Electric power system weight and overload monitoring and flexible regulation and control system

Abstract

The invention relates to self-adaptive control of a power grid, in particular to a weight and overload monitoring and flexible regulation and control system for a power system, which comprises a sensing layer for acquiring operation data of the power system in real time through distributed data acquisition equipment, processing the acquired data and extracting key features; the communication layer is used for realizing data transmission between the sensing layer and the control layer through a distributed communication architecture; the control layer is used for carrying out weight and overload monitoring according to key features of the collected data, generating an optimal flexible regulation and control adaptive control strategy by adopting an improved artificial travel mouse algorithm, converting the optimal flexible regulation and control adaptive control strategy into a corresponding control instruction and issuing the control instruction to the execution layer; the execution layer is used for executing a control instruction through a distributed instruction execution terminal so as to relieve a heavy overload state; according to the technical scheme, the defects that in the prior art, it is difficult to generate an effective self-adaptive control strategy in combination with the characteristics of the power system, and efficient and flexible regulation and control cannot be conducted on the power system can be effectively overcome.

Description

Technical Field

[0001] The present invention relates to the adaptive control of power grids, and particularly to a system for monitoring and flexibly regulating heavy overloads in a power system. Background Art

[0002] With the continuous growth of global energy demand and the continuous transformation of the energy structure, the power system faces unprecedented challenges. On the one hand, the large-scale access of renewable energy has significantly increased the complexity and uncertainty of the power grid, bringing huge pressure to the stable operation of the power system; on the other hand, users' requirements for power supply quality and reliability are increasing day by day, and the power system needs to have stronger adaptive capabilities and regulation flexibility.

[0003] In a power system, heavy overloads occur frequently, mainly due to reasons such as load fluctuations, equipment failures, or unreasonable power grid structures. Heavy overloads not only affect the stable operation of the power grid but may also cause serious consequences such as equipment damage and power supply interruptions. Traditional power system monitoring and regulation schemes are often based on fixed rules and parameters and are difficult to adapt to the complex and changing power grid environment. Especially when faced with sudden load changes and fluctuations in the output of renewable energy, traditional schemes often seem inadequate.

[0004] To address the above challenges, the power system needs to introduce more intelligent and better-adaptive monitoring and regulation schemes. As a control method that can automatically adjust control strategies according to the dynamic characteristics of the system and changes in the external environment, adaptive control provides a new solution for the monitoring and flexible regulation of heavy overloads in the power system. By means of real-time monitoring of the power grid state, prediction of load changes, and optimization of regulation strategies, adaptive control can help the power system achieve stable operation and supply-demand balance.

[0005] However, the current research on applying adaptive control to the field of monitoring and flexible regulation of heavy overloads in the power system is still in its infancy. How to combine the characteristics of the power system, design effective adaptive control algorithms and strategies, and achieve the stable operation and efficient regulation of the power system is an urgent problem to be solved currently. Summary of the Invention

[0006] In view of the above-mentioned drawbacks of the prior art, the present invention provides a system for monitoring and flexibly regulating heavy overloads in a power system, which can effectively overcome the defects of the prior art that it is difficult to generate effective adaptive control strategies in combination with the characteristics of the power system and cannot perform efficient and flexible regulation on the power system.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions: A system for monitoring and flexibly regulating heavy overloads in a power system, comprising: The perception layer collects the operation data of the power system in real time through distributed data acquisition devices, processes the collected data, and extracts key features; The communication layer realizes data transmission between the perception layer and the control layer through a distributed communication architecture; The control layer monitors overloads and heavy loads based on the key features of the collected data. Meanwhile, it uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer; The execution layer executes the control instructions through distributed instruction execution terminals to relieve the overload and heavy load states; Among them, in the improved artificial lemming algorithm: When simulating the long-distance migration behavior of lemmings, on the one hand, an adaptive step factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optima; on the other hand, a mutation operation is introduced to increase population diversity and avoid premature convergence to local optima; After generating a new solution, a memory mechanism is introduced to use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency; Optimize the energy decay mechanism by introducing an acceleration factor to accelerate convergence when approaching the optimal solution.

[0008] Preferably, the perception layer collects the operation data of the power system in real time through distributed data acquisition devices, processes the collected data, and extracts key features, including: Through intelligent meters, synchronized phasor measurement units PMU and sensors arranged in a distributed manner, the voltage, current and power operation data of the power system are collected in real time; Use edge computing technology to process the collected data, extract key features, and send them to the control layer through the communication layer.

[0009] Preferably, the control layer monitors overloads and heavy loads based on the key features of the collected data, including: Use state estimation technology to evaluate the overload and heavy load states of the power system in combination with the key features of the collected data; Based on the state estimation results, potential risks are detected in advance through an overload and heavy load risk warning model, and risk warnings are issued.

[0010] Preferably, the control layer uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer, including: S1. Determine the objective function of flexible regulation adaptive control; S2. Determine the constraint conditions of flexible regulation adaptive control; S3. Combine the objective function and constraint conditions of flexible regulation adaptive control to construct a flexible regulation adaptive control model; S4. Use the improved artificial lemming algorithm to perform multi-objective optimization on the flexible regulation adaptive control model, and convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and send them to the execution layer.

[0011] Preferably, determining the objective function of flexible regulation adaptive control in S1 includes: Based on the power grid power loss function f 1( x ), the regulation cost function f 2( x ), and the distributed energy consumption function f 3( x ), determine the objective function of flexible regulation adaptive control F : ; Wherein, x Is the decision variable, including the active power output and reactive power output of the generator, the distribution adjustment amount of the load, the output of distributed energy, and the switching state of reactive power compensation equipment, , , Are the weight coefficients of the power grid power loss function f 1( x ), the regulation cost function f 2( x ), and the distributed energy consumption function f 3( x ); Determining the constraint conditions of flexible regulation adaptive control in S2 includes: Take the power grid voltage constraint, power grid current constraint, power grid power balance constraint, and equipment capacity constraint as the constraint conditions of flexible regulation adaptive control.

[0012] Preferably, in S4, using the improved artificial lemming algorithm to perform multi-objective optimization on the flexible regulation adaptive control model, and converting the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and sending them to the execution layer includes: S41. Randomly generate an initial population of a certain scale within the search space. Each lemming individual in the initial population represents a potential solution, and parameter initialization is performed; S42. In each iteration, generate a new solution by simulating one of the behaviors of long-distance migration of lemmings, lemming burrowing behavior, lemming foraging behavior, and lemming avoidance behavior to optimize the quality of the solution; S43. After generating a new solution, introduce a memory mechanism, use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency; S44. Use the objective function of flexible regulation and adaptive control F Evaluate each lemming individual in the population and calculate the corresponding fitness value; S45. Record and update the current optimal solution; S46. Determine whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, determine the simulated target behavior according to the optimized energy decreasing mechanism and return to S42. Otherwise, use the current optimal solution as the optimal flexible regulation and adaptive control strategy; S47. Convert the generated optimal flexible regulation and adaptive control strategy into corresponding control instructions and send them to the execution layer.

[0013] Preferably, in S42, in each iteration, generate a new solution by simulating one of the behaviors of lemming long-distance migration behavior, lemming burrowing behavior, lemming foraging behavior, and lemming avoidance behavior to optimize the quality of the solution, including: By simulating the long-distance migration behavior of lemmings when food is scarce, explore a new search space, and introduce the random factor of Brownian motion during migration to enhance the randomness of migration and the global search ability: ; Where and are the positions of the lemming individual i at the k th and the k +1th iterations respectively, is the position of the current optimal solution, is the position of a randomly selected lemming individual A at the k th iteration, is the Brownian motion vector, F is the direction flag, randomly taking values 1 or -1, r 1 is a random number; By simulating the behavior of lemmings digging burrows, perform local search in the current area: ; Where is the position of a randomly selected lemming individual B at the k th iteration, r 2 is a random number related to the number of iterations; By simulating the behavior of lemmings foraging near caves, local search is carried out in the current high-quality area, that is, the current high-quality area is exploited, and spiral search is introduced during foraging to conduct more refined local search: ; Among them, is a random search factor in a spiral shape, r 3 is a random number; By simulating the behavior of lemmings avoiding when encountering predators, further local search is carried out in the current high-quality area, that is, the current high-quality area is further exploited, and deceptive actions are introduced during avoidance to make it difficult for predators to track lemmings and improve the success rate of avoidance: ; Among them, Levy ( Dim ) is the Levy flight function, simulating the deceptive actions during the lemmings' avoidance process, G is the escape coefficient, which decreases with the increase of the number of iterations.

[0014] Preferably, when simulating the long-distance migration behavior of lemmings, an adaptive step size factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optimum: The adaptive step size factor is expressed by the following formula: ; Among them, is the lemming individual i at the k +1th iteration of the adaptive step size factor, S max is the maximum step size, k max is the maximum number of iterations, Var , Mean are the position variance and position mean of the current population respectively, is the step size attenuation coefficient, is the weight coefficient; The long-distance migration behavior of lemmings after introducing the adaptive step size factor is expressed by the following formula: ; Among them, is the lemming individual i at the k th iteration of the adaptive step size factor; When simulating the long-distance migration behavior of lemmings, mutation operation is introduced to increase population diversity and avoid falling into local optimum prematurely: Based on the introduction of the adaptive step size factor, the long-distance migration behavior of lemmings after introducing the mutation operation is expressed by the following formula: ; Among them, is the mutation vector, , is a vector randomly generated from the uniform distribution , is the mutation parameter, p is the mutation probability, r 4 is a random number.

[0015] Preferably, in S43, after the new solution is generated, a memory mechanism is introduced to use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency, including: The memory mechanism is expressed by the following formula: ; Among them, is the position after updating the position of the lemming individual i at the k +1-th iteration by introducing the memory mechanism, is the position of the historical optimal solution, is the learning factor, is the random perturbation factor.

[0016] Preferably, in S46, it is judged whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, the simulated target behavior is determined according to the optimized energy decreasing mechanism and S42 is returned. Otherwise, the current optimal solution is used as the optimal flexible control adaptive control strategy, including: Optimize the energy decreasing mechanism by introducing an acceleration factor to accelerate convergence when approaching the optimal solution. The optimized energy decreasing mechanism is expressed by the following formula: ; Among them, E k+1 is the energy at the k +1-th iteration, E 0 is the initial energy, is the attenuation coefficient, is the acceleration factor, d 1 is the distance between the current optimal solution and the population average solution, d 2 is the distance between the initial optimal solution and the population average solution, is the acceleration factor coefficient; When E k+1When >1, determine that the target behavior for the next iteration simulation is the long-distance migration behavior or the burrowing behavior of lemmings, and return to S42; when E k+1 ≤1, determine that the target behavior for the next iteration simulation is the foraging behavior or the avoidance behavior of lemmings, and return to S42.

[0017] Compared with the prior art, a power system heavy overload monitoring and flexible regulation system provided by the present invention adopts an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy. In the improved artificial lemming algorithm, when simulating the long-distance migration behavior of lemmings, on the one hand, an adaptive step factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optimum; on the other hand, a mutation operation is introduced to increase population diversity and avoid premature convergence to local optimum; and after a new solution is generated, a memory mechanism is introduced to use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency; at the same time, the energy decay mechanism is optimized by introducing an acceleration factor to accelerate convergence when approaching the optimal solution, so as to quickly generate an effective adaptive control strategy in combination with the characteristics of the power system, fully adapt to the complex and changeable power grid environment, make the power system have stronger adaptive ability and regulation flexibility, and realize the stable operation and efficient flexible regulation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0019] Figure 1 is a schematic diagram of the system of the present invention; Figure 2 is a schematic flowchart of generating an optimal flexible regulation adaptive control strategy by using an improved artificial lemming algorithm in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0021] A power system heavy overload monitoring and flexible regulation system, as Figure 1 shown, includes: The sensing layer collects the operation data of the power system in real time through distributed data acquisition devices, and processes the collected data to extract key features; The communication layer realizes data transmission between the sensing layer and the control layer through a distributed communication architecture; The control layer monitors heavy overload according to the key features of the collected data. At the same time, it uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer; The execution layer executes the control instructions through distributed instruction execution terminals to relieve the heavy overload state; Among them, in the improved artificial lemming algorithm: When simulating the long-distance migration behavior of lemmings, on the one hand, an adaptive step factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optimum; on the other hand, a mutation operation is introduced to increase population diversity and avoid falling into local optimum prematurely; After generating a new solution, a memory mechanism is introduced to use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency; Optimize the energy decreasing mechanism, introduce an acceleration factor to accelerate convergence when approaching the optimal solution.

[0022] The sensing layer collects the operation data of the power system in real time through distributed data acquisition devices, and processes the collected data to extract key features, including: Through smart meters, synchronized phasor measurement units PMU and sensors set distributively, the voltage, current and power operation data of the power system are collected in real time; Use edge computing technology to process the collected data, extract key features, and send them to the control layer through the communication layer.

[0023] The control layer monitors heavy overload according to the key features of the collected data, including: Use state estimation technology, combined with the key features of the collected data, to evaluate the heavy overload state of the power system; Based on the state estimation results, potential risks are discovered in advance through a heavy overload risk early warning model, and risk early warning is carried out.

[0024] The control layer uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer, including: S1. Determine the objective function of flexible regulation adaptive control; S2. Determine the constraint conditions of flexible regulation adaptive control; S3. Combine the objective function and constraint conditions of flexible regulation adaptive control to construct a flexible regulation adaptive control model; S4. Use the improved artificial lemming algorithm to perform multi-objective optimization solution on the flexible regulation adaptive control model, and convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and send them to the execution layer.

[0025] Specifically, determining the objective function of flexible regulation adaptive control in S1 includes: According to the power grid power loss function f 1( x ), regulation cost function f 2( x ) and distributed energy consumption function f 3( x ), determine the objective function of flexible regulation adaptive control F : ; Among them, x is the decision variable, including the active power output and reactive power output of the generator, the distribution adjustment amount of the load, the output of distributed energy, and the switching state of reactive power compensation equipment, , , are the weight coefficients of the power grid power loss function f 1( x ), regulation cost function f 2( x ), and distributed energy consumption function f 3( x ) respectively; Specifically, determining the constraint conditions of flexible regulation adaptive control in S2 includes: Regard the power grid voltage constraint, power grid current constraint, power grid power balance constraint, and equipment capacity constraint as the constraint conditions of flexible regulation adaptive control.

[0026] Specifically, in S4, use the improved artificial lemming algorithm to perform multi-objective optimization solution on the flexible regulation adaptive control model, and convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and send them to the execution layer. As Figure 2 shown, it includes: S41. Randomly generate an initial population of a certain scale in the search space. Each lemming individual in the initial population represents a potential solution, and parameter initialization is performed; S42. In each iteration, generate a new solution by simulating one of the behaviors of lemming long-distance migration behavior, lemming cave-digging behavior, lemming foraging behavior, and lemming avoidance behavior to optimize the quality of the solution; S43. After generating a new solution, introduce a memory mechanism, use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency; S44. Use the objective function of flexible regulation and adaptive control F Evaluate each lemming individual in the population and calculate the corresponding fitness value; S45. Record and update the current optimal solution; S46. Determine whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, determine the simulated target behavior according to the optimized energy decreasing mechanism and return to S42. Otherwise, use the current optimal solution as the optimal flexible regulation and adaptive control strategy; S47. Convert the generated optimal flexible regulation and adaptive control strategy into corresponding control instructions and send them to the execution layer.

[0027] ①S42. In each iteration, generate a new solution by simulating one of the behaviors of lemming long-distance migration behavior, lemming burrowing behavior, lemming foraging behavior, and lemming evasion behavior to optimize the quality of the solution, including: By simulating the long-distance migration behavior of lemmings when food is scarce, explore a new search space, and introduce the random factor of Brownian motion during migration to enhance the randomness of migration and the global search ability: ; where , are the positions of the lemming individual i at the k th and the k +1th iterations respectively, is the position of the current optimal solution, is the position of a randomly selected lemming individual A at the k th iteration, is the Brownian motion vector, F is the direction flag, randomly taking values of 1 or -1, r 1 is a random number; By simulating the behavior of lemmings digging burrows, perform local search in the current area: ; where is the position of a randomly selected lemming individual B at the k th iteration, r 2 is a random number related to the iteration number; By simulating the behavior of lemmings foraging near caves, local search is carried out in the current high-quality area, that is, the current high-quality area is exploited, and spiral search is introduced during foraging to conduct more refined local search: ; Among them, is a random search factor in a spiral shape, r 3 is a random number; By simulating the behavior of lemmings avoiding when encountering predators, further local search is carried out in the current high-quality area, that is, the current high-quality area is further exploited, and deceptive actions are introduced during avoidance to make it difficult for predators to track lemmings and improve the success rate of avoidance: ; Among them, Levy ( Dim ) is the Lévy flight function, simulating the deceptive actions during the lemmings' avoidance process, G is the escape coefficient, which decreases with the increase of the number of iterations.

[0028] Specifically, when simulating the long-distance migration behavior of lemmings, an adaptive step size factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optima: The adaptive step size factor is expressed by the following formula: ; Among them, is the adaptive step size factor of lemming individual i at the k +1th iteration, S max is the maximum step size, k max is the maximum number of iterations, Var , Mean are the position variance and position mean of the current population respectively, is the step size attenuation coefficient, is the weight coefficient; The long-distance migration behavior of lemmings after introducing the adaptive step size factor is expressed by the following formula: ; Among them, is the adaptive step size factor of lemming individual i at the k th iteration; When simulating the long-distance migration behavior of lemmings, mutation operations are introduced to increase population diversity and avoid premature convergence to local optima: Based on the introduction of the adaptive step size factor, the long-distance migration behavior of lemmings after introducing the mutation operation is expressed by the following formula: ; Among them, is the mutation vector, , is a vector randomly generated from the uniform distribution , is the mutation parameter, p is the mutation probability, r 4 is a random number.

[0029] ② In S43, after generating a new solution, a memory mechanism is introduced. Using the historical search information contained in the historical optimal solution to guide the search direction, enhancing the global exploration ability and improving the search efficiency, including: The memory mechanism is expressed by the following formula: ; Among them, is the position of the lemming individual i after updating the position at the k +1-th iteration by introducing the memory mechanism, is the position of the historical optimal solution, is the learning factor, is the random perturbation factor.

[0030]

[0030] ③ In S46, it is judged whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, the simulated target behavior is determined according to the optimized energy decreasing mechanism and S42 is returned. Otherwise, the current optimal solution is used as the optimal flexible control adaptive control strategy, including: Optimize the energy decreasing mechanism by introducing an acceleration factor to accelerate convergence when approaching the optimal solution. The optimized energy decreasing mechanism is expressed by the following formula: ; Among them, E k+1 is the energy at the k +1-th iteration, E 0 is the initial energy, is the attenuation coefficient, is the acceleration factor, d 1 is the distance between the current optimal solution and the population average solution, d 2 is the distance between the initial optimal solution and the population average solution, is the acceleration factor coefficient; When E k+1When >1, determine that the target behavior for the next iteration simulation is the long-distance migration behavior or the burrowing behavior of lemmings, and return to S42; when E k+1 When ≤1, determine that the target behavior for the next iteration simulation is the foraging behavior or the avoidance behavior of lemmings, and return to S42.

[0031] ④ In S47, convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and send them to the execution layer, including: Use the current optimal solution as the basis for formulating the optimal flexible regulation adaptive control strategy. According to the current optimal solution, the active power output and reactive power output of the generator can be adjusted; the distribution adjustment amount of the load can be optimized to reduce the load pressure in the heavy-load area; distributed energy can be preferentially dispatched to increase its consumption; the reactive power compensation device can be switched on or off according to the voltage situation to maintain voltage stability; After formulating the above optimal flexible regulation adaptive control strategy, convert it into corresponding control instructions and send them to the execution layer.

[0032] In the technical solution of this application, an improved artificial lemming algorithm is used to generate the optimal flexible regulation adaptive control strategy. In the improved artificial lemming algorithm, when simulating the long-distance migration behavior of lemmings, on the one hand, an adaptive step factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optima; on the other hand, a mutation operation is introduced to increase population diversity and avoid premature convergence to local optima; and a memory mechanism is introduced after the generation of new solutions, using the historical search information contained in the historical optimal solution to guide the search direction, enhancing the global exploration ability and improving the search efficiency; at the same time, the energy decay mechanism is optimized by introducing an acceleration factor to accelerate convergence when approaching the optimal solution, so as to be able to quickly generate effective adaptive control strategies in combination with the characteristics of the power system, fully adapt to the complex and changeable power grid environment, make the power system have stronger adaptive ability and regulation flexibility, and realize the stable operation and efficient flexible regulation of the power system.

[0033] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power system heavy overload monitoring and flexible regulation system, characterized in that: Including: The perception layer collects the operation data of the power system in real time through distributed data acquisition devices, processes the collected data, and extracts key features; The communication layer realizes data transmission between the perception layer and the control layer through a distributed communication architecture; The control layer monitors heavy overloads according to the key features of the collected data. Meanwhile, it uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer; The execution layer executes the control instructions through distributed instruction execution terminals to relieve the heavy overload state; Among them, in the improved artificial lemming algorithm: When simulating the long-distance migration behavior of lemmings, on the one hand, an adaptive step factor is introduced and dynamically adjusted according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optima; on the other hand, a mutation operation is introduced to increase population diversity and avoid premature convergence to local optima; After a new solution is generated, a memory mechanism is introduced. The historical search information contained in the historical optimal solution is used to guide the search direction, enhance the global exploration ability, and improve the search efficiency; The energy decay mechanism is optimized by introducing an acceleration factor to accelerate convergence when approaching the optimal solution.

2. The power system heavy overload monitoring and flexible regulation system according to claim 1, wherein: The perception layer collects the operation data of the power system in real time through distributed data acquisition devices, processes the collected data, and extracts key features, including: The voltage, current, and power operation data of the power system are collected in real time through smart meters, synchronized phasor measurement units PMU, and sensors distributedly arranged; Edge computing technology is used to process the collected data, extract key features, and send them to the control layer through the communication layer.

3. The power system heavy overload monitoring and flexible regulation system according to claim 1, wherein: The control layer monitors heavy overloads according to the key features of the collected data, including: Using state estimation technology, combined with the key features of the collected data, to evaluate the heavy overload state of the power system; Based on the state estimation results, potential risks are detected in advance through a heavy overload risk warning model, and risk warnings are issued.

4. The power system heavy overload monitoring and flexible regulation system according to claim 1, characterized in that: The control layer uses an improved artificial lemming algorithm to generate an optimal flexible regulation adaptive control strategy, and converts it into corresponding control instructions to be sent to the execution layer, including: S1. Determine the objective function of flexible regulation adaptive control; S2. Determine the constraint conditions of flexible regulation adaptive control; S3. Combine the objective function and constraint conditions of flexible regulation adaptive control to construct a flexible regulation adaptive control model; S4. Use the improved artificial lemming algorithm to perform multi-objective optimization and solution on the flexible regulation adaptive control model, and convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions to be sent to the execution layer.

5. The power system heavy overload monitoring and flexible regulation system according to claim 4, characterized in that: Determining the objective function of flexible regulation adaptive control in S1 includes: According to the power grid loss function f 1( x ), the regulation cost function f 2( x ), and the distributed energy consumption function f 3( x ), determine the objective function of flexible regulation adaptive control F : ； Among them, x are decision variables, including the active power output and reactive power output of generators, the distribution adjustment amount of loads, the output of distributed energy, and the switching states of reactive power compensation devices. , , are the weight coefficients of the grid power loss function f 1( x ), the regulation cost function f 2( x ), and the distributed energy consumption function f 3( x ), respectively. Determining the constraint conditions of flexible regulation adaptive control in S2 includes: Taking grid voltage constraints, grid current constraints, grid power balance constraints, and equipment capacity constraints as the constraint conditions of flexible regulation adaptive control.

6. The power system heavy overload monitoring and flexible regulation system according to claim 4, wherein: In S4, using the improved artificial lemming algorithm to perform multi-objective optimization and solution on the flexible regulation adaptive control model, and convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions to be sent to the execution layer, including: S41. Randomly generate an initial population of a certain scale within the search space. Each lemming individual in the initial population represents a potential solution, and parameter initialization is performed. S42. In each iteration, generate a new solution by simulating one of the behaviors of lemming long-distance migration behavior, lemming burrowing behavior, lemming foraging behavior, and lemming avoidance behavior to optimize the quality of the solution. S43. After the new solution is generated, introduce a memory mechanism, use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency. S44. Use the objective function of flexible regulation and adaptive control F Evaluate each lemming individual in the population and calculate the corresponding fitness value; S45. Record and update the current optimal solution. S46. Determine whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, determine the simulated target behavior according to the optimized energy decreasing mechanism and return to S42. Otherwise, use the current optimal solution as the optimal flexible regulation adaptive control strategy. S47. Convert the generated optimal flexible regulation adaptive control strategy into corresponding control instructions and send them to the execution layer.

7. The power system heavy overload monitoring and flexible regulation system according to claim 6, characterized in that: S42. In each iteration, generate a new solution by simulating one of the behaviors of lemming long-distance migration behavior, lemming burrowing behavior, lemming foraging behavior, and lemming avoidance behavior to optimize the quality of the solution, including: By simulating the long-distance migration behavior of lemmings when food is scarce, explore a new search space, and introduce the random factor of Brownian motion during migration to enhance the randomness of migration and the global search ability. ； Among them, , are the positions of the lemming individuals i at the k -th and the k +1-th iterations respectively, is the position of the current optimal solution, is the position of a randomly selected lemming individual A at the k -th iteration, is the Brownian motion vector, F is the direction flag, randomly taking values of 1 or -1, r 1 is a random number; By simulating the behavior of lemmings burrowing holes, perform local search in the current area. ； Among them, is the randomly selected lemming individual B at the k position at the r n-th iteration, where r 2 is a random number related to the number of iterations; By simulating the foraging behavior of lemmings near the burrow, perform local search in the current high-quality area, that is, develop the current high-quality area, and introduce spiral search during foraging to perform more refined local search. ； Among them, is a random search factor in a spiral shape, r 3 is a random number; By simulating the avoidance behavior of lemmings when encountering predators, perform further local search in the current high-quality area, that is, further develop the current high-quality area, and introduce deceptive actions during avoidance to make it difficult for predators to track lemmings and improve the success rate of avoidance. ； Among them, Levy ( Dim ) is the Lévy flight function, simulating the deceptive actions during the process of lemmings avoiding, G is the escape coefficient, which decreases with the increase of the number of iterations.

8. The power system heavy overload monitoring and flexible regulation system according to claim 7, characterized in that: When simulating the long-distance migration behavior of lemmings, introduce an adaptive step size factor and dynamically adjust it according to the number of iterations and population diversity to balance global search and local search and prevent falling into local optimum. The adaptive step size factor is expressed by the following formula: ； Among them, is the individual of the lemming i at the k +(1)th iteration of the adaptive step size factor, S max is the maximum step size, k max is the maximum number of iterations, Var , Mean are respectively the position variance and the position mean of the current population, is the step size attenuation coefficient, is the weight coefficient; The long-distance migration behavior of lemmings after introducing the adaptive step size factor is expressed by the following formula: ； Among them, is the adaptive step size factor of the lemming individual i at the k th iteration; When simulating the long-distance migration behavior of lemmings, introduce mutation operation to increase population diversity and avoid premature convergence to local optimum. Based on the introduction of the adaptive step size factor, the long-distance migration behavior of lemmings after introducing mutation operation is expressed by the following formula: ； Among them, is the mutation vector, , is a vector randomly generated from a uniform distribution , is the mutation parameter, p is the mutation probability, r 4 is a random number.

9. The power system heavy overload monitoring and flexible regulation system according to claim 6, characterized in that: In S43, after the new solution is generated, introduce a memory mechanism, use the historical search information contained in the historical optimal solution to guide the search direction, enhance the global exploration ability, and improve the search efficiency, including: The memory mechanism is expressed by the following formula: ； Among them, To introduce a memory mechanism for lemming individuals i At the k Position at the +1-th iteration after update, Is the position of the historical optimal solution, Is the learning factor, Is the random perturbation factor.

10. The power system heavy overload monitoring and flexible regulation system according to claim 6, wherein: In S46, determine whether the iteration termination condition is satisfied. If the iteration termination condition is not satisfied, determine the simulated target behavior according to the optimized energy decreasing mechanism and return to S42. Otherwise, use the current optimal solution as the optimal flexible regulation adaptive control strategy, including: Optimize the energy decreasing mechanism by introducing an acceleration factor to accelerate convergence when approaching the optimal solution. The optimized energy decreasing mechanism is expressed by the following formula: ； Among them, E k+1 is the energy at the k +(1)th iteration, E 0 is the initial energy, is the attenuation coefficient, is the acceleration factor, d 1 is the distance between the current optimal solution and the population average solution, d 2 is the distance between the initial optimal solution and the population average solution, is the acceleration factor coefficient; When E k+1 > 1, determine that the target behavior for the next iteration simulation is the long-distance migration behavior or the burrowing behavior of lemmings, and return to S42; when E k+1 ≤ 1, determine that the target behavior for the next iteration simulation is the foraging behavior or the avoidance behavior of lemmings, and return to S42.

Images