Power distribution network emergency resource scheduling strategy generation method and system

Abstract

The invention discloses a power distribution network emergency resource scheduling strategy generation method and system, and relates to the technical field of power distribution network operation and management. Operation situation data of a power distribution network are acquired, a preset time attenuation function is adopted to carry out dynamic influence evaluation on the operation situation data to obtain a plurality of time response values, and a plurality of time response values are obtained based on a preset coupling function; and generating a corresponding response vector by adopting each time response value, performing risk assessment on the response vector according to each time response value to obtain a corresponding risk energy index, and performing emergency resource optimization processing on the risk energy index and a pre-acquired historical risk energy index according to a preset initial multi-objective optimization function to obtain an emergency resource optimization result. And obtaining an optimization emergency strategy corresponding to the power distribution network. The technical problems that a conventional emergency resource scheduling strategy generation method mainly formulates a fixed scheduling scheme based on historical fault cases, but resource redundancy or insufficiency is easily caused, and the emergency disposal efficiency of the power distribution network is reduced are solved.

Description

Technical Field

[0001] This invention relates to the field of power distribution network operation and management technology, and in particular to a method and system for generating emergency resource scheduling strategies for power distribution networks. Background Technology

[0002] With the acceleration of urbanization and the advancement of new power system construction, the low-voltage distribution network, as the "last mile" of power supply, directly affects the stability of people's livelihood, industrial and commercial production, and the continuity of social public services. In recent years, the frequent occurrence of extreme weather events (such as heavy rainfall, typhoons, and cold waves), the rigid growth of user electricity load (an average annual growth rate of over 5%), and the aging of distribution network equipment (equipment in some areas has been in service for over 20 years) have led to a fluctuating upward trend in the incidence of power outages in low-voltage distribution networks. Emergency resource dispatch, as the core link in restoring power supply after a power outage, directly determines the efficiency of emergency response and the effectiveness of resource utilization through its scientific strategy.

[0003] Currently, traditional emergency resource scheduling strategy generation methods are mainly based on historical fault cases to formulate fixed scheduling schemes, but this can easily lead to resource redundancy or insufficiency, reducing the efficiency of emergency response in the distribution network. Summary of the Invention

[0004] This invention provides a method and system for generating emergency resource scheduling strategies for distribution networks. It solves the technical problem that traditional emergency resource scheduling strategy generation methods mainly rely on historical fault cases to formulate fixed scheduling schemes, which can easily lead to resource redundancy or insufficiency and reduce the efficiency of emergency response in distribution networks.

[0005] The first aspect of this invention provides a method for generating emergency resource scheduling strategies for a power distribution network, comprising:

[0006] The operation status data of the power distribution network is acquired, and the operation status data is dynamically evaluated using a preset time decay function to obtain multiple time response values;

[0007] Based on a preset coupling function, a corresponding response vector is generated using each of the time response values;

[0008] Based on each of the time response values, a risk assessment is performed on the response vector to obtain the corresponding risk energy index;

[0009] Based on the preset initial multi-objective optimization function, the risk energy index and the pre-acquired historical risk energy index are subjected to emergency resource optimization processing to obtain the optimized emergency strategy corresponding to the distribution network.

[0010] Optionally, the step of generating a corresponding response vector based on each of the time response values ​​using a preset coupling function includes:

[0011] Based on a preset coupling function, a correlation analysis is performed on any two time response values ​​to obtain multiple coupling coefficients;

[0012] A coupling matrix is ​​constructed using the coupling coefficients described above;

[0013] The coupling matrix is ​​reduced in dimensionality using principal component analysis to obtain the corresponding response vector.

[0014] Optionally, the step of performing risk assessment on the response vector based on each of the time response values ​​to obtain the corresponding risk energy index includes:

[0015] Based on a preset prediction function, the power outage probability is predicted by the response vector obtained in advance according to the historical response vector, and the corresponding power outage probability value is obtained.

[0016] The power outage probability value and each of the time response values ​​are input into a preset risk energy function to obtain the corresponding risk energy index.

[0017] Optionally, the step of performing emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index according to a preset initial multi-objective optimization function to obtain the optimized emergency strategy corresponding to the distribution network includes:

[0018] The risk energy index and the pre-acquired historical risk energy index are input into a preset initial multi-objective optimization function to obtain the corresponding multi-objective optimization function;

[0019] The multi-objective optimization function is solved using the Lagrange multiplier method to obtain the optimized emergency strategy corresponding to the distribution network.

[0020] Optionally, the coupling function is specifically:

[0021] ;

[0022] in, Let be the coupling coefficient between the i-th type of operational situation data and the j-th type of operational situation data at time t. Let be the time response value of the i-th type of operational situation data at time t. Let be the time response value of the j-th type of operational situation data at time t. The coupling amplitude adjustment strength between the i-th type of operational situation data and the j-th type of operational situation data. This is the frequency adjustment factor between the i-th type of operational situation data and the j-th type of operational situation data. Let t be the first constant, i be the first index of the operational status data, j be the second index of the operational status data, and t be the time index.

[0023] Optionally, the initial multi-objective optimization function is specifically:

[0024] ;

[0025] in, Let be the average risk energy value for the s-th time period. Let be the duration of the s-th time interval. for Risk energy index at any moment For time integration variables, Let be the stability weight of the resource scheduling path from the s-th time period to the (s+1)-th time period. For smoothing sensitivity coefficient, This represents the average risk energy value for the (s+1)th time period. Let m be the number of resources of type m allocated in the s-th time period. Let m be the quantity of the m-th type of resource allocated in the (s+1)th time period. Optimize the target value. Let be the unit response efficiency coefficient of the m-th type of resource. Let be the unit response efficiency coefficient of the m-th type of resource. This is the resource cost weighting coefficient. t is the path smoothing reward coefficient. s Let be the start time of the s-th time period, where s is the index of the time period, and S is the total number of time periods. To control the non-linear increase, m is the index of the resource.

[0026] A second aspect of the present invention provides a power distribution network emergency resource scheduling strategy generation system, comprising:

[0027] The acquisition module is used to acquire the operating status data of the power distribution network, and to perform dynamic impact assessment on the operating status data using a preset time decay function to obtain multiple time response values.

[0028] The coupling module is used to generate corresponding response vectors based on the preset coupling function and each of the time response values;

[0029] The assessment module is used to perform risk assessment on the response vector based on each of the time response values ​​to obtain the corresponding risk energy index.

[0030] The emergency resource allocation module is used to perform emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index according to the preset initial multi-objective optimization function, so as to obtain the optimized emergency strategy corresponding to the distribution network.

[0031] A third aspect of the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of the distribution network emergency resource scheduling strategy generation method as described in any of the preceding claims.

[0032] The fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the distribution network emergency resource scheduling strategy generation method as described in any of the preceding claims.

[0033] The fifth aspect of the present invention provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein, when the program instructions are executed by a computer, the computer performs the distribution network emergency resource scheduling strategy generation method as described in any of the preceding claims.

[0034] As can be seen from the above technical solutions, the present invention has the following advantages:

[0035] This invention acquires operational status data of the distribution network, uses a preset time decay function to dynamically assess the impact of the operational status data, and obtains multiple time response values. Based on a preset coupling function, corresponding response vectors are generated using each time response value. Risk assessment is then performed on the response vectors based on each time response value to obtain a corresponding risk energy index. Finally, emergency resource optimization processing is performed on the risk energy index and pre-acquired historical risk energy indices using a preset initial multi-objective optimization function to obtain an optimized emergency strategy for the distribution network. This overcomes the technical problem of traditional emergency resource scheduling strategy generation methods, which mainly rely on historical fault cases to formulate fixed scheduling schemes, easily leading to resource redundancy or insufficiency and reducing the efficiency of distribution network emergency response. Compared with traditional emergency resource scheduling strategy generation methods, this invention accurately captures the response vectors of operational status data using a preset time decay function and a preset coupling function, and then performs risk assessment on the response vectors based on each time response value, thereby quickly identifying the risk energy index of the distribution network. Finally, the initial multi-objective optimization function is solved based on the risk energy index to obtain an optimized emergency strategy for the distribution network, improving the efficiency of power grid emergency response and achieving synergistic optimization of emergency efficiency, economic cost, and scheduling stability. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating the steps of a method for generating an emergency resource scheduling strategy for a power distribution network, as provided in Embodiment 1 of the present invention.

[0038] Figure 2 This is a flowchart illustrating the steps of a method for generating an emergency resource scheduling strategy for a power distribution network, as provided in Embodiment 2 of the present invention.

[0039] Figure 3 This is a structural block diagram of a power distribution network emergency resource scheduling strategy generation system provided in Embodiment 3 of the present invention;

[0040] Figure 4 This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention. Detailed Implementation

[0041] This invention provides a method and system for generating emergency resource scheduling strategies for distribution networks, which addresses the technical problem that traditional emergency resource scheduling strategy generation methods mainly rely on historical fault cases to formulate fixed scheduling schemes, but this can easily lead to resource redundancy or insufficiency, reducing the efficiency of emergency response in distribution networks.

[0042] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0043] Please see Figure 1 , Figure 1 The flowchart illustrates the steps of a method for generating emergency resource scheduling strategies for a power distribution network, as provided in Embodiment 1 of the present invention.

[0044] This invention provides a method for generating emergency resource scheduling strategies for power distribution networks, comprising:

[0045] Step 101: Obtain the operation status data of the distribution network, and use a preset time decay function to perform dynamic impact assessment on the operation status data to obtain multiple time response values.

[0046] Operational status data refers to a multi-source heterogeneous data set that can comprehensively reflect the current and historical operating status of the distribution network. This includes historical power outage data (extracted from the fault work order system, recording the time, duration, scope of impact, and fault type of power outage events), equipment operation data (collected by the SCADA system, reflecting the real-time operating parameters of power distribution equipment), meteorological condition data (obtained from meteorological access nodes, reflecting environmental factors affecting the operation of the distribution network), and user load data (sampled by the smart meter system, reflecting user electricity demand and load change patterns).

[0047] The time response value refers to the numerical value obtained through dynamic impact assessment, which quantifies the comprehensive impact of a certain type of operational status data on the current operating status of the distribution network.

[0048] In this embodiment of the invention, historical power outage data is extracted through a fault work order system, equipment operation data is collected in real time through SCADA (i.e., data acquisition and monitoring control system), meteorological condition data is synchronously obtained through a local meteorological access node, and user load data is periodically obtained through a smart meter acquisition system. The historical power outage data, equipment operation data, meteorological condition data, and user load data are respectively input into a preset time decay function to obtain the time response values ​​corresponding to the historical power outage data, equipment operation data, meteorological condition data, and user load data.

[0049] It should be noted that the time decay function is as follows:

[0050]

[0051] in, The time response value of the i-th type of operational status data at time t (when i is 1, the operational status data is historical power outage data; when i is 2, the operational status data is equipment operation data; when i is 3, the operational status data is meteorological condition data; when i is 4, the operational status data is user load data). This is the decay weight coefficient for the nth historical time step. Here, i is the first index of the operational status data, N is the length of the historical time window, n is the index of the historical time step, and i is the first index of the operational status data.

[0052] Step 102: Based on the preset coupling function, generate the corresponding response vector using the response values ​​at each time.

[0053] A response vector is a vector that can comprehensively reflect the joint influence of multiple source time response values. It is usually composed of the principal components with the highest variance contribution (such as retaining only the first principal component). Its core function is to transform the complex coupled information of multi-source data into a concise quantitative indicator.

[0054] In this embodiment of the invention, the time response values ​​corresponding to historical power outage data, equipment operation data, meteorological condition data, and user load data are input into a preset coupling function for correlation analysis to obtain multiple coupling coefficients. A coupling matrix is ​​constructed using these coefficients. Principal component analysis is then used to reduce the dimensionality of the coupling matrix, yielding the corresponding response vector.

[0055] Step 103: Perform risk assessment on the response vector based on the response values ​​at each time point to obtain the corresponding risk energy index.

[0056] The risk energy index is a comprehensive risk indicator obtained by integrating the power outage probability value and the response value at various times. The larger the value, the stronger the potential power outage impact in the region at time t. It is the core driving signal for emergency resource dispatch.

[0057] In this embodiment of the invention, based on a preset prediction function, the power outage probability is predicted from the pre-acquired historical response vectors to obtain the corresponding power outage probability value. The power outage probability value and the response values ​​at various times are then input into a preset risk energy function to obtain the corresponding risk energy index.

[0058] Step 104: Based on the preset initial multi-objective optimization function, perform emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index to obtain the optimized emergency strategy corresponding to the distribution network.

[0059] Optimizing emergency response strategies refers to the emergency resource allocation schemes obtained by solving multi-objective optimization functions and organized by time period and resource type. It clarifies the optimal allocation quantity of each type of emergency resource in each time period and can directly guide the emergency resource scheduling and execution of the distribution network under different risk scenarios.

[0060] Historical risk energy index refers to the risk energy index extracted in advance from the historical operation database of the distribution network at various times in the past multiple operating cycles. It is used to reflect the temporal distribution pattern of the risk energy index, provide historical reference for dividing the time period within the prediction period and determining the duration of the time period, and improve the rationality of resource optimization.

[0061] The initial multi-objective optimization function refers to a mathematical function with the core objectives of maximizing emergency response benefits, minimizing resource scheduling costs, and ensuring the stability of scheduling paths.

[0062] In this embodiment of the invention, the risk energy index and the pre-acquired historical risk energy index are input into a preset initial multi-objective optimization function to obtain the corresponding multi-objective optimization function. The Lagrange multiplier method is used to solve the multi-objective optimization function to obtain the optimized emergency strategy for the distribution network.

[0063] In this embodiment of the invention, by acquiring the operational status data of the distribution network, a preset time decay function is used to dynamically assess the impact of the operational status data, resulting in multiple time response values. Based on a preset coupling function, corresponding response vectors are generated using each time response value. Risk assessment is then performed on the response vectors based on each time response value to obtain a corresponding risk energy index. Emergency resource optimization processing is then performed on the risk energy index and the pre-acquired historical risk energy index using a preset initial multi-objective optimization function to obtain an optimized emergency strategy for the distribution network. This overcomes the technical problem that traditional emergency resource scheduling strategy generation methods mainly rely on historical fault cases to formulate fixed scheduling schemes, which can easily lead to resource redundancy or insufficiency, reducing the efficiency of distribution network emergency response. Compared with traditional emergency resource scheduling strategy generation methods, this invention accurately captures the response vectors of operational status data using a preset time decay function and a preset coupling function, and then performs risk assessment on the response vectors based on each time response value, thereby quickly identifying the risk energy index of the distribution network. Finally, the initial multi-objective optimization function is solved based on the risk energy index to obtain an optimized emergency strategy for the distribution network, improving the efficiency of power grid emergency response and achieving synergistic optimization of emergency efficiency, economic cost, and scheduling stability.

[0064] Please see Figure 2 , Figure 2 The flowchart illustrates the steps of a method for generating an emergency resource scheduling strategy for a power distribution network, as provided in Embodiment 2 of the present invention.

[0065] This invention provides a method for generating emergency resource scheduling strategies for power distribution networks, comprising:

[0066] Step 201: Obtain the operation status data of the distribution network, and use a preset time decay function to perform dynamic impact assessment on the operation status data to obtain multiple time response values.

[0067] In this embodiment of the invention, historical power outage data, equipment operation data, meteorological condition data, and user load data of the power distribution network are acquired. A preset time decay function is used to perform dynamic impact assessment on the historical power outage data, equipment operation data, meteorological condition data, and user load data, respectively, to obtain multiple time response values.

[0068] Step 202: Based on the preset coupling function, generate the corresponding response vector using the response values ​​at each time.

[0069] Further, step 202 includes the following sub-steps:

[0070] S11. Based on the preset coupling function, perform correlation analysis on any two time response values ​​to obtain multiple coupling coefficients.

[0071] In this embodiment of the invention, any two time response values ​​are input into a preset coupling function to obtain multiple coupling coefficients. For example, based on the preset coupling function, correlation analysis is performed on the combinations of time response values ​​corresponding to historical power outage data, equipment operation data, meteorological condition data, and user load data to obtain 16 coupling coefficients.

[0072] It should be noted that the coupling function is specifically as follows:

[0073] ;

[0074] in, Let be the coupling coefficient between the i-th type of operational situation data and the j-th type of operational situation data at time t. Let be the time response value of the i-th type of operational situation data at time t. Let be the time response value of the j-th type of operational situation data at time t. The coupling amplitude adjustment strength between the i-th type of operational situation data and the j-th type of operational situation data. This is the frequency adjustment factor between the i-th type of operational situation data and the j-th type of operational situation data. Let t be the first constant, i be the first index of the operational status data, j be the second index of the operational status data, and t be the time index.

[0075] S12. Construct a coupling matrix using the various coupling coefficients.

[0076] In this embodiment of the invention, a coupling matrix containing nonlinear correlation information of multi-source data is generated using various coupling relationship coefficients.

[0077] S13. The coupling matrix is ​​reduced in dimension by principal component analysis to obtain the corresponding response vector.

[0078] In this embodiment of the invention, the coupling matrix is ​​used as input for principal component analysis (PCA) dimensionality reduction. The principal component with the highest contribution in the coupling matrix is ​​retained by linear transformation (usually the first principal component is selected, and its variance contribution ratio must meet a preset threshold, such as ≥85%, to ensure that the core information is not lost), and the corresponding response vector is obtained.

[0079] It should be noted that the expression for the response vector is:

[0080]

[0081] in, Let be the response vector at time t. Let be the coupling matrix at time t. Principal component analysis is performed on the coupling matrix at time t.

[0082] Step 203: Perform risk assessment on the response vector based on the response values ​​at each time point to obtain the corresponding risk energy index.

[0083] Further, step 203 includes:

[0084] S21. Based on the preset prediction function, predict the power outage probability of the response vector according to the historical response vector obtained in advance, and obtain the corresponding power outage probability value.

[0085] Historical response vectors refer to response vectors that are extracted in advance from the historical operation database of the distribution network and obtained by dimensionality reduction of multiple past moments through a coupling matrix.

[0086] The power outage probability value refers to the probability value of a power outage event occurring in the area corresponding to the current time t in the future, calculated by a preset prediction function. The value range is usually [0,1]. The larger the value, the higher the risk of power outage in the area.

[0087] In this embodiment of the invention, the response vector and the pre-acquired historical response vector are input into a preset prediction function to obtain the corresponding power outage probability value.

[0088] It should be noted that the prediction function is as follows:

[0089]

[0090] in, The power outage probability value predicted at time t. The linear weighting coefficients of the response vector represent the degree of direct impact of the current system state on the risk of power outage. These are the weighting coefficients of the difference term, measuring the moderating effect of a growing or declining trend in the response on the probability of risk. The coefficients of the k-th order historical coupling term are used to capture the joint effect of historical trends and current responses. Let be the response vector at time t. Let be the response vector at time t-1. The main response value at time t, Let the value be the master response at time step k. Let be the response vector at time tk-1, K be the length of the history backtracking window, and k be the index of the previous time step.

[0091] S22. Input the power outage probability value and each time response value into the preset risk energy function to obtain the corresponding risk energy index.

[0092] In this embodiment of the invention, the time response values ​​corresponding to the power outage probability value, historical power outage data, equipment operation data, meteorological condition data, and user load data are input into a preset risk energy function to obtain the corresponding risk energy index.

[0093] It should be noted that the risk energy function is as follows:

[0094]

[0095] in, Let be the risk energy index at time t. The power outage probability value predicted at time t. The dominant enhancement coefficient is used to control the strength of the dominant input variable's amplification effect on overall risk. The larger the value, the more sensitive the dominant input is. It is the first constant.

[0096] Step 204: Input the risk energy index and the pre-acquired historical risk energy index into the preset initial multi-objective optimization function to obtain the corresponding multi-objective optimization function.

[0097] In this embodiment of the invention, an initial multi-objective optimization function is constructed with the core objectives of maximizing emergency response benefits, minimizing resource scheduling costs, and ensuring scheduling path stability. The risk energy index and the pre-acquired historical risk energy index are input into the initial multi-objective optimization function to obtain the corresponding multi-objective optimization function.

[0098] It should be noted that the initial multi-objective optimization function is as follows:

[0099] ;

[0100] in, Let be the average risk energy value for the s-th time period. Let be the duration of the s-th time interval. for Risk energy index at any moment For time integration variables, Let be the stability weight of the resource scheduling path from the s-th time period to the (s+1)-th time period. For smoothing sensitivity coefficient, This represents the average risk energy value for the (s+1)th time period. Let m be the number of resources of type m allocated in the s-th time period. Let m be the quantity of the m-th type of resource allocated in the (s+1)th time period. Optimize the target value. Let be the unit response efficiency coefficient of the m-th type of resource. Let be the unit response efficiency coefficient of the m-th type of resource. This is the resource cost weighting coefficient. t is the path smoothing reward coefficient. s Let be the start time of the s-th time period, where s is the index of the time period, and S is the total number of time periods. To control the non-linear increase, m is the index of the resource.

[0101] Step 205: Solve the multi-objective optimization function using the Lagrange multiplier method to obtain the optimized emergency strategy for the distribution network.

[0102] It should be noted that the Lagrange multiplier method refers to a mathematical method for solving constrained optimization problems. The core of it is to transform the original constrained optimization problem into an unconstrained Lagrange function extremum problem by introducing Lagrange multipliers. In this invention, it is used to handle emergency resource capacity constraints in multi-objective optimization functions and to achieve the optimal calculation of resource allocation quantities.

[0103] In this embodiment of the invention, the Lagrange multiplier method is used to solve the multi-objective optimization function to obtain the optimal allocation quantity of each type of resource in each time period as the corresponding optimized emergency strategy for the distribution network.

[0104] In this embodiment of the invention, by acquiring the operational status data of the distribution network, a preset time decay function is used to dynamically assess the impact of the operational status data, resulting in multiple time response values. Based on a preset coupling function, corresponding response vectors are generated using each time response value. Risk assessment is then performed on the response vectors based on each time response value to obtain a corresponding risk energy index. Emergency resource optimization processing is then performed on the risk energy index and the pre-acquired historical risk energy index using a preset initial multi-objective optimization function to obtain an optimized emergency strategy for the distribution network. This overcomes the technical problem that traditional emergency resource scheduling strategy generation methods mainly rely on historical fault cases to formulate fixed scheduling schemes, which can easily lead to resource redundancy or insufficiency, reducing the efficiency of distribution network emergency response. Compared with traditional emergency resource scheduling strategy generation methods, this invention accurately captures the response vectors of operational status data using a preset time decay function and a preset coupling function, and then performs risk assessment on the response vectors based on each time response value, thereby quickly identifying the risk energy index of the distribution network. Finally, the initial multi-objective optimization function is solved based on the risk energy index to obtain an optimized emergency strategy for the distribution network, improving the efficiency of power grid emergency response and achieving synergistic optimization of emergency efficiency, economic cost, and scheduling stability.

[0105] Please see Figure 3 , Figure 3 This is a structural block diagram of a power distribution network emergency resource scheduling strategy generation system provided in Embodiment 3 of the present invention.

[0106] This invention provides a power distribution network emergency resource scheduling strategy generation system, comprising:

[0107] The acquisition module 301 is used to acquire the operating status data of the distribution network, and to perform dynamic impact assessment on the operating status data using a preset time decay function to obtain multiple time response values.

[0108] The coupling module 302 is used to generate a corresponding response vector based on the response values ​​at each time point using a preset coupling function.

[0109] The assessment module 303 is used to assess the risk of the response vector based on the response values ​​at various times and obtain the corresponding risk energy index.

[0110] The emergency resource allocation module 304 is used to perform emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index according to the preset initial multi-objective optimization function, so as to obtain the optimized emergency strategy corresponding to the distribution network.

[0111] Furthermore, the coupling module 302 includes:

[0112] The correlation analysis submodule is used to perform correlation analysis on any two time response values ​​based on a preset coupling function, and obtain multiple coupling relationship coefficients.

[0113] Construct a submodule to build a coupling matrix using the various coupling coefficients;

[0114] The dimensionality reduction submodule is used to reduce the dimensionality of the coupling matrix using principal component analysis to obtain the corresponding response vector.

[0115] Furthermore, the evaluation module 303 includes:

[0116] The prediction submodule is used to predict the power outage probability of the response vector based on the preset prediction function and the historical response vector obtained in advance, so as to obtain the corresponding power outage probability value.

[0117] The evaluation submodule is used to input the power outage probability value and the response values ​​at various times into a preset risk energy function to obtain the corresponding risk energy index.

[0118] Furthermore, the emergency resource allocation module 304 includes:

[0119] The optimization submodule is used to input the risk energy index and the pre-acquired historical risk energy index into the preset initial multi-objective optimization function to obtain the corresponding multi-objective optimization function;

[0120] The solution submodule is used to solve the multi-objective optimization function using the Lagrange multiplier method to obtain the corresponding optimized emergency strategy for the distribution network.

[0121] Furthermore, the coupling function is specifically as follows:

[0122] ;

[0123] in, Let be the coupling coefficient between the i-th type of operational situation data and the j-th type of operational situation data at time t. Let be the time response value of the i-th type of operational situation data at time t. Let be the time response value of the j-th type of operational situation data at time t. The coupling amplitude adjustment strength between the i-th type of operational situation data and the j-th type of operational situation data. This is the frequency adjustment factor between the i-th type of operational situation data and the j-th type of operational situation data. Let t be the first constant, i be the first index of the operational status data, j be the second index of the operational status data, and t be the time index.

[0124] Furthermore, the initial multi-objective optimization function is specifically as follows:

[0125] ;

[0126] in, Let be the average risk energy value for the s-th time period. Let be the duration of the s-th time interval. for Risk energy index at any moment For time integration variables, Let be the stability weight of the resource scheduling path from the s-th time period to the (s+1)-th time period. For smoothing sensitivity coefficient, This represents the average risk energy value for the (s+1)th time period. Let m be the number of resources of type m allocated in the s-th time period. Let m be the quantity of the m-th type of resource allocated in the (s+1)th time period. Optimize the target value. Let be the unit response efficiency coefficient of the m-th type of resource. Let be the unit response efficiency coefficient of the m-th type of resource. This is the resource cost weighting coefficient. t is the path smoothing reward coefficient. s Here, s is the index of the time period, and S is the total number of time periods. To control the non-linear increase, m is the index of the resource.

[0127] Please see Figure 4 , Figure 4This is a structural block diagram of a computer device provided in Embodiment 4 of the present invention.

[0128] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402. The memory 401 stores a computer program. When the computer program is executed by the processor 402, the processor 402 executes the distribution network emergency resource scheduling strategy generation method as described in any of the above embodiments.

[0129] Memory 401 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 401 has storage space 403 for program code 413 for performing any of the method steps described above. For example, storage space 403 for program code may include individual program codes 413 for implementing the various steps in the methods described above. This program code may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When run by a computing processing device, this code causes the computing processing device to perform the various steps in the methods described above. This program code may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. The program code may be compressed, for example, in a suitable form. When this code is run by a computing device, it causes the computing device to execute the various steps in the distribution network emergency resource scheduling strategy generation method described above.

[0130] Embodiment 5 of the present invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the distribution network emergency resource scheduling strategy generation method as described in any of the above embodiments.

[0131] Embodiment 6 of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the distribution network emergency resource scheduling strategy generation method as described in any of the above embodiments.

[0132] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0133] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0134] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0135] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0136] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0137] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating emergency resource scheduling strategies for a power distribution network, characterized in that, include: The operation status data of the power distribution network is acquired, and the operation status data is dynamically evaluated using a preset time decay function to obtain multiple time response values; Based on a preset coupling function, a corresponding response vector is generated using each of the time response values; Based on each of the time response values, a risk assessment is performed on the response vector to obtain the corresponding risk energy index; Based on the preset initial multi-objective optimization function, the risk energy index and the pre-acquired historical risk energy index are subjected to emergency resource optimization processing to obtain the optimized emergency strategy corresponding to the distribution network.

2. The method for generating emergency resource scheduling strategies for distribution networks according to claim 1, characterized in that, The step of generating a corresponding response vector using each of the time response values ​​based on a preset coupling function includes: Based on a preset coupling function, a correlation analysis is performed on any two time response values ​​to obtain multiple coupling coefficients; A coupling matrix is ​​constructed using the coupling coefficients described above; The coupling matrix is ​​reduced in dimensionality using principal component analysis to obtain the corresponding response vector.

3. The method for generating emergency resource scheduling strategies for power distribution networks according to claim 1, characterized in that, The step of performing risk assessment on the response vector based on each of the time response values ​​to obtain the corresponding risk energy index includes: Based on a preset prediction function, the power outage probability is predicted by the response vector obtained in advance according to the historical response vector, and the corresponding power outage probability value is obtained. The power outage probability value and each of the time response values ​​are input into a preset risk energy function to obtain the corresponding risk energy index.

4. The method for generating emergency resource scheduling strategies for distribution networks according to claim 1, characterized in that, The step of performing emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index according to a preset initial multi-objective optimization function to obtain the optimized emergency strategy corresponding to the distribution network includes: The risk energy index and the pre-acquired historical risk energy index are input into a preset initial multi-objective optimization function to obtain the corresponding multi-objective optimization function; The multi-objective optimization function is solved using the Lagrange multiplier method to obtain the optimized emergency strategy corresponding to the distribution network.

5. The method for generating emergency resource scheduling strategies for distribution networks according to claim 1, characterized in that, The coupling function is specifically: ； in, Let be the coupling coefficient between the i-th type of operational situation data and the j-th type of operational situation data at time t. Let be the time response value of the i-th type of operational situation data at time t. Let be the time response value of the j-th type of operational situation data at time t. The coupling amplitude adjustment strength between the i-th type of operational situation data and the j-th type of operational situation data. This is the frequency adjustment factor between the i-th type of operational situation data and the j-th type of operational situation data. Let t be the first constant, i be the first index of the operational status data, j be the second index of the operational status data, and t be the time index.

6. The method for generating emergency resource scheduling strategies for distribution networks according to claim 1, characterized in that, The initial multi-objective optimization function is specifically as follows: ； in, Let be the average risk energy value for the s-th time period. Let be the duration of the s-th time interval. for Risk energy index at any moment For time integration variables, Let be the stability weight of the resource scheduling path from the s-th time period to the (s+1)-th time period. For smoothing sensitivity coefficient, This represents the average risk energy value for the (s+1)th time period. Let m be the number of resources of type m allocated in the s-th time period. Let m be the quantity of the m-th type of resource allocated in the (s+1)th time period. Optimize the target value. Let be the unit response efficiency coefficient of the m-th type of resource. Let be the unit response efficiency coefficient of the m-th type of resource. This is the resource cost weighting coefficient. t is the path smoothing reward coefficient. s Let be the start time of the s-th time period, where s is the index of the time period, and S is the total number of time periods. To control the non-linear increase, m is the index of the resource.

7. A power distribution network emergency resource dispatch strategy generation system, characterized in that, include: The acquisition module is used to acquire the operating status data of the power distribution network, and to perform dynamic impact assessment on the operating status data using a preset time decay function to obtain multiple time response values. The coupling module is used to generate corresponding response vectors based on the preset coupling function and each of the time response values; The assessment module is used to perform risk assessment on the response vector based on each of the time response values ​​to obtain the corresponding risk energy index. The emergency resource allocation module is used to perform emergency resource optimization processing on the risk energy index and the pre-acquired historical risk energy index according to the preset initial multi-objective optimization function, so as to obtain the optimized emergency strategy corresponding to the distribution network.

8. An electronic device, characterized in that, The device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the distribution network emergency resource scheduling strategy generation method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed, it implements the distribution network emergency resource scheduling strategy generation method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, wherein when the program instructions are executed by a computer, the computer performs the distribution network emergency resource scheduling strategy generation method as described in any one of claims 1-6.

Images