulus symbol; Determining whether the block distance is less than a preset distance threshold; If not, returning to the step of selecting the meteorological blocks in the neighboring block group one by one as the target neighboring blocks; If yes, the target meteorological block and the target adjacent block are merged into a target merged block, the target merged block is used to update the meteorological blocks in the meteorological block group, and the step of selecting meteorological blocks in the meteorological block group as target meteorological blocks is returned to one by one; When the target meteorological block is the last meteorological block in the meteorological block group, the meteorological block group is used as a standard meteorological block group.

5. The power control method based on source-grid-load-storage according to claim 1, characterized in that: The method of jointly training the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model includes: Extracting the site structure of the historical power grid data set to obtain a power grid distribution structure; Using the power grid distribution structure to perform time sequence sorting and structure grouping operations on the historical meteorological data set to obtain a site meteorological data group sequence; Using the power grid distribution structure, the historical power grid data set is subjected to time sequence sorting and structure grouping operations to obtain a historical power grid data set sequence; Performing a jump feature fusion operation on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence; The power grid meteorological feature group sequence and the historical power grid data group sequence are used to perform model training on the power grid structure model to obtain a power grid analysis model.

6. The power control method based on source-grid-load-storage according to claim 5, characterized in that: The step of performing a jump feature fusion operation on the site meteorological data group sequence and the historical power grid data group sequence to obtain a power grid meteorological feature group sequence includes: Extracting meteorological features from the site meteorological data group sequence to obtain a site meteorological feature group sequence; Extracting power grid features from the historical power grid data group sequence to obtain a historical power grid feature group sequence; The following jump fusion algorithm is used to perform feature fusion on the site meteorological feature group sequence and the historical power grid feature group sequence to obtain a power grid meteorological feature group sequence: Among them, Z i,j-1 refers to the i-th grid meteorological feature in the j-1-th grid meteorological feature group in the grid meteorological feature group sequence, i refers to the sequence number, I refers to the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence, and the total number of site meteorological features in each site meteorological feature group in the site meteorological feature group sequence is equal to the total number of historical grid features in each historical grid feature group in the historical grid feature group sequence, J refers to the sequence length of the site meteorological feature group sequence, and the sequence length of the site meteorological feature group sequence is equal to the sequence length of the historical grid feature group sequence, softmax is a normalization function, Q i,j-1 is the i-th historical power grid feature in the j-1-th historical power grid feature group in the historical power grid feature group sequence, R i,j is the i-th site meteorological feature in the j-th site meteorological feature group in the site meteorological feature group sequence, α, β, γ are preset attention coefficient matrices, w() is a dimensional function, and T is a transposition symbol.

7. The power control method based on source-grid-load-storage according to claim 5, characterized in that: The method of using the power grid meteorological feature group sequence and the historical power grid data group sequence to perform model training on the power grid structure model to obtain a power grid analysis model includes: Using the grid meteorological feature group sequence to perform feature mapping operation on the grid structure model to obtain an embedded grid model; Performing recursive cyclic convolution and output mapping operations on the embedded power grid model to obtain a sequence of analyzed power grid feature groups; Using the analyzed power grid feature group sequence to perform sequence alignment on the historical power grid data group sequence to obtain an aligned power grid data group sequence; Extracting power grid features from the aligned power grid data group sequence to obtain an aligned power grid feature group sequence; Calculating a power grid loss value between the aligned power grid feature group sequence and the analyzed power grid feature group sequence; The embedded power grid model is iteratively updated with parameters according to the power grid loss value to obtain a power grid analysis model.

8. The power control method based on source-grid-load-storage according to claim 1, characterized in that: The method of calculating and analyzing power grid data by using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data includes: Performing a block meteorological feature extraction operation on the real-time meteorological data to obtain a real-time meteorological feature group; Performing meteorological analysis on the real-time meteorological feature group using the meteorological analysis model to obtain a target meteorological feature group; Performing structure grouping and grid feature extraction operations on the real-time grid data to obtain a real-time grid feature group; Performing a jump feature fusion operation on the real-time power grid feature group and the target meteorological feature group to obtain a target power grid meteorological feature group; Calculating a target power grid feature group corresponding to the target power grid meteorological feature group using the power grid analysis model; A feature inverse mapping operation is performed on the target power grid feature group to obtain analysis power grid data.

9. A power control system based on source, grid, load and storage, characterized in that: The system comprises: A structural modeling module is used to obtain a historical power grid data set and a historical meteorological data set of a target area, perform power grid structure analysis and positioning modeling on the historical power grid data set, and obtain a power grid structure model; A grid modeling module is used to perform geographic grid division and meteorological feature clustering mapping operations on the historical meteorological data set to obtain a meteorological grid model; A meteorological training module is used to perform time series meteorological training on the meteorological grid model using the historical meteorological data set to obtain a meteorological analysis model, wherein the use of the historical meteorological data set to perform time series meteorological training on the meteorological grid model to obtain a meteorological analysis model includes: sorting the historical meteorological data set to obtain a historical meteorological data sequence; extracting a block structure from the meteorological grid model, and performing a block meteorological feature extraction operation on the historical meteorological data sequence according to the block structure to obtain a meteorological feature group sequence; using the meteorological grid model to perform time series feature extraction and residual feature mapping operations on the meteorological feature group sequence to obtain an analysis meteorological feature group sequence; using the analysis meteorological feature group sequence to perform sequence alignment on the meteorological feature group sequence to obtain an aligned meteorological feature group sequence; using the following meteorological loss value algorithm to calculate the meteorological loss value of the meteorological analysis model according to the analysis meteorological feature group sequence and the aligned meteorological feature group sequence: Wherein, W refers to the meteorological loss value, h, j refers to the sequence number, H refers to the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence, and the total number of features of each analysis meteorological feature group in the analysis meteorological feature group sequence is equal to the total number of features of each alignment meteorological feature group in the alignment meteorological feature group sequence, J refers to the sequence length of the analysis meteorological feature group sequence, and the sequence length of the analysis meteorological feature group sequence is equal to the sequence length of the analysis meteorological feature group sequence, and D j,h refers to the hth analytical meteorological feature in the jth analytical meteorological feature group in the analytical meteorological feature group sequence, Y j,h It refers to the hth aligned meteorological feature in the jth aligned meteorological feature group in the aligned meteorological feature group sequence, ε is a preset constant, λ is a preset loss weight, and Δ is the Laplace operator symbol; the meteorological grid model is iteratively parameter updated according to the meteorological loss value to obtain a meteorological analysis model; A joint training module, used for jointly training the power grid structure model using the historical meteorological data set and the historical power grid data set to obtain a power grid analysis model; A power control module is used to obtain real-time power grid data and real-time meteorological data of the target area, calculate analytical power grid data using the meteorological analysis model, the power grid analysis model, the real-time power grid data and the real-time meteorological data, and perform power control on the target area according to the analytical power grid data.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the power control method based on source, grid, load and storage as described in any one of claims 1 to 8.

Images