An energy scheduling method, device, equipment and storage medium for a low-voltage distribution network

Abstract

Embodiments of the present application relate to the field of low-voltage power distribution, and provide an energy scheduling method, device, equipment and storage medium for a low-voltage power distribution network. The method includes: obtaining operation data of a target low-voltage power distribution network; in response to an input instruction for inputting the operation data of the target low-voltage power distribution network into a fault diagnosis and recognition model, obtaining a fault area and a fault type of the target low-voltage power distribution network; obtaining a target energy scheduling planning strategy according to the fault area and the fault type; receiving load feedback information at a user load end after executing the target energy scheduling planning strategy; optimizing the target energy scheduling planning strategy with the power supply feedback information in a strategy optimization function as a target, obtaining an optimized target energy scheduling planning strategy and executing the optimized target energy scheduling planning strategy. By combining the operation data of the target low-voltage power distribution network with the fault diagnosis and recognition model, the adaptability and response speed of the low-voltage power distribution network are improved, and the reliable and stable operation of the low-voltage power distribution network is ensured.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of low-voltage power distribution, and in particular, to an energy scheduling method for a low-voltage power distribution network, an energy scheduling device for a low-voltage power distribution network, a corresponding electronic device, and a corresponding computer-readable storage medium. Background Art

[0002] In the current power supply system, the low-voltage distribution network (referred to as the low-voltage power distribution network) in the low-voltage area, as a key link directly facing users, its stable operation is crucial for ensuring reliable power supply. For example, in the scenario of the construction of a large factory, it is predicted that the load of the distribution transformer near the newly built large factory will increase significantly. At this time, there is a need to build a new distribution transformer for load switching. However, for the low-voltage power distribution network with complex structure, numerous devices and wide distribution, regional faults are likely to occur in the low-voltage power distribution network.

[0003] In the related technologies of energy scheduling planning for a low-voltage power distribution network with regional faults, an energy scheduling scheme based on rules or an energy scheduling scheme based on an optimization algorithm can be adopted. Among them, the energy scheduling scheme based on rules usually performs energy scheduling according to pre-set simple rules; the energy scheduling scheme based on an optimization algorithm usually adopts an optimization algorithm such as a genetic algorithm or a particle swarm algorithm to consider various constraints of the power distribution network and seek an optimal scheduling scheme. However, whether it is an energy scheduling scheme based on rules or an energy scheduling scheme based on an optimization algorithm, due to the uncertainty of the operating environment of the low-voltage power distribution network, it is difficult to ensure the reliable and stable operation of the low-voltage power distribution network. Summary of the Invention

[0004] The embodiments of the present application provide an energy scheduling method, device, equipment and storage medium for a low-voltage power distribution network, which can improve the adaptability and response speed of the low-voltage power distribution network and ensure the reliable and stable operation of the low-voltage power distribution network.

[0005] In one aspect, the embodiments of the present application provide an energy scheduling method for a low-voltage power distribution network, which relates to an energy scheduling terminal, and the energy scheduling terminal has a fault diagnosis and recognition model. The method includes:

[0006] Obtain the operation data of the target low-voltage power distribution network;

[0007] Respond to the input instruction that inputs the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model to obtain the fault area and fault type of the target low-voltage distribution network; wherein, the fault diagnosis and recognition model includes a network topology layer, a feature analysis layer, and a fault analysis layer, the fault area and fault type are obtained by the fault analysis layer performing fault analysis on fault feature data, the fault feature data is obtained by the feature analysis layer performing feature mining on a fault analysis graph, and the fault analysis graph is generated by the network topology layer performing topology analysis on the operation data;

[0008] According to the fault area and the fault type, obtain a target energy scheduling planning strategy;

[0009] Receive the load feedback information of the user load end after executing the target energy scheduling planning strategy; the load feedback information is used to construct a strategy optimization function;

[0010] Optimize the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function as the target, obtain the optimized target energy scheduling planning strategy, and execute the optimized target energy scheduling planning strategy.

[0011] On the other hand, an embodiment of the present application further provides an energy scheduling device for a low-voltage distribution network, which is applied to an energy scheduling end, and the energy scheduling end has a fault diagnosis and recognition model. The device includes:

[0012] An operation data acquisition module, configured to acquire the operation data of the target low-voltage distribution network;

[0013] A fault diagnosis module, configured to respond to the input instruction that inputs the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model to obtain the fault area and fault type of the target low-voltage distribution network; wherein, the fault diagnosis and recognition model includes a network topology layer, a feature analysis layer, and a fault analysis layer, the fault area and fault type are obtained by the fault analysis layer performing fault analysis on fault feature data, the fault feature data is obtained by the feature analysis layer performing feature mining on a fault analysis graph, and the fault analysis graph is generated by the network topology layer performing topology analysis on the operation data;

[0014] A planning strategy generation module, configured to obtain a target energy scheduling planning strategy according to the fault area and the fault type;

[0015] A feedback information receiving module, configured to receive the load feedback information of the user load end after executing the target energy scheduling planning strategy; the load feedback information is used to construct a strategy optimization function;

[0016] An energy scheduling module, which is used to optimize the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function, obtain the optimized target energy scheduling planning strategy, and execute the optimized target energy scheduling planning strategy.

[0017] In another aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory, and a computer program stored on the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the energy scheduling method for the low-voltage distribution network described in any one of the above.

[0018] In another aspect, an embodiment of 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, it implements the energy scheduling method for the low-voltage distribution network described in any one of the above.

[0019] In another aspect, an embodiment of the present application further provides a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the energy scheduling method for the low-voltage distribution network described in each of the above aspects.

[0020] The energy scheduling method, device, equipment, and storage medium for the low-voltage distribution network provided by the embodiments of the present application combine the operation data of the target low-voltage distribution network through a fault diagnosis and recognition model, and comprehensively analyze the real-time state of the low-voltage distribution network layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, quickly and accurately identify the fault area and fault type, and obtain the target energy scheduling planning strategy for the fault area based on the accurately identified fault area and fault type, and can obtain the corresponding energy scheduling planning strategy in a relatively short time under complex and changeable fault scenarios, improving the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network; and, the energy scheduling planning strategy can also be continuously optimized through the load feedback information at the user load end, aiming at the power supply feedback information in the strategy optimization function constructed by the load feedback information, optimizing the target energy scheduling planning strategy, and executing the optimized target energy scheduling planning strategy, further improving the adaptability of the low-voltage distribution network while improving the response speed of the low-voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low-voltage distribution network. Description of the Drawings

[0021] Figure 1 It is a schematic diagram of the architecture of a distribution network planning system provided by an embodiment of the present application;

[0022] Figure 2 It is a flowchart of the steps of an energy scheduling method for a low-voltage distribution network provided by an embodiment of the present application;

[0023] Figure 3It is a flowchart of the steps of another energy scheduling method for a low-voltage distribution network according to an embodiment of the present application;

[0024] Figure 4 It is a structural block diagram of an energy scheduling device for a low-voltage distribution network according to an embodiment of the present application;

[0025] Figure 5 It is a structural block diagram of an electronic device provided by an embodiment of the present application;

[0026] Figure 6 It is a structural block diagram of a computer-readable storage medium provided by an embodiment of the present application. Detailed implementation manners

[0027] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0028] The reliable and stable operation of the low-voltage distribution network is conducive to ensuring the reliable supply of electricity. Therefore, when a fault occurs in a region of the low-voltage distribution network, there is a need for energy scheduling of the low-voltage distribution network to ensure the reliable and stable operation of the low-voltage distribution network, and thus ensure the reliable stability of the power supply.

[0029] In the related technologies of energy scheduling planning for a low-voltage distribution network with a regional fault, as an example, a rule-based energy scheduling scheme can be adopted. This scheme usually performs energy scheduling according to pre-set simple rules. For example, when a fault occurs in a certain region, the standby power supply can be switched or the power supply line can be adjusted according to a fixed priority. However, the aforementioned energy scheduling method based on set simple rules lacks the comprehensive perception and flexible response ability to the real-time state of the distribution network, and it is difficult to achieve efficient energy scheduling in complex and changeable fault scenarios, which easily causes insufficient power supply in some regions, resulting in low adaptability of the low-voltage distribution network; as another example, an energy scheduling scheme based on an optimization algorithm can be adopted. This scheme usually performs by using algorithms such as genetic algorithms and particle swarm algorithms to consider various constraints of the distribution network and seek the optimal scheduling scheme. However, the algorithms used in the aforementioned scheme have high computational complexity, high requirements for computing resources, and in practical applications, due to the uncertainty of the operating environment of the low-voltage distribution network, the convergence speed of the algorithm is slow, and it is difficult to give an effective scheduling strategy in a short time, and it cannot meet the rapid response when a fault occurs, thus unable to ensure the reliable and stable operation of the low-voltage distribution network.

[0030] In summary, due to the uncertainty of the operating environment of the low-voltage distribution network, the above-mentioned related technologies are difficult to ensure the reliable and stable operation of the low-voltage distribution network.

[0031] In the embodiment of the present application, the fault diagnosis and identification model combines the operation data of the target low-voltage distribution network, and comprehensively analyzes the real-time state of the low-voltage distribution network layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, quickly and accurately identifying the fault area and the fault type, and obtaining the target energy scheduling planning strategy for the fault area based on the accurately identified fault area and fault type. It can obtain the corresponding energy scheduling planning strategy in a relatively short time under complex and changeable fault scenarios, improve the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network, which is beneficial to ensuring the reliable and stable operation of the low-voltage distribution network; and, the energy scheduling planning strategy can also be continuously optimized through the load feedback information at the user load end. Taking the power supply feedback information in the strategy optimization function constructed by the load feedback information as the target, the target energy scheduling planning strategy is optimized, and the optimized target energy scheduling planning strategy is executed. While improving the response speed of the low-voltage distribution network, the adaptability of the low-voltage distribution network is further improved, which is more beneficial to ensuring the reliable and stable operation of the low-voltage distribution network.

[0032] Refer to Figure 1 , which shows a schematic architecture diagram of a distribution network planning system provided by an embodiment of the present application. The distribution network planning system can monitor the state of the power distribution network in real time. When a fault occurs in the power distribution network, it can perform energy scheduling on the aforementioned power distribution network according to the load situation of the power distribution network, thereby optimizing the resource allocation of the power distribution network and ensuring the reliable and stable operation of the power distribution network.

[0033] As Figure 1 shown, the distribution network planning system 100 may include an energy scheduling end 101 and a user load end 102. The energy scheduling end 101 may be mainly responsible for the overall scheduling and management of the power distribution network, such as performing energy scheduling on the faulty power distribution network, etc.; the user load end 102 may be mainly responsible for monitoring the power consumption load of power users and feeding back the load information to the energy scheduling end 101. It should be noted that for the specific energy scheduling end and the specific user load end, they can be determined based on the actual distribution network planning scenario, and the embodiments of the present application do not limit this.

[0034] Exemplarily, when the distribution network planning system 100 is in the operating environment of the low-voltage distribution network, in the scenario of a newly built large factory, the distribution network planning system 100 predicts that the load of the distribution transformer near the newly built large factory will increase significantly, and there is a need to build a new distribution transformer for load switching. For the low-voltage distribution network with complex structure, numerous devices and wide distribution, regional faults are likely to occur in the low-voltage distribution network. At this time, the distribution network planning system 100 can perform energy scheduling planning for the low-voltage distribution network with regional faults. Among them, the energy scheduling terminal 101 can be a highly automated control center, and the user load terminal 102 can refer to various users in the low-voltage distribution network, including but not limited to the electrical equipment of various industrial, commercial and residential users such as the newly built large factory. The embodiments of the present application do not limit this.

[0035] In practical applications, the energy scheduling terminal 101 can store a pre-trained fault diagnosis and recognition model 1011. The energy scheduling terminal 101 can combine the fault diagnosis and recognition model 1011 to execute the energy scheduling method for the low-voltage distribution network provided by the embodiments of the present application, and overcome the regional faults that occur in the target low-voltage distribution network when a new distribution transformer is built for the target low-voltage distribution network.

[0036] In some embodiments of the present application, the fault diagnosis and recognition model 1011 can be composed of three levels: a network topology layer, a feature analysis layer, and a fault analysis layer. Specifically, the fault diagnosis and recognition model 1011 can perform topology analysis on the operation data of the low-voltage distribution network with regional faults based on the network topology layer to generate a fault analysis diagram, and perform feature mining based on the generated fault analysis diagram according to the feature analysis layer to obtain fault feature data, and perform fault analysis on the fault feature data based on the fault analysis layer to obtain the fault area and fault type of the low-voltage distribution network, so that the energy scheduling terminal 101 can obtain the target energy scheduling planning strategy according to the fault area and fault type output by the fault diagnosis and recognition model 1011, and then receive the load feedback information of the user load terminal 102 after executing the foregoing target energy scheduling planning strategy, and use the power supply feedback information in the strategy optimization function constructed by the load feedback information as the target to optimize the target energy scheduling planning strategy, and execute the optimized target energy scheduling planning strategy to achieve the energy scheduling of the low-voltage distribution network with regional faults described above.

[0037] In the embodiments of the present application, the distribution network planning system combines the operation data of the target low-voltage distribution network through a fault diagnosis and identification model, and comprehensively analyzes the real-time state of the low-voltage distribution network layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, quickly and accurately identifying the fault area and fault type, and obtaining the target energy scheduling and planning strategy for the fault area based on the accurately identified fault area and fault type, capable of obtaining the corresponding energy scheduling and planning strategy in a relatively short time under complex and changeable fault scenarios, improving the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network; and, the energy scheduling and planning strategy can also be continuously optimized through the load feedback information at the user load end, further improving the adaptability of the low-voltage distribution network while improving the response speed of the low-voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low-voltage distribution network.

[0038] Referring to Figure 2 , the flowchart of the steps of an energy scheduling method for a low-voltage distribution network provided by the embodiments of the present application is shown, which may specifically include the following steps:

[0039] Step S201, obtain the operation data of the target low-voltage distribution network;

[0040] When the distribution network planning system performs the operation of newly building a distribution transformer in the operation environment of the low-voltage distribution network, the distribution network planning system can perform energy scheduling and planning on the low-voltage distribution network with regional faults.

[0041] In an embodiment of the present application, the operation data of the target low-voltage distribution network can be collected through an energy scheduling terminal to comprehensively master the real-time state of the target low-voltage distribution network based on the collected operation data.

[0042] Optionally, the target low-voltage distribution network can be any low-voltage distribution network in the power system. The low-voltage distribution network can include multiple nodes, and multiple types of sensors can be deployed at each node, such as voltage sensors, current sensors, temperature sensors, etc.; optionally, distributed energy and energy storage devices can also be connected to the low-voltage distribution network, where the distributed energy includes solar photovoltaic energy, geothermal energy, natural gas sub-energy, etc., and the energy storage devices include heat storage devices, flywheel energy storage units, small compressed air energy storage devices, etc., and the embodiments of the present application do not limit this.

[0043] In practical applications, the energy scheduling terminal can collect the operation data of the target low-voltage distribution network through multiple types of sensors. Exemplarily, the operation data can include but is not limited to the temperature parameters, voltage parameters, current parameters, and power parameters of each node in the target low-voltage distribution network, as well as the output power of the distributed energy connected to the target low-voltage distribution network and the state information of the energy storage device connected to the target low-voltage distribution network. Among them, the state information mentioned in the embodiments of the present application refers to the state of charge information of the energy storage device.

[0044] Step S202: In response to the input instruction for inputting the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model, obtain the fault area and fault type of the target low-voltage distribution network.

[0045] In some embodiments of the present application, the energy dispatching terminal may store a pre-trained fault diagnosis and recognition model. The fault diagnosis and recognition model can comprehensively analyze the real-time state of the low-voltage distribution network layer by layer in combination with the operation data of the target low-voltage distribution network, and quickly and accurately identify the fault area and fault type. Specifically, it can be manifested that the energy dispatching terminal can respond to the input instruction for inputting the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model, and analyze the operation data of the target low-voltage distribution network layer by layer through the fault diagnosis and recognition model, and output the fault area and fault type of the target low-voltage distribution network.

[0046] Exemplarily, the fault diagnosis and recognition model involves artificial intelligence training, and it can be trained based on the sample parameter vector and its corresponding fault label result. Among them, the sample parameter vector may include, but is not limited to, sample temperature parameter, sample voltage parameter, sample current parameter, sample power parameter, sample output power, and sample status information, and the fault label result may include, but is not limited to, fault area label result and fault type label result. It should be noted that the specific training process of the fault diagnosis and recognition model is not limited in the embodiments of the present application.

[0047] Optionally, the model structure of the fault diagnosis and recognition model may include a network topology layer, a feature analysis layer, and a fault analysis layer. Among them, the fault area and fault type output by the fault diagnosis and recognition model can be obtained based on the fault analysis of the fault feature data by the fault analysis layer; the fault feature data used for the fault analysis by the fault analysis layer can be obtained based on the feature mining of the fault analysis diagram by the feature analysis layer; the fault analysis diagram used for the feature mining by the feature analysis layer can be generated based on the topology analysis of the operation data by the network topology layer. That is, through the network topology layer, feature analysis layer, and fault analysis layer of the fault diagnosis and recognition model from top to bottom, combined with the temperature parameter, voltage parameter, current parameter, and power parameter of each node, the output power of distributed energy, and the status information of energy storage devices, comprehensively master the real-time state of the low-voltage distribution network and conduct layer-by-layer analysis, quickly and accurately identify the fault area and fault type, and achieve efficient energy dispatching in complex and changeable fault scenarios, thereby improving the adaptability of the low-voltage distribution network.

[0048] Step S203: Obtain the target energy dispatching planning strategy according to the fault area and fault type.

[0049] In some embodiments of the present application, after quickly and accurately identifying the fault area and fault type, a target energy scheduling planning strategy for the fault area can be obtained based on the accurately identified fault area and fault type, and the corresponding energy scheduling planning strategy can be obtained in a relatively short time under complex and changeable fault scenarios, improving the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network.

[0050] In practical applications, the fault information of the fault area can be obtained, and based on the fault information and the fault type, strategy matching can be performed in a preset energy scheduling strategy library to obtain at least one final candidate energy scheduling planning strategy. Then, the evaluation index of the target low-voltage distribution network for energy scheduling can be obtained, and based on the evaluation index, strategy matching can be performed among at least one final candidate energy scheduling planning strategy to obtain the target energy scheduling planning strategy.

[0051] The preset energy scheduling strategy library can store a set of energy scheduling strategies for various situations. Exemplarily, first, the relevant information about the fault occurring in the fault area can be collected, such as but not limited to the fault size, fault level, and fault range, etc. Then, based on the aforementioned fault information and the fault type, strategy matching can be performed in the pre-set energy scheduling strategy library to obtain at least one selectable energy scheduling planning strategy, that is, the final candidate energy scheduling planning strategy. Next, the evaluation index of the target low-voltage distribution network for energy scheduling can be obtained, such as but not limited to the power supply restoration time, energy utilization efficiency, scheduling cost, and equipment performance parameters, etc. Then, according to the aforementioned evaluation index, further matching and screening can be performed among the at least one final candidate energy scheduling planning strategy obtained above, so as to determine the target energy scheduling planning strategy that meets the requirements. The target energy scheduling planning strategy can be an energy scheduling planning strategy matching the fault area. At this time, the aforementioned target energy scheduling planning strategy can be used as the current distribution network planning for execution.

[0052] Step S204, receiving the load feedback information of the user load end after executing the target energy scheduling planning strategy;

[0053] In some embodiments of the present application, the energy scheduling end executes the target energy scheduling planning strategy and conveys energy to the user load community connected to the fault area according to the aforementioned strategy. In order to further optimize the energy scheduling planning strategy and further improve the adaptability of the low-voltage distribution network, the energy scheduling end can receive the load feedback information fed back by the user load end of the user load community, so as to optimize the executed target energy scheduling planning strategy based on the fed-back load feedback information.

[0054] Exemplarily, the load feedback information may include actual load information, load change trend information, power supply feedback information, etc. Among them, the actual load information may refer to the specific load values and other conditions in the actual operating state of the user load terminal after executing the target energy scheduling planning strategy, which can reflect the real load quantity; the load change trend information may refer to the information about the upward, downward or stable change trends of the load with factors such as time, which helps to estimate the future load conditions; the power supply feedback information may be the feedback content related to power supply, such as whether the power supply is stable, whether the power supply quantity is sufficient, etc. In this regard, the embodiments of the present application are not limited thereto.

[0055] Step S205: Optimize the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function to obtain the optimized target energy scheduling planning strategy and execute the optimized target energy scheduling planning strategy.

[0056] Optionally, the embodiments of the present application may construct a strategy optimization function based on the load feedback information, that is, construct the strategy optimization function based on the actual load information, load change trend information and power supply feedback information in the load feedback information, and then may optimize the target energy scheduling planning strategy based on the constructed strategy optimization function to further improve the adaptability of the low-voltage distribution network while improving the response speed of the low-voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low-voltage distribution network.

[0057] In an embodiment of the present application, it may be manifested as optimizing the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function to further improve the adaptability of the low-voltage distribution network while improving the response speed of the low-voltage distribution network. It should be noted that the specific optimization process of the target energy scheduling planning strategy is not limited in the embodiments of the present application.

[0058] Among them, the optimized target energy scheduling planning strategy may refer to the optimal energy scheduling planning strategy. Optionally, after obtaining the optimal energy scheduling planning strategy, the energy scheduling terminal may execute the optimal energy scheduling planning strategy to achieve the energy scheduling of the target low-voltage distribution network and overcome the regional faults that occur in the target low-voltage distribution network when newly building a distribution transformer for the target low-voltage distribution network.

[0059] In the embodiments of the present application, by combining the fault diagnosis and recognition model with the operation data of the target low-voltage distribution network, the real-time state of the low-voltage distribution network is comprehensively analyzed layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, quickly and accurately identifying the fault area and fault type, and obtaining the target energy scheduling planning strategy for the fault area based on the accurately identified fault area and fault type, which can obtain the corresponding energy scheduling planning strategy in a relatively short time under complex and changeable fault scenarios, improving the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network; and, the energy scheduling planning strategy can also be continuously optimized through the load feedback information at the user load end. Taking the power supply feedback information in the strategy optimization function constructed by the load feedback information as the target, the target energy scheduling planning strategy is optimized, and the optimized target energy scheduling planning strategy is executed, further improving the adaptability of the low-voltage distribution network while improving the response speed of the low-voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low-voltage distribution network.

[0060] Referring to Figure 3 , a flowchart of steps of another energy scheduling method for a low-voltage distribution network provided by an embodiment of the present application is shown, which may specifically include the following steps:

[0061] Step S301, in response to an input instruction for inputting the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model, obtain the fault area and fault type of the target low-voltage distribution network;

[0062] In the embodiments of the present application, the energy scheduling terminal may store a pre-trained fault diagnosis and recognition model, and the fault diagnosis and recognition model can combine the operation data of the target low-voltage distribution network to comprehensively analyze the real-time state of the low-voltage distribution network layer by layer, quickly and accurately identifying the fault area and fault type.

[0063] In some embodiments of the present application, the energy scheduling terminal may respond to an input instruction for inputting the operation data of the target low-voltage distribution network, which is specifically manifested as inputting the temperature parameters, voltage parameters, current parameters, and power parameters of each node, as well as the output power and status information into the fault diagnosis and recognition model, and then analyzing the operation data of the target low-voltage distribution network layer by layer through the fault diagnosis and recognition model, and outputting the fault area and fault type of the target low-voltage distribution network.

[0064] Optionally, the model structure of the fault diagnosis and recognition model may include a network topology layer, a feature analysis layer, and a fault analysis layer. Among them, the fault area and fault type output by the fault diagnosis and recognition model can be obtained by performing fault analysis on the fault feature data in the fault analysis layer; the fault feature data used for fault analysis in the fault analysis layer can be obtained by performing feature mining on the fault analysis graph in the feature analysis layer; the fault analysis graph used for feature mining in the feature analysis layer can be generated by performing topology analysis on the operation data in the network topology layer.

[0065] In practical applications, the operation data of the target low-voltage distribution network can pass through the network topology layer, feature analysis layer, and fault analysis layer of the fault diagnosis and recognition model from top to bottom. Based on the network topology layer, topology analysis is performed on the operation data of the target low-voltage distribution network to generate a fault analysis graph. Then, based on the feature analysis layer, feature mining is performed according to the fault analysis graph to obtain fault feature data. Finally, based on the fault analysis layer, fault analysis is performed on the fault feature data to obtain the fault area and fault type of the target low-voltage distribution network.

[0066] Specifically, after inputting the temperature parameters, voltage parameters, current parameters, and power parameters of each node, as well as the output power and status information into the fault diagnosis and recognition model, topology analysis can be performed on the temperature parameters, voltage parameters, current parameters, and power parameters of each node, as well as the output power and status information in time series based on the network topology layer to generate a fault analysis graph.

[0067] Topology analysis mainly focuses on processing these data from the perspective of the network structure to generate a fault analysis graph that can reflect the relationship between the network structure and the operating state.

[0068] Optionally, the generation process of the fault analysis graph can be expressed as fusing the temperature parameters, voltage parameters, current parameters, and power parameters of each node to obtain the parameter vector of each node. Then, according to the parameter vectors between any two different nodes, as well as the output power and status information, calculate the topological connection strength between any two different nodes; construct a topological relationship matrix with the topological connection strength between any two nodes as matrix elements, and then update the value of each matrix element in the topological relationship matrix in time series to obtain the topological connection strength between any two nodes at a certain time point. And based on the topological connection strength between any two nodes at a certain time point mentioned above, construct a three-dimensional topological matrix. Furthermore, represent each node as the vertex of the graph, use the non-zero elements in the three-dimensional topological matrix as the weights of the edges, and generate a fault analysis graph through the minimum spanning tree of the topological relationship strength.

[0069] Exemplarily, assume that the temperature parameter of each node is T n , the voltage parameter of each node is V n , the current parameter of each node is I n, the power parameter of each node is W n , the output power is P D and the status information is S E . The network topology layer combines the temperature parameter T n , voltage parameter V n , current parameter I n and power parameter W n of each node to obtain the parameter vector of each node. Among them, the parameter vector of the nth node can be expressed as ; Further, the network topology layer can calculate the topological connection strength between any two different nodes according to the parameter vectors between any two different nodes, output power P D and status information S E , and the specific formula is as follows:

[0070]

[0071] where M ij can refer to the topological connection strength between node i and node j; T i can refer to the temperature parameter of node i, T j can refer to the temperature parameter of node j, V i can refer to the voltage parameter of node i, V j can refer to the voltage parameter of node j, I i can refer to the current parameter of node i, I j can refer to the current parameter of node j, W i can refer to the power parameter of node i, W j can refer to the power parameter of node j; d ij can refer to the distance between node i and node j, and this distance can be calculated based on the distance formula; α and β can refer to preset adjustment parameters; can refer to the exponential function. As an example, if the status information S E is in a normal state, then , as another example, if the status information S E is in an abnormal state, then .

[0072] Optionally, the network topology layer constructs an n*n-dimensional topological relationship matrix with the topological connection strength between any two nodes as matrix elements. Among them, when i = j in the topological relationship matrix, the matrix element M ij = 1; For a time series including m time points, each time point t = 1, 2,... m, the network topology layer updates the value of each matrix element in the topological relationship matrix according to the time series to obtain the topological connection strength A between any two nodes at time point titj , where A itj represents the topological relationship strength between node i and node j at time point t.

[0073] Optionally, the network topology layer can construct a three-dimensional topology matrix A according to the topological connection strength A between any two nodes at time point t, represent each node as a vertex of a graph, use the non-zero elements in the three-dimensional topology matrix A as the weights of the edges, and generate a fault analysis graph through the minimum spanning tree of the topological relationship strength. itj Specifically, for the algorithm of the fault analysis graph, the analysis is as follows:

[0074] Exemplarily, the algorithm of the fault analysis graph is analyzed as follows:

[0075]

[0076]

[0077] where Minimize represents the minimization operation, and subject to represents the constraint condition; represents for all nodes i, ; represents for all nodes j, ; x ij is used to indicate whether there is an edge connecting node i and node j. As an example, if there is an edge connecting node i and node i, then x ij = 1. As another example, if there is no edge connecting node i and node j, then x ij = 0.

[0078] The generated fault analysis graph can be used to indicate the specific location of the fault and the influence range of the fault on the low-voltage distribution network. By analyzing the nodes and connection relationships in the analysis graph, the feeder, distribution equipment, or user terminal where the fault is located can be quickly located; and, through the connection relationships and operation data such as current and voltage in the graph, information such as the power outage area and the number of affected users caused by the fault can be evaluated.

[0079] In some embodiments of the present application, after generating the fault analysis graph based on the network topology layer, the generated fault analysis graph can be feature-mined based on the feature analysis layer to obtain fault feature data.

[0080] Optionally, the fault feature data may include parameter association features and parameter change patterns between different parameters of each node, as well as parameter frequent itemsets of each node. Among them, the parameter association feature may refer to the mutual connection characteristics between different parameters of each node. For example, in a power system, there may be a certain association relationship between the mining power parameter and the output power of a certain node, or there may be a certain association relationship between the voltage parameter and the status information of a certain node. Analyzing the foregoing parameter association features can help determine whether the power system is operating normally. The parameter association feature in the embodiments of the present application may refer to a fault association relationship feature; the parameter change pattern may refer to the law or style presented by the parameters of each node changing over time or other factors, such as the current parameter change pattern, the temperature parameter change pattern, etc. The foregoing change patterns can usually reflect the change of the operating state of the power system; the parameter frequent itemset may refer to a set of items that frequently appear in the dataset. For the parameters of each node, the parameter frequent itemset may be manifested as a parameter combination that appears simultaneously. For example, in the records of multiple faults occurring, certain specific parameters of some nodes always appear together, and these parameter combinations can form a parameter frequent itemset. Analyzing the parameter frequent itemset helps quickly locate the key factor combinations that may cause faults.

[0081] Exemplarily, for the mining of parameter association features, it may specifically be manifested as:

[0082] The feature analysis layer can mine the first association feature between the power parameter and the output power according to the power parameters of each node in the fault analysis diagram and the output power of the distributed energy source. The specific formula may be as follows:

[0083]

[0084] Among them, may refer to the first association feature between the power parameter and the output power, may refer to the power parameter of node i, may refer to the average value of the power parameters of all nodes, may refer to the average output power of the distributed energy source over a period of time.

[0085] The feature analysis layer mines the second association feature between the voltage parameter and the status information according to the voltage parameters of each node in the fault analysis diagram and the status information of the energy storage device. The specific formula may be as follows:

[0086]

[0087] Among them, may refer to the second association feature between the voltage parameter and the status information, It represents the state information S of the energy storage device E entropy of It represents the entropy of all node voltage parameters; It can represent the state information S of the energy storage device E the joint entropy between the state information S of the energy storage device and the voltage parameters of all nodes, used to measure uncertainty.

[0088] Optionally, for the entropy the formula can be as follows:

[0089]

[0090] where k represents the state dimension of the state information S E and p1 represents the probability that the state information S E is in the first state. Similarly, the entropy can be calculated.

[0091] For the entropy the calculation formula is as follows:

[0092]

[0093] where, if it satisfies , for the state information S of the first state E its .

[0094] That is, the feature analysis layer can mine the first correlation feature between the power parameter and the output power , and the second correlation feature between the voltage parameter and the state information .

[0095] Exemplarily, for the mining of the parameter change pattern, the feature analysis layer determines the second-order difference in the time series according to the current parameters and temperature parameters of each node in the fault analysis diagram to determine the parameter change pattern. Optionally, the mined parameter change patterns can include the current parameter change pattern and the temperature parameter change pattern, and the specific formula can be as follows:

[0096]

[0097]

[0098] where represents the temperature parameter change pattern, represents the current parameter change pattern, represents the time series, T i represents the temperature parameter of node i, I i represents the current parameter of node i, represents the preset interval time.

[0099] Exemplarily, for the mining of parameter frequent itemsets, it can be manifested as calculating the weighted support based on the feature analysis layer to determine the frequent itemsets based on the weighted support.

[0100] Optionally, for each parameter, its importance can be measured by its weight coefficient. At this time, the weighted support of the parameter set can be calculated for this set. Assume that the parameter set in the embodiment of the present application is , for parameter g, its weight coefficient is w g , and it satisfies ; at this time, for an itemset , its weighted support The calculation formula can be as follows:

[0101]

[0102] Among them, Indicator(g,i) represents the indicator function. As an example, if there is valid data of parameter g at node i, then Indicator(g,i)=1; as another example, if there is no valid data of parameter g at the node, otherwise Indicator(g,i)=0.

[0103] Optionally, for the valid data of parameter g at node i, it can be understood that when the data of parameter g meets all the conditions of data integrity, data accuracy, data validity range, and data timeliness, it is considered that there is valid data of the parameter at the node. As an example, if there is no missing value in the data of parameter g at the node, it can be considered to meet the data integrity. For example, for the temperature parameter of the node, if the measurement device is working properly and can accurately record and transmit the temperature value of the node, and there is no situation where the temperature data is empty or not recorded, it can be considered that there is valid data of the temperature parameter at the node. If the temperature measurement device fails and causes the temperature data to be missing at a certain moment, it cannot be considered that there is valid data at that moment. As another example, when the acquired data is accurate and reliable and not affected by interference, incorrect measurement, or other factors causing data distortion, it can be considered to meet the data accuracy. For example, when measuring the voltage parameter of the node, the measuring instrument is not affected by electromagnetic interference, and the measurement result can truly reflect the actual voltage situation of the node. The aforementioned voltage data is valid data. If the measuring instrument itself has a fault or the surrounding environment interferes, resulting in a large deviation between the measured voltage value and the actual value, this data cannot be regarded as valid data. As yet another example, if the data value of parameter g is within a reasonable and meaningful range, it can be considered to meet the data validity range. Taking the output power of distributed energy as an example, in actual operation, its output power cannot be negative in some specific models. If the recorded output power of distributed energy at the node is negative, it means that this data is not within the valid range and cannot be considered valid data. Or for the status information of the energy storage device, there is a specific set of values (such as normal, faulty, charging, discharging, etc.). If the recorded status information is not within this set, it also belongs to invalid data. As yet another example, for some parameters that change with time, if the data is the latest and can reflect the current state of the node within its specific time requirements, it can be considered to meet the data timeliness. For example, in real-time fault diagnosis, the current parameter I of node i i needs to be updated in a timely manner to reflect the current current situation. If the acquired current data is from a long time ago, since the system operating state may have changed, then this data cannot meet the requirements of the current fault diagnosis and cannot be regarded as valid data.

[0104] Furthermore, as an example, when time, the item set o can be regarded as a frequent item set; when time, the item set o is not regarded as a frequent item set. It should be noted that According to the actual setting, the embodiments of the present application do not limit this.

[0105] In an embodiment of the present application, after the fault feature data is mined based on the feature analysis layer, the fault analysis layer can perform fault analysis on the fault feature data to obtain the fault area and fault type of the target low-voltage distribution network. Specifically, it can be manifested as performing fault area analysis based on the fault analysis layer according to the fault association relationship features and parameter frequent itemsets, outputting the fault area of the target low-voltage distribution network, and then performing fault type analysis based on the parameter change pattern according to the fault analysis layer, and outputting the fault type of the target low-voltage distribution network.

[0106] Exemplarily, for the analysis process of the fault area, the fault analysis layer can perform weighted calculation on the sum of the first association feature, the second association feature of all nodes in each area of the target low-voltage distribution network and the weighted support degree of all frequent itemsets to obtain the fault tendency score of each area in the target low-voltage distribution network. Optionally, if it is determined that the fault tendency score of a certain area is greater than or equal to the preset score, the fault analysis layer can determine that area as the fault area of the target low-voltage distribution network.

[0107] For the analysis process of the fault type, the fault analysis layer is based on the first parameter change pattern in the parameter change pattern and the second parameter change pattern , and performs fault type analysis with the help of the fault type table, and outputs the fault type of the target low-voltage distribution network. In one embodiment, the fault type table can refer to an association matching table established according to the parameter change pattern and its corresponding fault type. For example, it can be as shown in Table 1:

[0108] Table 1 Fault Type Table

[0109]

[0110] Through the network topology layer, feature analysis layer and fault analysis layer of the fault diagnosis and identification model from top to bottom in the embodiment of the present application, combined with the temperature parameters, voltage parameters, current parameters and power parameters of each node, the output power of distributed energy and the state information of energy storage devices, the real-time state of the low-voltage distribution network is comprehensively grasped and analyzed layer by layer, the fault area and fault type are quickly and accurately identified, and efficient energy scheduling is realized under complex and changeable fault scenarios, thereby improving the adaptability of the low-voltage distribution network.

[0111] Step S302, obtain the fault information of the fault area, perform policy matching in the preset energy scheduling strategy library based on the fault information and the fault type, and obtain at least one final candidate energy scheduling planning strategy;

[0112] In some embodiments of the present application, after quickly and accurately identifying the fault area and fault type, a target energy scheduling planning strategy for the fault area can be obtained based on the accurately identified fault area and fault type, which can obtain the corresponding energy scheduling planning strategy in a relatively short time under complex and changeable fault scenarios, improving the adaptability and response speed of the low-voltage distribution network.

[0113] In practical applications, the fault information of the fault area can be obtained, and strategy matching can be performed in a preset energy scheduling strategy library based on the fault information and fault type to obtain at least one final candidate energy scheduling planning strategy, so as to screen out the target energy scheduling planning strategy from at least one final candidate energy scheduling planning strategy.

[0114] Exemplarily, the fault information may include, but is not limited to, the fault size, fault level, and fault scope, etc. Among them, the fault size is the fault area where the fault occurs; the fault level can be used to characterize the importance of the fault area in the target low-voltage distribution network, usually reflected by the distance between the fault area and the load end. The closer the distance, the higher the level. Exemplarily, assuming that the fault level includes 3 levels, if the distance between the fault area and the load end is less than or equal to the first preset distance, the fault level is 3; if the distance between the fault area and the load end is greater than the first preset distance and less than or equal to the second preset distance, the fault level is 2; if the distance between the fault area and the load end is greater than the second preset distance, the fault level is 1; the fault scope can be used to characterize the number of user load communities connected by the fault area in the target low-voltage distribution network.

[0115] The process of performing strategy matching based on the fault information and fault type can be specifically manifested as follows. First, strategy matching is performed in the preset energy scheduling strategy library based on the fault type to obtain multiple initial candidate energy scheduling planning strategies. Then, the first fault severity coefficient can be determined according to the fault impact coefficient, fault level, and fault scope, so as to screen out at least one target candidate energy scheduling planning strategy from the multiple initial candidate energy scheduling planning strategies based on the first fault severity coefficient.

[0116] The preset energy scheduling policy library can store a collection of energy scheduling policies for various situations. In practical applications, each energy scheduling planning policy in the preset energy scheduling policy library can be pre-labeled with the applicable fault types. The energy scheduling terminal can perform policy matching in the preset energy scheduling policy library according to the fault type, and obtain all the energy scheduling planning policies applicable to the fault type in the preset energy scheduling policy library, so as to obtain multiple initial candidate energy scheduling planning policies. Exemplarily, assume that the preset energy scheduling policy library includes {Energy Scheduling Planning Policy 1, short circuit}, {Energy Scheduling Planning Policy 2, open circuit}, {Energy Scheduling Planning Policy 3, short circuit}, {Energy Scheduling Planning Policy 4, overload}, etc. When the fault type is a short circuit, the energy scheduling planning policies matched in the preset energy scheduling policy library can be Energy Scheduling Planning Policy 1 and Energy Scheduling Planning Policy 3.

[0117] Optionally, the energy scheduling terminal can calculate a first fault severity coefficient according to the fault magnitude, fault level, and fault scope. Among them, there is a mapping relationship between the fault magnitude and the fault impact coefficient. The fault level can represent the importance of the fault area in the target low-voltage distribution network, and the fault scope can represent the number of user load communities connected to the fault area in the target low-voltage distribution network. Specifically, it can be determined based on the fault impact coefficient, the importance of the fault area in the target low-voltage distribution network, and the number of user load communities connected to the fault area in the target low-voltage distribution network to determine the first fault severity coefficient.

[0118] Among them, the mapping relationship between the fault magnitude and the fault impact coefficient can be reflected based on a preset mapping table. The preset mapping table is an association table constructed in advance according to the mapping relationship between the fault magnitude and its corresponding fault impact coefficient. The energy scheduling terminal can first perform matching in the preset mapping table according to the fault magnitude, that is, obtain the fault impact coefficient corresponding to the fault magnitude according to the range where the fault magnitude is located, and then use the mapped and matched fault impact coefficient to determine the first fault severity coefficient.

[0119] Exemplarily, assume that the preset mapping table is {fault magnitude greater than 10, fault impact coefficient 10}, {fault magnitude in (5, 10], fault impact coefficient 8}, {fault magnitude in (1, 5], fault impact coefficient 5}, {fault magnitude less than 1, fault impact coefficient 1}. When the fault magnitude is 4, the fault impact coefficient matched in the preset mapping table can be the fault impact coefficient 5.

[0120] Optionally, the calculation formula of the first fault severity coefficient can be as follows:

[0121]

[0122] Among them, represents the first fault severity coefficient, represents the fault impact coefficient, represents the fault level; represents the fault scope, that is, the number of user load cells connected to the fault area.

[0123] It should be noted that each energy scheduling planning strategy in the embodiments of the present application is set with its applicable fault severity coefficient. The energy scheduling end can screen among multiple initial candidate energy scheduling planning strategies according to the first fault severity coefficient, and select the energy scheduling planning strategies with a fault severity coefficient greater than or equal to the first fault severity coefficient as the target candidate energy scheduling planning strategies.

[0124] In some embodiments of the present application, the at least one target candidate energy scheduling planning strategy obtained by the above screening may include a first energy scheduling planning strategy with the same fault severity coefficient as the first fault severity system. At this time, at least one final candidate energy scheduling planning strategy can be obtained based on the first energy scheduling planning strategy. Optionally, the at least one target candidate energy scheduling planning strategy may further include a second energy scheduling planning strategy, and the second energy scheduling planning strategy may refer to the strategies other than the first energy scheduling planning strategy among the at least one target candidate energy scheduling planning strategies.

[0125] In the embodiments of the present application, the first energy scheduling planning strategy can be used as the center to determine the strategy similarity and / or strategy relevance between the first energy scheduling planning strategy and each second energy scheduling planning strategy, and then at least one final candidate energy scheduling planning strategy in the target candidate energy scheduling planning strategy can be determined based on the strategy similarity and / or strategy relevance.

[0126] Optionally, for the calculation of the strategy similarity and / or strategy relevance, it can be realized through vector calculation.

[0127] Exemplarily, assume that the first strategy vector of the first energy scheduling planning strategy is , and the second strategy vector of the second energy scheduling planning strategy is , where N represents the vector dimension, and the specific calculation formula of the strategy similarity can be as follows:

[0128]

[0129] Among them, represents the strategy similarity between the first energy scheduling planning strategy T1 and the jth second energy scheduling planning strategy Z 2j , , when , it means that the first energy scheduling planning strategy T1 and the jth second energy scheduling planning strategy Z 2j are completely similar; when , indicating the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j is exactly the opposite; when it is, indicating the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j has no obvious similarity relationship. Indicates the energy interaction degree between the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j t i represents the i-th policy vector in the first policy vector z ji represents the i-th policy vector in the second policy vector

[0130] The specific calculation formula of the policy correlation degree can be shown as follows:

[0131]

[0132]

[0133]

[0134] Among them, indicates the policy correlation degree between the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j , , the larger the value, the stronger the correlation between the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j indicates the vector projection degree between the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j , represents the projection vector of the first policy vector on the second policy vector , represents the modulo operation.

[0135] In some embodiments of the present application, after calculating the policy similarity and policy correlation degree between the first energy scheduling planning strategy and each second energy scheduling planning strategy, the final correlation coefficient between the first energy scheduling planning strategy and each second energy scheduling planning strategy can be calculated to screen at least one final candidate energy scheduling planning strategy from the target candidate energy scheduling planning strategies based on the final correlation coefficient.

[0136] Exemplarily, the specific calculation formula for the final correlation coefficient can be shown as follows:

[0137] ​​

[0138] Among them, represents the final correlation coefficient between the first energy scheduling planning strategy T1 and the j-th second energy scheduling planning strategy Z 2j ; represents a preset coefficient, generally set to .

[0139] Optionally, after obtaining the final correlation coefficients between the first energy scheduling planning strategy and each second energy scheduling planning strategy, the energy scheduling terminal can traverse the final correlation coefficients between the first energy scheduling planning strategy and each second energy scheduling planning strategy, and determine the second energy scheduling planning strategy and the first energy scheduling planning strategy with the final correlation coefficient greater than or equal to the preset correlation coefficient as multiple final candidate energy scheduling planning strategies in the target candidate energy scheduling planning strategies. It should be noted that the preset correlation coefficient can be set based on actual needs, and the embodiments of the present application do not limit this.

[0140] Step S303, obtain the evaluation indexes of the target low-voltage distribution network, and perform strategy matching among at least one final candidate energy scheduling planning strategy based on the evaluation indexes to obtain the target energy scheduling planning strategy;

[0141] In some embodiments of the present application, after screening to obtain at least one final candidate energy scheduling planning strategy, the target energy scheduling planning strategy for the energy scheduling terminal to execute can be matched from at least one final candidate energy scheduling planning strategy based on the evaluation indexes.

[0142] Exemplarily, the energy scheduling terminal can obtain the historical energy scheduling data of each final candidate energy scheduling planning strategy based on the evaluation indexes, then perform energy scheduling prediction on each final candidate energy scheduling planning strategy based on the preset target optimization function and the historical energy scheduling data to obtain the comprehensive scheduling coefficients of each final candidate energy scheduling planning strategy, and further perform strategy matching among at least one final candidate energy scheduling planning strategy based on each comprehensive scheduling coefficient to obtain the target energy scheduling planning strategy.

[0143] Among them, the evaluation indexes can include but are not limited to power supply restoration time, energy utilization efficiency, scheduling cost, and equipment performance parameters, etc. The historical energy scheduling data obtained based on the evaluation indexes can include the historical restoration time, historical utilization efficiency, equipment operation and maintenance cost, and energy conversion equipment performance parameters of each final candidate energy scheduling planning strategy, etc. The historical restoration time is in hours, and the energy conversion equipment performance parameters are determined according to the operating state of the energy conversion equipment, and the value ranges from 1 to 100.

[0144] Optionally, the specific calculation formula of the comprehensive scheduling coefficient can be as follows:

[0145]

[0146] wherein, represents the comprehensive scheduling coefficient of the i-th final candidate energy scheduling planning strategy, represents the historical utilization efficiency of the i-th final candidate energy scheduling planning strategy, represents the historical recovery time of the i-th final candidate energy scheduling planning strategy, represents the equipment operation and maintenance cost of the i-th final candidate energy scheduling planning strategy, represents the performance parameters of the energy conversion equipment of the i-th final candidate energy scheduling planning strategy.

[0147] In practical applications, the energy scheduling terminal can screen out at least one initial energy scheduling planning strategy from multiple final candidate energy scheduling planning strategies based on the comprehensive scheduling coefficient. Specifically, it can traverse the comprehensive scheduling coefficients of each final candidate energy scheduling planning strategy, and determine the energy scheduling planning strategies with comprehensive scheduling coefficients greater than or equal to the preset scheduling coefficient among multiple final candidate energy scheduling planning strategies as at least one initial energy scheduling planning strategy; then, it can obtain the predicted load of the user load cell connected to the fault area at the current time, and determine the target energy scheduling planning strategy based on the predicted load and the available capacity of the energy supply sources of each initial energy scheduling planning strategy.

[0148] Among them, the predicted load can be predicted based on the historical load curve of the user load cell connected to the fault area. Specifically, it can obtain the historical load of the user load cell connected to the fault area at the current time as the predicted load of the user load cell connected to the fault area at the current time. In some embodiments of the present application, the energy scheduling terminal can determine the initial energy scheduling planning strategy with the available capacity of the energy supply source greater than the predicted load and the smallest available capacity of the energy supply source as the target energy scheduling planning strategy.

[0149] In one embodiment, assume that there are multiple initial energy scheduling planning strategies, such as {Initial Energy Scheduling Planning Strategy 1, available capacity of energy supply source 100}, {Initial Energy Scheduling Planning Strategy 2, available capacity of energy supply source 110}, {Initial Energy Scheduling Planning Strategy 3, available capacity of energy supply source 150}, {Initial Energy Scheduling Planning Strategy 4, available capacity of energy supply source 80}. Assume that the current predicted load is 100. At this time, filtering can be performed according to the predicted load of 100 to obtain Initial Energy Scheduling Planning Strategy 2 and Initial Energy Scheduling Planning Strategy 3. The available capacity of the energy supply source of Initial Energy Scheduling Planning Strategy 2 is the smallest. Therefore, Initial Energy Scheduling Planning Strategy 2 can be determined as the target energy scheduling planning strategy.

[0150] In the embodiment of the present application, the target energy scheduling planning strategy for the fault area is matched according to the historical recovery time, historical utilization efficiency, equipment operation and maintenance cost, and energy conversion equipment performance parameters of the energy scheduling planning strategy. It can match the scheduling planning strategy in a short time, reduce the calculation amount and calculation time, improve the response speed of the low-voltage distribution network, and thus ensure the reliable and stable operation of the low-voltage distribution network.

[0151] Step S304: Receive the load feedback information at the user load end after executing the target energy scheduling planning strategy;

[0152] Step S305: Construct a strategy optimization function based on the actual load information;

[0153] In some embodiments of the present application, the energy scheduling end executes the target energy scheduling planning strategy and conducts energy transmission for the user load community connected to the fault area according to the foregoing strategy. In order to further optimize the energy scheduling planning strategy and further improve the adaptability of the low-voltage distribution network, the energy scheduling end can receive the load feedback information fed back by the user load end of the user load community, so as to optimize the executed target energy scheduling planning strategy based on the fed-back load feedback information.

[0154] Optimizing the executed target energy scheduling planning strategy depends on the strategy optimization function. In practical applications, the strategy optimization function can be constructed based on the load feedback information, so as to realize strategy optimization based on the constructed strategy optimization function.

[0155] Optionally, the load feedback information may include actual load information, load change trend information, power supply feedback information, etc. Specifically, it can be manifested as determining the energy supply deviation value based on the available capacity of the energy supply source of the actual load information and the target energy scheduling planning strategy, and determining the degree of difference in the energy change trend based on the load change trend information and the energy change trend information of the target energy scheduling planning strategy, and then constructing a strategy optimization function with the energy supply deviation value, the degree of difference in the energy change trend, and the power supply feedback information.

[0156] Exemplarily, assume that the actual load information is , where M represents the information dimension, represents the actual load values at different times; the available capacity of the energy supply source of the target energy scheduling planning strategy is , where c i represents the available capacity of the energy supply source at the corresponding time. The specific calculation formula for the energy supply deviation value can be as follows:

[0157]

[0158] Among them, Indicates the energy supply deviation value.

[0159] The energy change trend information characterizes the energy supply quantity within a unit time. Assume that the load change trend information is expressed as , where represents the change amount of the load in the i-th time interval; the energy change trend information of the target energy scheduling planning strategy is expressed as , where represents the change amount of the corresponding energy supply in the i-th time interval. The specific formula for the degree of difference in energy change trends can be as follows:

[0160]

[0161] where represents the degree of difference in energy change trends.

[0162] In the process of constructing the strategy optimization function, assume that the power supply feedback information includes the first frequency of voltage instability occurrence, the second frequency of current frequency fluctuation occurrence, the first amplitude of voltage sag, the second amplitude of voltage swell, and harmonic content . Based on the energy supply deviation value , the degree of difference in energy change trends , the first frequency , the second frequency , the first amplitude , the second amplitude

[0163] and harmonic content , the constructed strategy optimization function can be expressed as: . In the above strategy optimization function, each factor can be combined through different non-linear functions. Exemplarily, the square can be taken for the energy supply deviation value , and the cube can be taken for the degree of difference in energy change trends , so that the contributions of the energy supply deviation value and the degree of difference in energy change trends in the optimization function are more non-linear; for the voltage-related parameters, the cosine function can be used to associate the second amplitude It can be associated with the sum of the arctangent function and and to reflect its comprehensive relationship with the energy supply deviation and trend difference. In this regard, the embodiments of the present application do not impose any restrictions.

[0164] Step S306: Optimize the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function to obtain the optimized target energy scheduling planning strategy;

[0165] In some embodiments of the present application, the optimization of the target energy scheduling planning strategy can be manifested as optimizing the strategy parameters in the target energy scheduling planning strategy with the goal of minimizing the power supply feedback information in the strategy optimization function to obtain the optimized target energy scheduling planning strategy. Specifically, it can be manifested as adjusting the energy supply per unit time in the target energy scheduling planning strategy, as well as the energy supply, current frequency, and harmonic content in the target energy scheduling planning strategy with the goal of minimizing the first frequency, second frequency, first amplitude, second amplitude, and harmonic content in the strategy optimization function to obtain the optimized target energy scheduling planning strategy, that is, the optimal energy scheduling planning strategy.

[0166] Optionally, the analysis can be combined with the simulated annealing algorithm. Assume that the energy supply per unit time in the target energy scheduling planning strategy is represented as , the energy supply is , the current frequency is , and the harmonic content is . Its analysis process can be manifested as follows: First, step 1 can be manifested as performing an initialization operation, for example, setting the initial temperature to , the initial solution to , the energy supply to , the current frequency to and the harmonic content to ; then step 2 can perform an iterative operation. For the current temperature , generate a new solution , a new energy supply , a new current frequency and a new harmonic content , obtained by making a small perturbation on the basis of the current solution; at this time, step 3 can calculate the energy difference , and step 4 can be manifested as if , then accept the new solution. If , then accept the new solution with a probability of ; step 5 can be manifested as reducing the temperature , where is the cooling factor, usually between 0 and 1. In this example, steps 2 to 5 can be repeated until the termination condition is met. The termination condition can be, for example, the temperature being lower than a preset threshold or the non - acceptance of new solutions for multiple consecutive times. It should be noted that the accepted new solution is the optimized target energy scheduling planning strategy, that is, the optimal energy scheduling planning strategy, and the embodiments of the present application do not limit this.

[0167] Step S307, execute the optimized target energy scheduling planning strategy.

[0168] When the distribution network planning system is in the operating environment of the low - voltage distribution network, after the energy scheduling terminal executes the target energy scheduling planning strategy and optimizes the executed target energy scheduling planning strategy, the energy scheduling terminal can execute the optimized target energy scheduling planning strategy, overcome the regional faults that occur in the target low - voltage distribution network when a new distribution transformer is built for the target low - voltage distribution network, improve the response speed of the low - voltage distribution network, and further improve the adaptability of the low - voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low - voltage distribution network.

[0169] In the embodiments of the present application, through the fault diagnosis and identification model combined with the operation data of the target low - voltage distribution network, the real - time state of the low - voltage distribution network is comprehensively analyzed layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, quickly and accurately identifying the fault area and fault type, and obtaining the target energy scheduling planning strategy for the fault area based on the accurately identified fault area and fault type, which can obtain the corresponding energy scheduling planning strategy in a relatively short time in a complex and changeable fault scenario, improving the adaptability of the low - voltage distribution network and the response speed of the low - voltage distribution network; and, the energy scheduling planning strategy can also be continuously optimized through the load feedback information of the user load end. Taking the power supply feedback information in the strategy optimization function constructed by the load feedback information as the target, the target energy scheduling planning strategy is optimized, and the optimized target energy scheduling planning strategy is executed, improving the response speed of the low - voltage distribution network and further improving the adaptability of the low - voltage distribution network, which is more conducive to ensuring the reliable and stable operation of the low - voltage distribution network.

[0170] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present application are not limited by the described action sequence, because according to the embodiments of the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential for the embodiments of the present application.

[0171] Refer to Figure 4, which shows a structural block diagram of an energy scheduling device for a low-voltage distribution network provided by an embodiment of the present application, applied to an energy scheduling terminal. The energy scheduling terminal has a fault diagnosis and recognition model, and specifically may include the following modules:

[0172] An operating data acquisition module 401, configured to acquire the operating data of a target low-voltage distribution network;

[0173] A fault diagnosis module 402, configured to respond to an input instruction for inputting the operating data of the target low-voltage distribution network into the fault diagnosis and recognition model, and obtain the fault area and fault type of the target low-voltage distribution network; wherein, the fault diagnosis and recognition model includes a network topology layer, a feature analysis layer, and a fault analysis layer. The fault area and fault type are obtained by performing fault analysis on fault feature data by the fault analysis layer. The fault feature data is obtained by performing feature mining on a fault analysis graph by the feature analysis layer. The fault analysis graph is generated by performing topology analysis on the operating data by the network topology layer;

[0174] A planning strategy generation module 403, configured to obtain a target energy scheduling planning strategy according to the fault area and the fault type;

[0175] A feedback information receiving module 404, configured to receive the load feedback information of a user load terminal after executing the target energy scheduling planning strategy; the load feedback information is used to construct a strategy optimization function;

[0176] An energy scheduling module 405, configured to optimize the target energy scheduling planning strategy with the power supply feedback information in the strategy optimization function as the target, obtain an optimized target energy scheduling planning strategy, and execute the optimized target energy scheduling planning strategy.

[0177] In an embodiment of the present application, the planning strategy generation module 403 may include the following sub-modules:

[0178] A planning strategy generation sub-module, configured to obtain the fault information of the fault area, perform strategy matching in a preset energy scheduling strategy library based on the fault information and the fault type, and obtain at least one final candidate energy scheduling planning strategy; obtain the evaluation index of the target low-voltage distribution network, and perform strategy matching in at least one final candidate energy scheduling planning strategy based on the evaluation index to obtain a target energy scheduling planning strategy.

[0179] In an embodiment of the present application, the fault information includes the fault size, fault level, and fault range. The fault level represents the importance of the fault area in the target low-voltage distribution network, and the fault range represents the number of user load communities connected to the fault area in the target low-voltage distribution network;

[0180] The planning strategy generation sub-module may include the following units:

[0181] A candidate planning strategy acquisition unit, configured to perform strategy matching in the preset energy scheduling strategy library based on the fault type to obtain multiple initial candidate energy scheduling planning strategies; determine a first fault severity coefficient based on the fault magnitude, the importance degree of the fault area in the target low-voltage distribution network, and the number of user load communities connected to the fault area in the target low-voltage distribution network; screen out at least one target candidate energy scheduling planning strategy from the multiple initial candidate energy scheduling planning strategies based on the first fault severity coefficient; the at least one target candidate energy scheduling planning strategy includes a first energy scheduling planning strategy with a fault severity coefficient the same as the first fault severity coefficient; obtain at least one final candidate energy scheduling planning strategy based on the first energy scheduling planning strategy.

[0182] In an embodiment of the present application, the candidate planning strategy acquisition unit may include the following sub-units:

[0183] A candidate planning strategy acquisition sub-unit, configured to determine the strategy similarity and / or strategy relevance between the first energy scheduling planning strategy and each second energy scheduling planning strategy with the first energy scheduling planning strategy as the center; the second energy scheduling planning strategy is a strategy other than the first energy scheduling planning strategy among the at least one target candidate energy scheduling planning strategies; determine at least one final candidate energy scheduling planning strategy in the target candidate energy scheduling planning strategies based on the strategy similarity and / or the strategy relevance.

[0184] In an embodiment of the present application, the planning strategy generation sub-module may include the following units:

[0185] A planning strategy generation unit, configured to obtain the historical energy scheduling data of each final candidate energy scheduling planning strategy based on the evaluation index; perform energy scheduling prediction on each final candidate energy scheduling planning strategy based on a preset target optimization function and the historical energy scheduling data to obtain a comprehensive scheduling coefficient of each final candidate energy scheduling planning strategy; screen out at least one initial energy scheduling planning strategy from the multiple final candidate energy scheduling planning strategies based on the comprehensive scheduling coefficient; obtain the predicted load of the user load community connected to the fault area at the current time; determine the target energy scheduling planning strategy based on the predicted load and the available capacity of the energy supply source of each initial energy scheduling planning strategy.

[0186] In an embodiment of the present application, the load feedback information includes actual load information, load change trend information, and power supply feedback information; after the load feedback information at the user load end, the device provided by the embodiment of the present application may further include the following modules:

[0187] A policy optimization function construction module, configured to determine an energy supply deviation value based on the actual load information and the available capacity of the energy supply sources in the target energy scheduling planning strategy; determine the degree of difference in the energy change trend based on the load change trend information and the energy change trend information in the target energy scheduling planning strategy; and construct a policy optimization function with the energy supply deviation value, the degree of difference in the energy change trend, and the power supply feedback information.

[0188] In an embodiment of the present application, the energy scheduling module 405 may include the following sub-modules:

[0189] An energy scheduling sub-module, configured to optimize the policy parameters in the target energy scheduling planning strategy with the goal of minimizing the power supply feedback information in the policy optimization function, so as to obtain an optimized target energy scheduling planning strategy.

[0190] In the embodiment of the present application, through the fault diagnosis and identification model combined with the operation data of the target low-voltage distribution network, the real-time state of the low-voltage distribution network is comprehensively analyzed layer by layer through the network topology layer, the feature analysis layer, and the fault analysis layer, the fault area and the fault type are quickly and accurately identified, and the target energy scheduling planning strategy for the fault area is obtained based on the accurately identified fault area and fault type, so that the corresponding energy scheduling planning strategy can be obtained in a relatively short time in a complex and changeable fault scenario, improving the adaptability of the low-voltage distribution network and the response speed of the low-voltage distribution network; and, the energy scheduling planning strategy can also be continuously optimized through the load feedback information at the user load end. Taking the power supply feedback information in the policy optimization function constructed by the load feedback information as the goal, the target energy scheduling planning strategy is optimized, and the optimized target energy scheduling planning strategy is executed. While improving the response speed of the low-voltage distribution network, the adaptability of the low-voltage distribution network is further improved, which is more conducive to ensuring the reliable and stable operation of the low-voltage distribution network.

[0191] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiment.

[0192] The embodiment of the present application further provides an electronic device. Referring to Figure 5 , the provided electronic device 500 includes a memory 510, a processor 520, and a computer program 511 stored on the memory 510 and capable of running on the processor 520. When the computer program 511 is executed by the processor, it implements each process of the above-mentioned method embodiment for energy scheduling of the low-voltage distribution network, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0193] The embodiment of the present application further provides a computer-readable storage medium. Referring toFigure 6 A computer program 511 is stored on the provided computer-readable storage medium 600. When the computer program 511 is executed by a processor, it implements each process of the above-mentioned embodiment of the energy scheduling method for a low-voltage distribution network and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0194] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other.

[0195] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of the embodiments of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules does not necessarily have to be limited to those steps or modules clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. The division of modules in the embodiments of the present application is only a logical division, and there may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the shown or discussed couplings, direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections between modules can be electrical or other similar forms, which are not limited in the embodiments of the present application. And the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed to multiple circuit modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.

[0196] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0197] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices and modules can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0198] In several embodiments provided by the embodiments of the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the device or module can be in an electrical, mechanical, or other form.

[0199] The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0200] In addition, in each embodiment of the embodiments of the present application, each functional module can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0201] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product.

[0202] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a Solid State Disk (SSD)).

[0203] Embodiments of the present application are described with reference to the flowcharts and / or block diagrams of methods, terminal 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, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0204] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks; these computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the functions inFigure 1 one process or multiple processes and / or blocks Figure 1 steps of functions specified in one block or multiple blocks.

[0205] Although the preferred embodiments of the embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts. 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 embodiments of the present application.

[0206] Finally, 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 the present application are all information and data that have been authorized by the user or fully authorized by all parties. Moreover, the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of the relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or reject.

[0207] The technical solutions provided by the embodiments of the present application have been introduced in detail above. Specific examples are used in the embodiments of the present application to elaborate on the principles and implementation manners of the embodiments of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the embodiments of the present application; at the same time, for those of ordinary skill in the art, based on the idea of the embodiments of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on the embodiments of the present application.

Claims

1. An energy scheduling method for a low-voltage distribution network, characterized in that, Relating to an energy dispatching terminal, the energy dispatching terminal has a fault diagnosis and recognition model, and the method includes: Obtain the operation data of the target low-voltage distribution network; Respond to the input instruction to input the operation data of the target low-voltage distribution network into the fault diagnosis and recognition model, and obtain the fault area and fault type of the target low-voltage distribution network; wherein, the fault diagnosis and recognition model includes a network topology layer, a feature analysis layer and a fault analysis layer, the fault area and fault type are obtained by the fault analysis layer performing fault analysis on the fault feature data, the fault feature data is obtained by the feature analysis layer performing feature mining on the fault analysis graph, and the fault analysis graph is generated by the network topology layer performing topology analysis on the operation data; the fault analysis graph is generated by constructing a three-dimensional topology matrix according to the topology connection strength between any two nodes at the same time point, representing each node as the vertex of the graph, using the non-zero elements in the three-dimensional topology matrix as the weight of the edge, and generating through the minimum spanning tree of the topology relationship strength; the topology connection strength between any two different nodes is calculated according to the parameter vectors between any two different nodes, as well as the output power and status information; the parameter vectors of each node are obtained by fusing the temperature parameter, voltage parameter, current parameter and power parameter of each node; the algorithm analysis of the fault analysis graph is as follows: ； ； Among them, Minimize represents the minimization operation, and subject to represents the constraint condition; M ij is the topological connection strength between node i and node j; represents for all nodes i, ; represents for all nodes j, ; x ij is used to indicate whether there is an edge connecting node i and node j; According to the fault area and the fault type, obtain the target energy dispatching planning strategy; Receive the load feedback information of the user load end after executing the target energy dispatching planning strategy; the load feedback information is used to construct a strategy optimization function; Optimize the strategy parameters in the target energy dispatching planning strategy with the goal of minimizing the power supply feedback information in the strategy optimization function, obtain the optimized target energy dispatching planning strategy and execute the optimized target energy dispatching planning strategy; the power supply feedback information includes the first frequency of voltage instability, the second frequency of current frequency fluctuation, the first amplitude of voltage sag, the second amplitude of voltage swell and the harmonic content, and the strategy optimization function is constructed based on the energy supply deviation value, the energy change trend difference degree, the first frequency, the second frequency, the first amplitude, the second amplitude and the harmonic content; the specific steps include: with the goal of minimizing the first frequency, the second frequency, the first amplitude, the second amplitude and the harmonic content in the strategy optimization function, adjust the energy supply amount per unit time in the target energy dispatching planning strategy, as well as the energy supply amount, current frequency and harmonic content in the target energy dispatching planning strategy, to obtain the optimized target energy dispatching planning strategy.

2. The method according to claim 1, characterized in that, The obtaining the target energy dispatching planning strategy according to the fault area and the fault type includes: Obtain the fault information of the fault area, perform strategy matching in the preset energy dispatching strategy library based on the fault information and the fault type, and obtain at least one final candidate energy dispatching planning strategy; Obtain the evaluation indexes of the target low-voltage distribution network, and perform strategy matching among at least one final candidate energy scheduling planning strategy based on the evaluation indexes to obtain the target energy scheduling planning strategy.

3. The method according to claim 2, wherein The fault information includes the fault size, fault level, and fault scope. The fault level represents the importance of the fault area in the target low-voltage distribution network, and the fault scope represents the number of user load communities connected by the fault area in the target low-voltage distribution network. The performing strategy matching in a preset energy scheduling strategy library based on the fault information and the fault type to obtain at least one final candidate energy scheduling planning strategy includes: Perform strategy matching in the preset energy scheduling strategy library based on the fault type to obtain multiple initial candidate energy scheduling planning strategies. Determine a first fault severity coefficient based on the fault size, the importance of the fault area in the target low-voltage distribution network, and the number of user load communities connected by the fault area in the target low-voltage distribution network. Based on the first fault severity coefficient, screen out at least one target candidate energy scheduling planning strategy from the multiple initial candidate energy scheduling planning strategies; the at least one target candidate energy scheduling planning strategy includes a first energy scheduling planning strategy with a fault severity coefficient the same as the first fault severity coefficient. Based on the first energy scheduling planning strategy, obtain at least one final candidate energy scheduling planning strategy.

4. The method according to claim 3, characterized in that, The obtaining at least one final candidate energy scheduling planning strategy based on the first energy scheduling planning strategy includes: Taking the first energy scheduling planning strategy as the center, determine the strategy similarity and / or strategy relevance between the first energy scheduling planning strategy and each second energy scheduling planning strategy; the second energy scheduling planning strategy is the strategy other than the first energy scheduling planning strategy among the at least one target candidate energy scheduling planning strategies. Based on the strategy similarity and / or the strategy relevance, determine at least one final candidate energy scheduling planning strategy among the target candidate energy scheduling planning strategies.

5. The method according to claim 2, wherein The performing strategy matching among at least one final candidate energy scheduling planning strategy based on the evaluation indexes to obtain the target energy scheduling planning strategy includes: Obtain the historical energy scheduling data of each final candidate energy scheduling planning strategy based on the evaluation indexes. Perform energy scheduling prediction on each final candidate energy scheduling planning strategy based on a preset target optimization function and the historical energy scheduling data to obtain the comprehensive scheduling coefficient of each final candidate energy scheduling planning strategy. Based on the comprehensive scheduling coefficient, screen out at least one initial energy scheduling planning strategy from the multiple final candidate energy scheduling planning strategies. Obtain the predicted load of the user load communities connected by the fault area at the current time. Based on the predicted load and the available capacity of the energy supply sources of each initial energy scheduling planning strategy, determine the target energy scheduling planning strategy.

6. The method according to claim 1, wherein The load feedback information includes actual load information, load change trend information, and power supply feedback information. After the load feedback information at the user load end, the method further includes: Determine an energy supply deviation value based on the available capacity of the energy supply source according to the actual load information and the target energy scheduling planning strategy; Determine the degree of difference in the energy change trend based on the load change trend information and the energy change trend information of the target energy scheduling planning strategy; Construct a strategy optimization function with the energy supply deviation value, the degree of difference in the energy change trend, and the power supply feedback information.

7. An energy scheduling device for a low-voltage distribution network, characterized in that, Applied to the energy scheduling terminal, the energy scheduling terminal has a fault diagnosis and identification model, and the device includes: An operation data acquisition module for acquiring the operation data of the target low-voltage distribution network; A fault diagnosis module for obtaining the fault area and fault type of the target low-voltage distribution network in response to an input instruction to input the operation data of the target low-voltage distribution network into the fault diagnosis and identification model; wherein, the fault diagnosis and identification model includes a network topology layer, a feature analysis layer, and a fault analysis layer, the fault area and fault type are obtained by performing fault analysis on fault feature data by the fault analysis layer, the fault feature data is obtained by performing feature mining on a fault analysis graph by the feature analysis layer, and the fault analysis graph is generated by performing topology analysis on the operation data by the network topology layer; the fault analysis graph is generated by constructing a three-dimensional topology matrix according to the topology connection strength between any two nodes at the same time point, representing each node as a vertex of the graph, taking the non-zero elements in the three-dimensional topology matrix as the weights of the edges, and generating a minimum spanning tree of the topology relationship strength; the topology connection strength between any two different nodes is calculated according to the parameter vectors between any two different nodes, as well as the output power and status information; the parameter vectors of each node are obtained by fusing the temperature parameter, voltage parameter, current parameter, and power parameter of each node; the algorithm analysis of the fault analysis graph is as follows: ； ； Among them, Minimize represents the minimization operation, and subject to represents the constraint condition; M ij is the topological connection strength between node i and node j; represents for all nodes i, ; represents for all nodes j, ; x ij is used to indicate whether there is an edge connection between node i and node j; A planning strategy generation module for obtaining a target energy scheduling planning strategy according to the fault area and the fault type; A feedback information receiving module for receiving the load feedback information of the user load terminal after executing the target energy scheduling planning strategy; the load feedback information is used to construct a strategy optimization function; An energy scheduling module is configured to optimize the policy parameters in the target energy scheduling planning policy with the goal of minimizing the power supply feedback information in the policy optimization function, obtain the optimized target energy scheduling planning policy, and execute the optimized target energy scheduling planning policy; the power supply feedback information includes the first frequency of voltage instability, the second frequency of current frequency fluctuation, the first amplitude of voltage sag, the second amplitude of voltage swell, and the harmonic content, and the policy optimization function is constructed based on the energy supply deviation value, the degree of difference in energy change trend, the first frequency, the second frequency, the first amplitude, the second amplitude, and the harmonic content; the specific steps include: adjusting the energy supply amount per unit time in the target energy scheduling planning policy, as well as the energy supply amount, current frequency, and harmonic content in the target energy scheduling planning policy, with the goal of minimizing the first frequency, the second frequency, the first amplitude, the second amplitude, and the harmonic content in the policy optimization function, to obtain the optimized target energy scheduling planning policy.

8. An electronic device, characterized in that, It includes: A processor, a memory, and a computer program stored on the memory and capable of running on the processor, where when the computer program is executed by the processor, it implements the energy scheduling method for the low-voltage distribution network according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the energy scheduling method for the low-voltage distribution network according to any one of claims 1 to 6.

Images