Power distribution network adaptive monitoring method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of power distribution network monitoring, and discloses a power distribution network adaptive monitoring method and system based on multi-source data fusion, and the method comprises the steps: determining a plurality of first target power suppliers and a plurality of first target power demanders according to the first historical power data of a power distribution network; performing electric power significance analysis on each first target electric power supplier and each first target electric power demander to obtain a first electric power characteristic information set; determining a plurality of pieces of first power combination information according to the first power characteristic information set; and determining a first power distribution network monitoring strategy based on the plurality of pieces of first power combination information. According to the technical scheme of the invention, the power combination which may cause the risk of the power distribution network is determined from the two perspectives of absolute saliency and relative saliency, so that the determined power distribution network monitoring strategy is higher in pertinence.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network monitoring, and particularly to a distribution network adaptive monitoring method and system based on multi-source data fusion. Background Art

[0002] With the transformation of the energy structure and the growth of power demand, the distribution network is undergoing unprecedented changes. Currently, the supply side presents a situation where traditional energy sources (such as coal and natural gas power generation) coexist with various new energy types (such as renewable energy sources like solar, wind, and hydro energy). This diversified energy supply mode not only increases the diversity and reliability of energy supply but also brings complex management challenges. At the same time, the demand characteristics on the demand side are also becoming increasingly diverse. For example, compared with ordinary residential houses, electric vehicle fast charging stations have significant differences in power consumption time periods and power consumption characteristics. These changes require the distribution network to be able to flexibly adapt to different types of supply and demand patterns and effectively allocate resources and manage loads.

[0003] However, when analyzing the characteristics of the power supply side and the demand side, existing technologies often only start from a single dimension, that is, mainly analyze a single supply side or demand side based on electrical characteristic parameters (such as voltage, current, power factor, etc.). This method is difficult to comprehensively reflect the dynamic changes in the operating state of the entire distribution network and cannot meet the requirements of real-time monitoring and adaptive adjustment. Therefore, when facing a complex and changeable supply and demand environment, traditional monitoring methods are overwhelmed and cannot achieve the overall optimal control of the distribution network.

[0004] To solve the above problems, "a distribution network adaptive monitoring method and system based on multi-source data fusion" has emerged, which integrates data from different sources to achieve accurate perception and intelligent control of the overall situation of the distribution network. Summary of the Invention

[0005] In view of the existing problems above, the present invention is proposed.

[0006] Therefore, the present invention provides a distribution network adaptive monitoring method and system based on multi-source data fusion to solve the problem that the existing technology cannot perform adaptive monitoring of the distribution network from the perspective of the whole distribution network.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In the first aspect, the present invention provides a distribution network adaptive monitoring method based on multi-source data fusion, including:

[0009] Determine a plurality of first target power suppliers and a plurality of first target power demanders according to the first historical power data of the distribution network;

[0010] Perform power significance analysis on each of the first target power suppliers and each of the first target power consumers to obtain a set of first power characteristic information; the power significance analysis is to analyze the power data of the first target power suppliers and the first target power consumers, extract first power supply characteristic information and first power demand characteristic information related to the stability of the distribution network, and obtain the set of first power characteristic information based on the first power supply characteristic information and the first power demand characteristic information;

[0011] Determine a plurality of first power combination information according to the set of first power characteristic information; the first power combination information includes power conflict information between different first target power suppliers and different first target power consumers;

[0012] Determine a first distribution network monitoring strategy based on a plurality of the first power combination information.

[0013] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: the determination of a plurality of first target power suppliers and a plurality of first target power consumers includes:

[0014] Determine a plurality of first power suppliers and a plurality of first power consumers according to the first historical power data of the distribution network;

[0015] Input the power data of each of the first power suppliers into a first power consumption significance model one by one to determine the first target power suppliers;

[0016] Input the power data of each of the first power consumers into a second power consumption significance model one by one to determine the first target power consumers.

[0017] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: the obtaining of the set of first power characteristic information includes:

[0018] Determine the first power threshold information of the distribution network;

[0019] Determine a plurality of the first power supply characteristic information and a plurality of the first power demand characteristic information according to the first target power information and the first power threshold information;

[0020] Determine the set of first power characteristic information according to the first time series information of a plurality of the first power supply characteristic information and a plurality of the first power demand characteristic information.

[0021] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: the determination of a plurality of first power combination information includes:

[0022] Determine a number of first timing information groups from the first power characteristic information set;

[0023] For each of the first timing information groups, determine a plurality of second target power suppliers and a plurality of second target power consumers;

[0024] According to the first power characteristic information set, determine a plurality of third target power suppliers and a plurality of third target power consumers from the plurality of second target power suppliers and the plurality of second target power consumers;

[0025] Determine the first power combination information according to the plurality of third target power suppliers and the plurality of third target power consumers;

[0026] The first power combination information includes power conflict information between different first target power suppliers and different first target power consumers.

[0027] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: each of the first timing information groups includes at least two power entities, and the power entities include the first target power suppliers and the first target power consumers.

[0028] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: in each of the first timing information groups, the coincidence degree of the first timing information of every two power entities is greater than a first preset value.

[0029] As a preferred solution of the distribution network adaptive monitoring method based on multi-source data fusion according to the present invention, wherein: the first power significance model and the second power significance model are obtained by training based on a deep neural network model. During the training process, a first data vector is determined as the input of the model, and the probability of occurrence of a distribution network risk is used as the output.

[0030] In a second aspect, the present invention provides a distribution network adaptive monitoring system based on multi-source data fusion, including:

[0031] A target determination module, configured to determine a plurality of first target power suppliers and a plurality of first target power consumers according to the first historical power data of the distribution network;

[0032] A characteristic set acquisition module, configured to perform power significance analysis on each of the first target power suppliers and each of the first target power consumers to obtain a first power characteristic information set;

[0033] A combined information acquisition module, configured to determine a plurality of first power combination information according to the first power characteristic information set;

[0034] A monitoring strategy acquisition module, configured to determine a first distribution network monitoring strategy based on the plurality of first power combination information.

[0035] In a third aspect, the present invention provides an electronic device, including:

[0036] A memory and a processor;

[0037] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distribution network adaptive monitoring method based on multi-source data fusion are implemented.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the distribution network adaptive monitoring method based on multi-source data fusion are implemented.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a distribution network adaptive monitoring method and system based on multi-source data fusion. According to the historical power data of the first distribution network, a plurality of first target power suppliers and a plurality of first target power demanders are determined according to the standard of significant power indicators. Next, a first power characteristic information set is determined according to the first power threshold of the first distribution network, and the power consumption time sequence information of different power entities is included in the power characteristic information set. Next, the power combinations that will cause distribution network risks are determined according to the first power characteristic information set, and finally, corresponding first distribution network monitoring strategies are determined according to the characteristics of each power combination. The technical solution of the present invention determines the power combinations that may cause distribution network risks from two perspectives of absolute significance and relative significance, so that the determined distribution network monitoring strategy is more targeted. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is a schematic diagram of the overall process logic of the distribution network adaptive monitoring method based on multi-source data fusion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0043] Example 1. Refer to Figure 1 This is an embodiment of the present invention, which provides a method for adaptive monitoring of a distribution network based on multi-source data fusion to solve the problem that the prior art cannot perform adaptive monitoring of a distribution network from the overall perspective of the distribution network. As Figure 1 shown, it specifically includes the following steps:

[0044] S100: Determine a plurality of first target power suppliers and a plurality of first target power demanders according to the first historical power data of the distribution network;

[0045] S200: Perform power significance analysis on each first target power supplier and each first target power demander to obtain a first set of power characteristic information;

[0046] S300: Determine a plurality of first power combination information according to the first set of power characteristic information;

[0047] S400: Determine a first distribution network monitoring strategy based on the plurality of first power combination information.

[0048] It should be noted that the present invention provides a method and system for adaptive monitoring of a distribution network based on multi-source data fusion. According to the historical power data of the first distribution network, a plurality of first target power suppliers and a plurality of first target power demanders are determined based on the standard of significant power indicators. Next, a first set of power characteristic information is determined according to the first power threshold of the first distribution network, and the power consumption time sequence information of different power entities is included in the set of power characteristic information. Next, the power combinations that may cause risks to the distribution network are determined according to the first set of power characteristic information. Finally, the corresponding first distribution network monitoring strategy is determined for the characteristics of each power combination. The technical solution of the present invention determines the power combinations that may cause risks to the distribution network from two perspectives of absolute significance and relative significance, so that the determined distribution network monitoring strategy is more targeted.

[0049] Example 2. Based on the previous embodiment, this embodiment provides a specific implementation manner of a method for adaptive monitoring of a distribution network based on multi-source data fusion, which specifically includes:

[0050] S100: Determine a plurality of first target power suppliers and a plurality of first target power demanders according to the first historical power data of the distribution network;

[0051] In an optional embodiment, the first historical power data of the distribution network may be power supply data and power consumption data; the first historical power data of the distribution network may be network operation data, such as electrical parameters in the distribution network, such as voltage level, current intensity, power factor, etc.; the first historical power data of the distribution network may also be transaction and market data, such as transaction records between each supplier and demander, including power purchase contracts, real-time transaction prices, etc.

[0052] In the embodiment of the present application, the first historical power data of the distribution network includes the power supply and consumption data of all power suppliers and demanders having a docking relationship with the distribution network; among them, multiple first target power suppliers and multiple first target power demanders are all power entities with certain significant power consumption characteristics.

[0053] The above step S100 includes the following sub-steps A1 to A3:

[0054] In A1: According to the first historical power data of the distribution network, determine multiple first power suppliers and multiple first power demanders;

[0055] Specifically, in the first historical power data, it includes the power supply and demand data of the distribution network within a preset time interval, and each power supply and consumption data corresponds to a first power supplier or a first power demander.

[0056] For example, within a week, the total power supply of the distribution network is A, which is provided by power suppliers B, C, and D respectively, then B, C, and D are all first power suppliers of the distribution network.

[0057] In A2: Input the power data of each first power supplier into the first power consumption significance model one by one to determine the first target power suppliers;

[0058] In the subsequent steps, it is necessary to select power information with a greater impact on the stability of the distribution network from two perspectives of absolute significance and relative significance. Among them, absolute significance refers to the absolute power data that the first power supplier will have a greater impact on the distribution network, such as parameters such as power load and power consumption; relative significance refers to the power data that the first power supplier will have a power supply conflict with another first power supplier. For example, if different types of new energy power suppliers generate a large amount of power supply at the same time, it will have a greater impact on the stability of the distribution network.

[0059] In this step, the first target power suppliers are mainly determined according to the absolute significance of each first power supplier.

[0060] In an optional embodiment, the first electricity significance model may be a model based on statistical analysis, that is, by analyzing indicators such as the historical power generation, power supply stability (such as volatility), and response time of each power supplier, statistical methods are used to determine which suppliers' performance has a significant impact on the overall performance of the distribution network; the first electricity significance model may be a multi-criteria decision analysis model, that is, by combining multiple evaluation criteria, methods such as the analytic hierarchy process and data envelopment analysis are used to comprehensively evaluate the relative importance of each supplier; the first electricity significance model may also be a deep learning model, that is, by capturing the behavior patterns of suppliers changing over time and evaluating their importance accordingly;

[0061] In the embodiment of the present application, the first electricity significance model is obtained by training based on a CNN model. The power supply and demand data of the historical distribution network are selected as sample data. Specifically, the relevant power data of the power suppliers that have a greater impact on the distribution network are selected as sample data. The data types of the sample data include but are not limited to parameters such as the carrying capacity of the distribution network, power load, and power consumption. During the training process, a first data vector is determined based on the sample data as the input of the model, and the probability of the occurrence of the distribution network risk is used as the output.

[0062] Among them, after the risk probability of the distribution network is determined, the first power supplier with a probability value greater than the preset value can be determined as the first target power supplier.

[0063] Through step A2, the power suppliers that will generate a relatively high distribution network risk can be determined from multiple first power suppliers as the first target power suppliers. In the determination process, various power data types of the first power suppliers are comprehensively considered, so that a power data combination that will generate a relatively high distribution network risk can be determined based on historical big data.

[0064] It should be noted that what is obtained by training the first electricity significance model is the relative relationship between the carrying capacity of the distribution network and various types of power parameters. Therefore, after the power data of the first power supplier are input into the first electricity significance model, the distribution network risk probability can be determined according to the data similarity between the power data of the first power supplier and the first electricity significance model.

[0065] In A3: The power data of each first power demander are input into the second electricity significance model one by one to determine the first target power demander.

[0066] For the electricity demand side, with the rise of emerging electricity-consuming entities such as fast charging stations for vehicles in recent years, when different types of electricity-consuming entities simultaneously generate large electricity demands, it will also have a significant impact on the stability of the distribution network. Therefore, in this step, it is also necessary to identify, based on historical big data, the first target electricity demand sides with a high risk probability among all the first electricity demand sides connected to the first distribution network.

[0067] In an alternative embodiment, the second electricity significance model can be a model based on statistical analysis, that is, by analyzing indicators such as the historical power generation, power supply stability (such as volatility), and response time of each power supply side, statistical methods are used to determine which supply sides have a significant impact on the overall performance of the distribution network; the second electricity significance model can be a multi-criteria decision analysis model, that is, by combining multiple evaluation criteria, methods such as the analytic hierarchy process and data envelopment analysis are used to comprehensively evaluate the relative importance of each supply side; the second electricity significance model can also be a deep learning model, that is, by capturing the behavior patterns of the supply side over time and evaluating its importance accordingly;

[0068] In the embodiment of the present application, the second electricity significance model is similar to the first electricity significance model and is also obtained by training based on the CNN model. The difference is only that several electricity parameters related to the electricity demand side are used as the training samples of the model, and the types of electricity parameters included include, but are not limited to, information such as the carrying capacity of the distribution network, peak load, load rate, power factor, and peak electricity consumption period. During the training process, the above parameters in the sample data are used as the input, and the probability of the occurrence of distribution network risks is used as the output.

[0069] Through the above big data model, power data combinations that will generate significant distribution network risks can be mined. It should be noted that through the combination of the above input parameters, not only the absolute power data in the historical data that will cause distribution network risks are considered, but also by considering the peak electricity consumption period information, whether it will form an electricity consumption conflict with electricity-consuming entities such as residential electricity, thus leading to the situation of distribution network risks can be included in the evaluation scope.

[0070] It should be noted that the above step S100 can accurately identify the supply and demand sides in the power grid, provide clear objects and data support for subsequent power significance analysis and strategy formulation, and lay a foundation for optimizing the monitoring and management of the distribution network.

[0071] S200: Conduct power significance analysis on each first target power supply side and each first target power demand side to obtain a set of first power characteristic information;

[0072] Among them, power significance analysis refers to analyzing the power data of the first target power supplier and the power demander, extracting the first power supply characteristic information and the first power demand characteristic information related to the stability of the distribution network, and obtaining the first power characteristic information set based on the first power supply characteristic information and the first power demand characteristic information.

[0073] The above step S200 includes the following sub-steps B1 to B3:

[0074] In B1: Determine the first power threshold information of the distribution network;

[0075] In an optional embodiment, the first power threshold information includes but is not limited to the maximum load rate, the maximum voltage deviation, the maximum short-circuit capacity, the maximum harmonic content, the maximum thermal stability, and the maximum dynamic stability;

[0076] In the embodiment of the present application, the determination of the first power threshold information of the distribution network includes:

[0077] Determine indicators such as the average load rate, the average voltage deviation, the average short-circuit capacity, the average harmonic content, the average thermal stability, and the average dynamic stability of the distribution network;

[0078] Use the above indicators to match the first similar distribution network whose similarity to the distribution network exceeds the preset threshold. During the matching process, the indicators of the first distribution network can be combined into a vector, and the first similar distribution network can be obtained by calculating the Euclidean distance between the vectors;

[0079] Use various power threshold information of the first similar distribution network as the first power threshold information of the first distribution network. The first power threshold information includes but is not limited to: the maximum load rate, the maximum voltage deviation, the maximum short-circuit capacity, the maximum harmonic content, the maximum thermal stability, and the maximum dynamic stability.

[0080] In B2: Determine multiple first power supply characteristic information and multiple first power demand characteristic information according to the first target power information and the first power threshold information;

[0081] Among them, the first target power information refers to the power information of each first target power supplier or each first target power demander. Such as the load rate, the voltage deviation, the short-circuit capacity, etc.

[0082] For each first target power supplier and each first target power demander, calculate the first proportional relationship between their various power information and the first power threshold information, and determine the power information with the first proportional relationship greater than the preset threshold as the first power supply characteristic information or the first power demand characteristic information.

[0083] In B3: Determine a first set of power characteristic information based on the first timing information of multiple first power supply characteristic information and multiple first power demand characteristic information.

[0084] In step B2, the characteristic information corresponding to the distribution network with a certain distribution network risk has been determined. However, between different power supply parties and power demand parties with characteristic information, it is also possible to trigger a higher distribution network risk when there is a conflict in the power consumption time interval.

[0085] Therefore, in this step, based on the determined multiple first power supply characteristic information and multiple first power demand characteristic information, determine the first timing information according to the centralized power consumption time interval of the power entities with the first power supply characteristic information or the first power demand characteristic information, so as to determine the first set of power characteristic information according to the multiple first power supply characteristic information, multiple first power demand characteristic information and the first timing information.

[0086] For example, if the first fast charging station for cars that has a docking relationship with the first distribution network has the first power demand characteristic information, then determine the centralized power consumption time interval of the first fast charging station for cars as the first timing information and record it in the first set of power characteristic information.

[0087] It should be noted that the above step S200 can deeply explore the unique power usage patterns and characteristics of each supply and demand party, provide detailed data support for subsequent construction of a reasonable power combination, and help formulate a more accurate and effective distribution network monitoring strategy.

[0088] S300: Determine multiple first power combination information according to the first set of power characteristic information;

[0089] Among them, the first power combination information includes the first power conflict information between different first target power supply parties and different first target power demand parties;

[0090] The above step S300 includes the following sub-steps C1 to C4:

[0091] In C1: Determine several first timing information groups from the first set of power characteristic information;

[0092] Specifically, the first power combination information includes the first timing information corresponding to multiple first target power supply parties and multiple first target power demand parties, that is, the centralized power supply or power consumption period.

[0093] In this step, determine several first timing information groups based on the multiple first timing information. Among them, when determining the first timing information group, the overlapping time interval duration of every two first timing information can be used as the determination criterion.

[0094] For example, in the first set of power characteristic information, there are two pieces of first timing information, namely 7:00 - 9:00 and 8:00 - 10:00. It can be determined that their overlapping time interval is 1 hour. Assuming that the preset overlapping time interval threshold is 1 hour, then the overlapping time interval is greater than or equal to the overlapping time interval threshold. Therefore, the above two pieces of first timing information form a first timing information group.

[0095] In C2: For each first timing information group, determine multiple second target power suppliers and multiple second target power demanders;

[0096] Specifically, according to the two pieces of first timing information included in the first timing information group, determine multiple second target power suppliers and multiple second target power demanders with the same timing information from multiple first target power suppliers and multiple first target power demanders.

[0097] In C3: According to the first set of power characteristic information, determine multiple third target power suppliers and multiple third target power demanders from multiple second target power suppliers and multiple second target power demanders;

[0098] Specifically, perform an overlap analysis of each second target power supplier and each second target power demander with the first set of power characteristic information, and determine the second target power suppliers and second target power demanders with an overlap greater than the threshold as the third target power suppliers and third target power demanders.

[0099] In C4: Determine the first power combination information according to multiple third target power suppliers and multiple third target power demanders;

[0100] Specifically, use multiple third target power suppliers and multiple third target power demanders as the first power combination information. The suppliers and demanders in the first power combination information are paired two by two to form a power combination that may cause risks to the distribution network.

[0101] It should be noted that each first timing information group includes at least two power entities. The power entities include first target power suppliers and first target power demanders; in each first timing information group, the overlap of the first timing information of every two power entities is greater than the first preset value.

[0102] It should be noted that the above step S300 can effectively integrate the characteristics of different power suppliers and demanders, form an optimized power combination plan, not only improve the efficiency of resource allocation, but also provide a solid foundation for formulating a targeted and highly adaptable distribution network monitoring strategy.

[0103] S400: Determine the first distribution network monitoring strategy based on multiple first power combination information;

[0104] Specifically, multiple groups of first power combination information are determined according to the first power characteristic information set. Among the first power combination information, any two power entities may jointly trigger distribution network risks. However, the distribution network risks triggered by the joint actions of power supply - power supply, power supply - power consumption, and power consumption - power consumption entities are different.

[0105] Therefore, in this step, the corresponding first distribution network monitoring strategy can be determined according to the types of two power entities in the first power combination information. For example, for the power supply - power supply combination, the corresponding type of power index can be selected for monitoring.

[0106] It should be noted that the above step S400 can formulate specific and effective monitoring measures according to different power supply and demand characteristics, improve the stability and efficiency of the distribution network operation, and at the same time ensure the optimal allocation of resources and the balance between supply and demand.

[0107] Embodiment 3 provides a distribution network adaptive monitoring system based on multi - source data fusion, including a target determination module, a characteristic set acquisition module, a combination information acquisition module, and a monitoring strategy acquisition module;

[0108] Specifically, the target determination module is used to determine multiple first target power suppliers and multiple first target power consumers according to the first historical power data of the distribution network;

[0109] Specifically, the characteristic set acquisition module is used to perform power significance analysis on each first target power supplier and each first target power consumer to obtain the first power characteristic information set;

[0110] Specifically, the combination information acquisition module is used to determine multiple first power combination information according to the first power characteristic information set;

[0111] Specifically, the monitoring strategy acquisition module is used to determine the first distribution network monitoring strategy based on multiple first power combination information.

[0112] It should be noted that the technical solution of the distribution network adaptive monitoring system based on multi - source data fusion belongs to the same concept as the technical solution of the above - mentioned distribution network adaptive monitoring method based on multi - source data fusion. For the details not described in the technical solution of the distribution network adaptive monitoring system based on multi - source data fusion in this embodiment, reference can be made to the description of the technical solution of the distribution network adaptive monitoring method based on multi - source data fusion.

[0113] The above-mentioned unit modules can be embedded in the processor of a computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0114] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for adaptive monitoring of a distribution network based on multi-source data fusion. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0115] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by the processor, it implements the method proposed in the above embodiment.

[0116] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. For the technical details not described in detail in this embodiment, reference can be made to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0117] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk, or an optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method of the embodiments of the present invention.

[0118] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0119] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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. The solutions in the embodiments of the present application can be implemented in various computer languages.

[0120] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in one Figure 1 process or multiple processes and / or blocks Figure 1 block or multiple blocks.

[0121] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the specified functions in one Figure 1 process or multiple processes and / or blocks Figure 1 block or multiple blocks.

[0122] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in one Figure 1 process or multiple processes and / or blocks Figure 1 block or multiple blocks.

[0123] Although the preferred embodiments of the present application have been described, additional changes and modifications can be made to these embodiments by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An adaptive monitoring method for a distribution network based on multi-source data fusion, characterized in that Including: Determine a plurality of first target power suppliers and a plurality of first target power demanders according to the first historical power data of the distribution network; Conduct power significance analysis on each of the first target power suppliers and each of the first target power demanders to obtain a first set of power characteristic information; the power significance analysis is to extract first power supply characteristic information and first power demand characteristic information related to the stability of the distribution network after analyzing the power data of the first target power suppliers and the first target power demanders, and obtain the first set of power characteristic information based on the first power supply characteristic information and the first power demand characteristic information; Determine a plurality of first power combination information according to the first set of power characteristic information; the first power combination information includes power conflict information between different first target power suppliers and different first target power demanders; Determine a first distribution network monitoring strategy based on a plurality of the first power combination information.

2. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 1, wherein, The determining of the plurality of first target power suppliers and the plurality of first target power demanders includes: Determine a plurality of first power suppliers and a plurality of first power demanders according to the first historical power data of the distribution network; Input the power data of each of the first power suppliers into the first power consumption significance model one by one to determine the first target power suppliers; Input the power data of each of the first power demanders into the second power consumption significance model one by one to determine the first target power demanders.

3. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 2, wherein, The obtaining of the first set of power characteristic information includes: Determine the first power threshold information of the distribution network; Determine a plurality of the first power supply characteristic information and a plurality of the first power demand characteristic information according to the first target power information and the first power threshold information; Determine the first set of power characteristic information according to the first time sequence information of the plurality of the first power supply characteristic information and the plurality of the first power demand characteristic information.

4. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 3, wherein, The determining of the plurality of first power combination information includes: Determine several first time sequence information groups from the first set of power characteristic information; For each of the first time sequence information groups, determine a plurality of second target power suppliers and a plurality of second target power demanders; According to the first set of power characteristic information, determine a plurality of third target power suppliers and a plurality of third target power demanders from the plurality of second target power suppliers and the plurality of second target power demanders; Determine the first power combination information according to the plurality of third target power suppliers and the plurality of third target power demanders; The first power combination information includes power conflict information between different first target power suppliers and different first target power demanders.

5. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 4, wherein Each of the first time sequence information groups includes at least two power entities, and the power entities include the first target power suppliers and the first target power demanders.

6. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 5, wherein In each of the first time sequence information groups, the coincidence degree of the first time sequence information of every two of the power entities is greater than a first preset value.

7. The adaptive monitoring method for a distribution network based on multi-source data fusion according to claim 2, wherein The first power consumption significance model and the second power consumption significance model are obtained by training based on a deep neural network model. During the training process, a first data vector is determined from sample data as the input of the model, and the probability of a distribution network risk occurring is used as the output.

8. A distribution network adaptive monitoring system based on multi-source data fusion, which applies the method according to any one of claims 1 to 7, characterized in that, It includes: A target determination module, configured to determine a plurality of first target power suppliers and a plurality of first target power consumers according to the first historical power data of the distribution network; A characteristic set acquisition module, configured to perform power significance analysis on each of the first target power suppliers and each of the first target power consumers to obtain a first power characteristic information set; A combination information acquisition module, configured to determine a plurality of first power combination information according to the first power characteristic information set; A monitoring strategy acquisition module, configured to determine a first distribution network monitoring strategy based on the plurality of first power combination information.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer-executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images