Microgrid configuration method under remote area grid fault condition
By using decoding rules and genetic algorithm optimization methods under grid failure conditions, the challenge of power supply in remote areas is solved, and the optimal configuration of the power grid and adaptability in complex environments are achieved.
Patent Information
- Application Number
- CN202411616420.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-03-07
AI Technical Summary
In the case of grid failure, power supply in remote areas faces challenges, and prior art is difficult to effectively diagnose and handle grid failures, especially in complex multi-energy coupled microgrid environments.
The radical optimization method of decoding rules and genetic algorithms is adopted to read the grid optimization data parameters through an external plug-in circuit detector, select appropriate genetic algorithm encoding and decoding rules, select scheduling models, and perform grid optimization scheduling according to the model to obtain the lowest degree of power consumption and resistance loss energy loss.
Ensure the orderly progress of model training, avoid falling into local optimal solutions, improve the training efficiency and effect of the model, can adapt to complex multi-energy coupled microgrid environments, and achieve optimal configuration under power grid failure conditions in remote areas.
Smart Images
Figure CN119578767A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power grid distribution technology, and in particular to a method for configuring a microgrid under power grid fault conditions in remote areas. Background Art
[0002] The power system consists of generators, transformers, busbars, transmission and distribution lines, and electrical equipment. Electrical components and systems are usually in normal operation, but they may also fail or operate abnormally. Power system failure refers to a state in which the equipment cannot work according to the expected indicators, that is, the equipment does not achieve the function it should achieve. There are several types of failures: generator set failure, transmission line failure, substation failure, bus failure, etc.
[0003] The development of power grids and the progress of society have put forward higher requirements for the operation of power grids. It is particularly important to strengthen the diagnosis and treatment of power grid faults. However, as the scale of power systems becomes larger and the structure becomes more complex, faults are inevitable. In the entire power production process, the most common, most dangerous and most serious fault is the short circuit fault. The causes of short circuit faults include aging or mechanical damage of insulation materials of electrical equipment, overvoltage caused by lightning strikes, tower collapse or wire breakage caused by natural disasters, short circuit caused by birds and animals jumping wires, and operator misoperation, which have brought some new problems to the safe operation of power systems.
[0004] With the development of computer technology, communication technology, network technology, etc., it is of great research value and practical significance to use more advanced intelligent technology to improve the performance of fault diagnosis system. In view of this, the applicant has developed an optimal configuration method for microgrids under power grid fault conditions in remote areas. Summary of the invention
[0005] The present invention provides a method for configuring a microgrid under power grid fault conditions in remote areas. The decoding rules and the genetic algorithm are used to radically optimize the power grid, which can ensure the orderly progress of model training and avoid falling into local optimal solutions, thereby helping to improve the training efficiency and effect of the model and enable it to better adapt to the complex environment of multi-energy coupled microgrids.
[0006] The present invention is achieved through the following technical solutions:
[0007] The present invention provides a method for configuring a microgrid under a power grid fault condition in a remote area, comprising the following steps:
[0008] S1. Reading grid optimization data parameters through an external plug-in circuit detector;
[0009] S2. Select the corresponding genetic algorithm encoding and obtain the decoding rules through the built-in program of the circuit detector;
[0010] S3. Selecting a corresponding dispatching model according to the power grid optimization data parameters, time scale and real-time scale;
[0011] S4. Optimizing power grid dispatching according to the dispatching model;
[0012] S5. The solution with the lowest power consumption and resistance depreciation energy consumption is taken as the optimal solution model.
[0013] The configuration method of a microgrid under a power grid fault condition in a remote area provided by the present invention first reads the power grid optimization data parameters through an external plug-in circuit detector, and selects the corresponding genetic algorithm encoding and obtains the decoding rules through the built-in program of the circuit detector, and then selects the corresponding scheduling model according to the power grid optimization data parameters, time scale and real-time scale, and then performs power grid optimization scheduling according to the scheduling model, and takes the solution with the lowest power consumption and resistance depreciation energy loss as the optimal solution model, thereby obtaining the optimal configuration of the microgrid under the power grid fault condition in the remote area.
[0014] Therefore, the present invention uses decoding rules and genetic algorithms to radically optimize the power grid. There is no need to randomly initialize the strategy network parameters and value network parameters corresponding to the regional intelligent agents. This can ensure the orderly progress of model training and avoid falling into local optimal solutions. It improves the training efficiency and effect of the model and can adapt to the complex environment of multi-energy coupled microgrids.
[0015] In an optional implementation of the present application, the circuit detector uses a universal digital / analog integrated IC device library, and the circuit detector is capable of performing online functional testing of the integrated IC.
[0016] In an optional embodiment of the present application, the circuit detector is a computer terminal, and the computer terminal includes a connected processor, a data storage device, a communication interface, a display screen and an input device.
[0017] In an optional implementation of the present application, the data storage device includes a non-volatile storage medium and an internal memory, and the internal memory provides an environment for the operation of an operating system in the non-volatile storage medium and a built-in program of the circuit detector.
[0018] In an optional implementation of the present application, the signal transmission mode of the communication interface is one of WiFi connection, operator network and near field communication.
[0019] In an optional implementation of the present application, the power grid optimization data parameters include transmission path, connection status, transmission load value of each node line and surrounding power consumption.
[0020] In an optional embodiment of the present application, the time scale is a long / short time scale.
[0021] In an optional implementation of the present application, when the verification fails in step S3, the read power grid optimization data parameters are checked and reviewed through the game model system, and step S1 is continued after the review is passed.
[0022] In an optional implementation of the present application, step S4 includes the steps of: after constructing the scheduling model, solving the scheduling model to obtain an optimal scheduling result.
[0023] In an optional implementation manner of the present application, the step of determining the optimal scheduling result is: solving the scheduling model to obtain the aggregated charging and discharging curves under different charging and discharging modes, and the minimum operating cost of the distribution network under different charging and discharging modes;
[0024] The optimal scheduling result is determined based on the aggregated charge and discharge curve and the minimum operating cost of the distribution network.
[0025] Compared with the prior art, the present invention has the following advantages and beneficial effects:
[0026] The configuration method of the microgrid under the condition of a power grid failure in a remote area provided by the present invention first reads the power grid optimization data parameters through an external plug-in circuit detector, and selects the corresponding genetic algorithm encoding and obtains the decoding rules through the built-in program of the circuit detector, and then selects the corresponding scheduling model according to the power grid optimization data parameters, time scale and real-time scale, and then performs power grid optimization scheduling according to the scheduling model, and takes the scheme with the lowest power consumption and resistance depreciation energy loss as the optimal scheme model, thereby obtaining the optimal configuration of the microgrid under the condition of a power grid failure in the remote area, and does not need to randomly initialize the strategy network parameters and value network parameters corresponding to the regional intelligent body, which can ensure the orderly progress of the model training and avoid falling into the local optimal solution, thereby improving the training efficiency and effect of the model and being able to adapt to the complex environment of the multi-energy coupling microgrid. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope.
[0028] in:
[0029] Figure 1 A flow chart of a method for configuring a microgrid in a remote area under a power grid failure condition provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.
[0031] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0032] It should be noted that the embodiments and features in the embodiments in this application can be combined with each other without conflict. In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that these specific details do not need to be adopted to implement the present invention. In other embodiments, in order to avoid confusing the present invention, known methods are not specifically described.
[0033] Example
[0034] Combination Figure 1 , this embodiment provides a method for configuring a microgrid under a power grid failure condition in a remote area, comprising the following steps:
[0035] S1. Read the grid optimization data parameters through an external plug-in circuit detector.
[0036] Specifically, the circuit detector uses a universal digital / analog integrated IC device library, and the circuit detector can perform online functional testing of integrated ICs, and can perform special tests on optocouplers, capacitors, transistors, etc., to locate circuit board faults on integrated ICs, discrete components or circuit nodes.
[0037] It can be understood that the circuit detector is a computer terminal, which includes a connected processor, a data storage, a communication interface, a display screen and an input device, and the processor is used to provide computing and control capabilities.
[0038] The data storage device includes a non-volatile storage medium and an internal memory, and the internal memory provides an environment for the operation of the operating system in the non-volatile storage medium and the built-in program of the circuit detector.
[0039] At the same time, the communication interface is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, operator network, NFC (near field communication) or other technologies. In this embodiment, the signal transmission mode of the communication interface is one of WiFi connection, operator network and near field communication.
[0040] In addition, the so-called power grid optimization data parameters in this embodiment include transmission paths, connection conditions, transmission load values of each node line and surrounding power consumption, so as to truly simulate the power grid operation environment.
[0041] S2. Select the corresponding genetic algorithm encoding and obtain the decoding rules through the built-in program of the circuit detector.
[0042] It is known that the circuit detector has a built-in dedicated application, based on which, humans can directly select the corresponding genetic algorithm encoding and obtain decoding rules on the circuit detector.
[0043] It should be noted that the genetic algorithm (GA) is an optimization algorithm based on the principles of natural selection and genetics. It simulates natural selection, crossover, mutation and other operations in the biological evolution process to solve various optimization problems. The core of the genetic algorithm is to find the optimal solution through iterative evolution. Coding is a very critical part of the genetic algorithm, which involves how to express the solution to the problem in a form suitable for genetic operations.
[0044] Among them, the basic process of genetic algorithm includes the following steps:
[0045] Initialize the population: Randomly generate an initial population, where each individual (chromosome) represents a possible solution.
[0046] Fitness evaluation: Calculate the fitness value of each individual and evaluate its quality.
[0047] Selection operation: select some individuals to enter the next generation based on their fitness values.
[0048] Crossover operation: Cross the selected individuals to generate new individuals.
[0049] Mutation operation: mutate individuals to increase diversity.
[0050] Replacement operation: Replace the old generation with the new generation individuals and enter the next generation.
[0051] Termination condition: Determine whether the termination condition is met (such as the maximum number of iterations, or finding a good enough solution).
[0052] As for the encoding method, in genetic algorithms, encoding refers to the way to represent the solution to the problem as a chromosome. The following encoding methods are usually used:
[0053] Binary encoding, one of the most common encoding methods, represents the solution as a string of binary digits (0 and 1).
[0054] Real-Coded Encoding, which represents the solution directly as a real value rather than a binary string. For some continuous optimization problems, real-coded encoding is a more natural choice.
[0055] Integer Encoding, in some problems, the solution may be an integer value, rather than a binary or real number. In this case, integer encoding can be used to represent the solution.
[0056] Symbolic encoding is used for discrete, symbolic problems, such as the traveling salesman problem (TSP), where the solution is represented by the order of cities.
[0057] Multi-Representation Encoding: For some complex problems, different encoding methods can be combined. For example, some variables are encoded in binary format, others in real number format, or a combination of symbolic and integer encoding.
[0058] For genetic operations, the three main operations in genetic algorithms are selection, crossover, and mutation. These operations need to be adapted to the encoding method. The selection operation determines the probability of an individual entering the next generation based on its fitness. Common selection methods include: roulette selection, tournament selection, sorting selection, and crossover.
[0059] Among them, the crossover operation simulates the gene exchange of organisms, and produces offspring individuals by exchanging some genes of two parent individuals. The specific implementation method of crossover depends on the encoding method, specifically:
[0060] Binary coding, single-point crossover, two-point crossover or uniform crossover;
[0061] Real number encoding, simulating actual gene exchange, can use arithmetic crossover (such as weighted average of parents);
[0062] Arrangement coding, such as partially matched crossover (PMX), order crossover (OX), etc.;
[0063] Mutation: Mutation is a small random change to individuals to increase the diversity of the population. The method of mutation operation also depends on the encoding type, such as binary encoding (flipping a bit), real number encoding (making a small random shift to certain positions), and integer encoding (randomly selecting an integer and adjusting it).
[0064] The principles for encoding selection can be determined based on the following aspects:
[0065] The nature of the problem: whether it is a continuous, discrete, integer, or permutation problem;
[0066] Computational complexity: Some encoding methods may make the representation of the solution space very complex, thus affecting the efficiency of the algorithm;
[0067] Design of genetic operations: Some encoding methods require special design of crossover and mutation operations.
[0068] S3. Select a corresponding dispatching model according to the power grid optimization data parameters, time scale and real-time scale.
[0069] Specifically, the time scale is a long / short time scale.
[0070] In the process of selecting the dispatching model, if the verification fails, the read power grid optimization data parameters are checked and reviewed through the game model system. After the review is passed, step S1 is continued.
[0071] The power grid dispatch model can be mainly divided into several key components, including power generation dispatch, load dispatch, and transmission network dispatch. Each part has its corresponding mathematical modeling method. Specifically:
[0072] Generation dispatch, determining the output power of individual generator sets to minimize generation costs and meet power demand and network constraints.
[0073] Load scheduling is the rational distribution of loads in the power grid to ensure that all users can get electricity while avoiding overloading of the power grid.
[0074] Transmission dispatching ensures that electricity can be transmitted from the power generation source to the load center and that the capacity of the transmission network is not overloaded by scheduling the flow of transmission lines.
[0075] Electricity market dispatch,In the electricity market, the dispatch model also needs to consider the market’s price mechanism, auction method, bidding strategy, etc.
[0076] For the economic dispatch model, the output power of the generator set is usually optimized under the conditions of meeting the power demand and various system constraints. The commonly used objective function is to minimize the total power generation cost, and its objective function is to minimize the total power generation cost (\sum_{i=1}^{N}C_i(P_i)), where (C_i(P_i)) is the cost function of the generator set (i), (P_i) is the output power of the generator set, and (N) is the total number of generator sets. The constraints are that the sum of the power of all generator sets must be equal to the demand of the power grid, the output power of the generator set must be between its minimum and maximum values, the power generation capacity and demand of the system meet the safety constraints of the power grid, and the power flow of the transmission line must meet its carrying capacity.
[0077] The purpose of the safe dispatch model is to ensure that there are no problems such as system collapse, overload, frequency fluctuation, etc. during the operation of the power grid. At the same time, the safe dispatch model needs to take into account the physical constraints of the power system on the basis of economic dispatch to ensure the stability of the power system. Its objective function is usually the same as that of economic dispatch, but safety constraints need to be added on this basis. The safety constraints include:
[0078] Frequency constraints: the grid frequency must be kept within a certain range to avoid system collapse;
[0079] Voltage constraint: the voltage amplitude must be within the normal range;
[0080] Transmission capacity constraints, the power flow of each transmission line cannot exceed its maximum capacity.
[0081] The generator set regulation range ensures that the generator set operates within its regulation capacity.
[0082] An important concept in economic dispatch and load dispatch is load pricing (LMP, Locational Marginal Pricing). LMP refers to the calculation of the electricity price of each node based on the supply and demand relationship at different locations in the electricity market. The LMP model determines the electricity price of each node in the power grid by considering the power demand of the node, the cost of the generator set, and the limitations of the transmission network.
[0083] S4. Optimize power grid dispatching according to the dispatching model.
[0084] That is to say, after the scheduling model is constructed, the scheduling model is solved to obtain the optimal scheduling result. Specifically, the scheduling model is solved to obtain the aggregated charging and discharging curves under different charging and discharging modes, and the minimum operating cost of the distribution network under different charging and discharging modes; then, based on the aggregated charging and discharging curves and the minimum operating cost of the distribution network, the optimal scheduling result is determined.
[0085] Existing power grid dispatch algorithms include:
[0086] Linear programming (LP), used to solve scheduling problems with linear constraints and objective functions;
[0087] Integer programming (IP), which is applicable to unit commitment problems because the start and stop of units are usually binary decisions (start / stop);
[0088] Dynamic programming (DP), which is widely used in unit commitment problems to solve multi-stage decision problems;
[0089] Heuristic algorithms, such as simulated annealing and genetic algorithms, are usually used to solve large-scale complex problems;
[0090] Mixed integer linear programming (MILP) is applicable to scheduling problems that consider both discrete and continuous decisions.
[0091] S5. The solution with the lowest power consumption and resistance depreciation energy consumption is taken as the optimal solution model.
[0092] In summary, the configuration method of a microgrid under a power grid fault condition in a remote area provided in this embodiment first reads the power grid optimization data parameters through an external plug-in circuit detector, and selects the corresponding genetic algorithm encoding and obtains the decoding rules through the built-in program of the circuit detector, and then selects the corresponding scheduling model according to the power grid optimization data parameters, time scale and real-time scale, and then performs power grid optimization scheduling according to the scheduling model, and takes the solution with the lowest power consumption and resistance depreciation energy loss as the optimal solution model, thereby obtaining the optimal configuration of the microgrid under the power grid fault condition in the remote area.
[0093] In summary, this embodiment uses decoding rules and genetic algorithms to aggressively optimize the power grid. There is no need to randomly initialize the strategy network parameters and value network parameters corresponding to the regional intelligent agents. This can ensure the orderly progress of the model training and avoid falling into the local optimal solution. It improves the training efficiency and effect of the model and can adapt to the complex environment of the multi-energy coupled microgrid.
[0094] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.
Claims
1. A method for configuring a microgrid under a power grid failure condition in a remote area, characterized in that: The following steps are involved: S1. Reading grid optimization data parameters through an external plug-in circuit detector; S2. Select the corresponding genetic algorithm encoding and obtain the decoding rules through the built-in program of the circuit detector; S3. Selecting a corresponding dispatching model according to the power grid optimization data parameters, time scale and real-time scale; S4. Optimizing power grid dispatching according to the dispatching model; S5. The solution with the lowest power consumption and resistance depreciation energy consumption is taken as the optimal solution model.
2. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 1, characterized in that: The circuit detector adopts a universal digital / analog integrated IC device library, and the circuit detector can perform integrated IC online functional testing.
3. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 2, characterized in that: The circuit detector is a computer terminal, which includes a connected processor, a data storage, a communication interface, a display screen and an input device.
4. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 3, characterized in that: The data storage device includes a nonvolatile storage medium and an internal memory, wherein the internal memory provides an environment for the operation of an operating system in the nonvolatile storage medium and a built-in program of the circuit detector.
5. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 3, characterized in that: The signal transmission mode of the communication interface is one of WiFi connection, operator network and near field communication.
6. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 1, characterized in that: The power grid optimization data parameters include transmission path, connection status, transmission load value of each node line and surrounding power consumption.
7. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 1, characterized in that: The time scale is the long / short time scale.
8. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 1, characterized in that: When the verification fails in step S3, the read power grid optimization data parameters are checked and reviewed through the game model system. After the review is passed, step S1 is continued.
9. The method for configuring a microgrid in a remote area under a power grid failure condition according to any one of claims 1 to 8, characterized in that: Step S4 includes the steps of: after the scheduling model is constructed, solving the scheduling model to obtain the optimal scheduling result.
10. The method for configuring a microgrid under a power grid failure condition in a remote area according to claim 9, characterized in that: The steps to determine the optimal scheduling result are: Solving the dispatch model to obtain aggregated charge-discharge curves under different charge-discharge modes and the minimum operating cost of the distribution network under different charge-discharge modes; The optimal scheduling result is determined based on the aggregated charge and discharge curve and the minimum operating cost of the distribution network.