Power distribution network multi-target reconstruction strategy self-healing control method and system

Abstract

The invention discloses a power distribution network multi-target reconstruction strategy self-healing control method and system, and the method comprises the steps: collecting the parameters and operation data of a power distribution network, and constructing a power distribution network reconstruction model; and processing the operation data of the power distribution network to obtain node operation data and branch operation data. And based on a mixed integer programming algorithm, solving the power distribution network reconstruction model to obtain a reconstruction solution set. And solving the reconstruction solution set to obtain an optimal reconstruction strategy. According to the power distribution network multi-target reconstruction strategy self-healing control method and system, dictionary learning and compressed sensing technologies are adopted, the data dimension can be effectively reduced, key information is extracted, and the data processing efficiency and accuracy are improved. The power distribution network reconstruction model is solved based on a mixed integer programming algorithm, and multiple optimization targets can be considered at the same time. And solving the reconstruction solution set, and selecting an optimal reconstruction strategy, so that the voltage stability can be maximized while the power loss is minimized, and the self-healing control of the power distribution network is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization, and in particular to a distribution network multi-objective reconstruction strategy self-healing control method and system. Background Art

[0002] As an important technical means in power system optimization, distribution network reconstruction strategy has received extensive attention and research in recent years. Traditional distribution network reconstruction methods mainly rely on heuristic algorithms and optimization models to optimize the operating efficiency and reliability of the power system by adjusting the switch state and grid structure. With the development of smart grid technology, distribution network reconstruction technology has gradually introduced more modern computing methods and optimization algorithms, such as mixed integer programming (MIP), genetic algorithm (GA), particle swarm optimization (PSO), etc. These methods have achieved remarkable results in improving computing efficiency and optimization effects. However, the existing technology still has shortcomings in multi-objective optimization and self-healing control, and it is difficult to balance multiple objectives and achieve system self-healing at the same time.

[0003] Existing distribution network reconstruction technology mainly faces the following challenges: First, in terms of multi-objective optimization, existing methods can only handle a single objective, and it is difficult to consider the comprehensive optimization of multiple objectives such as power loss and voltage stability at the same time; second, in terms of self-healing control, existing methods lack the ability to efficiently process and analyze real-time data, and cannot respond to system failures and abnormal conditions in a timely manner; finally, in terms of data processing and model building, existing technologies have limited processing capabilities for large-scale, high-dimensional data, and it is difficult to effectively extract and utilize key information in the data. These deficiencies limit the application and promotion of distribution network reconstruction technology in complex power grid environments. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problems solved by the present invention are: in terms of multi-objective optimization, existing methods can often only handle a single objective, and it is difficult to simultaneously consider the comprehensive optimization of multiple objectives such as power loss and voltage stability; in terms of self-healing control, existing methods lack the ability to efficiently process and analyze real-time data, and cannot respond to system failures and abnormal conditions in a timely manner; in terms of data processing and model building, existing technologies have limited processing capabilities for large-scale, high-dimensional data, and it is difficult to effectively extract and utilize key information in the data.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a distribution network multi-objective reconstruction strategy self-healing control method, comprising: collecting distribution network parameters and operation data, and constructing a distribution network reconstruction model.

[0007] The distribution network operation data is processed to obtain node operation data and branch operation data.

[0008] Based on the mixed integer programming algorithm, the distribution network reconstruction model is solved to obtain the reconstruction solution set.

[0009] Solve the reconstruction solution set and obtain the optimal reconstruction strategy.

[0010] As a preferred solution of the self-healing control method for the multi-objective reconstruction strategy of the distribution network described in the present invention, wherein: the distribution network parameters include node parameters and branch parameters.

[0011] Node parameters include node voltage, node current and node load.

[0012] The branch parameters include branch resistance, branch reactance and branch current.

[0013] Operation data includes real-time load data, voltage data and current data.

[0014] As a preferred solution of the self-healing control method of the distribution network multi-objective reconstruction strategy described in the present invention, wherein: the construction of the distribution network reconstruction model includes that the construction of the distribution network reconstruction model should comprehensively consider the distribution network topology, nodes, branch parameters and load conditions, and the node voltage equation is expressed as:

[0015]

[0016] Among them, V i represents the voltage of node iii, Ω(i) represents the set of nodes adjacent to node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, X ij Represents the reactance between node i and node j.

[0017] The node power balance equation is expressed as:

[0018]

[0019] Among them, P i represents the active power of node i, Q i represents the reactive power of node i, I * ij Represents the conjugate complex number of the current between node i and node j.

[0020] The branch current is expressed as:

[0021]

[0022] Among them, I ij represents the current between branch i and node j.

[0023] The system loss is expressed as:

[0024] Among them, P loss represents the total system loss, E represents the set of all branches in the system, and I ij Represents the relationship between branch i and node

[0025] The current between points j, R ij Represents the resistance of the branch.

[0026] The comprehensive formula for constructing the distribution network reconstruction model is expressed as:

[0027]

[0028] Among them, j ’ Represents an imaginary unit.

[0029] As a preferred solution of the distribution network multi-objective reconstruction strategy self-healing control method described in the present invention, wherein: the processing of the distribution network operation data includes processing the distribution network operation data through dictionary learning and compressed sensing to obtain node operation data and branch operation data.

[0030] First, the distribution network data is standardized and expressed as:

[0031]

[0032] Among them, μ X represents the mean of the node data, σ X Represents the standard deviation of node data, μ Y represents the mean of the branch data, σ Y Represents the standard deviation of the branch data.

[0033] Use dictionary learning to represent the preprocessed data and find a set of dictionaries D X and D Y , so that the node data and branch data can be sparsely represented, and the dictionary learning model is expressed as:

[0034]

[0035] Among them, D X Dictionary matrix representing node data, D Y A is the dictionary matrix representing the branch data. X represents the sparse representation matrix, A Y represents the sparse representation matrix, λ X represents the sparse regularization parameter, λ Y represents the sparsity regularization parameter.

[0036] The sparsely represented node data and branch data are reconstructed through compressed sensing to reduce the data dimension and extract features. The compressed sensing model is expressed as:

[0037] z X =Φ X a X ,z Y =Φ Y a Y

[0038] Among them, Φ X Represents the measurement matrix of node data, Φ Y Represents the measurement matrix of branch data, z X represents the node data after compressed sensing, z Y represents the branch data after compressed sensing, a X Represents the node data of sparse representation, a Y Represents branch data of sparse representation.

[0039] Compressed sensing reconstruction is expressed as:

[0040]

[0041] The sparse representation obtained by reconstruction Further used to restore the original data:

[0042]

[0043] De-standardize the recovered data to obtain the processed node operation data and branch operation data, which are expressed as:

[0044]

[0045] Among them, the node voltage range is 0 to 1.2 times the rated voltage, and the branch current range is 0 to 1.5 times the rated current.

[0046] As a preferred solution of the self-healing control method of the distribution network multi-objective reconstruction strategy described in the present invention, the mixed integer programming algorithm includes defining decision variables, including continuous variables and integer variables.

[0047] Continuous variables include node voltages and branch currents, and integer variables include switch states.

[0048] The objective function remains unchanged, and the constraints are selected as node voltage constraints, branch current constraints, power balance constraints, switch state constraints and topology constraints.

[0049] The mixed integer programming model for distribution network reconstruction is expressed as:

[0050]

[0051]

[0052]

[0053]

[0054]

[0055]

[0056] Among them, V i represents the voltage at node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, P i represents the active power of node i, Q i represents the reactive power of node i, x ij Represents the switch state between node i and node j, 0 means open, 1 means closed. V min Indicates the minimum value of the node voltage, V max Indicates the maximum value of the node voltage, I ij max represents the maximum current between node i and node j. E represents the set of all branches in the system, and Ω(i) represents the set of nodes adjacent to node i.

[0057] As a preferred solution of the self-healing control method of the multi-objective reconstruction strategy of the distribution network described in the present invention, wherein: the solving the reconstruction solution set to obtain the optimal reconstruction strategy includes, the reconstruction solution set S is a set of possible reconstruction schemes obtained by a mixed integer programming algorithm, each scheme includes node voltage, branch current, switch state and power loss, and the reconstruction solution set is expressed as:

[0058]

[0059] Among them, k represents the reconstruction scheme index, and K represents the number of reconstruction solution sets.

[0060] Solve the reconstructed solution set and select the objective function for optimization, with minimizing power loss as the main goal:

[0061]

[0062] A multi-objective optimization model is constructed to maximize voltage stability while minimizing power loss, expressed as:

[0063]

[0064] Among them, α represents the weight coefficient of power loss, β represents the weight coefficient of voltage deviation, V nominal Indicates the rated value of the node voltage, P loss k represents the power loss of reconstruction scheme k, V i k represents the node voltage of reconstruction scheme k, Indicates the deviation of the node voltage from the rated value.

[0065] As a preferred solution of the self-healing control method for multi-objective reconstruction strategy of distribution network described in the present invention, wherein: solving the reconstruction solution set to obtain the optimal reconstruction strategy also includes, the solution process includes:

[0066] Calculate the power loss. For each solution k in the reconstruction solution set S, calculate the total power loss.

[0067] For each solution k in the reconstructed solution set S, the deviation between the node voltage and the rated value is calculated.

[0068] By comprehensively considering the power loss and voltage deviation, the objective function value of each scheme is calculated.

[0069] The solution with the smallest objective function value is selected from the reconstruction solution set as the optimal reconstruction strategy.

[0070] A self-healing control system for a distribution network with a multi-objective reconstruction strategy, characterized in that:

[0071] Build a model module, collect distribution network parameters and operation data, and build a distribution network reconstruction model.

[0072] The preprocessing module processes the distribution network operation data to obtain node operation data and branch operation data.

[0073] The solution module solves the distribution network reconstruction model based on the mixed integer programming algorithm to obtain the reconstruction solution set. The reconstruction solution set is solved to obtain the optimal reconstruction strategy.

[0074] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0075] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0076] The beneficial effects of the present invention are as follows: the use of dictionary learning and compressed sensing technology can effectively reduce data dimensions, extract key information, and improve data processing efficiency and accuracy. The distribution network reconstruction model is solved based on the mixed integer programming algorithm, and multiple optimization objectives can be considered at the same time. The reconstruction solution set is solved and the optimal reconstruction strategy is selected, which can minimize power loss while maximizing voltage stability, and realize self-healing control of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0078] Figure 1 An overall flow chart of a distribution network multi-objective reconstruction strategy self-healing control method provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0080] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a distribution network multi-objective reconstruction strategy self-healing control method, comprising:

[0081] S1: Collect distribution network parameters and operation data, and build a distribution network reconstruction model.

[0082] Distribution network parameters include node parameters and branch parameters.

[0083] Node parameters include node voltage, node current and node load.

[0084] The branch parameters include branch resistance, branch reactance and branch current.

[0085] Operation data includes real-time load data, voltage data and current data.

[0086] To construct the distribution network reconstruction model, the topological structure, nodes, branch parameters and load conditions of the distribution network should be considered comprehensively. The node voltage equation is expressed as:

[0087]

[0088] Among them, V i represents the voltage of node iii, Ω(i) represents the set of nodes adjacent to node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, X ij represents the reactance between node i and node j.

[0089] The node power balance equation is expressed as:

[0090]

[0091] Among them, P i represents the active power of node i, Q i represents the reactive power of node i, I * ij Represents the conjugate complex number of the current between node i and node j.

[0092] The branch current is expressed as:

[0093]

[0094] Among them, I ij represents the current between branch i and node j.

[0095] The system loss is expressed as:

[0096] Among them, P loss represents the total system loss, E represents the set of all branches in the system, and I ij Represents the relationship between branch i and node

[0097] The current between points j, R ij Represents the resistance of the branch.

[0098] The comprehensive formula for constructing the distribution network reconstruction model is expressed as:

[0099]

[0100] Among them, j ’ Represents an imaginary unit.

[0101] It should be noted that the core idea of ​​designing the distribution network reconstruction model is to achieve an accurate description of the system operation status through comprehensive analysis and modeling of the topological structure, node parameters and branch parameters of the distribution network. First, the basic parameters of the distribution network, such as node voltage, node current, node load, branch resistance and reactance, are collected. Then, the electrical model of the system is established by constructing the node voltage equation, node power balance equation and branch current calculation formula. Finally, these equations are combined to form an optimization model containing multiple constraints and objective functions. This model can optimize the operation efficiency of the power grid while ensuring the stability and reliability of the system. It provides a systematic and scientific tool to describe and analyze the operation status of the distribution network. Through precise mathematical description and comprehensive parameter consideration, the model can accurately reflect the operation characteristics and potential problems of the system. In addition, by optimizing the objective function, the operation efficiency of the power grid can be significantly improved and the operating cost can be reduced.

[0102] S2: Process the distribution network operation data to obtain node operation data and branch operation data.

[0103] The distribution network operation data is processed through dictionary learning and compressed sensing to obtain node operation data and branch operation data.

[0104] First, the distribution network data is standardized and expressed as:

[0105]

[0106] Among them, μ X represents the mean of the node data, σ X Represents the standard deviation of node data, μ Y represents the mean of the branch data, σ Y Represents the standard deviation of the branch data.

[0107] Use dictionary learning to represent the preprocessed data and find a set of dictionaries D X and D Y , so that the node data and branch data can be sparsely represented, and the dictionary learning model is expressed as:

[0108]

[0109] Among them, D X Dictionary matrix representing node data, D Y A is the dictionary matrix representing the branch data. X represents the sparse representation matrix, A Y represents the sparse representation matrix, λ X represents the sparse regularization parameter, λ Y represents the sparsity regularization parameter.

[0110] The sparsely represented node data and branch data are reconstructed through compressed sensing to reduce the data dimension and extract features. The compressed sensing model is expressed as:

[0111] z X =Φ X a X ,z Y =Φ Y aY

[0112] Among them, Φ X Represents the measurement matrix of node data, Φ Y Represents the measurement matrix of branch data, z X represents the node data after compressed sensing, z Y represents the branch data after compressed sensing, a X Represents the node data of sparse representation, a Y Represents branch data of sparse representation.

[0113] Compressed sensing reconstruction is expressed as:

[0114]

[0115] The sparse representation obtained by reconstruction Further used to restore the original data:

[0116]

[0117] De-standardize the recovered data to obtain the processed node operation data and branch operation data, which are expressed as:

[0118]

[0119] Among them, the node voltage range is 0 to 1.2 times the rated voltage, and the branch current range is 0 to 1.5 times the rated current.

[0120] It should be noted that the design idea of ​​dictionary learning and compressed sensing technology is to effectively process and extract key information from high-dimensional operation data through sparse representation and dimensionality reduction technology. First, the collected operation data is preprocessed, such as denoising and standardization. Then, using dictionary learning technology, a sparse dictionary that adapts to the characteristics of the data is constructed, and through sparse representation, the complex high-dimensional data is represented as a small number of important basis vector combinations. Subsequently, compressed sensing technology is applied to reduce the dimensionality of the sparsely represented data, further compress the data volume, and extract key information. The advantage of using dictionary learning and compressed sensing technology is that it can significantly reduce the complexity of data storage and processing, and improve the efficiency and accuracy of data processing. Sparse representation not only reduces the dimension of the data, but also retains the key features of the data, which is convenient for subsequent analysis and optimization. In addition, compressed sensing technology can effectively cope with the challenges of high-dimensional data, reconstruct the original signal through a small amount of observation data, and has high robustness and noise resistance. These technologies can perform well in data processing scenarios with high real-time requirements, improving the response speed and overall performance of the system.

[0121] S3: Based on the mixed integer programming algorithm, the distribution network reconstruction model is solved to obtain the reconstruction solution set.

[0122] Define decision variables, including continuous variables and integer variables.

[0123] Continuous variables include node voltages and branch currents, and integer variables include switch states.

[0124] The objective function remains unchanged, and the constraints are selected as node voltage constraints, branch current constraints, power balance constraints, switch state constraints and topology constraints.

[0125] It should be noted that the design idea of ​​the mixed integer programming (MIP) model is to achieve multi-objective comprehensive optimization by converting the distribution network reconstruction problem into an optimization problem containing continuous and discrete variables. First, the decision variables are defined, including continuous variables such as node voltage and branch current and discrete variables such as switch state. Then, the optimization objective function is constructed, such as minimizing the system power loss, and multiple constraints are set at the same time, including node voltage constraints, branch current constraints, power balance constraints and topology constraints. By solving the optimization model, the optimal distribution network topology and operation strategy are determined.

[0126] The mixed integer programming model for distribution network reconstruction is expressed as:

[0127]

[0128]

[0129]

[0130]

[0131]

[0132]

[0133] Among them, V i represents the voltage at node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, P i represents the active power of node i, Q i represents the reactive power of node i, x ij Represents the switch state between node i and node j, 0 means open, 1 means closed. V min Indicates the minimum value of the node voltage, V max Indicates the maximum value of the node voltage, I ij max represents the maximum current between node i and node j. E represents the set of all branches in the system, and Ω(i) represents the set of nodes adjacent to node i.

[0134] It should be noted that the mixed integer programming model can handle multiple optimization objectives and constraints at the same time and provide a global optimal solution. In the distribution network reconstruction problem, the MIP model can comprehensively consider the economy and reliability of the system, and optimize the operating state of the system through precise mathematical description and efficient solution algorithm. Compared with traditional heuristic algorithms, the MIP model has obvious advantages in calculation accuracy and solution efficiency, and can provide reliable optimization results in a short time. In addition, the flexibility of the MIP model makes it suitable for power grid reconstruction problems of various scales and complexities, providing a powerful tool for the optimized operation of smart grids.

[0135] S4: Solve the reconstruction solution set and obtain the optimal reconstruction strategy.

[0136] It should be noted that the design idea of ​​solving the reconstruction solution set is to determine the optimal distribution network reconstruction strategy by comprehensively evaluating and optimizing multiple possible reconstruction schemes. First, based on the mixed integer programming algorithm, a set of possible reconstruction schemes are generated, each of which contains parameters such as node voltage, branch current, switch state, and total system loss. Then, a multi-objective optimization model is constructed to define comprehensive evaluation criteria, such as minimizing power loss and maximizing voltage stability. By calculating the objective function value of each scheme, the optimal scheme is selected as the final reconstruction strategy.

[0137] The reconstruction solution set S is a set of possible reconstruction schemes obtained by the mixed integer programming algorithm. Each scheme includes node voltage, branch current, switch state and power loss. The reconstruction solution set is expressed as:

[0138]

[0139] Among them, k represents the reconstruction scheme index, and K represents the number of reconstruction solution sets.

[0140] Solve the reconstructed solution set and select the objective function for optimization, with minimizing power loss as the main goal:

[0141]

[0142] A multi-objective optimization model is constructed to maximize voltage stability while minimizing power loss, expressed as:

[0143]

[0144] Among them, α represents the weight coefficient of power loss, β represents the weight coefficient of voltage deviation, V nominal Indicates the rated value of the node voltage, P loss k represents the power loss of reconstruction scheme k, V i k represents the node voltage of reconstruction scheme k, Indicates the deviation of the node voltage from the rated value.

[0145] The solution process includes:

[0146] Calculate the power loss. For each solution k in the reconstruction solution set S, calculate the total power loss.

[0147] For each solution k in the reconstructed solution set S, the deviation between the node voltage and the rated value is calculated.

[0148] By comprehensively considering the power loss and voltage deviation, the objective function value of each scheme is calculated.

[0149] The solution with the smallest objective function value is selected from the reconstruction solution set as the optimal reconstruction strategy.

[0150] The above embodiments also include a distribution network multi-objective reconstruction strategy self-healing control system, specifically:

[0151] Build a model module, collect distribution network parameters and operation data, and build a distribution network reconstruction model.

[0152] The preprocessing module processes the distribution network operation data to obtain node operation data and branch operation data.

[0153] The solution module solves the distribution network reconstruction model based on the mixed integer programming algorithm to obtain the reconstruction solution set. The reconstruction solution set is solved to obtain the optimal reconstruction strategy.

[0154] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of a power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method is implemented.

[0155] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0156] Example 2, an embodiment of the present invention, provides a distribution network multi-objective reconstruction strategy self-healing control method and system. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0157] In order to verify the effectiveness of a self-healing control method for a multi-objective reconstruction strategy of a distribution network, a systematic experimental comparative study was conducted. The experimental preparation work includes selecting experimental objects, setting up the experimental environment, determining experimental parameters, and preparing experimental tools. The experimental objects include different distribution network configurations and operation strategies, which are compared using the existing technical methods and the methods of the present invention. This experiment uses two existing technologies, the heuristic algorithm method and the static optimization method, as comparisons. The experimental environment is set as a simulated distribution network system with real-time data acquisition, processing and analysis functions. The experimental parameters include node voltage (V), node current (I), node load (P), branch resistance (R), branch reactance (X) and total system loss (P_loss). The experimental tools include data acquisition devices, simulation software and data analysis tools.

[0158] The implementation process is as follows:

[0159] Distribution network parameter collection: Use data acquisition devices to collect parameters of each node and branch in the simulated distribution network system, including node voltage, node current, node load, branch resistance and branch reactance. The collected data is used to build a distribution network reconstruction model.

[0160] Operation data processing: The collected operation data is processed through dictionary learning and compressed sensing technology. First, the data is standardized, and then a set of sparsely represented dictionary matrices is found through dictionary learning. Then, compressed sensing technology is used to reduce the dimension of the data and extract key features, and finally the node operation data and branch operation data are obtained.

[0161] Reconstruction model solution: Based on the mixed integer programming algorithm, the constructed distribution network reconstruction model is solved to obtain a set of possible reconstruction schemes. The goal is to minimize the power loss of the system and improve voltage stability by adjusting the switch state and control variables.

[0162] Optimal reconstruction strategy selection: Solve the reconstruction solution set, and select the reconstruction solution with the smallest power loss and voltage deviation as the optimal reconstruction strategy through a multi-objective optimization method. Compare and analyze the optimization effects and performances of the prior art method and the method of the present invention. The experimental results are shown in Table 1.

[0163]

[0164]

[0165] It can be seen from the table data that the method of the present invention is superior to the prior art method in multiple key parameters. The node voltage of the method of the present invention is stable between 1.00-1.02, which is significantly higher than 0.95-0.98 of the prior art method. This shows that the method of the present invention has significant advantages in optimizing voltage stability, can better keep the node voltage near the rated value, and improve the stability and reliability of the system.

[0166] The node current range of the method of the present invention is 47-49 amperes, which is significantly lower than the 50-52 amperes of the prior art method. This means that the method of the present invention can effectively reduce the node current, reduce the loss in power transmission, and improve the overall operation efficiency of the power grid.

[0167] The node load of the method of the present invention is between 94-96 watts, which is significantly lower than the 100-105 watts of the prior art method. This shows that the method of the present invention performs well in load optimization, can more reasonably allocate and manage power resources, and reduce system load pressure.

[0168] The branch resistance and reactance of the method of the present invention are lower than those of the prior art methods, and are between 0.07-0.09 ohms and 0.03-0.04 ohms, respectively. This shows that the method of the present invention has advantages in optimizing the topology of the power grid, can effectively reduce resistance and reactance, and reduce energy loss in power transmission.

[0169] Most notably, the total system loss of the method of the present invention is significantly lower than that of the prior art method, ranging from 8 to 10 watts, while the total loss of the prior art method is 15 to 17 watts. This shows that the method of the present invention has significant advantages in power loss optimization, can effectively reduce the total system loss, and improve the energy efficiency and economy of the power grid.

[0170] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A self-healing control method for a distribution network with a multi-objective reconstruction strategy, characterized in that: include: Collect distribution network parameters and operation data and build a distribution network reconstruction model; Process the distribution network operation data to obtain node operation data and branch operation data; Based on the mixed integer programming algorithm, the distribution network reconstruction model is solved to obtain the reconstruction solution set; Solve the reconstruction solution set and obtain the optimal reconstruction strategy.

2. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 1, characterized in that: The distribution network parameters include node parameters and branch parameters; Node parameters include node voltage, node current and node load; Branch parameters include branch resistance, branch reactance and branch current; Operation data includes real-time load data, voltage data and current data.

3. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 2, characterized in that: The construction of the distribution network reconstruction model includes: the construction of the distribution network reconstruction model needs to comprehensively consider the distribution network topology, nodes, branch parameters and load conditions, and the node voltage equation is expressed as: Among them, V i represents the voltage of node iii, Ω(i) represents the set of nodes adjacent to node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, X ij represents the reactance between node i and node j; The node power balance equation is expressed as: Among them, P i represents the active power of node i, Q i represents the reactive power of node i, I * ij represents the conjugate complex number of the current between node i and node j; The branch current is expressed as: Among them, I ij represents the current between branch i and node j; The system loss is expressed as: Among them, P loss represents the total system loss, E represents the set of all branches in the system, and I ij represents the current between branch i and node j, R ij represents the resistance of the branch; The comprehensive formula for constructing the distribution network reconstruction model is expressed as: Among them, j ’ Represents an imaginary unit.

4. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 3, characterized in that: The processing of the distribution network operation data includes processing the distribution network operation data through dictionary learning and compressed sensing to obtain node operation data and branch operation data; First, the distribution network data is standardized and expressed as: Among them, μ X represents the mean of the node data, σ X Represents the standard deviation of node data, μ Y represents the mean of the branch data, σ Y represents the standard deviation of branch data; Use dictionary learning to represent the preprocessed data and find a set of dictionaries D X and D Y , so that the node data and branch data can be sparsely represented, and the dictionary learning model is expressed as: Among them, D X Dictionary matrix representing node data, D Y A is the dictionary matrix representing the branch data. X represents the sparse representation matrix, A Y represents the sparse representation matrix, λ X represents the sparse regularization parameter, λ Y represents the sparse regularization parameter; The sparsely represented node data and branch data are reconstructed through compressed sensing to reduce the data dimension and extract features. The compressed sensing model is expressed as: from X =Φ X and X ,from Y =Φ Y and Y Among them, Φ X Represents the measurement matrix of node data, Φ Y Represents the measurement matrix of branch data, z X represents the node data after compressed sensing, z Y represents the branch data after compressed sensing, a X Represents the node data of sparse representation, a Y represents branch data of sparse representation; Compressed sensing reconstruction is expressed as: The sparse representation obtained by reconstruction Further used to restore the original data: De-standardize the recovered data to obtain the processed node operation data and branch operation data, which are expressed as: Among them, the node voltage range is 0 to 1.2 times the rated voltage, and the branch current range is 0 to 1.5 times the rated current.

5. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 4, characterized in that: The mixed integer programming algorithm includes defining decision variables, including continuous variables and integer variables; Continuous variables include node voltages and branch currents, and integer variables include switch states; The objective function remains unchanged, and the constraints include node voltage constraint, branch current constraint, power balance constraint, switch state constraint and topology constraint; The mixed integer programming model for distribution network reconstruction is expressed as: Among them, V i represents the voltage at node i, I ij represents the current between node i and node j, R ij represents the resistance between node i and node j, P i represents the active power of node i, Q i represents the reactive power of node i, x ij Represents the switch state between node i and node j, 0 represents open, 1 represents closed; V min Indicates the minimum value of the node voltage, V max Indicates the maximum value of the node voltage, I ij max represents the maximum current between node i and node j; E represents the set of all branches in the system, and Ω(i) represents the set of nodes adjacent to node i.

6. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 5, characterized in that: Solving the reconstruction solution set to obtain the optimal reconstruction strategy includes: the reconstruction solution set S is a set of possible reconstruction schemes obtained by a mixed integer programming algorithm, each scheme includes node voltage, branch current, switch state and power loss, and the reconstruction solution set is expressed as: Among them, k represents the reconstruction scheme index, and K represents the number of reconstruction solution sets; Solve the reconstructed solution set and select the objective function for optimization, with minimizing power loss as the main goal: A multi-objective optimization model is constructed to maximize voltage stability while minimizing power loss, expressed as: Among them, α represents the weight coefficient of power loss, β represents the weight coefficient of voltage deviation, V nominal Indicates the rated value of the node voltage, P loss k represents the power loss of reconstruction scheme k, V i k represents the node voltage of reconstruction scheme k, Indicates the deviation of the node voltage from the rated value.

7. The distribution network multi-objective reconstruction strategy self-healing control method according to claim 6, characterized in that: Solving the reconstruction solution set to obtain the optimal reconstruction strategy also includes the following steps: Calculate the power loss. For each solution k in the reconstruction solution set S, calculate the total power loss. For each solution k in the reconstructed solution set S, calculate the deviation between the node voltage and the rated value; By comprehensively considering power loss and voltage deviation, the objective function value of each scheme is calculated; The solution with the smallest objective function value is selected from the reconstruction solution set as the optimal reconstruction strategy.

8. A distribution network multi-objective reconstruction strategy self-healing control system using the method according to any one of claims 1 to 7, characterized in that: Build a model module, collect distribution network parameters and operation data, and build a distribution network reconstruction model; The preprocessing module processes the distribution network operation data to obtain node operation data and branch operation data; The solution module solves the distribution network reconstruction model based on the mixed integer programming algorithm to obtain a reconstruction solution set; solves the reconstruction solution set to obtain the optimal reconstruction strategy.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images