Micro-grid dispatching optimization method and system based on multi-objective arctic sea pigeon optimization algorithm

Abstract

The application discloses a micro-grid scheduling optimization method and system based on a multi-target arctic sea parrot optimization algorithm, and the method comprises the following steps: establishing a multi-target optimization scheduling model of a micro-grid, wherein at least an operation and maintenance cost target function and an environmental protection cost target function are included in the multi-target optimization scheduling model; solving the multi-target optimization scheduling model by using a multi-strategy fusion multi-target arctic sea parrot optimization algorithm to obtain a Pareto optimal solution set; and determining an optimal output strategy of each distributed power generation unit in the micro-grid according to the Pareto optimal solution set. The algorithm has space exploration ability in the early stage and optimization precision in the later stage, and the optimization effect of micro-grid scheduling is improved.

Description

Technical Field

[0001] This invention belongs to the field of microgrid scheduling technology, and in particular relates to a microgrid scheduling optimization method and system based on the multi-objective puffin optimization algorithm. Background Technology

[0002] Microgrids, as small-scale power generation and distribution systems that integrate distributed photovoltaics, wind turbines, energy storage devices, and loads, are a key technology for achieving efficient consumption and flexible power supply of renewable energy. Their optimized scheduling is crucial for improving energy utilization efficiency and ensuring power supply reliability and economy.

[0003] However, the optimal scheduling of microgrids is essentially a high-dimensional, nonlinear, multi-objective optimization problem. It involves numerous decision variables and complex constraints, requiring trade-offs between multiple conflicting objectives, such as reducing system operation and maintenance costs and minimizing environmental pollution emissions. Traditional solutions typically employ weighted coefficient methods to aggregate the multi-objective problem into a single-objective problem for solution. However, this method heavily relies on the decision-maker's subjective experience to set weights, making it difficult to objectively reflect the complex trade-offs between objectives. Furthermore, it fails to provide a diverse set of compromise solutions for decision-makers to choose from, exhibiting poor adaptability in dynamically changing operating scenarios.

[0004] To address this challenge, swarm intelligence optimization algorithms, such as genetic algorithms (GA) and particle swarm optimization (PSO), have been widely applied in microgrid dispatch optimization. However, faced with the complex nonlinear characteristics of microgrid dispatch models, these traditional algorithms generally suffer from slow convergence speed, insufficient solution accuracy, and susceptibility to local optima, making it difficult to quickly and accurately determine the optimal power output strategy for each distributed generation unit. Summary of the Invention

[0005] This invention provides a microgrid scheduling optimization method and system based on the multi-objective puffin optimization algorithm, which is used to solve the technical problem of difficulty in quickly and accurately determining the optimal output strategy of each distributed generation unit.

[0006] In a first aspect, the present invention provides a microgrid scheduling optimization method based on a multi-objective puffin optimization algorithm, comprising:

[0007] A multi-objective optimization scheduling model for microgrids is established, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function;

[0008] The multi-objective puffin optimization algorithm with multi-strategy fusion is used to solve the multi-objective optimization scheduling model to obtain the Pareto optimal solution set. The multi-objective puffin optimization algorithm with multi-strategy fusion includes:

[0009] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0010] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0011] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0012] The optimal output strategy for each distributed generation unit in the microgrid is determined based on the Pareto optimal solution set.

[0013] Secondly, the present invention provides a microgrid scheduling optimization system based on a multi-objective puffin optimization algorithm, comprising:

[0014] The module is configured to establish a multi-objective optimization scheduling model for a microgrid, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function.

[0015] The solution module is configured to use a multi-strategy fusion multi-objective puffin optimization algorithm to solve the multi-objective optimization scheduling model and obtain the Pareto optimal solution set. The multi-strategy fusion multi-objective puffin optimization algorithm includes:

[0016] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0017] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0018] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0019] The determination module is configured to determine the optimal output strategy for each distributed generation unit in the microgrid based on the Pareto optimal solution set.

[0020] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm according to any embodiment of the present invention.

[0021] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm according to any embodiment of the present invention.

[0022] This application presents a microgrid scheduling optimization method and system based on the multi-objective puffin optimization algorithm. The joint initialization strategy of Tent-Logistic-Cosine chaotic mapping and lens imaging back learning generates an initial population that allows the algorithm to obtain a larger search range with uniform distribution and a better initial solution set in the early stages. This helps maintain the diversity of the early population and achieves better spatial search capabilities. Furthermore, the multi-strategy elite pool balances global search and local exploitation, ensuring the algorithm's spatial exploration capability in the early stages and its optimization accuracy in the later stages, thus improving the optimization effect of microgrid scheduling. In summary, the multi-objective puffin optimization algorithm demonstrates excellent performance in solving the proposed multi-objective optimization scheduling model for microgrids, thus providing a new method and technology for practical microgrid scheduling optimization. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating a microgrid scheduling optimization method based on a multi-objective puffin optimization algorithm, provided in an embodiment of the present invention;

[0025] Figure 2 This is a structural block diagram of a microgrid scheduling optimization system based on a multi-objective puffin optimization algorithm, provided in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0028] Please see Figure 1 The diagram shows a flowchart of a microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm of this application.

[0029] like Figure 1 As shown, the microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm specifically includes the following steps:

[0030] Step S101: Establish a multi-objective optimization scheduling model for the microgrid, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function.

[0031] In this step, the expression for the objective function of operation and maintenance costs is:

[0032]

[0033] ,

[0034] ,

[0035] ,

[0036] ,

[0037] In the formula, For operation and maintenance costs, The operating and management cost of the diesel generator during time period t. The operating and management costs of the micro gas turbine power generation during time period t. The operating and management cost of the battery during period t. Let t be the interaction cost between the microgrid and the main grid during time period t. Maintenance costs for diesel generators. The fuel cost of generating electricity from diesel engines. This represents the maintenance cost coefficient for diesel generators. For DG's contribution at a certain moment, , , These are all fuel cost coefficients for diesel generators. Maintenance costs for micro gas turbine power generation, Fuel costs for generating electricity from micro gas turbines This is the natural gas maintenance cost coefficient. For the output of natural gas at a certain moment, For natural gas prices, The lower heating value of natural gas, To improve the operating efficiency of micro gas turbines, This is the battery maintenance cost coefficient. For the output of the storage battery at a certain moment, The electricity price of the large power grid during time period t. The electricity price of the microgrid during time period t. The power purchased by the microgrid and the main grid during time period t. Let t represent the electricity sales power of the microgrid and the main grid during time period t.

[0038] The expression for the environmental protection cost objective function is:

[0039] ,

[0040] ,

[0041] In the formula, For environmental protection costs, The cost of pollutant treatment during the main network interaction in time period t. The cost of treating pollutants from a micro gas turbine during time period t. The cost of treating pollutants generated by diesel generators during time period t. This represents the total number of pollutant categories. The cost coefficient for treating pollutants of type k, This refers to the emissions of Class K pollutants generated during the operation of a large power grid. The emissions of Class K pollutants generated by the operation of micro gas turbines. This refers to the emissions of Class K pollutants generated by the operation of diesel engines. Let t be the output power of the diesel generator during the time period.

[0042] Step S102: The multi-objective Pareto optimal scheduling model is solved using a multi-strategy fusion multi-objective puffin optimization algorithm to obtain the Pareto optimal solution set.

[0043] In this step, the multi-strategy fusion multi-objective puffin optimization algorithm includes:

[0044] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0045] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0046] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0047] Specifically, initializing the population: The mathematical model of the Arctic puffin optimization algorithm is described as follows: Let the population size of the puffin be P, and the initial puffin population... If the dimension of the feasible solution space is d, then the i-th puffin in the solution space can be represented as... The initial puffin population in the Arctic Puffin optimization algorithm is randomly generated within a certain search range and uniformly distributed in the solution space.

[0048] Randomly forming the initial population refers to the optimization of the output of each distributed generation unit at each time step during the microgrid dispatch optimization process. That is, each dispatch scheme uses a puffin-like initial population. This indicates that the output of each power generation unit at each moment is represented by a puffin. This means that the output of each power generation device and the number of puffins P are determined, and they are combined to form a puffin colony. That is, one puffin is used to represent a solution for a set of microgrid scheduling situations. Within a certain range of search parameters, each puffin in the puffin colony is determined using a random rand method (i.e., the working state of the power generation unit is used as the value corresponding to the puffin in the puffin colony), forming the initial population.

[0049] For microgrid scheduling optimization, the Arctic Puffin optimization algorithm effectively balances the global and local search performance, which is beneficial for the efficient search of the global optimum and the improvement of local development capabilities. However, the initial population distribution of the Arctic Puffin optimization algorithm is not uniform enough, which affects the convergence speed of the algorithm. In order to address the above-mentioned defects of the basic Dandelion optimization algorithm, this invention proposes an initialization strategy based on Tent-Logistic-Cosine chaotic lens imaging back learning to improve the initialization performance of the hiking optimization algorithm.

[0050] Chaotic distributions are relatively uniform distribution functions. Due to their randomness, ergodicity, and regularity, they can effectively maintain population diversity and have been widely used in swarm intelligence algorithms. Tent-Logistic-Cosine chaotic mapping initialization can ensure a uniform distribution of initial solutions, accelerating convergence while improving population diversity and effectively handling complex optimization problems. The formula for Tent-Logistic-Cosine chaotic mapping initialization is: ,

[0051] In the formula, Let i be the i-th chaotic variable, with a value range of [0, 1], and an initial value of nonzero. This is the chaos factor, with a value of 0.7.

[0052] While using the Tent-Logistic-Cosine chaotic mapping to generate initial solutions, a lens imaging back-learning strategy is introduced. This expands the search space of the hikers, thereby improving the quality of the initial solutions for the population. The mathematical expression of the lens imaging back-learning strategy is:

[0053] ,

[0054] ,

[0055] In the formula, For the i-th initial value, The maximum number of iterations, This represents the current iteration number. The upper limit of the variable. The lower bound of the variable. This is the position after reverse learning of lens imaging. This is the adaptive scaling factor.

[0056] This invention employs a tent chaotic initialization and stochastic back-learning strategy to improve the construction of the initial population, thus avoiding the effects of uneven distribution and low quality of the initial population in the basic Arctic Puffin optimization algorithm.

[0057] To improve the algorithm's optimization performance, this invention introduces a multi-strategy elite pool iterative mechanism, significantly enhancing optimization capabilities by fusing four differentiated iterative strategies. Specifically, firstly, a linear combination strategy of population averaging and the current optimal solution is adopted to balance the synergy between local development and global exploration; secondly, a hybrid mechanism of optimal average deviation and random perturbation is designed to enhance population diversity and avoid local convergence; thirdly, a Levy-flight global exploration strategy is introduced, utilizing its long jump characteristics to expand the search space; and fourthly, an iterative adaptive perturbation strategy is constructed to dynamically adjust the perturbation intensity to adapt to different optimization stages. This multi-strategy fusion mechanism achieves complementary advantages among strategies through the elite pool, effectively improving the algorithm's optimization accuracy and convergence efficiency. The elite pool iterative strategy is shown below:

[0058] ,

[0059] ,

[0060] ,

[0061] In the formula, The maximum number of iterations, This represents the current iteration number. As a dimension, Let i be the i-th candidate solution in the t-th iteration of the population. This represents the position of the globally optimal solution in the current iteration. The average value for all individual locations. In order to select the elite pool strategy, The upper limit of the variable. The lower bound of the variable. , , All are random numbers in the range [0,1] that follow a normal distribution. A location randomly selected within the population. Let Lévy's flight vector be a random vector. It is the i-th candidate solution in the (t-1)-th iteration of the population.

[0062] To further balance global exploration and local development, this invention constructs a dynamic selection probability model based on the temperature parameter decay characteristics and probabilistic mutation criteria of the simulated annealing algorithm, while incorporating the Multi-Objective Puffin Algorithm (MOAPO). By adaptively adjusting the switching probability in real time based on parameters such as the number of iterations and the fitness variance of the solution, a reasonable switching between the global search capability of the MOHOA algorithm and the MOAPO algorithm is achieved, forming a collaborative optimization mechanism, thereby improving the algorithm's convergence efficiency and solution accuracy.

[0063] Simulated annealing is a stochastic optimization algorithm derived from the physical annealing process. Its core advantage lies in escaping local optima and achieving global optimization by probabilistically accepting "worse solutions." Probabilistic mutation, as the core mechanism of simulated annealing, is key to balancing global solution exploration and local optimization. This invention incorporates the Levy flight strategy into the probabilistic mutation probability, forming a new mutation probability. The mutation probabilities of the new simulated annealing algorithm are as follows:

[0064] ,

[0065] To ensure that the new "mutation probability" is within the range [0,1], a linear normalization method is introduced. This method maps the original probability value to this interval through a specific linear transformation formula. The expression for linear normalization is:

[0066] ,

[0067] In the formula, This represents the normalized current mutation probability. This represents the current mutation probability. The minimum mutation probability, The maximum mutation probability, The maximum number of iterations, This represents the current iteration number. For shape parameters, set to 1.5. This is the step scaling factor, set to 0.4.

[0068] The multi-objective puffin optimization algorithm comprises two phases: aerial flight and underwater foraging. During the aerial flight phase, the puffin utilizes its unique flight strategy to explore the global optimum. During the underwater foraging phase, its aggregation and reinforcement search behaviors enable the algorithm to perform a refined search near better solutions, improving solution accuracy. To balance global exploration with local exploitation, a behavior switching factor (B) is introduced. This behavior switching factor B enables the switching between the aerial flight and underwater foraging phases. The formula for behavior switching factor B is:

[0069] ,

[0070] In the formula, rand represents a random number in the range [0,1].

[0071] When the behavior transition factor B > 0.5, the aerial flight phase is executed. During the aerial flight phase, the APO algorithm focuses on global optimization. To achieve efficient hunting behavior, the Arctic puffin employs two strategies: aerial searching and diving into the water to find prey, to cope with different situations.

[0072] In aerial search strategies, puffins typically coordinate their flight in groups, focusing on finding potential prey. The corresponding expression for this strategy in puffins is:

[0073] ,

[0074] ,

[0075] In the formula, , Let i and r be the puffins randomly selected from the Pareto front in the t-th iteration, respectively. ≠ . This represents the random number generated by Levy's flight. D represents the dimension. This represents a random number that conforms to a standard normal distribution.

[0076] In the swooping predation strategy, puffins face competition from other predators, and in order to capture prey faster and more successfully, the APO algorithm emphasizes local area exploitation. The corresponding expression under this strategy is:

[0077] ,

[0078] ,

[0079] In the formula, These are candidate solutions generated during the air search phase. The velocity coefficient;

[0080] To achieve the optimal result, the algorithm chooses to merge the candidate positions generated in the two stages of flight into a new solution. The corresponding expression under this strategy is:

[0081] ,

[0082] ,

[0083] ,

[0084] In the formula, The algorithm sorts the new population by fitness values ​​from smallest to largest, and selects the top N individuals as the new population for the t-th iteration. .

[0085] When the behavior transition factor B ≤ 0.5, the underwater foraging phase is executed. During the underwater foraging phase, the APO algorithm emphasizes global optimization. The underwater foraging phase employs three strategies: clustering foraging, intensified searching, and predator avoidance.

[0086] In their gregarious foraging strategy, Arctic puffins typically gather near schools of fish close to the surface to forage collectively. Simultaneously, they remain on the surface to observe the behavior of other puffins, thus determining the location of food resources. The update formula for gregarious foraging is:

[0087] ,

[0088] In the formula, Represents the cooperation factor. , , These are three puffins randomly selected from the Pareto front in the t-th iteration;

[0089] In an intensive search strategy, after gathering to forage, Arctic puffins may sense that food in their current foraging area is slowly running out. To continue replenishing food, they must change location or direction to intensify their search. The location update formula for this stage is:

[0090] ,

[0091] ,

[0092] In the formula, Candidate solutions generated during the gathering and foraging phase;

[0093] In predator avoidance strategies, Arctic puffins alert other puffins by emitting specific sounds or calls. When they detect a predator approaching, they quickly change position. The update equation used in this strategy is:

[0094] ,

[0095] In the formula, Represents a uniformly distributed random number within the range [0,1].

[0096] Step S103: Determine the optimal power output strategy for each distributed generation unit in the microgrid based on the Pareto optimal solution set.

[0097] In one specific embodiment, a multi-strategy fusion walking optimization algorithm (MSI-MOHOA) is used for microgrid scheduling optimization. The specific implementation steps are as follows:

[0098] Microgrid parameter initialization: Initialize the microgrid's operating parameters, including the operating parameters of DG, MT, ES, WT and PV power forecast data, and daily load.

[0099] MSI-MOHOA initialization: First, a population is generated using a Tent-Logistic-Cosine chaotic mapping and lens imaging back-learning initialization strategy. Then, the fitness of the initial population is calculated to generate an initial Pareto front, preparing for MSI-MOHOA iterations.

[0100] Iterative optimization: First, the behavior transition factor B is calculated. Then, the corresponding stage is selected based on the behavior transition factor. If B > 0.5, the aerial flight stage is selected; otherwise, the underwater foraging stage is selected. If the underwater foraging stage is selected, the selection probability is calculated to determine whether to execute the MOHOA or MOAPO position update strategy. Finally, the existing population is perturbed based on a multi-strategy elite pool, the fitness of the updated population is calculated, and the Pareto front is updated.

[0101] Algorithm iteration termination: Determine if the algorithm iteration is complete. If not, recalculate the behavior transformation factor to select the corresponding optimization algorithm. Additionally, obtain the Pareto optimal front and optimal scheduling scheme; the calculation is complete.

[0102] In summary, the method in this application, based on the existing multi-objective puffin optimization algorithm, introduces a joint initialization strategy of Tent-Logistic-Cosine chaotic mapping and lens imaging back learning to generate a more uniform and higher-quality initial solution set. A multi-strategy elite pool is also introduced, using different position update strategies to enhance global exploration and local optimization. Finally, a dynamic selection mechanism is constructed based on the probabilistic mutation criterion of the simulated annealing algorithm. By adaptively adjusting the selection probability, a reasonable switching between the APO and HOA algorithms is achieved, forming a collaborative optimization mechanism. The organic combination of these strategies enhances the algorithm's spatial exploration capability and optimization accuracy. Applying this improved walking optimization algorithm to the constructed microgrid mathematical model yields the optimal scheduling scheme, ensuring the minimization of the total cost of microgrid optimal scheduling.

[0103] In this application, the joint initialization strategy of Tent-Logistic-Cosine chaotic mapping and lens imaging back learning generates an initial population that allows the algorithm to obtain a larger search range with uniform distribution and a better initial solution set in the early stages. This helps maintain the diversity of the early population and achieves better spatial search capabilities. Furthermore, the multi-strategy elite pool balances global search and local exploitation, ensuring the algorithm's spatial exploration capability in the early stages and its optimization accuracy in the later stages, thus improving the optimization effect of microgrid scheduling. In summary, the MSI-MOHOA algorithm demonstrates good performance in solving the proposed multi-objective optimization scheduling model for microgrids, thus providing a new method and technology for practical microgrid scheduling optimization.

[0104] Please see Figure 2 The diagram shows a block diagram of a microgrid scheduling optimization system based on the multi-objective puffin optimization algorithm of this application.

[0105] like Figure 2 As shown, the microgrid scheduling optimization system 200 includes a construction module 210, a solution module 220, and a determination module 230.

[0106] The construction module 210 is configured to establish a multi-objective optimization scheduling model for the microgrid, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function;

[0107] The solver module 220 is configured to use a multi-strategy fusion multi-objective puffin optimization algorithm to solve the multi-objective optimization scheduling model and obtain the Pareto optimal solution set. The multi-strategy fusion multi-objective puffin optimization algorithm includes:

[0108] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0109] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0110] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0111] The determination module 230 is configured to determine the optimal output strategy of each distributed generation unit in the microgrid based on the Pareto optimal solution set.

[0112] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2The various modules in the document will not be described in detail here.

[0113] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the microgrid scheduling optimization method of the multi-objective Arctic Puffin optimization algorithm in any of the above method embodiments.

[0114] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0115] A multi-objective optimization scheduling model for microgrids is established, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function;

[0116] The multi-objective puffin optimization algorithm with multi-strategy fusion is used to solve the multi-objective optimization scheduling model to obtain the Pareto optimal solution set. The multi-objective puffin optimization algorithm with multi-strategy fusion includes:

[0117] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0118] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0119] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0120] The optimal output strategy for each distributed generation unit in the microgrid is determined based on the Pareto optimal solution set.

[0121] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created by the use of the microgrid dispatch optimization system based on the multi-objective Puffin optimization algorithm, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to the processor, which can be connected to the microgrid dispatch optimization system based on the multi-objective Puffin optimization algorithm via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0122] Figure 3This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the microgrid scheduling optimization method using the multi-objective puffin optimization algorithm described in the above method embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the microgrid scheduling optimization system using the multi-objective puffin optimization algorithm. The output device 340 may include a display screen or other display device.

[0123] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0124] In one implementation, the above-described electronic device is applied to a microgrid scheduling optimization system based on a multi-objective puffin optimization algorithm. As a client, it includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0125] A multi-objective optimization scheduling model for microgrids is established, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function;

[0126] The multi-objective puffin optimization algorithm with multi-strategy fusion is used to solve the multi-objective optimization scheduling model to obtain the Pareto optimal solution set. The multi-objective puffin optimization algorithm with multi-strategy fusion includes:

[0127] An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy.

[0128] A multi-strategy elite pool iteration mechanism is introduced during the iteration process;

[0129] Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm.

[0130] The optimal output strategy for each distributed generation unit in the microgrid is determined based on the Pareto optimal solution set.

[0131] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm, characterized in that, include: A multi-objective optimization scheduling model for microgrids is established. This model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function. The expression for the operation and maintenance cost objective function is as follows: ， ， ， ， ， In the formula, For operation and maintenance costs, The operating and management cost of the diesel generator during time period t. The operating and management costs of the micro gas turbine power generation during time period t. The operating and management cost of the battery during period t. Let t be the interaction cost between the microgrid and the main grid during time period t. Maintenance costs for diesel generators. The fuel cost of diesel generators. This represents the maintenance cost coefficient for diesel generators. For DG's contribution at a certain moment, , , These are all fuel cost coefficients for diesel generators. Maintenance costs for micro gas turbine power generation, Fuel costs for generating electricity from micro gas turbines, This is the natural gas maintenance cost coefficient. For the output of natural gas at a certain moment, For natural gas prices, The lower heating value of natural gas, To improve the operating efficiency of micro gas turbines, This is the battery maintenance cost coefficient. For the output of the storage battery at a certain moment, The electricity price of the large power grid during time period t. The electricity price of the microgrid during time period t. The power purchased by the microgrid and the main grid during time period t. The electricity sales power of the microgrid and the main grid during time period t; The expression for the environmental protection cost objective function is as follows: ， ， In the formula, For environmental protection costs, The cost of pollutant treatment during the main network interaction in time period t. The cost of treating pollutants from a micro gas turbine during time period t. The cost of treating pollutants generated by diesel generators during time period t. The total number of pollutant categories, The cost coefficient for treating pollutants of type k, This refers to the emissions of Class K pollutants generated during the operation of a large power grid. The emissions of Class K pollutants generated by the operation of micro gas turbines. This refers to the emissions of Class K pollutants generated by the operation of diesel engines. The output power of the diesel generator during time period t; The multi-objective puffin optimization algorithm with multi-strategy fusion is used to solve the multi-objective optimization scheduling model to obtain the Pareto optimal solution set. The multi-objective puffin optimization algorithm with multi-strategy fusion includes: An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy. A multi-strategy elite pool iteration mechanism is introduced during the iteration process. The expression for the multi-strategy elite pool iteration mechanism is as follows: ， ， ， In the formula, The maximum number of iterations, This represents the current iteration number. As a dimension, Let i be the i-th candidate solution in the t-th iteration of the population. This represents the position of the global optimal solution in the current iteration. The average value for all individual locations. In order to select the elite pool strategy, The upper limit of the variable. The lower bound of the variable. , , All are random numbers in the range [0,1] that follow a normal distribution. A location randomly selected within the population. Let Lévy's flight vector be a random vector. This is the i-th candidate solution in the (t-1)-th iteration of the population; Based on the probabilistic mutation criterion of the simulated annealing algorithm, a location update strategy is dynamically selected to execute either the Arctic Puffin Optimization Algorithm or the Hiking Optimization Algorithm. The expression for the probabilistic mutation criterion is as follows: ， ， In the formula, This represents the normalized current mutation probability. This represents the current mutation probability. The minimum mutation probability, The maximum mutation probability, The maximum number of iterations, This represents the current iteration number. For shape parameters, set to 1.

5. This is the step size scaling factor, set to 0.4; The optimal output strategy for each distributed generation unit in the microgrid is determined based on the Pareto optimal solution set.

2. The microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm according to claim 1, characterized in that, The expression for the Tent-Logistic-Cosine chaotic mapping is: ， In the formula, Let i be the i-th chaotic variable, with a value range of [0, 1], and an initial value of nonzero. This is the chaos factor, with a value of 0.

7.

3. The microgrid scheduling optimization method based on the multi-objective puffin optimization algorithm according to claim 1, characterized in that, The expression for the lens imaging reverse learning strategy is: ， ， In the formula, For the i-th initial value, The maximum number of iterations, This represents the current iteration number. The upper limit of the variable. The lower bound of the variable. This is the position after reverse learning of lens imaging. This is the adaptive scaling factor.

4. A microgrid scheduling optimization system based on a multi-objective puffin optimization algorithm according to any one of claims 1-3, characterized in that, include: The module is configured to establish a multi-objective optimization scheduling model for a microgrid, wherein the multi-objective optimization scheduling model includes at least an operation and maintenance cost objective function and an environmental protection cost objective function. The solution module is configured to use a multi-strategy fusion multi-objective puffin optimization algorithm to solve the multi-objective optimization scheduling model and obtain the Pareto optimal solution set. The multi-strategy fusion multi-objective puffin optimization algorithm includes: An initial population is generated using a pre-defined Tent-Logistic-Cosine chaotic mapping and a pre-defined lens imaging reverse learning strategy. A multi-strategy elite pool iteration mechanism is introduced during the iteration process; Based on the probabilistic mutation criterion of the simulated annealing algorithm, a position update strategy is dynamically selected to execute either the Arctic Puffin optimization algorithm or the walking optimization algorithm. The determination module is configured to determine the optimal output strategy for each distributed generation unit in the microgrid based on the Pareto optimal solution set.

5. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1 to 3.

Images