Load transfer analysis processing system based on knowledge graph

Abstract

The invention relates to the technical field of intelligent power grids, and discloses a load transfer analysis processing system based on a knowledge graph, and the system comprises a topology power supply network subsystem which builds a topology network with a main transformer topology starting point, and builds a topology node at each distribution transformer in each power supply line in the topology network; quantifying the electric energy dynamic consumption correlation between the topology starting point and the plurality of topology nodes; the load analysis processing subsystem comprises a data acquisition module for extracting corresponding dynamic consumption correlation characteristics based on the dynamic consumption correlation of the electric energy of the topological nodes in the topological network; and the data analysis module inputs the input feature vector into the completely trained power grid operation load demonstration model, and outputs a peak predicted value of each corresponding topological node. According to the method, the generation probability of the operation load pressure of the power supply line can be reduced, and the operation efficiency and stability of the whole power grid can be optimized.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a load transfer analysis and processing system based on a knowledge graph. Background Art

[0002] With the development of smart grids, the management of power grids has become more convenient and faster. The current optimization for smart grids is to facilitate data processing. Due to the huge power supply network, the amount of data analysis for the entire system is also huge. In addition, data transmission is also limited by the network, that is, the problem of network delay cannot be ignored. There will be a lag in the processing of these data, which makes data processing very important in smart grids.

[0003] As disclosed in announcement number: CN106464714A, announcement date: 2017-02-22, the nodes within the disclosed wireless mesh network are configured to monitor time series data associated with a utility network (or any other device network). One or more servers coupled to the wireless mesh network configure the data ingestion cloud to receive and process the time series data from the nodes to generate a data stream. The server also configures the distributed processing cloud to perform historical analysis on the data stream, and configures the real-time processing cloud to perform real-time analysis on the data stream. The distributed processing cloud and the real-time processing cloud can interact with each other in response to processing the data stream. In particular, the real-time processing cloud can trigger historical analysis of the distributed processing cloud, and the distributed processing cloud can trigger real-time processing of the real-time processing cloud. Any processing cloud may include an edge node configured to perform real-time processing and generate a data stream.

[0004] In the existing technologies including the above-mentioned patents, it can be seen that the main development direction of smart grids is data processing, which means that data must be collected, sorted and processed first, which belongs to terminal processing. By establishing topological relationships, data can be processed in a decentralized manner, that is, each node analyzes the data in a centralized manner, and then traces back according to the node level and finally feeds back to the terminal. This can effectively solve the drawbacks brought about by the centralized processing of huge data collection. Summary of the invention

[0005] The purpose of the present invention is to provide a load transfer analysis and processing system based on knowledge graph to solve the above problems.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A load transfer analysis and processing system based on knowledge graph, comprising:

[0008] A topological power supply network subsystem, which establishes a topological network with the main transformer as the topological starting point, and creates a topological node in each distribution transformer in each power supply line in the topological network;

[0009] and quantifying the correlation between the dynamic power consumption of the topology starting point and a plurality of the topology nodes;

[0010] Load analysis and processing subsystem, which includes:

[0011] A data acquisition module, based on the correlation of the dynamic consumption of electric energy of the topological nodes in the topological network, extracts corresponding dynamic consumption related features;

[0012] The data analysis module inputs the input feature vector into a well-trained power grid operation load demonstration model, and outputs the corresponding peak prediction value of each topological node to determine the peak time of the topological node and the total amount of electric energy consumption within the peak time range.

[0013] Preferably, the input feature vector generates training samples according to the dynamic consumption related features, and the training samples are sorted by cluster analysis to determine the input feature vector;

[0014] The arrangement includes:

[0015] S11, splitting the training samples into a first training sample set and a second training sample set;

[0016] S12, performing dimensionality reduction on the first training sample set and the second training sample set by PCA respectively, and then clustering the data to generate a first transformation matrix and a second transformation matrix corresponding to the above;

[0017] S13. Determine the input feature vector according to the first training sample set, the second training sample set, the first transformation matrix, and the second transformation matrix.

[0018] Preferably, determining the correlation of the dynamic power consumption of the topological node is based on predicting the dynamic power consumption data of the topological node, the adjacent upstream topological node and the downstream topological node;

[0019] Based on the topological network, a random predicted topological node and the corresponding upstream topological node and downstream topological node, as well as the co-located topological nodes of the same level as the previous topological node for each power supply line in the topological network and the number of the co-located topological nodes are determined.

[0020] Preferably, the dynamic power consumption correlation includes a time coefficient and a space coefficient, and the quantification of the dynamic power consumption correlation of the topology starting point and the upstream position and the downstream position of the plurality of topology nodes includes:

[0021] Determine the corresponding time coefficient according to the peak time period of the predicted topological node, the power consumption quota in the peak time period and the power consumption quota in the non-peak time period;

[0022] The spatial coefficient is determined based on the determined predicted topological node, the co-located topological node corresponding to the upstream position, and the co-located topological node corresponding to the downstream position.

[0023] Preferably, determining the corresponding time coefficient according to the determined power consumption quota of the predicted topological node in the peak time period and the power consumption quota in the non-peak time period includes:

[0024] The historical power consumption quota corresponding to the peak time period of the predicted topological node is retrieved, and a power consumption quota value range for the corresponding peak time period of the predicted topological node is generated.

[0025] Preferably, based on the determined predicted topological node, the co-located topological node corresponding to the upstream position, and the co-located topological node corresponding to the downstream position, determining the corresponding spatial coefficient includes:

[0026] S21, determining a corresponding first spatial set according to a set of electric energy consumption quota value ranges in a corresponding peak time period of the traffic flow of the predicted topological node and the co-located topological node corresponding to the upstream position;

[0027] S22, determining a corresponding second spatial set according to a set of electric energy consumption quota value ranges of the traffic flow of the predicted topological node and the co-located topological nodes corresponding to the downstream position in the corresponding peak time period;

[0028] S23: Determine the maximum power consumption quota of each co-located topological node and the predicted topological node in the dynamic space according to the first space set and the second space set.

[0029] Preferably, the input feature vector is input into a well-trained power grid operation load demonstration model, and the corresponding peak prediction value of each of the topological nodes is output, including the corresponding peak prediction values ​​of the co-located topological nodes.

[0030] In the above technical solution, the present invention provides a load transfer analysis and processing system based on knowledge graph, which has the following beneficial effects:

[0031] 1. Create a topological network with the main transformer as the topological starting point, and each distribution transformer under the main transformer, and each distribution transformer under the distribution transformer as the topological node, and use the first distribution transformer under the main transformer as the line reference to determine each power supply line in the network. Then generate multiple topological networks based on the same main transformer, and each topological network performs load pressure calculation separately, and feeds back to the terminal separately, so as to form a blockchain-like data processing method to reduce operating pressure. However, this application divides several power supply lines of each topological network according to the above-mentioned rules in the form of the topological network, and then calculates each power supply line separately, thereby showing the purpose of reducing operating pressure.

[0032] 2. By randomly selecting a predicted topological node, the upstream and downstream of the predicted topological node and the co-located topological nodes of several power supply lines of the topological network are determined, thereby generating a time coefficient and a space coefficient. Then, based on the time coefficient, the peak time of each co-located topological node is obtained, thereby providing time support for subsequent load transfer. The space coefficient provides the range of power consumption quotas of the co-located topological nodes during peak time and non-peak time. Then, based on the range of power consumption quotas, the amount of power that can be transferred is determined.

[0033] 3. Through the analysis of historical data, the range of electricity consumption quota is determined to obtain the maximum electricity consumption quota, so as to cooperate with the existing power generation prediction system such as photovoltaic power generation, based on the maximum electricity demand in each power supply line, to form a reasonable electricity distribution, thereby reducing the probability of load pressure on the power supply line. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] Figure 1 A module diagram provided for an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a topological network provided in an embodiment of the present invention;

[0037] Figure 3 A schematic diagram of the process structure of organizing the training samples using the cluster analysis method provided in an embodiment of the present invention;

[0038] Figure 4 A schematic diagram of the structure of a process for determining a corresponding space coefficient provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] like Figure 1 and Figure 2 As shown, a load transfer analysis and processing system based on knowledge graph includes the following embodiments:

[0041] Embodiment 1: The system comprises:

[0042] A topological power supply network subsystem, which establishes a topological network with the main transformer as the topological starting point, and creates a topological node in each distribution transformer in each power supply line in the topological network;

[0043] And quantify the correlation between the dynamic power consumption of the topology starting point and multiple topology nodes;

[0044] Load analysis and processing subsystem, which includes:

[0045] The data acquisition module extracts the corresponding dynamic consumption related features based on the correlation of the dynamic power consumption of the topological nodes in the topological network;

[0046] The data analysis module inputs the input feature vector into the well-trained power grid operation load demonstration model, and outputs the corresponding peak prediction value of each topological node to determine the peak time of the topological node and the total amount of electric energy consumption within the peak time range.

[0047] Specifically, the main transformer in the embodiment is the main transformer, and the distribution transformer is the distribution transformer under the main transformer. Because there are multiple specific power equipment connected to the transformer, by monitoring the transformer, the operating load voltage of the corresponding transformer and the peak and valley time of the voltage can be obtained, thereby providing the possibility for the implementation of this system.

[0048] Optimize the allocation of power resources, improve the efficiency of power grid operation, reduce the risk of power failures, etc. For example, during peak power demand periods, the power supply strategy can be adjusted in advance to ensure the stable operation of the power grid; during low power demand periods, the power output can be reasonably reduced to reduce energy waste.

[0049] Secondly, the input feature vector is input into a well-trained power grid operation load demonstration model, and the peak prediction value of each topological node corresponding to the output includes the corresponding peak prediction values ​​of the co-located topological nodes.

[0050] In the above technology, a topological network is created with the main transformer as the topological starting point, and each distribution transformer under the main transformer, and each distribution transformer under the distribution transformer as the topological node, and the first distribution transformer under the main transformer is used as the line reference to determine each power supply line in the network. Then, multiple topological networks are generated based on the same-position main transformer, and each topological network performs load pressure calculation separately to feed back to the terminal separately, thereby forming a blockchain-like data processing method to reduce operating pressure. However, this application divides each topological network into several power supply lines according to the above-mentioned rules in the form of the topological network, and then calculates each power supply line separately, thereby showing the purpose of reducing operating pressure.

[0051] Embodiment 2

[0052] Combination Figure 3 As shown, based on the input feature vector in the data analysis module in the first embodiment above, a training sample is generated according to the dynamic consumption related features, and the training sample is sorted by cluster analysis to determine the input feature vector;

[0053] The finishing includes:

[0054] S11, splitting the training samples into a first training sample set and a second training sample set;

[0055] S12, respectively performing dimensionality reduction on the first training sample set and the second training sample set through PCA and then clustering the data to generate a first transformation matrix and a second transformation matrix corresponding to the above;

[0056] S13. Determine an input feature vector according to the first training sample set, the second training sample set, the first transformation matrix, and the second transformation matrix.

[0057] Specifically, cluster analysis can identify the features that are most relevant to power consumption, thereby avoiding the introduction of redundant or irrelevant features and improving the accuracy of the prediction model. Secondly, using PCA (principal component analysis) to reduce the dimension of the training samples can remove noise and redundant information in the data while retaining the most critical information, which helps to simplify the model and improve prediction efficiency.

[0058] Splitting the training samples into the first training sample set and the second training sample set can ensure that the model is exposed to different types of samples during the training process, thereby enhancing the generalization ability of the model and enabling it to better adapt to various practical scenarios. By generating the first transformation matrix and the second transformation matrix, the new input data can be transformed in the same way, ensuring that the model can maintain consistency during prediction and improving the reliability of the prediction results.

[0059] Based on the optimized input feature vector, the prediction model can more accurately predict the peak time and total power consumption of each topological node, thereby providing strong data support for power resource allocation.

[0060] Embodiment 3

[0061] Combination Figure 4 As shown, the process of determining the correlation of the dynamic power consumption of the topological nodes in the first embodiment is to determine the correlation of the dynamic power consumption of the topological nodes based on the predicted topological nodes, and predict the dynamic power consumption data of the adjacent upstream topological nodes and the downstream topological nodes;

[0062] Based on the topological network, a random predicted topological node and the corresponding upstream topological node and downstream topological node, as well as the co-located topological nodes of the same level as the previous topological node and the number of co-located topological nodes for each power supply line in the topological network are determined.

[0063] Furthermore, the correlation of the dynamic consumption of electric energy includes a time coefficient and a space coefficient, and the correlation of the dynamic consumption of electric energy of the quantified topological starting point and the upstream position and the downstream position of multiple topological nodes includes:

[0064] Determine the corresponding time coefficient according to the predicted peak time period of the topological node, the power consumption quota in the peak time period and the power consumption quota in the non-peak time period;

[0065] The spatial coefficient is determined based on the determined predicted topological nodes, the co-located topological nodes corresponding to the upstream position, and the co-located topological nodes corresponding to the downstream position.

[0066] Secondly, according to the determined power consumption quota of the predicted topological node in the peak time period and the power consumption quota in the non-peak time period, the corresponding time coefficient is determined, including:

[0067] The historical power consumption quota of the corresponding predicted topological node in the peak time period is retrieved to generate a value range of the power consumption quota in the corresponding peak time period of the predicted topological node.

[0068] Furthermore, based on the determined predicted topological node, the co-located topological node corresponding to the upstream position, and the co-located topological node corresponding to the downstream position, determining the corresponding spatial coefficient includes:

[0069] S21, determining a corresponding first spatial set according to a set of power consumption quota value ranges of a traffic flow of a predicted topological node and a co-located topological node corresponding to an upstream position in a corresponding peak time period;

[0070] S22, determining a corresponding second space set according to a set of power consumption quota value ranges of the traffic flow of the predicted topological node and the co-located topological nodes corresponding to the downstream position in the corresponding peak time period;

[0071] S23: Determine the maximum power consumption quota of each co-located topological node and the predicted topological node in the dynamic space according to the first space set and the second space set.

[0072] Specifically, a random predicted topological node is selected to determine the upstream and downstream of the predicted topological node and the co-located topological nodes of several power supply lines of the topological network, thereby generating a time coefficient and a space coefficient, and then the peak time of each co-located topological node is obtained based on the time coefficient, so as to provide time support for subsequent load transfer, while the space coefficient provides the range of power consumption quota of the co-located topological node during peak time and non-peak time, and then based on the range of power consumption quota, the amount of power that can be transferred is determined.

[0073] Secondly, through the analysis of historical data, the range of electricity consumption quota is determined to obtain the maximum electricity consumption quota, so as to cooperate with the existing power generation prediction system such as photovoltaic power generation, based on the maximum electricity demand in each power supply line, to form a reasonable electricity distribution, thereby reducing the probability of load pressure on the power supply line operation.

[0074] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0078] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0079] The embodiments of the present application also provide a specific implementation of an electronic device capable of implementing all steps of the method in the above embodiments, and the electronic device specifically includes the following contents:

[0080] Processor, memory, communications interface and bus;

[0081] Wherein, the processor, memory, and communication interface communicate with each other via the bus;

[0082] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiment are implemented.

[0083] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, all the steps of the method in the above embodiments are implemented.

[0084] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Although the embodiment of this specification provides the method operation steps described in the embodiment or flow chart, more or less operation steps can be included based on conventional or non-creative means. The order of steps listed in the embodiment is only one way of executing the order of many steps, and does not represent the only execution order. When the device or terminal product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiment or the accompanying drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the embodiments of this specification, the functions of each module can be implemented in the same one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The present invention is described with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the process and / or box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0085] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, the embodiments of this specification may be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment. In the description of this specification, the description of the reference term "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the embodiment of this specification.

[0086] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradicting each other. The above is only an embodiment of the embodiment of this specification and is not intended to limit the embodiment of this specification. For those skilled in the art, the embodiment of this specification may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiment of this specification shall be included in the scope of the claims of the embodiment of this specification.

Claims

1. A load transfer analysis and processing system based on knowledge graph, characterized in that: include: A topological power supply network subsystem, which establishes a topological network with the main transformer as the topological starting point, and creates a topological node in each distribution transformer in each power supply line in the topological network; and quantifying the correlation between the dynamic power consumption of the topology starting point and a plurality of the topology nodes; Load analysis and processing subsystem, which includes: A data acquisition module, based on the correlation of the dynamic consumption of electric energy of the topological nodes in the topological network, extracts corresponding dynamic consumption related features; The data analysis module inputs the input feature vector into a well-trained power grid operation load demonstration model, and outputs the corresponding peak prediction value of each topological node to determine the peak time of the topological node and the total amount of electric energy consumption within the peak time range.

2. According to the knowledge graph-based load transfer analysis and processing system of claim 1, it is characterized in that: The input feature vector generates training samples according to the dynamic consumption related features, and the training samples are sorted by cluster analysis to determine the input feature vector; The arrangement includes: S11, splitting the training samples into a first training sample set and a second training sample set; S12, performing dimensionality reduction on the first training sample set and the second training sample set by PCA respectively, and then clustering the data to generate a first transformation matrix and a second transformation matrix corresponding to the above; S13. Determine the input feature vector according to the first training sample set, the second training sample set, the first transformation matrix, and the second transformation matrix.

3. According to the knowledge graph-based load transfer analysis and processing system of claim 1, it is characterized in that: Determining the correlation of the dynamic power consumption of the topological node is based on predicting the dynamic power consumption data of the topological node, the adjacent upstream topological node and the downstream topological node; Based on the topological network, a random predicted topological node and the corresponding upstream topological node and downstream topological node, as well as the co-located topological nodes of the same level as the previous topological node for each power supply line in the topological network and the number of the co-located topological nodes are determined.

4. According to the knowledge graph-based load transfer analysis and processing system of claim 3, it is characterized in that: The dynamic power consumption correlation includes a time coefficient and a space coefficient, and the quantified dynamic power consumption correlation of the topology starting point and the upstream position and the downstream position of the plurality of topology nodes includes: Determine the corresponding time coefficient according to the peak time period of the predicted topological node, the power consumption quota in the peak time period and the power consumption quota in the non-peak time period; The spatial coefficient is determined based on the determined predicted topological node, the co-located topological node corresponding to the upstream position, and the co-located topological node corresponding to the downstream position.

5. According to the knowledge graph-based load transfer analysis and processing system of claim 4, it is characterized in that: Determining the corresponding time coefficient according to the determined power consumption quota of the predicted topological node in the peak time period and the power consumption quota in the non-peak time period includes: The historical power consumption quota corresponding to the peak time period of the predicted topological node is retrieved, and a power consumption quota value range for the corresponding peak time period of the predicted topological node is generated.

6. A load transfer analysis and processing system based on knowledge graph according to claim 4, characterized in that: Determining the corresponding spatial coefficient based on the determined predicted topological node, the co-located topological node corresponding to the upstream position, and the co-located topological node corresponding to the downstream position includes: S21, determining a corresponding first spatial set according to a set of electric energy consumption quota value ranges in a corresponding peak time period of the traffic flow of the predicted topological node and the co-located topological node corresponding to the upstream position; S22, determining a corresponding second spatial set according to a set of electric energy consumption quota value ranges of the traffic flow of the predicted topological node and the co-located topological nodes corresponding to the downstream position in the corresponding peak time period; S23: Determine the maximum power consumption quota of each co-located topological node and the predicted topological node in the dynamic space according to the first space set and the second space set.

7. The load transfer analysis and processing system based on knowledge graph according to claim 1 is characterized in that: The input feature vector is input into a well-trained power grid operation load demonstration model, and the corresponding peak prediction value of each topological node is output, including the corresponding peak prediction values ​​of the co-located topological nodes.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the steps of the load transfer analysis and processing system based on the knowledge graph as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the load transfer analysis and processing system based on the knowledge graph as described in any one of claims 1 to 7 are implemented.

Images