Distribution network load flexible regulation and control method, device, control equipment and system

Abstract

The invention relates to a distribution network load flexible regulation and control method, device, control equipment and system. The method comprises the steps of obtaining first power data corresponding to a target node in a distribution network, determining a first initial regulation and control strategy according to the first power data, sending the first initial regulation and control strategy to scheduling equipment, receiving a target regulation and control instruction sent by the scheduling equipment, and regulating and controlling the load of the target node according to the target regulation and control instruction. And regulating and controlling the load of the target node according to third power data corresponding to the target node obtained after regulating and controlling the load of the target node. According to the embodiment of the invention, under the condition that the first initial regulation and control strategy is obtained, the first initial regulation and control strategy is optimized by using the second initial regulation and control strategy and the second power data of each node in the distribution network to obtain the first target regulation and control strategy, so that the target regulation and control instruction for regulating and controlling the load of the target node is generated; the organic combination of distributed autonomy and centralized coordination is realized, and the load regulation and control efficiency and flexibility of the target node are improved.

Description

Technical Field

[0001] The present application relates to the technical field of smart grids, and particularly to a method, device, control equipment, and system for flexible regulation of distribution network load. Background Art

[0002] Flexible regulation of distribution network load refers to taking flexible and diverse regulation strategies according to the actual demands of the power grid system and load characteristics to dynamically adjust and optimize the load in the distribution network. This regulation method can achieve refined management of the load and improve the operation efficiency and stability of the power system. Therefore, how to improve the flexibility of flexible regulation of distribution network load has become a technical problem urgently to be solved in this field. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, control equipment, and system for flexible regulation of distribution network load that can improve the flexibility of flexible regulation of distribution network load for the above technical problems.

[0004] In a first aspect, the present application provides a method for flexible regulation of distribution network load, including:

[0005] Obtain first power data corresponding to a target node in the distribution network, determine a first initial regulation strategy according to the first power data, and send the first initial regulation strategy to a dispatching device;

[0006] Receive a target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on a first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and second power data;

[0007] Regulate the load of the target node according to third power data corresponding to the target node obtained after regulating the load of the target node.

[0008] In one embodiment, the determining the first initial regulation strategy according to the first power data includes:

[0009] Obtain a predicted risk assessment result according to the first power data and a risk assessment model;

[0010] Determine the first initial regulation strategy according to the predicted risk assessment result and the first power data.

[0011] In one embodiment, the regulating the load of the target node according to third power data corresponding to the target node obtained after regulating the load of the target node includes:

[0012] Based on the third power data and the index evaluation model, an index evaluation result is obtained;

[0013] In the case where the index evaluation result does not meet the preset index evaluation requirements, feedback information is sent to the dispatching device;

[0014] Receive a new target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the new target regulation instruction; the new target regulation instruction is generated by the dispatching device based on a first new target regulation strategy, and the first new target regulation strategy is obtained by the dispatching device optimizing the first target regulation strategy based on the feedback information.

[0015] In one embodiment, the method further includes:

[0016] When regulating the load of the target node, the aggregation and decomposition technology is used to optimize the resource allocation of the load of the target node.

[0017] In one embodiment, the method further includes:

[0018] Obtain the historical power data of the load in the distribution network;

[0019] Clean and normalize the historical power data to obtain processed historical power data;

[0020] Based on the characteristics and prediction requirements of the historical power data, feature extraction is performed on the processed historical power data to obtain feature information;

[0021] Based on the feature information, an initial risk assessment model is trained to obtain the risk assessment model.

[0022] In a second aspect, the present application further provides a distribution network load flexible regulation device, including:

[0023] A first acquisition module, configured to acquire first power data corresponding to a target node in a distribution network, determine a first initial regulation strategy according to the first power data, and send the first initial regulation strategy to a dispatching device;

[0024] A regulation module, configured to receive a target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on a first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and second power data;

[0025] A second acquisition module, configured to regulate the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node.

[0026] In a third aspect, the present application further provides a control device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method steps provided in the first aspect are implemented.

[0027] In a fourth aspect, the present application further provides a flexible distribution network load regulation system. The system includes a data acquisition device, a dispatching device, and a control device as provided in the third aspect;

[0028] The data acquisition device is configured to acquire first power data corresponding to a target node in the distribution network and send the first power data to the control device;

[0029] The control device is configured to determine a first initial regulation strategy according to the first power data and send the first initial regulation strategy to the dispatching device;

[0030] The dispatching device is configured to optimize the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and second power data to obtain a first target regulation strategy, and generate a target regulation instruction based on the first target regulation strategy, and send the target regulation instruction to the control device;

[0031] The control device is configured to regulate the load of the target node according to the target regulation instruction, and regulate the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method steps provided in the first aspect are implemented.

[0033] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the method steps provided in the first aspect are implemented.

[0034] The above-mentioned distribution network load flexible regulation method, device, control equipment and system obtain the first power data corresponding to the target node in the distribution network, determine the first initial regulation strategy according to the first power data, and send the first initial regulation strategy to the dispatching equipment. Then, it receives the target regulation instruction sent by the dispatching equipment, and regulates the load of the target node according to the target regulation instruction. According to the third power data corresponding to the target node obtained after regulating the load of the target node, the load of the target node is regulated; the target regulation instruction is generated by the dispatching equipment based on the first target regulation strategy, and the first target regulation strategy is obtained by the dispatching equipment optimizing the first initial regulation strategy based on the second initial regulation strategies and the second power data of each node in the distribution network. When the first initial regulation strategy is obtained in the embodiments of the present application, the first initial regulation strategy is optimized by using the second initial regulation strategies and the second power data of each node in the distribution network to obtain the first target regulation strategy, thereby generating the target regulation instruction for regulating the load of the target node, realizing the organic combination of distributed autonomy and centralized coordination, and improving the load regulation efficiency and flexibility of the target node. Moreover, after regulating the load of the target node based on the target regulation instruction, the load of the target node is also regulated based on the real-time monitoring of the third power data, and the adaptive ability of the distribution network is enhanced through real-time feedback to cope with the sudden situation of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is an application environment diagram of the distribution network load flexible regulation method in an embodiment;

[0037] Figure 2 It is a flowchart of the distribution network load flexible regulation method in an embodiment;

[0038] Figure 3 It is a flowchart of the first initial regulation strategy determination method in an embodiment;

[0039] Figure 4 It is a flowchart of the load regulation method in an embodiment;

[0040] Figure 5 It is a structural block diagram of the distribution network load flexible regulation device in an embodiment;

[0041] Figure 6 It is an internal structure diagram of the control equipment in an embodiment. Specific implementation manners

[0042] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further details the present application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely used to explain the present application and are not used to limit the present application.

[0043] The flexible distribution network load regulation method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the application environment includes a data acquisition device 101, and a control device 102 communicates with a dispatching device 103 through a network. A data storage system can store data that the dispatching device 103 needs to process. The data storage system can be integrated on the dispatching device 103, or can be placed on the cloud or other network dispatching devices. Among them, the dispatching device 103 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0044] In an exemplary embodiment, as Figure 2 shown, a flexible distribution network load regulation method is provided. Taking the method applied to the Figure 1 control device 102 as an example for description, it includes the following S201 to S203. Among them:

[0045] S201, obtain first power data corresponding to a target node in the distribution network, determine a first initial regulation strategy according to the first power data, and send the first initial regulation strategy to the dispatching device.

[0046] Among them, various sensors are installed at each node (such as transformers, feeders, user ends, etc.) in the distribution network. Assume that the target node is the user end, and the sensors set on the user end use Internet of Things technology to monitor the first power data corresponding to the target node in real time, and send the first power data to the control device. Optionally, the first power data can be load data (such as active power, reactive power), voltage parameters, current parameters, electrical parameters, and other factors that may affect load regulation (such as weather, holidays, economic activity levels), etc.

[0047] In the embodiments of the present application, the data acquisition device obtains the first power data of the target node and sends the first power data to the control device. Specifically, the first power data collected by the data acquisition device is transmitted to a data concentrator or gateway by wired or wireless means (such as low-power wide-area network technologies such as Zigbee, LoRa, NB-IoT, etc.). The data concentrator or gateway is responsible for collecting data from each sensor, performing preliminary processing and packaging, and then sending the packaged first power data to the control device through a faster network (such as a fiber optic network, 4G / 5G network).

[0048] To improve data quality and integrity, the control device can first perform preprocessing such as data cleaning on the first power data, and store the preprocessed first power data in a database for subsequent analysis and use.

[0049] In a possible implementation, based on the preprocessed first power data and a risk assessment model, a predicted risk assessment result of the target node can be obtained. According to the first power data and the predicted risk assessment result, a first initial regulation strategy for the target node can be obtained. At the same time, through a high-speed communication network, the first initial regulation strategy is uploaded to the dispatching device. Optionally, the first initial regulation strategy can be to adjust load distribution, adjust the tap position of the transformer, etc.

[0050] In another possible implementation, based directly on the preprocessed first power data and a risk assessment model, a predicted risk assessment result of the target node can be obtained, and a first initial regulation strategy for the target node can be generated according to the predicted risk assessment result.

[0051] In another possible implementation, a first initial regulation strategy for the target node can be directly generated based on the preprocessed first power data.

[0052] Optionally, the first power data can also be displayed through a visualization interface to facilitate monitoring and analysis.

[0053] S202, receive the target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on a first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the second initial regulation strategies and the second power data of each node in the distribution network.

[0054] In the embodiments of the present application, each node in the distribution network includes a target node, that is, the second initial regulation strategy of each node includes the first initial regulation strategy, and the second power data of each node includes the first power data. For example, each node in the distribution network includes Node 1, Node 2, and Node 3. The second initial regulation strategies of each node are the second initial regulation strategy of Node 1, the second initial regulation strategy of Node 2, and the second initial regulation strategy of Node 3. The second power data of each node includes the second power data of Node 1, the second power data of Node 2, and the second power data of Node 3. If the target node is Node 3, then the second initial regulation strategy of Node 3 is the first initial regulation strategy, and the second power data of Node 3 is the first power data. The dispatching device receives the second initial regulation strategies and the second power data of each node, and uses a global optimization algorithm to globally optimize the first initial regulation strategy to balance the load, voltage distribution, and current distribution of the entire distribution network, and improve the safety and economy of the power grid. Optionally, the global optimization algorithm can be a genetic algorithm, a particle swarm algorithm, etc.

[0055] For example, the second initial regulation strategies and the second power data of each node are input into a global optimization algorithm (such as a genetic algorithm, a particle swarm algorithm). The global optimization algorithm establishes an objective function to balance the load, voltage distribution, and current distribution of the entire distribution network, and improve the safety and economy of the power grid. Based on the objective function, the first initial regulation strategy of the target node is optimized to obtain the first target regulation strategy. For example, the objective function can be set as a function to minimize the active power loss of the entire network and maximize the voltage stability index.

[0056] When optimizing the first initial regulation strategy, the global optimization algorithm will adjust and optimize the first initial regulation strategy on the premise of satisfying various constraint conditions (such as line transmission capacity constraints, voltage upper and lower limit constraints, etc.). Through continuous iterative calculations, a set of regulation parameter combinations that make the objective function value optimal is found, that is, the first target regulation strategy. Then, based on the first target regulation strategy, a first target regulation instruction is generated, and the first target regulation instruction is sent to the control device through the communication network, and the control device executes specific regulation operations to ensure the safety and effectiveness of the regulation.

[0057] Optionally, the first target regulation instruction includes instructions such as load transfer, capacitor switching, and transformer tap adjustment.

[0058] S203. According to the third power data corresponding to the target node obtained after regulating the load of the target node, regulate the load of the target node.

[0059] In an embodiment of the present application, an index evaluation result can be obtained based on third power data and an index evaluation model. When the index evaluation result does not meet the preset index evaluation requirements, feedback information is sent to a dispatching device. The dispatching device optimizes a first target regulation strategy based on the feedback information to obtain a first new target regulation strategy, and then generates a new target regulation instruction based on the first new target regulation strategy and sends the new target regulation instruction to a control device. The control device regulates the load of a target node based on the new target regulation instruction.

[0060] In a possible implementation manner, when the index evaluation result meets the preset index evaluation requirements, the control device continuously obtains the third power data of the target node and regularly feeds back the third power data of the target node to the dispatching device, so that the dispatching device can comprehensively understand the operation condition of the distribution network. When the operating state of the control device changes (such as adjustment of the first target regulation strategy, equipment failure, etc.), it is also necessary to promptly feed back to the dispatching device.

[0061] In another possible implementation manner, after receiving the first target regulation strategy sent by the dispatching device, when the index evaluation result does not meet the preset index evaluation requirements, the first target regulation strategy can also be optimized based on the third power data, and the load of the target node is regulated according to the optimized result.

[0062] In the above distribution network load flexible regulation method, the first power data corresponding to the target node in the distribution network is obtained, a first initial regulation strategy is determined according to the first power data, and the first initial regulation strategy is sent to the dispatching device. The target regulation instruction sent by the dispatching device is received, and the load of the target node is regulated according to the target regulation instruction. The load of the target node is regulated according to the third power data corresponding to the target node obtained after regulating the load of the target node; the target regulation instruction is generated by the dispatching device based on the first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the second initial regulation strategies and the second power data of each node in the distribution network. When the first initial regulation strategy is obtained in the embodiment of the present application, the first initial regulation strategy is optimized by using the second initial regulation strategies and the second power data of each node in the distribution network to obtain the first target regulation strategy, thereby generating a target regulation instruction for regulating the load of the target node, realizing the organic combination of distributed autonomy and centralized coordination, and improving the load regulation efficiency and flexibility of the target node. Moreover, after regulating the load of the target node based on the target regulation instruction, the load of the target node is also regulated based on the real-time monitored third power data, and the adaptive capacity of the distribution network is enhanced through real-time feedback to cope with unexpected situations in the distribution network.

[0063] Figure 3 It is a schematic flow chart of a method for determining a first initial regulation strategy in an embodiment, asFigure 3 As shown in Figure 3 , an embodiment of the present application relates to a possible implementation manner of how to determine a first initial regulation strategy according to first power data, including the following steps:

[0064] S301, obtaining a predicted risk assessment result according to the first power data and a risk assessment model.

[0065] In the embodiment of the present application, the first power data can be directly input into the risk assessment model to obtain a predicted risk assessment result; alternatively, feature extraction can be performed on the first power data to obtain feature information, and the feature information can be input into the risk assessment model to obtain a predicted risk assessment result.

[0066] S302, determining a first initial regulation strategy according to the predicted risk assessment result and the first power data.

[0067] In the embodiment of the present application, a preset algorithm can be used to analyze the predicted risk assessment result and the first power data to obtain a first initial regulation strategy. Optionally, the preset algorithm can be a regulation algorithm based on load balance, a regulation algorithm based on voltage stability, etc.

[0068] In a possible implementation manner, a first initial regulation strategy is formulated based on a regulation algorithm based on load balance: if the first power data shows that the active power of some feeders is too high, approaching its rated capacity, while the active power of other feeders is low. At the same time, the predicted risk assessment result shows that the load of the high-load feeder will continue to increase in a future period of time, and the load of the low-load feeder will not change much. Based on the regulation algorithm based on load balance, the control device can formulate a first initial regulation strategy to transfer some transferable loads (such as some non-critical industrial users or commercial users) on the high-load feeder to the low-load feeder to balance the loads of each feeder. For example, by controlling the switching equipment, some users originally connected to the high-load feeder are switched to the low-load feeder.

[0069] In another possible implementation manner, a first initial regulation strategy is formulated based on a regulation algorithm based on voltage stability: if the first power data shows that the voltage of a certain area in the target node is low, and the predicted risk assessment result shows that the load in this area is about to increase, which will cause the voltage to drop further. Based on the regulation algorithm based on voltage stability, the control device can formulate a first initial regulation strategy, such as adjusting the tap position of the transformer to increase the voltage in this area; if the adjustment of the transformer tap cannot meet the voltage requirement, capacitors can also be considered to be put into operation to increase reactive power compensation and improve the voltage level.

[0070] In the embodiments of the present application, according to the first power data and the risk assessment model, a predicted risk assessment result is obtained, and according to the predicted risk assessment result and each second power data, a first initial regulation strategy is determined, which improves the accuracy and efficiency of generating the first initial regulation strategy.

[0071] Figure 4 FIG. is a schematic flowchart of a load regulation method in an embodiment, as Figure 4 shown, the embodiments of the present application relate to a possible implementation manner of regulating the load of a target node according to the third power data corresponding to the target node obtained after regulating the load of the target node, including the following steps:

[0072] S401, according to the third power data and the index evaluation model, an index evaluation result is obtained.

[0073] Among them, the preset index evaluation requirements may include safety indexes, economic indexes, reliability indexes, etc.

[0074] In the embodiments of the present application, the third power data is input into a pre-trained index evaluation model to obtain an index evaluation result.

[0075] S402, in the case that the index evaluation result does not meet the preset index evaluation requirements, feedback information is sent to the dispatching device.

[0076] In the embodiments of the present application, in the case that the index evaluation result does not meet the preset index evaluation requirements, feedback information is sent to the dispatching device, and the feedback information may be that the index evaluation result does not meet the preset index evaluation, or the third power data.

[0077] S403, receive a new target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the new target regulation instruction; the new target regulation instruction is generated by the dispatching device based on a first new target regulation strategy, and the first new target regulation strategy is obtained by the dispatching device optimizing the first target regulation strategy based on the feedback information.

[0078] In the embodiments of the present application, the first target regulation strategy may be optimized based on the third power data to obtain a first new target regulation strategy, so as to generate a new target regulation instruction based on the first new target regulation strategy, send the adjusted new target regulation instruction to the control device for execution, and continue to monitor the power data of the target node to form a closed-loop control process.

[0079] In a possible implementation, if other nodes except the target node also optimize the corresponding second initial control strategy to obtain the corresponding second target control strategy. For example, in addition to optimizing the first initial control strategy of the target node (node 3) in S202 above, the second initial control strategies corresponding to node 1 and node 2 are also optimized to obtain the second target control strategy of node 1 and the second target control strategy of node 2. Based on the second target control strategy of node 1, the second target control strategy of node 2, the first new target control strategy of the target node (node 3), the fourth power data of node 1, the fourth power data of node 2, and the third power data of the target node (node 3), the first target control strategy is optimized to obtain the first new target control strategy. Among them, the fourth power data of node 1 and the fourth power data of node 2 are the power data obtained after regulating the loads of node 1 and node 2 using the corresponding second target control strategy, that is, the acquisition time is the same as that of the third power data of the target node.

[0080] In the embodiments of the present application, according to the third power data and the index evaluation model, an index evaluation result is obtained. When the index evaluation result does not meet the preset index evaluation requirements, feedback information is sent to the dispatching device, a new target control instruction sent by the dispatching device is received, and the load of the target node is regulated according to the new target control instruction. The embodiments of the present application adaptively adjust the first target control strategy according to the feedback information, can monitor the distribution network status in real time, discover and handle potential safety hazards in time, so as to improve the operation condition of the distribution network.

[0081] In one embodiment, the method further includes: when regulating the load of the target node, optimizing the resource allocation of the load of the target node by using the aggregation and decomposition technology.

[0082] In a possible implementation, when regulating the load of the target node, optimizing the resource allocation of the load of the target node by using the load aggregation technology may include two aggregation methods: demand response aggregation and distributed energy aggregation:

[0083] Demand response aggregation: Load aggregation can aggregate multiple small-capacity user loads (such as residential users, small commercial users) in the target node into a larger-capacity virtual load. During peak load periods, users are guided to reduce their electricity loads through economic incentives (such as electricity bill discounts), which can meet the electricity demand during peak periods without increasing the power generation capacity, and improve the operation efficiency and economy of the power grid.

[0084] Distributed energy aggregation: Aggregate the distributed energy corresponding to the target node (such as distributed photovoltaic, distributed wind power, energy storage devices, etc.) together to form a virtual power generation unit. According to the needs of the target node and the power generation characteristics of the distributed energy, the distributed energy can be uniformly scheduled and managed. For example, when there is sufficient sunlight, the excess electric energy generated by the distributed photovoltaic is stored in the energy storage device; during the peak load period, the electric energy in the energy storage device is released to provide power support for the target node in the distribution network, realizing the effective utilization of distributed energy and the optimal allocation of resources.

[0085] In a possible implementation, when regulating the load of the target node, using load decomposition technology to optimize the resource allocation of the load of the target node may include two decomposition methods: load characteristic decomposition and load device decomposition:

[0086] Load characteristic decomposition: Decompose the total load of the target node into different types of loads (such as residential load, industrial load, commercial load, etc.) through load decomposition technology, and analyze their respective electricity consumption characteristics (such as electricity consumption time, electricity consumption power, etc.); according to the characteristics of different types of loads, formulate targeted regulation strategies; for example, industrial loads can be arranged for production during the low grid load period to reduce electricity costs; for residential loads, peak shaving can be achieved through the control of smart home appliances.

[0087] Load device decomposition: Further decompose the same type of load (for example, user load) into different electrical appliances (such as air conditioners, refrigerators, washing machines, etc.), and monitor the operating status of the electrical appliances in real time. According to the priority and electricity consumption demand of the electrical appliances, optimize the control of the electrical appliances. For example, when the grid load is tight, some non-essential electrical appliances (such as the auxiliary heating function of the air conditioner) are preferentially turned off to ensure the normal operation of important equipment, realizing the refined management and optimal allocation of load resources.

[0088] In an embodiment, the method further includes: obtaining the historical power data of the load in the distribution network; cleaning and normalizing the historical power data to obtain the processed historical power data; extracting features from the processed historical power data based on the characteristics and prediction requirements of the historical power data to obtain feature information; training an initial risk assessment model based on the feature information to obtain a risk assessment model.

[0089] Optionally, the historical power data includes time series load data (such as daily load data, weekly load data, monthly load data, etc.) and other factors that may affect load regulation (such as weather, holidays, economic activity levels, etc.).

[0090] In the embodiments of the present application, historical power data is cleaned to remove outliers and missing values in the historical power data, and then the cleaned historical power data is further normalized to improve the training efficiency and prediction accuracy of the initial risk assessment model.

[0091] Based on the characteristics of historical power data and prediction requirements, features that have an important impact on the prediction results are extracted and constructed to obtain feature information. The feature information is input into the initial risk assessment model, and the parameters and structure of the initial risk assessment model are optimized according to the prediction results and the gold standard to obtain a risk assessment model, so as to improve the prediction performance of the risk assessment model for the predicted risk results and provide a basis for formulating the initial regulation strategy.

[0092] Optionally, the initial risk assessment model can be a Long Short-Term Memory (LSTM), a gated recurrent neural network (GRU), etc.

[0093] In the embodiments of the present application, historical power data of the load in the distribution network is obtained; the historical power data is cleaned and normalized to obtain the processed historical power data; based on the characteristics of the historical power data and prediction requirements, feature extraction is performed on the processed historical power data to obtain feature information; the initial risk assessment model is trained based on the feature information to obtain a risk assessment model, laying a foundation for obtaining the predicted risk assessment result based on the risk assessment model in the future, and significantly improving the accuracy and real-time performance of the risk prediction of the load.

[0094] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0095] Based on the same inventive concept, an embodiment of the present application further provides a flexible distribution network load regulation device for implementing the flexible distribution network load regulation method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the flexible distribution network load regulation device provided below can refer to the limitations on the flexible distribution network load regulation method in the above text, and will not be elaborated here.

[0096] In an exemplary embodiment, as Figure 5 shown, a flexible distribution network load regulation device is provided, including: a first acquisition module 51, a regulation module 52, and a second acquisition module 53, where:

[0097] The first acquisition module 51 is configured to acquire first power data corresponding to a target node in the distribution network, determine a first initial regulation strategy according to the first power data, and send the first initial regulation strategy to a dispatching device;

[0098] The regulation module 52 is configured to receive a target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on a first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and second power data;

[0099] The second acquisition module 53 is configured to regulate the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node.

[0100] In one embodiment, the first acquisition module 51 is specifically configured to obtain a predicted risk assessment result according to the first power data and a risk assessment model; determine the first initial regulation strategy according to the predicted risk assessment result and each second power data.

[0101] In one embodiment, the second acquisition module 53 is specifically configured to obtain an index assessment result according to the third power data and an index assessment model; send feedback information to the dispatching device when the index assessment result does not meet the preset index assessment requirements; receive a new target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the new target regulation instruction; the new target regulation instruction is generated by the dispatching device based on a first new target regulation strategy, and the first new target regulation strategy is obtained by the dispatching device optimizing the first target regulation strategy based on the feedback information.

[0102] In one embodiment, the device further includes:

[0103] Optimization module, used to optimize the resource allocation of the load of the target node by using the aggregation and decomposition technology when regulating the load of the target node.

[0104] In one embodiment, the device further includes:

[0105] The third acquisition module is used to acquire the historical power data of the load in the distribution network;

[0106] The processing module is used to clean and normalize the historical power data to obtain the processed historical power data;

[0107] The extraction module is used to extract feature information from the processed historical power data based on the characteristics of the historical power data and the prediction requirements;

[0108] The training module is used to train the initial risk assessment model based on the feature information to obtain the risk assessment model.

[0109] Each module in the above distribution network load flexible regulation device can be implemented in whole or in part by software, hardware and their combination. Each of the above modules can be embedded in the processor in the control device in hardware form or independent of it, or stored in the memory in the control device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0110] In an exemplary embodiment, a control device is provided. The control device can be a server, and its internal structure diagram can be as Figure 6 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the relevant data of the distribution network load flexible regulation. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it realizes a distribution network load flexible regulation method.

[0111] Those skilled in the art can understand, Figure 6The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the control device to which the solution of this application is applied. The specific control device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0112] In an exemplary embodiment, a control device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of any of the above method embodiments are implemented.

[0113] In an exemplary embodiment, a distribution network load flexible regulation system is provided. The system includes a data acquisition device, a scheduling device, and the control device provided in the above embodiment;

[0114] The data acquisition device is configured to acquire first power data corresponding to a target node in the distribution network and send the first power data to the control device;

[0115] The control device is configured to determine a first initial regulation strategy according to the first power data and send the first initial regulation strategy to the scheduling device;

[0116] The scheduling device is configured to optimize the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and second power data to obtain a first target regulation strategy, and generate a target regulation instruction based on the first target regulation strategy, and send the target regulation instruction to the control device;

[0117] The control device is configured to regulate the load of the target node according to the target regulation instruction, and regulate the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node.

[0118] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0119] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0121] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0122] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in the present application.

[0123] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A flexible regulation method for distribution network load, characterized in that The method includes: Obtain the first power data corresponding to the target node in the distribution network, determine the first initial regulation strategy according to the first power data, and send the first initial regulation strategy to the dispatching device; Receive the target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on the first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the second initial regulation strategies and the second power data of each node in the distribution network; Regulate the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node.

2. The method according to claim 1, wherein The determining the first initial regulation strategy according to the first power data includes: Obtain the predicted risk assessment result according to the first power data and the risk assessment model; Determine the first initial regulation strategy according to the predicted risk assessment result and the first power data.

3. The method according to claim 1, wherein The regulating the load of the target node according to the third power data corresponding to the target node obtained after regulating the load of the target node includes: Obtain the index assessment result according to the third power data and the index assessment model; In the case that the index assessment result does not meet the preset index assessment requirements, send feedback information to the dispatching device; Receive the new target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the new target regulation instruction; the new target regulation instruction is generated by the dispatching device based on the first new target regulation strategy, and the first new target regulation strategy is obtained by the dispatching device optimizing the first target regulation strategy based on the feedback information.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: When regulating the load of the target node, optimize the resource allocation of the load of the target node by using the aggregation and decomposition technology.

5. The method according to claim 2, wherein The method further includes: Obtain the historical power data of the load in the distribution network; Clean and normalize the historical power data to obtain the processed historical power data; Extract features from the processed historical power data based on the characteristics of the historical power data and the prediction requirements to obtain feature information; Train the initial risk assessment model based on the feature information to obtain the risk assessment model.

6. A flexible regulation device for distribution network load, characterized in that, The device includes: The first acquisition module is used to obtain the first power data corresponding to the target node in the distribution network, determine the first initial regulation strategy according to the first power data, and send the first initial regulation strategy to the dispatching device; The regulation module is used to receive the target regulation instruction sent by the dispatching device, and regulate the load of the target node according to the target regulation instruction; the target regulation instruction is generated by the dispatching device based on the first target regulation strategy, and the first target regulation strategy is obtained by the dispatching device optimizing the first initial regulation strategy based on the initial regulation strategies of each node in the distribution network and the second power data; A second acquisition module, configured to adjust the load of the target node according to the third power data corresponding to the target node acquired after adjusting the load of the target node.

7. A control device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A flexible regulation system for distribution network load, characterized in that, The system includes a data acquisition device, a scheduling device, and a control device as claimed in claim 7; The data acquisition device is configured to acquire first power data corresponding to a target node in the distribution network and send the first power data to the control device; The control device is configured to determine a first initial adjustment strategy according to the first power data and send the first initial adjustment strategy to the scheduling device; The scheduling device is configured to optimize the first initial adjustment strategy to obtain a first target adjustment strategy based on the initial adjustment strategies of each node in the distribution network and second power data, and generate a target adjustment instruction based on the first target adjustment strategy, and send the target adjustment instruction to the control device; The control device is configured to adjust the load of the target node according to the target adjustment instruction, and adjust the load of the target node according to the third power data corresponding to the target node acquired after adjusting the load of the target node.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images