A method and system for emergency response assessment based on power grid disaster losses

Abstract

The present invention discloses an emergency processing assessment method and system based on power grid disaster loss, which relates to the technical field of resource allocation. The method and system pre-collect power grid information sets, environmental information sets and emergency resource information sets, build and train a partition risk assessment model based on the power grid information sets and the environmental information sets, collect real-time power grid load data of the power grid, combine the partition risk assessment model and the power grid load data, calculate the estimated resource demand ratio distribution of the power grid, build a comprehensive loss index based on the estimated resource demand ratio distribution and the power grid load data, build a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set, use an optimization model solving tool to solve the resource allocation optimization model, and obtain an emergency resource allocation plan; the power outage time and economic losses of the power grid are reduced to the greatest extent.

Description

Technical Field

[0001] The present invention relates to the technical field of resource allocation, and in particular to an emergency processing evaluation method and system based on power grid disaster losses. Background Art

[0002] With the rapid development of modern cities and the increasing complexity of power systems, the vulnerability of power grids to natural disasters (such as typhoons, earthquakes, etc.) and man-made accidents has become increasingly apparent. The stable operation of power systems is the cornerstone of social and economic development. Therefore, in the event of disasters, the rapid recovery of power grids and effective emergency response are particularly important. However, traditional emergency resource allocation usually relies on the experience and subjective evaluation of experts, which may lead to improper resource allocation and failure to respond to emergencies in a timely and effective manner. When evaluating the allocation ratio of emergency resources, existing technologies often lack systematic data analysis and quantitative decision-making basis, resulting in low efficiency of resource allocation and even aggravated delays in power grid recovery. Therefore, there is an urgent need for a data-driven scientific evaluation method to optimize the allocation strategy of emergency resources and improve the recovery capacity of power grids in the event of disasters.

[0003] To this end, the present invention proposes an emergency response evaluation method and system based on power grid disaster losses. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an emergency treatment evaluation method and system based on power grid disaster losses, which can greatly reduce power grid outage time and economic losses.

[0005] To achieve the above purpose, an emergency treatment assessment method based on power grid disaster loss is proposed, which includes the following steps:

[0006] Step 1: Collect power grid information, environmental information and emergency resource information in advance;

[0007] Step 2: Based on the grid information set and the environmental information set, build and train the zoning risk assessment model;

[0008] Step 3: Collect real-time grid load data of the power grid;

[0009] Step 4: Combine the zoning risk assessment model and grid load data to calculate the estimated resource demand ratio distribution of the grid;

[0010] Step 5: Construct a comprehensive loss index based on the estimated resource demand ratio distribution and grid load data;

[0011] Step 6: Based on the comprehensive loss index and the emergency resource information set, a resource allocation optimization model is constructed, and the resource allocation optimization model is solved using the optimization model solving tool to obtain the emergency resource allocation plan;

[0012] The collection method of the power grid information set and the environment information set is:

[0013] According to the geographic information system and the power grid topology structure, the power grid is spatially and functionally partitioned in advance to obtain N power grid partitions, where N is the number mark of the obtained power grid partitions;

[0014] For each grid zone:

[0015] Various power parameter sensors and various environmental parameter sensors are pre-installed at key nodes of the power grid partition. During the historical operation of the power grid, the corresponding historical power parameter values ​​are collected in real time through the power parameter sensors, and the corresponding historical environmental parameter values ​​are collected through the environmental parameter sensors;

[0016] Access historical operation files within the power grid partition, collect historical fault records, equipment status information and key facility information of the power grid partition;

[0017] Collecting the grid topology of the grid partitions; the grid topology is a grid network diagram, including detailed configurations of nodes and lines;

[0018] The power historical parameter values ​​of the power parameters, historical fault records, equipment status information, key facility information and power grid topology structure constitute a power grid information set;

[0019] Collect geographic information about the area where the power grid is zoned;

[0020] The historical environmental parameter values ​​and geographic information constitute an environmental information set;

[0021] The emergency resource information set is collected in the following manner:

[0022] By collecting all emergency resources that can be mobilized in the event of an emergency in the database background of the emergency department, an emergency resource information collection is formed;

[0023] The method of constructing and training the partition risk assessment model based on the power grid information set and the environmental information set is:

[0024] For each grid zone, the following steps are performed to train the zone risk assessment model:

[0025] Step 21: Divide the power grid information set and the environment information set into time periods according to a preset time period;

[0026] Step 22: For each time period, mathematical statistics are performed on various parameters in the power grid information set and the environment information set to obtain several key statistical features;

[0027] Step 23: setting a fault label for each time period; the fault label is 0 or 1, wherein 1 indicates that a fault requiring maintenance occurs during the time period, and 0 indicates that a fault requiring maintenance does not occur during the time period;

[0028] Step 24: Using the Bayesian network model as a partition risk assessment model, wherein the partition risk assessment model uses key statistical features of each time period as input;

[0029] Step 25: Use a structural learning algorithm to construct the structure of the Bayesian network to represent the conditional dependencies between key statistical features, and manually add known physical or engineering constraints;

[0030] Step 26: The partition risk assessment model outputs an estimated probability of failure occurring in each time period according to the key statistical characteristics of the time period; and iteratively optimizes the parameters of each conditional probability table in the Bayesian network by using the maximum likelihood estimation or Bayesian estimation method for each time period;

[0031] The method of calculating the estimated resource demand ratio distribution of the power grid by combining the zoning risk assessment model and the power grid load data is as follows:

[0032] Each grid partition is numbered as i;

[0033] The real-time power load of the i-th grid partition is marked as Li;

[0034] The number of key power-consuming facilities in the i-th grid partition is marked as Ni;

[0035] The failure probability of the i-th power grid partition estimated by the partition risk assessment model is marked as FPi;

[0036] The estimated resource demand in the i-th grid partition is labeled Ri;

[0037] The calculation formula for estimated resource demand Ri is:

[0038] ; Wherein, a1, a2 and a3 are preset proportional coefficients;

[0039] The resource demand ratio in the i-th grid partition is labeled Bi;

[0040] Then the resource demand ratio Bi is calculated as: ;

[0041] The method of constructing the comprehensive loss index based on the estimated resource demand ratio distribution and power grid load data is as follows:

[0042] The grid loss index of the i-th grid partition is labeled as Si;

[0043] The calculation formula of the power grid loss index is:

[0044] ; Wherein, a4 and a5 are preset proportional coefficients, and Ltotal is the total load of all grid partitions;

[0045] The method of constructing the resource allocation optimization model based on the comprehensive loss index and the emergency resource information set is:

[0046] Set the allocation ratio variable xi for each grid partition;

[0047] Set the total amount of emergency resources to 1;

[0048] Construct the target optimization function M;

[0049] The expression of the objective optimization function M is: ; Where Pi is the cost of allocating emergency resources to the i-th grid partition;

[0050] Construct the first constraint: , which is used to limit the allocated emergency resources to not exceed the total amount of emergency resources; construct the second constraint: , which is used to limit the resources allocated to any grid partition, is a non-negative decimal;

[0051] Taking the minimization target optimization function M as the optimization target, taking the first constraint condition and the second constraint condition as the constraint condition set, a resource allocation optimization model is constructed;

[0052] The method of using the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan is:

[0053] Using a linear programming solver, by inputting the target optimization function M and the objective function and constraint set of the resource allocation optimization model, the emergency resource allocation plan for the proportion of emergency resources that need to be allocated to each power grid partition is solved.

[0054] An emergency response evaluation system based on power grid disaster loss is proposed, which includes a data collection module, a model training module, a resource allocation model construction module, and a resource allocation module; wherein each module is electrically connected;

[0055] The data collection module collects the power grid information set, the environmental information set, the emergency resource information set and the power grid load data in advance, and sends the power grid information set and the environmental information set to the model training module, and sends the emergency resource information set and the power grid load data to the resource allocation model construction module;

[0056] A model training module, based on a power grid information set and an environmental information set, constructs and trains a partition risk assessment model, and sends the partition risk assessment model to a resource allocation model construction module;

[0057] The resource allocation model construction module calculates the estimated resource demand ratio distribution of the power grid by combining the zoning risk assessment model and the power grid load data, constructs a comprehensive loss index based on the estimated resource demand ratio distribution and the power grid load data, constructs a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set, and sends the resource allocation optimization model to the resource allocation module;

[0058] The resource allocation module uses the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan.

[0059] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned emergency processing assessment method based on power grid disaster loss by calling the computer program stored in the memory.

[0060] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned emergency processing assessment method based on power grid disaster losses.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The present invention collects a power grid information set, an environmental information set and an emergency resource information set in advance, constructs and trains a partition risk assessment model based on the power grid information set and the environmental information set, collects real-time power grid load data of the power grid, combines the partition risk assessment model and the power grid load data, calculates the estimated resource demand ratio distribution of the power grid, constructs a comprehensive loss index based on the estimated resource demand ratio distribution and the power grid load data, constructs a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set, and uses an optimization model solving tool to solve the resource allocation optimization model to obtain an emergency resource allocation plan; first, the power grid is divided into several partitions through a geographic information system and a power grid topology structure, and a partition risk assessment model is constructed using real-time monitoring data, historical operation records and environmental information. Then, based on the comprehensive loss index and the resource demand ratio, a resource allocation optimization model is formulated, and transportation cost factors such as path length are introduced to balance uncompensated losses and total transportation costs. Through optimization techniques such as linear programming, an appropriate resource allocation ratio is determined, and it can respond quickly in a complex power grid environment, concentrate limited resources in key areas, and minimize power outage time and economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1This is a flow chart of an emergency processing assessment method based on power grid disaster loss in Example 1 of the present invention;

[0064] Figure 2 This is a module connection relationship diagram of an emergency processing and evaluation system based on power grid disaster loss in Example 2 of the present invention. DETAILED DESCRIPTION

[0065] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] like Figure 1 As shown, an emergency response evaluation method based on power grid disaster loss includes the following steps:

[0068] Step 1: Collect power grid information, environmental information and emergency resource information in advance;

[0069] Step 2: Based on the grid information set and the environmental information set, build and train the zoning risk assessment model;

[0070] Step 3: Collect real-time grid load data of the power grid;

[0071] Step 4: Combine the zoning risk assessment model and grid load data to calculate the estimated resource demand ratio distribution of the grid;

[0072] Step 5: Construct a comprehensive loss index based on the estimated resource demand ratio distribution and grid load data;

[0073] Step 6: Based on the comprehensive loss index and the emergency resource information set, a resource allocation optimization model is constructed, and the resource allocation optimization model is solved using the optimization model solving tool to obtain the emergency resource allocation plan;

[0074] The collection method of the power grid information set and the environment information set is as follows:

[0075] According to the geographic information system and the grid topology structure, the grid is spatially and functionally partitioned in advance to obtain N grid partitions, where N is the number mark of the obtained grid partitions; specifically, the grid is partitioned according to space, function, or a combination of space and function, which is based on actual needs and the grid topology structure;

[0076] For each grid zone:

[0077] Various power parameter sensors and various environmental parameter sensors are pre-installed at key nodes of the power grid partition. During the historical operation of the power grid, the corresponding historical power parameter values ​​are collected in real time through the power parameter sensors, and the corresponding historical environmental parameter values ​​are collected through the environmental parameter sensors;

[0078] Specifically, the collected power parameters include but are not limited to voltage, current, power factor, line temperature, vibration frequency, etc.;

[0079] The environmental parameters collected include, but are not limited to, the temperature, humidity, wind speed, rainfall, etc. of the area where the power grid partition is located;

[0080] Access historical operation files within the power grid partition, collect historical fault records, equipment status information and key facility information of the power grid partition;

[0081] Collecting the grid topology of the grid partitions; the grid topology is a grid network diagram, including detailed configurations of nodes and lines;

[0082] The power historical parameter values ​​of the power parameters, historical fault records, equipment status information, key facility information and power grid topology structure constitute a power grid information set;

[0083] Collect geographical information of the area where the power grid is located; the geographical information includes but is not limited to topography, landforms, land use types, flood zoning maps, etc.;

[0084] The historical environmental parameter values ​​and geographic information constitute an environmental information set;

[0085] The historical fault records include but are not limited to the time, location, type and recovery time of past faults in each power grid partition;

[0086] The equipment status information includes but is not limited to the health status of each grid equipment and the number of key grid equipment in each grid partition; the grid equipment includes but is not limited to transformers, switches, lines, etc.; the health status can be set to the operating time of the grid equipment, or the status signal of the grid equipment itself (for example, when a transformer fails, a fault indicator light will be used to warn);

[0087] The key facility information includes the number of key power-consuming facilities in the power grid partition; the power-consuming facilities generally refer to equipment and units with power demand, such as schools, hospitals, factories, large-scale experimental equipment, etc. The more the number of key power-consuming facilities, the greater the importance of the power grid partition;

[0088] Furthermore, the emergency resource information set is collected in the following manner:

[0089] By collecting all emergency resources that can be mobilized in the event of an emergency in the database background of the emergency department, an emergency resource information collection is formed;

[0090] The emergency resources include but are not limited to human resources, material and equipment resources, traffic and transportation resources, etc.;

[0091] Among them, human resources such as available maintenance personnel, technical experts and their skills and geographical locations;

[0092] Among them, materials and equipment resources such as maintenance equipment inventory (e.g. generators, transformers), material inventory (e.g. cables, spare parts);

[0093] Among them, traffic and transportation resources such as available maintenance vehicles, transportation tools and their locations and status;

[0094] Furthermore, the method of constructing and training the partition risk assessment model based on the power grid information set and the environmental information set is:

[0095] For each grid zone, the following steps are performed to train the zone risk assessment model:

[0096] Step 21: Divide the power grid information set and the environment information set into time periods according to a preset time period;

[0097] Step 22: For each time period, mathematical statistics are performed on various parameters in the power grid information set and the environment information set to obtain several key statistical features;

[0098] Specifically, the key statistical features may include the variance, average value, maximum and minimum value difference and other statistical features of various power historical parameter values ​​in the period, the health status of each power grid equipment, and various statistical features of various environmental parameters in the period, and the quantitative values ​​of all geographic information features, such as altitude, slope, land use type, terrain classification index, digital elevation and other information;

[0099] Step 23: setting a fault label for each time period; the fault label is 0 or 1, wherein 1 indicates that a fault requiring maintenance occurs during the time period, and 0 indicates that a fault requiring maintenance does not occur during the time period;

[0100] Step 24: Using the Bayesian network model as a partition risk assessment model, wherein the partition risk assessment model uses key statistical features of each time period as input;

[0101] Step 25: Use a structural learning algorithm to construct a Bayesian network structure to represent the conditional dependency between key statistical features, and manually add known physical or engineering constraints; specifically, the physical or engineering constraints are, for example, the physical dependency between overtemperature and transformer failure;

[0102] Step 26: The partition risk assessment model outputs an estimated probability of failure occurring in each time period according to the key statistical characteristics of the time period; and iteratively optimizes the parameters of each conditional probability table in the Bayesian network by using the maximum likelihood estimation or Bayesian estimation method for each time period;

[0103] Further preferably, a cross-validation method (such as k-fold cross-validation) can be used to evaluate the model performance, and indicators such as ROC curve and AUC can be used to evaluate the prediction accuracy of the partition risk assessment model;

[0104] It can be understood that the Bayesian network represents variables and their relationships through nodes and edges, and the conditional probability table describes the quantitative details of these relationships, so that the conditional probability table can be used to know which variables have a significant impact on the change in fault probability (that is, which factors are most likely to cause power grid failures), and quantify the contribution of different factors to power grid failures;

[0105] Furthermore, the method of collecting real-time grid load data of the grid is:

[0106] By means of smart meters arranged in each grid zone, real-time power load in the grid zone is collected in real time as grid load data;

[0107] Specifically, the real-time power load, i.e., the actual power consumption in each power grid partition, can be measured by the highest load value within a specific time, the lowest load value within a specific time, or the speed of load change over time;

[0108] Furthermore, the method of calculating the estimated resource demand ratio distribution of the power grid by combining the partition risk assessment model and the power grid load data is as follows:

[0109] Each grid partition is numbered as i;

[0110] The real-time power load of the i-th grid partition is marked as Li;

[0111] The number of key power-consuming facilities in the i-th grid partition is marked as Ni;

[0112] The failure probability of the i-th power grid partition estimated by the partition risk assessment model is marked as FPi; it can be understood that the estimated failure probability of the i-th power grid partition can be obtained by collecting various key statistical features in the latest period, and then inputting these key statistical features into the partition risk assessment model, and the partition risk assessment model outputs;

[0113] The estimated resource demand in the i-th grid partition is labeled Ri;

[0114] The calculation formula for estimated resource demand Ri is:

[0115] ; Wherein, a1, a2 and a3 are preset proportional coefficients;

[0116] Understandably, the power load reflects the amount of electricity demand in a sub-area. A higher power load generally means that the area may have a higher demand for resources. Therefore, under high load conditions, more resources (such as backup generation, additional maintenance personnel) are required to ensure the reliable operation of the power grid;

[0117] The number and importance of critical facilities directly affect the priority of resource allocation. These facilities usually have strict requirements for the continuity of power supply. Therefore, the more critical facilities there are, the more emergency resources they need to ensure;

[0118] A higher probability of failure means a higher risk, and more emergency resources need to be pre-allocated to deal with potential failures;

[0119] The resource demand ratio in the i-th grid partition is labeled Bi;

[0120] Then the resource demand ratio Bi is calculated as: ;It can be understood that the resource demand ratio Bi measures the proportion of emergency resources demanded by each grid area to the total number of emergency resources;

[0121] Furthermore, the method of constructing a comprehensive loss index based on the estimated resource demand ratio distribution and power grid load data is as follows:

[0122] The grid loss index of the i-th grid partition is labeled as Si;

[0123] The calculation formula of the power grid loss index is:

[0124] ; Wherein, a4 and a5 are preset proportional coefficients, and Ltotal is the total load of all grid partitions;

[0125] It can be understood that the resource demand ratio directly reflects the priority of the partition in the overall resource planning. In the event of a fault, the loss suffered by this grid partition will be greater than that of other grid partitions, and therefore, the loss index is greater;

[0126] Failures in high-load areas may lead to greater economic losses or service interruptions, and therefore need to be given priority;

[0127] Furthermore, the method of constructing a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set is as follows:

[0128] Set the allocation ratio variable xi for each grid partition;

[0129] The total amount of emergency resources is set to 1; it should be noted that, due to the large number of types of emergency resources, the total amount of emergency resources represents the total amount of each type of emergency resource, and xi represents the proportion of each type of emergency resource allocated to the i-th power grid partition to the total amount of emergency resources of that type, that is, the ratio of each type of emergency resource allocated to the i-th power grid partition to the total amount of emergency resources is consistent;

[0130] Construct the target optimization function M;

[0131] The expression of the objective optimization function M is: ; Where Pi is the cost of allocating emergency resources to the i-th grid partition; Generally, Pi is a preset parameter, which can be the route length and transportation cost of the emergency resources to the grid area;

[0132] where 1-xi is the proportion of resources not allocated to the ith grid partition, Si measures the potential loss, and It measures the cost of allocating emergency resources. Therefore, the more emergency resources are allocated, the greater the allocation cost. Therefore, the objective optimization function M measures the desire to balance the comprehensive loss not compensated by resources and the allocation cost by reasonably allocating limited emergency resources. That is, by minimizing M, more emergency resources can be arranged for the grid partitions with greater potential losses as much as possible, and too many emergency resources can be avoided as much as possible.

[0133] Construct the first constraint: , used to limit the emergency resources allocated to not exceed the total amount of emergency resources;

[0134] Construct the second constraint: , which is used to limit the resources allocated to any grid partition, is a non-negative decimal;

[0135] Taking the minimization target optimization function M as the optimization target, taking the first constraint condition and the second constraint condition as the constraint condition set, a resource allocation optimization model is constructed;

[0136] Furthermore, the method of using the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan is:

[0137] Using a linear programming solver, by inputting the target optimization function M and the objective function and constraint condition set of the resource allocation optimization model, the emergency resource allocation scheme of the proportion of emergency resources to be allocated to each power grid partition is solved;

[0138] The linear programming solver is such as Gurobi or CPLEX.

[0139] Example 2

[0140] like Figure 2 As shown, an emergency treatment and evaluation system based on power grid disaster loss includes a data collection module, a model training module, a resource allocation model construction module, and a resource allocation module; wherein each module is electrically connected;

[0141] The data collection module collects the power grid information set, the environmental information set, the emergency resource information set and the power grid load data in advance, and sends the power grid information set and the environmental information set to the model training module, and sends the emergency resource information set and the power grid load data to the resource allocation model construction module;

[0142] A model training module, based on a power grid information set and an environmental information set, constructs and trains a partition risk assessment model, and sends the partition risk assessment model to a resource allocation model construction module;

[0143] The resource allocation model construction module calculates the estimated resource demand ratio distribution of the power grid by combining the zoning risk assessment model and the power grid load data, constructs a comprehensive loss index based on the estimated resource demand ratio distribution and the power grid load data, constructs a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set, and sends the resource allocation optimization model to the resource allocation module;

[0144] The resource allocation module uses the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan.

[0145] Example 3

[0146] According to another aspect of the present application, an electronic device is provided. The electronic device may include one or more processors and one or more memories. The memories store computer-readable codes, and when the computer-readable codes are executed by the one or more processors, the factory monitoring and safety method integrating multiple systems as described above may be executed.

[0147] The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, an input / output component, a hard disk, etc. A storage device in the electronic device, such as a ROM or a hard disk, may store a factory monitoring and safety method integrating multiple systems provided in the present application.

[0148] Furthermore, the electronic device may also include a user interface. Of course, this architecture is only exemplary, and when implementing different devices, one or more components in the electronic device may be omitted according to actual needs.

[0149] Example 4

[0150] A computer-readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, an emergency treatment assessment method and system based on power grid disaster losses according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0151] In addition, according to the embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided by the present application;

[0152] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0155] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a method and system for emergency treatment assessment based on power grid disaster losses. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0158] The above embodiments are only used to illustrate the technical method 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An emergency response evaluation method based on power grid disaster loss, characterized in that: The following steps are involved: Step 1: Collect power grid information, environmental information and emergency resource information in advance; Step 2: Based on the grid information set and the environmental information set, build and train the zoning risk assessment model; Step 3: Collect real-time grid load data of the power grid; Step 4: Combine the zoning risk assessment model and grid load data to calculate the estimated resource demand ratio distribution of the grid; Step 5: Construct a comprehensive loss index based on the estimated resource demand ratio distribution and grid load data; Step 6: Based on the comprehensive loss index and the emergency resource information set, a resource allocation optimization model is constructed, and the resource allocation optimization model is solved using the optimization model solving tool to obtain the emergency resource allocation plan; The method of constructing and training the partition risk assessment model based on the power grid information set and the environmental information set is: For each grid zone, the following steps are performed to train the zone risk assessment model: Step 21: Divide the power grid information set and the environment information set into time periods according to a preset time period; Step 22: For each time period, mathematical statistics are performed on various parameters in the power grid information set and the environment information set to obtain several key statistical features; Step 23: setting a fault label for each time period; the fault label is 0 or 1, wherein 1 indicates that a fault requiring maintenance occurs during the time period, and 0 indicates that a fault requiring maintenance does not occur during the time period; Step 24: Using the Bayesian network model as a partition risk assessment model, wherein the partition risk assessment model uses key statistical features of each time period as input; Step 25: Use a structural learning algorithm to construct the structure of the Bayesian network to represent the conditional dependencies between key statistical features, and manually add known physical or engineering constraints; Step 26: The partition risk assessment model outputs an estimated probability of failure occurring in each time period according to the key statistical characteristics of the time period; and iteratively optimizes the parameters of each conditional probability table in the Bayesian network by using the maximum likelihood estimation or Bayesian estimation method for each time period; The method of constructing the resource allocation optimization model based on the comprehensive loss index and the emergency resource information set is: Set the allocation ratio variable xi for each grid partition; Set the total amount of emergency resources to 1; Construct the target optimization function M; The expression of the objective optimization function M is: ; Where Pi is the cost of allocating emergency resources to the i-th grid partition; Where Si is the pre-calculated grid loss index; Construct the first constraint: , used to limit the emergency resources allocated to not exceed the total amount of emergency resources; Construct the second constraint: , which is used to limit the resources allocated to any grid partition, is a non-negative decimal; The resource allocation optimization model is constructed by taking the minimization target optimization function M as the optimization target and taking the first constraint condition and the second constraint condition as the constraint condition set.

2. The method for emergency response assessment based on power grid disaster loss according to claim 1, characterized in that: The collection method of the power grid information set and the environment information set is: According to the geographic information system and the power grid topology structure, the power grid is spatially and functionally partitioned in advance to obtain N power grid partitions, where N is the number mark of the obtained power grid partitions; For each grid zone: Various power parameter sensors and various environmental parameter sensors are pre-installed at key nodes of the power grid partition. During the historical operation of the power grid, the corresponding historical power parameter values ​​are collected in real time through the power parameter sensors, and the corresponding historical environmental parameter values ​​are collected through the environmental parameter sensors; Access historical operation files within the power grid partition, collect historical fault records, equipment status information and key facility information of the power grid partition; Collecting the grid topology of the grid partitions; the grid topology is a grid network diagram, including detailed configurations of nodes and lines; The power historical parameter values ​​of the power parameters, historical fault records, equipment status information, key facility information and power grid topology structure constitute a power grid information set; Collect geographic information about the area where the power grid is zoned; The historical environmental parameter values ​​and geographic information constitute an environmental information set.

3. The method for emergency response assessment based on power grid disaster loss according to claim 2 is characterized in that: The method of calculating the estimated resource demand ratio distribution of the power grid by combining the zoning risk assessment model and the power grid load data is as follows: Each grid partition is numbered as i; The real-time power load of the i-th grid partition is marked as Li; The number of key power-consuming facilities in the i-th grid partition is marked as Ni; The failure probability of the i-th power grid partition estimated by the partition risk assessment model is marked as FPi; The estimated resource demand in the i-th grid partition is labeled Ri; The calculation formula for estimated resource demand Ri is: ; Wherein, a1, a2 and a3 are preset proportional coefficients; The resource demand ratio in the i-th grid partition is labeled Bi; Then the resource demand ratio Bi is calculated as: .

4. The method for emergency response assessment based on power grid disaster loss according to claim 3 is characterized in that: The method of constructing the comprehensive loss index based on the estimated resource demand ratio distribution and power grid load data is as follows: The grid loss index of the i-th grid partition is labeled as Si; The calculation formula of the power grid loss index is: ; Among them, a4 and a5 are preset proportional coefficients, and Ltotal is the total load of all grid partitions.

5. The method for emergency response assessment based on power grid disaster loss according to claim 4 is characterized in that: The method of using the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan is: Using a linear programming solver, by inputting the target optimization function M and the objective function and constraint set of the resource allocation optimization model, the emergency resource allocation plan for the proportion of emergency resources that need to be allocated to each power grid partition is solved.

6. An emergency response evaluation system based on power grid disaster loss, which is used to implement the emergency response evaluation method based on power grid disaster loss according to any one of claims 1 to 5, characterized in that: It includes a data collection module, a model training module, a resource allocation model construction module, and a resource allocation module; wherein each module is electrically connected; The data collection module collects the power grid information set, the environmental information set, the emergency resource information set and the power grid load data in advance, and sends the power grid information set and the environmental information set to the model training module, and sends the emergency resource information set and the power grid load data to the resource allocation model construction module; A model training module, based on a power grid information set and an environmental information set, constructs and trains a partition risk assessment model, and sends the partition risk assessment model to a resource allocation model construction module; The resource allocation model construction module calculates the estimated resource demand ratio distribution of the power grid by combining the zoning risk assessment model and the power grid load data, constructs a comprehensive loss index based on the estimated resource demand ratio distribution and the power grid load data, constructs a resource allocation optimization model based on the comprehensive loss index and the emergency resource information set, and sends the resource allocation optimization model to the resource allocation module; The resource allocation module uses the optimization model solving tool to solve the resource allocation optimization model and obtain the emergency resource allocation plan.

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the emergency processing and assessment method based on power grid disaster loss according to any one of claims 1 to 5 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute an emergency processing and evaluation method based on power grid disaster loss as claimed in any one of claims 1 to 5.

Images