Power grid intelligent repair collaborative optimization method and system based on perception-decision-execution closed loop and medium

Abstract

This invention discloses a collaborative optimization method, system, and medium for intelligent power grid emergency repair based on a closed-loop perception-decision-execution system. The method first collects meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area, integrating them into multi-source perception data. This data is then input into a two-layer optimization model for calculation. The outer layer model combines the fault location, road conditions, and load levels to generate the optimal repair path decision, while the inner layer model outputs a fault recovery decision based on the power grid topology and load priority. Finally, the two types of decisions are converted into emergency repair resource scheduling instructions and power grid control instructions, respectively, and emergency repair operations and load restoration operations are executed simultaneously. This invention effectively solves the problems of difficult path selection, information asymmetry, and slow response speed faced by power grid repair and restoration when power failures are caused by natural disasters or accidents, significantly improving the emergency response capability and power supply restoration speed of the power grid, and effectively ensuring power supply stability and security.

Description

Technical Field

[0001] This invention relates to the field of disaster emergency response and power grid repair technology, and in particular to a collaborative optimization method, system and medium for intelligent power grid repair based on a perception-decision-execution closed loop. Background Technology

[0002] Located near the collision zone of the Indian Ocean Plate and the Eurasian Plate, the Yunnan-Guizhou region experiences frequent geological activity and concentrated seasonal heavy rainfall, leading to a high incidence of geological disasters such as landslides and mudslides, posing a serious threat to the safe and stable operation of the regional power grid. In recent years, extreme weather events have increased, exacerbating the damage to power grid equipment and transmission lines, resulting in widespread power outages, difficulties in emergency repairs, and long recovery periods, severely impacting normal economic and social operations and emergency disaster relief efforts. Currently, although power companies have conducted research and application of geological disaster monitoring and early warning technologies, significant shortcomings remain in emergency response, primarily manifested in the following ways: First, a disaster emergency triggering mechanism based on meteorological correlations has not yet been established, making it difficult to achieve accurate early warnings and proactive deployment before heavy rainfall; second, in-disaster reconnaissance methods are limited, lacking real-time and accurate assessment of disaster development trends, resulting in a "disaster black box period"; third, post-disaster repair and dispatch rely on manual experience, lacking digital and intelligent decision support systems, leading to suboptimal allocation of repair resources and low recovery efficiency.

[0003] In the fields of disaster emergency response and power grid repair, unmanned aerial vehicle (UAV) technology, due to its flexibility, efficiency, and ability to access areas inaccessible to humans, has been gradually applied to tasks such as disaster reconnaissance and material delivery. Existing UAV systems mostly rely on GPS navigation and preset flight paths for mission execution. In complex mountainous terrain, environments with strong electromagnetic interference, or where communication is disrupted due to disasters, their positioning accuracy and autonomous adaptability are significantly insufficient. Furthermore, most UAV payloads have limited functionality; their vision systems only support basic image acquisition and lack the ability to be deeply integrated with specialized scenarios such as power grid fault identification, repair route planning, and multi-source data fusion. In recent years, although some research has combined computer vision with UAVs to achieve target recognition and tracking based on color and shape, its processing power is limited, its environmental adaptability is weak, and it has failed to achieve coordination with power grid emergency command systems, making it difficult to meet the high-order requirements of real-time performance, accuracy, and coordination in power grid repair under geological disasters. Summary of the Invention

[0004] Based on this, it is necessary to propose a collaborative optimization method, system, and medium for intelligent power grid emergency repair based on a closed loop of perception-decision-execution to address the above problems.

[0005] A collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop, the method comprising: Acquire meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data; The multi-source sensing data is input into a two-layer optimization model for calculation. The outer layer model generates the optimal emergency repair path decision based on the fault location, road condition, and load level, while the inner layer model generates the fault recovery decision based on the power grid topology and load priority. The optimal repair path decision is converted into a repair resource scheduling instruction, and the fault recovery decision is converted into a power grid control instruction. The repair resource scheduling instruction and the power grid control instruction are executed, and the repair operation and load restoration operation are performed simultaneously.

[0006] Specifically, acquiring meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data includes: Acquire meteorological data, resource allocation data, and drone oblique photography data of the disaster-stricken area; The SFM algorithm is used to convert UAV oblique photogrammetry data into 3D point cloud models of power grid equipment and roads. The CNN neural network is used to identify the power grid data and the road traffic data in the three-dimensional point cloud model of the power grid equipment, respectively. Multi-source sensing data is generated by fusing meteorological data, resource allocation data, power grid data, and road traffic data using a weighted average method.

[0007] The power grid data includes load importance, repair time, load volume, and fault location; the road traffic data includes travel time and road traffic status; the resource allocation data includes the number of repair teams, the number of tools and equipment, and the repair time; and the objective function of the outer model is: In the formula: For nodes The importance of the load, The node at time t The shear load, For time weighting coefficients, For the set of fault points, To get to the fault location Travel time Fault point The time for emergency repairs.

[0008] The constraints of the outer model include at least one of resource allocation data constraints, road traffic data constraints, and disaster dynamic constraints. The resource configuration data constraints include: the number of schedulable emergency repair teams is limited, and each fault point can only be assigned to one emergency repair team for repair within the same time period; The road traffic data constraints include: based on the real-time road traffic status obtained by UAV survey, damaged road sections are excluded in the route planning, and the planned driving route must meet the requirement that the maximum speed limit on mountain roads does not exceed 40km / h; The disaster dynamic constraints include: when the secondary disaster risk level calculated by the meteorological data through the risk assessment model is greater than or equal to a preset threshold of 0.7, the emergency repair work in the corresponding area is suspended, and the emergency repair route is replanned based on the updated disaster level data.

[0009] The objective function of the inner model is: In the formula: For load nodes The road traffic status, The node at time t The load capacity.

[0010] The power grid data includes active power, reactive power, node voltage, line current, and distributed generation output. The constraints of the inner model include at least one of power flow constraints, voltage and current constraints, and distributed generation constraints. The power flow constraints include: using the Distflow model to constrain the active power transmission and reactive power transmission of the lines; The voltage and current constraints include: the node voltage fluctuation range does not exceed ±5% of the rated voltage, and the line current does not exceed its rated current carrying capacity. The distributed power source constraints are as follows: the output of the distributed power source must meet the preset technical characteristic constraints and be adapted to the distribution characteristics of new energy sources in the Yunnan-Guizhou region.

[0011] Specifically, the multi-source sensing data is input into a two-layer optimization model for calculation. The outer layer model generates the optimal repair path decision based on the fault location, road condition, and load level, while the inner layer model generates a fault recovery decision based on the power grid topology and load priority. Substitute the multi-source sensing data into the objective function and constraints of the outer model, and solve for the optimal emergency repair path decision at the current moment based on the improved Harris Eagle optimization algorithm. Substitute the multi-source sensing data into the objective function and constraints of the inner model, and based on the optimal emergency repair path decision, solve to obtain the fault recovery decision at the current moment.

[0012] Specifically, substituting the multi-source sensing data into the objective function of the outer model and solving for the optimal repair path decision at the current moment based on the improved Harris Eagle optimization algorithm includes: Based on multi-source sensing data, an initial Harris Eagle population is generated using the Circle chaotic mapping formula. Each candidate solution in the population corresponds to a repair order and path allocation scheme. For each candidate solution, the multi-source sensing data is substituted into the objective function of the outer model. The objective function value of each candidate solution in the population is calculated based on the objective function of the outer model. The candidate solution that satisfies all constraints and has the smallest objective function value is selected as the optimal emergency repair path decision.

[0013] A smart power grid emergency repair collaborative optimization system based on a perception-decision-execution closed loop, the system comprising: The data acquisition module acquires meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data; The dual-layer model module is used to input multi-source sensing data into the dual-layer optimization model for calculation. The outer layer model generates the optimal emergency repair path decision based on the fault location, road condition and load level, while the inner layer model generates the fault recovery decision based on the power grid topology and load priority. The power grid emergency repair module is used to convert the optimal emergency repair path decision into emergency repair resource scheduling instructions, convert the fault recovery decision into power grid control instructions, execute the emergency repair resource scheduling instructions and power grid control instructions, and simultaneously perform emergency repair operations and load restoration operations.

[0014] A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method described above.

[0015] The embodiments of the present invention have the following beneficial effects: This invention, by setting up multi-source sensing data acquisition technology, can acquire meteorological data collected by meteorological sensors, power grid data of disaster-stricken areas collected by drones, and road traffic data in real time. This provides an accurate data foundation for subsequent optimization decisions. Because the multi-source sensing data covers real-time meteorological information, power grid status, and road traffic conditions, the outer layer model can determine the repair path within the optimal time window, while the inner layer model can generate detailed fault recovery decisions based on the power grid topology and load priorities.

[0016] Furthermore, a two-layer optimization model is set up. Because the outer layer model makes optimization decisions on fault location, road conditions, and load levels, and the inner layer model makes optimization decisions on power grid topology and load priority, the two-layer optimization model can ensure that the repair path and restoration strategy are optimal in terms of technology, economy, and safety. This improves the utilization efficiency of repair resources and the restoration speed, thus achieving the effect of improving repair efficiency and restoring power supply.

[0017] Furthermore, by translating optimal repair path decisions into specific action instructions that guide repair personnel, the system ensures that repair teams can carry out repair operations efficiently. Similarly, by translating fault restoration decisions into grid control commands, the system ensures rapid and accurate power restoration operations. This command-based execution method not only reduces communication costs but also ensures the accuracy and continuity of each step of the operation, thereby significantly improving the efficiency of repair and restoration.

[0018] In summary, this invention effectively solves the problems of difficult path selection, information asymmetry, and slow response speed in the process of power grid repair and restoration during power outages caused by natural disasters or accidents, thereby improving the power grid's emergency response capability and the speed of restoring normal power supply in the face of emergencies, and ensuring the stability and security of power supply. Attached Figure Description

[0019] 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.

[0020] in: Figure 1 A flowchart illustrating an embodiment of a collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop provided by the present invention; Figure 2 A schematic diagram of an embodiment of a power grid intelligent emergency repair collaborative optimization system based on a perception-decision-execution closed loop provided by the present invention; Figure 3 A schematic diagram of the structure of an embodiment of the medium provided by the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an embodiment of a collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop, provided by the present invention. The method includes: S101: Acquire meteorological data, resource allocation data, power grid data, and road traffic data of the disaster-stricken area to form multi-source sensing data.

[0023] For example, meteorological data, resource allocation data, and UAV oblique photogrammetry data of the disaster-stricken area are acquired; the UAV oblique photogrammetry data are converted into three-dimensional point cloud models of power grid equipment and roads using the SFM algorithm; power grid data and road traffic data in the three-dimensional point cloud models of power grid equipment are identified by the CNN neural network; and meteorological data, resource allocation data, power grid data, and road traffic data are fused by the weighted average method to generate multi-source sensing data.

[0024] S102: Input multi-source sensing data into a two-layer optimization model for calculation. The outer model generates the optimal repair path decision based on the fault location, road condition and load level, while the inner model generates fault recovery decision based on the power grid topology and load priority.

[0025] For example, the power grid data includes load importance, repair time, load volume, and fault location; the road traffic data includes travel time, road traffic status, active power, reactive power, node voltage, line current, and distributed generation output; and the resource allocation data includes the number of repair teams, the number of tools and equipment, and the repair time. The objective function of the outer model is set as follows: ; In the formula: For nodes The importance of the load, The node at time t The shear load, For time weighting coefficients, For the set of fault points, To get to the fault location Travel time Fault point The time for emergency repairs.

[0026] Furthermore, the constraints of the outer model include at least one of resource allocation data constraints, road traffic data constraints, and disaster dynamic constraints; Among them, the resource allocation data constraints include: the number of dispatchable emergency repair teams is limited, and each fault point can only be assigned to one emergency repair team for repair within the same time period; Road traffic data constraints include: based on real-time road traffic status obtained from UAV surveys, excluding damaged road sections in route planning, and ensuring that the planned driving route meets the requirement that the maximum speed limit on mountain roads does not exceed 40 km / h; The disaster dynamic constraints include: when the secondary disaster risk level calculated by the meteorological data through the risk assessment model is greater than or equal to a preset threshold of 0.7, the emergency repair work in the corresponding area is suspended, and the emergency repair route is replanned based on the updated disaster level data.

[0027] The objective function of the inner model is set as follows: ; In the formula: For load nodes The road traffic status, The node at time t The load capacity.

[0028] It should be noted that in the objective function of the inner model, To reach the fault point The road traffic coefficient, used to characterize the impact of road conditions on the arrival time of emergency repair personnel, is calculated by weighting parameters such as road surface water depth, number of fallen trees, and road slope sensed by drones. When the roads are clear, When road conditions deteriorate Increased, resulting in longer actual travel time (in (This refers to the ideal driving time).

[0029] In the inner model, the recovery state of load node i Limited by the time when the repair of fault point j is completed ,and Depend on The time of completion of repair at fault point j is determined by adding the base driving time and the actual repair time. Determined according to the formula shown below: ; in, This refers to the time allotted for emergency repairs at the fault location itself.

[0030] Therefore, road traffic conditions The value of this directly determines the degree of lag in the 'execution' of emergency repair forces, and thus, by constraining the earliest recoverable time of load nodes in the inner model, ultimately affects the total load recovery amount of the system (objective function value). If If the load is too high, the model will automatically prioritize scheduling the load on branch roads that are less affected by traffic or that are repaired faster, in order to achieve optimal recovery efficiency.

[0031] Furthermore, the constraints of the inner model include at least one of power flow constraints, voltage and current constraints, and distributed generation constraints. Among them, power flow constraints include: using the Distflow model to constrain the active power transmission and reactive power transmission of the line; voltage and current constraints include: the node voltage fluctuation range does not exceed ±5% of the rated voltage, and the line current does not exceed its rated current carrying capacity; and distributed generation constraints are: the output of distributed generation must meet the preset technical characteristic constraints and be adapted to the distribution characteristics of new energy in the Yunnan-Guizhou region.

[0032] Furthermore, by substituting multi-source sensing data into the objective function and constraints of the outer model, and based on the improved Harris Eagle optimization algorithm, the optimal repair path decision for the current moment is obtained. Specifically, the initial Harris Eagle population is generated using Circle chaotic mapping. When generating the initial Harris Eagle population using Circle chaotic mapping, its... Chaotic sequence of decision variables The iterative formula is: ; in, and The Circle mapping control parameters are set to values ​​of [values ​​to be filled in]. and ; The generated chaotic sequence Mapped to the domain of emergency repair path scheduling variables In the process, a uniformly distributed initial population solution is generated. Each candidate solution in the population corresponds to a repair order and path allocation scheme; for each candidate solution, multi-source sensing data is substituted into the objective function of the outer model.

[0033] Furthermore, the objective function value of each candidate solution in the population is calculated based on the objective function of the outer model. A nonlinear escape energy update mechanism is introduced, and iterative search is performed according to the escape energy update formula. In the later stages of iteration, an elite back-learning strategy is applied to the current best candidate solution, outputting the candidate solution that satisfies all constraints and minimizes the objective function value as the optimal repair path decision. The elite back-learning strategy specifically involves: at the end of each iteration, extracting the top-ranked solutions in the current population based on fitness. Individuals constitute the elite subpopulation The inverse solution is calculated using the following formula. : ; in, For elite individuals in the first Assigning variables to the repair nodes in the dimension. and The current search space is in the th order. The dynamic lower bound and dynamic upper bound of a dimension. To obey A uniformly distributed dynamic learning factor; if the inverse solution If the objective function value is better than that of the original elite individual, then that individual is replaced and introduced into the next generation of the population.

[0034] In the nonlinear escape energy update mechanism, the escape energy of the prey (the optimal solution of the objective function) is... The decay formula is updated to a cosine decreasing model: ; in, for Random initial energy between This represents the current iteration number. The maximum number of iterations, It is a non-linear adjustment factor; when When, the algorithm performs a discrete search targeting globally unexplored faulty nodes; when At that time, the algorithm performs local containment optimization for the current repair path.

[0035] Furthermore, multi-source sensing data is substituted into the objective function and constraints of the inner model, and the fault recovery decision at the current moment is obtained based on the optimal emergency repair path decision. Specifically, the nonlinear constraints of the power grid flow are transformed into second-order cone constraints; the objective function of the inner model is maximized, and the solution is obtained by combining the time-series information and power supply boundary provided by the optimal emergency repair path decision under the constraint conditions; the optimal fault recovery decision is output, including islanding, switching action, and distributed power dispatch scheme.

[0036] S103: Convert the optimal emergency repair path decision into an emergency repair resource scheduling instruction, convert the fault recovery decision into a power grid control instruction, execute the emergency repair resource scheduling instruction and the power grid control instruction, and simultaneously execute the emergency repair operation and load restoration operation.

[0037] For example, the optimal repair path decision is converted into a repair resource scheduling command, and the fault recovery decision is converted into a power grid control command. The repair resource scheduling command and the power grid control command are executed, and repair operations and load restoration operations are performed simultaneously. The simultaneous execution of repair operations and load restoration operations includes: prioritizing the restoration of primary load power to hospitals and communication base stations; dynamically adjusting the repair path based on real-time road status data transmitted by drones; and ensuring the time coordination between repair operations and power grid reconfiguration.

[0038] As described above, this invention, by incorporating multi-source sensing data acquisition technology, can acquire real-time meteorological data from weather sensors, power grid data from disaster-stricken areas collected by drones, and road traffic data. This provides an accurate data foundation for subsequent optimization decisions. Because the multi-source sensing data encompasses real-time meteorological information, power grid status, and road traffic conditions, the outer model can determine the repair path within the optimal time window, while the inner model can generate detailed fault recovery decisions based on the power grid topology and load priorities.

[0039] Furthermore, a two-layer optimization model is set up. Because the outer layer model makes optimization decisions on fault location, road conditions, and load levels, and the inner layer model makes optimization decisions on power grid topology and load priority, the two-layer optimization model can ensure that the repair path and restoration strategy are optimal in terms of technology, economy, and safety. This improves the utilization efficiency of repair resources and the restoration speed, thus achieving the effect of improving repair efficiency and restoring power supply.

[0040] Furthermore, by translating optimal repair path decisions into specific action instructions that guide repair personnel, the system ensures that repair teams can carry out repair operations efficiently. Similarly, by translating fault restoration decisions into grid control commands, the system ensures rapid and accurate power restoration operations. This command-based execution method not only reduces communication costs but also ensures the accuracy and continuity of each step of the operation, thereby significantly improving the efficiency of repair and restoration.

[0041] In summary, this invention effectively solves the problems of difficult path selection, information asymmetry, and slow response speed in the process of power grid repair and restoration during power outages caused by natural disasters or accidents, thereby improving the power grid's emergency response capability and the speed of restoring normal power supply in the face of emergencies, and ensuring the stability and security of power supply.

[0042] like Figure 2 As shown, Figure 2 This is a schematic diagram of an embodiment of a power grid intelligent emergency repair collaborative optimization system based on a perception-decision-execution closed loop, provided by the present invention. The system 10 comprises: The data acquisition module 11 acquires meteorological data, resource allocation data, power grid data, and road traffic data of the disaster-stricken area to form multi-source sensing data.

[0043] The dual-layer model module 12 is used to input multi-source sensing data into the dual-layer optimization model for calculation. The outer layer model generates the optimal emergency repair path decision based on the fault location, road condition and load level, while the inner layer model generates the fault recovery decision based on the power grid topology and load priority.

[0044] The power grid emergency repair module 13 is used to convert the optimal emergency repair path decision into emergency repair resource scheduling instructions, convert the fault recovery decision into power grid control instructions, execute the emergency repair resource scheduling instructions and power grid control instructions, and simultaneously execute emergency repair operations and load restoration operations.

[0045] For example, in the data acquisition module 11, meteorological data, resource allocation data, and UAV oblique photography image data of the disaster area are acquired; the UAV oblique photography image data are converted into a three-dimensional point cloud model of power grid equipment and a three-dimensional point cloud model of roads using the SFM algorithm; the power grid data and road traffic data in the three-dimensional point cloud model of power grid equipment are identified by the CNN neural network; and the meteorological data, resource allocation data, power grid data, and road traffic data are fused by the weighted average method to generate multi-source sensing data.

[0046] In the two-layer model module 12, multi-source sensing data is substituted into the objective function and constraints of the outer layer model, and the optimal repair path decision at the current moment is obtained based on the improved Harris Eagle optimization algorithm. Specifically, based on the multi-source sensing data, an initial Harris Eagle population is generated through the Circle chaotic mapping formula. Each candidate solution in the population corresponds to a repair order and path allocation scheme. For each candidate solution, the multi-source sensing data is substituted into the objective function of the outer layer model, and the objective function value of each candidate solution in the population is calculated according to the objective function of the outer layer model. The candidate solution that satisfies all constraints and has the smallest objective function value is taken as the optimal repair path decision. Further, the multi-source sensing data is substituted into the objective function and constraints of the inner layer model, and the fault recovery decision at the current moment is obtained based on the optimal repair path decision.

[0047] In the power grid emergency repair module 13, the optimal emergency repair path decision is converted into an emergency repair resource scheduling instruction, the fault recovery decision is converted into a power grid control instruction, the emergency repair resource scheduling instruction and the power grid control instruction are executed, and the emergency repair operation and load restoration operation are executed simultaneously.

[0048] like Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an embodiment of the medium provided by the present invention. The medium 20 stores at least one computer program 21, which is executed by a processor to perform the following... Figure 1 The method shown is detailed above and will not be repeated here. In one embodiment, the medium 30 can be a storage chip, hard disk, portable hard disk, USB flash drive, optical disk, or other read / write storage device, or even a server, etc.

[0049] Furthermore, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific or sequential order shown to achieve the desired result. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0050] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer-readable storage media are basically similar to the method embodiments, and therefore described more simply; relevant parts can be referred to the descriptions of the method embodiments.

[0051] The apparatus, device, non-volatile computer-readable storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and non-volatile computer storage medium will not be repeated here.

[0052] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0053] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0055] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0056] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0057] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0058] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0059] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0060] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0062] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0063] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop, characterized in that, The method includes: Acquire meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data; The multi-source sensing data is input into a two-layer optimization model for calculation. The outer layer model generates the optimal emergency repair path decision based on the fault location, road condition, and load level, while the inner layer model generates the fault recovery decision based on the power grid topology and load priority. The optimal repair path decision is converted into a repair resource scheduling instruction, and the fault recovery decision is converted into a power grid control instruction. The repair resource scheduling instruction and the power grid control instruction are executed, and the repair operation and load restoration operation are performed simultaneously.

2. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 1, characterized in that, The acquisition of meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data specifically includes: Acquire meteorological data, resource allocation data, and drone oblique photography data of the disaster-stricken area; The SFM algorithm is used to convert UAV oblique photogrammetry data into 3D point cloud models of power grid equipment and roads. The CNN neural network is used to identify the power grid data and the road traffic data in the three-dimensional point cloud model of the power grid equipment, respectively. Multi-source sensing data is generated by fusing meteorological data, resource allocation data, power grid data, and road traffic data using a weighted average method.

3. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 1, characterized in that, The power grid data includes load importance, repair time, load volume, and fault location; the road traffic data includes travel time and road traffic status; the resource allocation data includes the number of repair teams, the number of tools and equipment, and repair time; and the objective function of the outer model is: In the formula: For nodes The importance of the load, The node at time t The shear load, For time weighting coefficients, For the set of fault points, To get to the fault location Travel time Fault point The time for emergency repairs.

4. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 3, characterized in that, The constraints of the outer model include at least one of resource allocation data constraints, road traffic data constraints, and disaster dynamic constraints; The resource configuration data constraints include: the number of schedulable emergency repair teams is limited, and each fault point can only be assigned to one emergency repair team for repair within the same time period; The road traffic data constraints include: based on the real-time road traffic status obtained by UAV survey, damaged road sections are excluded in the route planning, and the planned driving route must meet the requirement that the maximum speed limit on mountain roads does not exceed 40km / h; The disaster dynamic constraints include: when the secondary disaster risk level calculated by the meteorological data through the risk assessment model is greater than or equal to a preset threshold of 0.7, the emergency repair work in the corresponding area is suspended, and the emergency repair route is replanned based on the updated disaster level data.

5. The method according to claim 3, characterized in that, The objective function of the inner layer model is: In the formula: For load nodes The road traffic status, The node at time t The load capacity.

6. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 5, characterized in that, The power grid data includes active power, reactive power, node voltage, line current, and distributed generation output. The constraints of the inner model include at least one of power flow constraints, voltage and current constraints, and distributed generation constraints. The power flow constraints include: using the Distflow model to constrain the active power transmission and reactive power transmission of the lines; The voltage and current constraints include: the node voltage fluctuation range does not exceed ±5% of the rated voltage, and the line current does not exceed its rated current carrying capacity. The distributed power source constraints are as follows: the output of the distributed power source must meet the preset technical characteristic constraints and be adapted to the distribution characteristics of new energy sources in the Yunnan-Guizhou region.

7. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 3 or 5, characterized in that, The process involves inputting the multi-source sensing data into a two-layer optimization model for calculation. The outer model generates the optimal repair path decision based on the fault location, road conditions, and load level, while the inner model generates a fault recovery decision based on the power grid topology and load priority. Specifically, this includes: Substitute the multi-source sensing data into the objective function and constraints of the outer model, and solve for the optimal emergency repair path decision at the current moment based on the improved Harris Eagle optimization algorithm. Substitute the multi-source sensing data into the objective function and constraints of the inner model, and based on the optimal emergency repair path decision, solve to obtain the fault recovery decision at the current moment.

8. The collaborative optimization method for intelligent power grid emergency repair based on a perception-decision-execution closed loop as described in claim 7, characterized in that, The step of substituting the multi-source sensing data into the objective function of the outer model and solving for the optimal repair path decision at the current moment based on the improved Harris Eagle optimization algorithm specifically includes: Based on multi-source sensing data, an initial Harris Eagle population is generated using the Circle chaotic mapping formula. Each candidate solution in the population corresponds to a repair order and path allocation scheme. For each candidate solution, the multi-source sensing data is substituted into the objective function of the outer model. The objective function value of each candidate solution in the population is calculated based on the objective function of the outer model. The candidate solution that satisfies all constraints and has the smallest objective function value is selected as the optimal emergency repair path decision.

9. A collaborative optimization system for intelligent power grid emergency repair based on a perception-decision-execution closed loop, characterized in that, The system includes: The data acquisition module acquires meteorological data, resource allocation data, power grid data, and road traffic data from the disaster-stricken area to form multi-source sensing data; The dual-layer model module is used to input multi-source sensing data into the dual-layer optimization model for calculation. The outer layer model generates the optimal emergency repair path decision based on the fault location, road condition and load level, while the inner layer model generates the fault recovery decision based on the power grid topology and load priority. The power grid emergency repair module is used to convert the optimal emergency repair path decision into emergency repair resource scheduling instructions, convert the fault recovery decision into power grid control instructions, execute the emergency repair resource scheduling instructions and power grid control instructions, and simultaneously perform emergency repair operations and load restoration operations.

10. A computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to perform the steps of the method as claimed in any one of claims 1 to 8.

Images