Microgrid optimal configuration method and system based on HEOA

Abstract

The invention discloses a micro-grid optimization configuration method and system based on HEOA, and the method comprises the steps: obtaining an optimization target based on the demands of a micro-grid, and converting the optimization target into a quantitative index; constructing a model based on HEOA, wherein the model comprises a target function based on the quantitative index and a constraint condition based on power balance and equipment capacity; acquiring an electricity price table, a power generation device operation plan, power generation device hardware parameters and an energy storage device operation plan in the micro-grid in real time, and inputting the information into the model; the model outputs an optimal configuration scheme based on the objective function and the constraint condition, and the micro-grid executes the optimal configuration scheme. A model is constructed through a human evolutionary optimization algorithm, and various data of the micro-grid are fully collected, so that an accurate, economical and reliable configuration scheme can be efficiently provided while specific requirements of different micro-grids can be met.

Description

Technical Field

[0001] This application relates to the field of energy management, and in particular to a microgrid optimization configuration method and system based on HEOA. Background Technology

[0002] A microgrid is a self-contained power system that can be connected to the public grid or operate independently in islanded mode. It provides a resilient, sustainable, and efficient energy solution by utilizing on-site renewable energy sources (such as distributed solar and wind power) and smart grid resources to achieve better connectivity, decarbonization, and energy access. The main components of a microgrid include distributed power sources, loads, and an energy management system, enabling internal power balancing. Compared to traditional large power grids, microgrids feature bidirectional interaction, allowing for local generation and regulation to maximize energy efficiency.

[0003] Existing microgrid configuration methods typically focus on the operation scheduling and resource coordination of renewable energy within the microgrid. They are usually based on a specific unit, and the coordination and overall planning of multiple entities is not effective, failing to achieve better economic efficiency. Furthermore, the continuous analysis of existing data can easily lead to the accumulation of statistical errors and hardware losses, resulting in deviations and significant biases in the final proposed solutions. Summary of the Invention

[0004] This application provides a microgrid optimization configuration method and system based on HEOA to solve the problems of poor economy, easy getting trapped in local optima, and large deviation in existing microgrid configuration methods.

[0005] To address the aforementioned technical problems, this application adopts the following technical solution: a microgrid optimization configuration method based on HEOA, comprising: S10: Based on the needs of the microgrid, obtain the optimization target and convert the optimization target into quantitative indicators; S20: Construct a model based on HEOA, the model including an objective function based on the quantified index and constraints based on power balance and equipment capacity; S30: Real-time acquisition of electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and input into the model; S40: The model outputs an optimal configuration scheme based on the objective function and the constraints, and the microgrid executes the optimal configuration scheme.

[0006] In one possible implementation, the step of obtaining optimization targets based on the needs of the microgrid and converting the optimization targets into quantitative indicators includes: S11: Based on the needs of the microgrid, obtain economic, reliability, and environmental objectives; S12: Prioritize and quantify the economic objectives, reliability objectives, and environmental objectives to obtain quantitative indicators.

[0007] In one possible implementation, the step of constructing a model based on HEOA, the model including an objective function based on the quantified index and constraints based on power balance and device capacity, includes: S21: Based on the HEOA definition, the decision variables of the configuration scheme are treated as individuals, a fitness function is constructed according to the quantitative indicators, and the individuals are assigned tasks according to the results of the fitness function.

[0008] In one possible implementation, the HEOA-based model construction step, which includes an objective function based on the quantification index and constraints based on power balance and device hardware, includes: S22: Construct power balance constraints based on the fact that the total output and total load are equal at any given time, and construct equipment hardware constraints based on equipment capacity, equipment power, and grid-connected power; S23: Apply the constraints to each of the individuals.

[0009] In one possible implementation, the step of acquiring in real-time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan of the microgrid, and inputting them into the model, includes: S31: Select a high-quality configuration scheme from historical data as the initial population input to the model; S32: Use the data of the day as the correction input to the model.

[0010] In one possible implementation, after the model outputs an optimal configuration scheme, which includes the optimal values ​​for each device at each time period, the following steps are included: S50: Store the optimal configuration scheme according to preset labels and iterate through historical data, and use it to correct the model.

[0011] In one possible implementation, the step of acquiring in real-time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan of the microgrid, and inputting them into the model, includes: S33: Set a threshold for each of the data. When the data is detected to exceed the threshold outside a fixed time in each cycle, reorganize and input the real-time data again, and obtain the updated optimal configuration scheme through the model.

[0012] In one possible implementation, the model outputs an optimal configuration scheme based on the objective function and the constraints, and the microgrid executes the optimal configuration scheme, including: S41: The model filters each individual based on the evaluation results of each individual using the fitness function, and obtains a new generation of individuals through cross-pollination. After iterating several times, the optimal configuration scheme is obtained.

[0013] In one possible implementation, the model filters individuals based on the evaluation results of each individual using the fitness function, cross-selects a new generation of individuals, and iterates several times to obtain the optimal configuration scheme, including: S42: Iterate several times until the fitness result of the individual fluctuates below a preset value, then stop the iteration and select the individual of that generation as the output of the optimal configuration scheme.

[0014] To solve the above-mentioned technical problems, another technical solution adopted in this application is: to provide a microgrid optimization configuration system based on HEOA, applicable to the aforementioned microgrid optimization configuration method based on HEOA, comprising: The quantization module is used to obtain optimization targets based on the needs of the microgrid and convert the optimization targets into quantitative indicators. A modeling module is used to build a model based on HEOA, the model including an objective function based on the quantification index and constraints based on power balance and equipment capacity; The data acquisition module is used to acquire in real time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and input them into the model; The calculation module is used to output the optimal configuration scheme of the model, which includes the optimal values ​​of each device at each time period.

[0015] The beneficial effects of this application are as follows: Unlike the prior art, this application discloses a microgrid optimization configuration method and system based on HEOA. By constructing a model through human evolutionary optimization algorithm and fully collecting various data of the microgrid, this application can meet the specific needs of different microgrids while efficiently providing accurate, economical, reliable and environmentally friendly configuration schemes. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a schematic flowchart of an embodiment of a microgrid optimization configuration method based on HEOA according to this application; Figure 2 This is a module structure diagram of an embodiment of a microgrid optimization configuration system based on HEOA according to this application; Figure 3 This is a schematic diagram of the microgrid structure in the microgrid optimization configuration method based on HEOA proposed in this application.

[0017] Explanation of key component symbols: 10-A microgrid optimization configuration system based on HEOA; 11-Quantization module; 12-Modeling module; 13-Acquisition module; 14-Calculation module. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0019] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0021] Please see Figure 1 The embodiments of this application include: a microgrid optimization configuration method based on HEOA, comprising: S10: Based on the needs of the microgrid, obtain the optimization objectives and transform the optimization objectives into quantitative indicators; S20: The model is built based on HEOA (Human Evolutionary Optimization Algorithm), which includes an objective function based on quantified indicators and constraints based on power balance and equipment capacity. S30: Real-time acquisition of electricity price tables, power generation device operation plans, power generation device hardware parameters, and energy storage device operation plans in the microgrid, and input of these data into the model; S40: The model outputs the optimal configuration scheme based on the objective function and constraints, and the microgrid executes the optimal configuration scheme.

[0022] Please see Figure 3 In this embodiment, the microgrid is typically a small power system comprising several distributed generation facilities (such as wind power, photovoltaics, and backup diesel generators), energy storage devices (such as batteries, supercapacitors, and flywheels), and several load facilities (DC loads and AC loads). It is connected to the power grid and must comply with relevant environmental policies and regulations, while also considering the economic requirements of the enterprise. This method proposes a solution tailored to the microgrid needs of user enterprises. By adopting this method, user enterprises can directly and rationally plan their microgrids, achieving a comprehensive optimization of economy, security, and reliability.

[0023] Specifically, in step S10, based on the needs of the microgrid, specific optimization objectives are obtained. These objectives may include meeting "dual-carbon" environmental protection requirements, reducing production costs, and improving efficiency. These requirements are then transformed into optimization objectives related to environmental friendliness, economic efficiency, and reliability, and further converted into quantitative indicators for subsequent processing. For example, economic indicators may be specifically defined as daily operating costs being lower than a preset value; reliability may be specifically defined as power supply guarantee rate (average outage duration lower than a preset value); and environmental friendliness may be specifically defined as daily carbon emissions being lower than a preset value or carbon emissions per unit of production capacity being lower than a preset value.

[0024] Quantifying the indicators can better guide subsequent processing and analysis, enabling quantitative analysis and indirectly improving the control accuracy of the final configuration scheme.

[0025] In step S20, a model is constructed based on the HEOA algorithm. The basic model of the microgrid includes the energy side and the load side, and the power of the energy side and the load side should be balanced. The model is then applied according to the definitions of various roles in HEOA, combined with the solution of the microgrid's solutions. For example, a feasible microgrid scheduling configuration scheme is encoded as an individual in HEOA. Each individual corresponds to a complete scheduling configuration scheme, which includes multiple controllable decision variables, such as the output of power generation facilities at each time, the power interaction with the main grid, the charging and discharging power of energy storage facilities, and the start-up and shutdown of backup energy. Each individual undergoes dynamic learning, i.e., optimization and adjustment of a certain scheduling configuration scheme; and cross-breeding, i.e., selecting and combining the best individuals from one generation to form new individuals. Individuals are evaluated based on the objective function (such as minimizing operating costs or minimizing emission costs) and constraints to determine their merits and select the best. The selected individuals form a new group for the next iteration, iterating several times to find the optimal configuration scheme.

[0026] In step S30, various parameters of the microgrid are continuously and in real time acquired, including the electricity price table, the operation plan of the power generation device, the hardware parameters of the power generation device, and the operation plan of the energy storage device, and are placed as inputs into the model.

[0027] Furthermore, the electricity price table can be refined into a time-of-use price table. The operation plan for power generation units can be obtained directly from the operating units of each unit for the next day, or it can be simulated using historical data combined with environmental data. The operation plan for energy storage units can also be obtained directly from the energy storage units themselves, either as a proposed plan or a simulated structure. Hardware parameters for power generation units include, but are not limited to, real-time power, grid connection point electrical parameters (current / voltage / frequency), speed of important rotating machinery, coolant temperature, energy storage battery charging and discharging power, and state of charge (SOC). Real-time monitoring of the above data allows for more accurate control of the microgrid's various states, maintaining an understanding of the hardware's health level, enabling better response to emergencies and data fluctuations, and improving the accuracy of configuration schemes.

[0028] In step S40, after acquiring the input data, the model built based on HEOA iteratively calculates the data according to the objective function and constraints to obtain the optimal configuration scheme. The scheduling configuration scheme includes the operating parameters of each facility in the microgrid within a preset time period. For example, in this embodiment, the optimal configuration scheme includes the preset operating parameters of the energy storage facilities and power generation facilities of the microgrid for each time period on the next day. The time period is divided into 15 minutes as a time period, and a configuration scheme is proposed for the parameters of each facility in each time period.

[0029] This embodiment constructs a model using a human evolutionary optimization algorithm and fully collects various data from the microgrid. This application can meet the specific needs of different microgrids while efficiently providing accurate, economical, reliable, and environmentally friendly configuration solutions.

[0030] In one embodiment, the step of obtaining optimization objectives based on the needs of the microgrid and converting the optimization objectives into quantitative indicators includes: S11: Based on the needs of the microgrid, obtain economic, reliability, and environmental objectives; S12: Prioritize and quantify economic, reliability, and environmental objectives to obtain quantitative indicators.

[0031] Specifically, in step S11, optimization objectives are listed based on the actual needs of the microgrid. These objectives may include economic, reliability, and environmental targets. Further economic objectives may include fuel costs, electricity purchase costs, operation and maintenance costs, and hardware depreciation costs (such as energy storage device losses). Reliability targets can be measured by potential loss costs, such as production load outage costs, non-production load outage costs, and emergency power supply costs. Production load outage costs refer to the losses incurred on the production load side due to power outages caused by insufficient reliability. Non-production load outage costs are the losses on the non-production load side during power outages. Emergency power supply costs refer to the costs incurred in taking emergency power supply measures due to power outages, such as the additional costs incurred in starting diesel generators in an emergency and the logistics costs incurred during emergency power supply. Environmental targets include emission costs and environmental penalty costs. Emission costs refer to the costs of treating pollutants emitted during the power generation process, such as the process costs of desulfurization and decarbonization processes corresponding to fuel combustion and the process costs of cleaning cooling water discharge from the water circulation system.

[0032] In step S12, the objectives are prioritized and quantified to make them quantifiable indicators, facilitating subsequent quantitative analysis. In this embodiment, the objectives are first prioritized from highest to lowest as economic objectives, reliability objectives, and environmental objectives. The prioritization of objectives serves as a reference for assigning weights to various parameters in the subsequent objective function.

[0033] In one embodiment, a model is constructed based on HEOA, the model including a target function based on quantified indicators and constraints based on power balance and device capacity, including: S21: Based on the HEOA definition, the decision variables of the configuration scheme are treated as individuals. A fitness function is constructed according to the quantitative indicators, and the individuals are assigned tasks according to the results of the fitness function.

[0034] Specifically, in step S21, HEOA (Human Evolutionary Optimization Algorithm) is used to define each data and behavior. For example, each configuration scheme containing various decision variables is defined as an individual in the algorithm, the optimization process of different configuration schemes is defined as the generational inheritance of humans in the algorithm based on the environment, and the fusion of different configuration schemes to obtain new configuration schemes is defined as evolution and reproduction. This achieves matching with the HEOA relationship and avoids the algorithm from being out of touch with the scenario.

[0035] Based on the quantitative indicators obtained in step S12, a fitness function is constructed.

[0036] Based on the objective function: MinC t =α·C e +β·C r +γ·C p , Where C t For the total cost, C e For economic costs, C r For reliability costs, C p For environmental protection costs, α, β, and γ are the first, second, and third coefficients, respectively, used to adjust the weights of economic costs, reliability costs, and environmental protection costs to suit the actual needs of the microgrid. In this embodiment, based on the target priority in step S12, the values ​​of α, β, and γ are set to 0.5, 0.3, and 0.2, respectively.

[0037] Furthermore, construct the fitness function: F=KC t , Where F represents fitness and K is a conversion constant, used to transform the cost in the objective function from finding the maximum value of the cost to finding the maximum fitness value, facilitating subsequent judgment and processing. In this embodiment, the conversion constant K is set to 18000, a large positive number to ensure that the final fitness value remains positive, facilitating calculation and judgment. Fitness is used to determine the quality of each individual; the higher the fitness, the better the configuration scheme, and the configuration scheme is selected based on the fitness value.

[0038] In one embodiment, a model is constructed based on HEOA, the model including a target function based on quantified indicators and constraints based on power balance and device hardware, including: S22: Construct power balance constraints based on the fact that the total output and total load are equal at any given time, and construct equipment hardware constraints based on equipment capacity, equipment power, and grid-connected power; S23: Apply constraints to each individual.

[0039] Specifically, after obtaining the fitness function, constraints are constructed based on the application environment, such as power balance constraints. This means that the sum of the loads of all devices must equal the sum of their outputs. Failure to meet these power balance constraints can lead to voltage and frequency fluctuations, or even power outages, severely impacting production. The power balance constraints are as follows: P L (t) = P T (t), Where P L (t) refers to the total load of the microgrid at time t, P T (t) refers to the total output of the microgrid at time t. The total output includes the actual output of various power generation facilities, the discharge power of the energy storage system, the output of emergency diesel generators, and the power exchanged with the main grid (positive values ​​for purchased electricity and negative values ​​for sold electricity). The total load of the microgrid includes the charging power of the energy storage system and the load demand of each facility. In actual microgrid operation, the total load and total output are not always balanced; they can vary instantaneously due to changes in conditions or production processes, leading to microgrid fluctuations. Using power balance as a constraint can minimize grid fluctuations, quickly adjust the grid load and output to balance, and prevent amplified fluctuations from causing oscillations and adverse effects on grid facilities.

[0040] Based on the hardware conditions of the equipment capacity, constraints are constructed, including: the output of each power generation facility does not exceed the maximum output value, and the energy storage SOC is limited to 20-90%. In the former case, the maximum output value is determined by the installed capacity, and the maximum output is limited to avoid overload and hardware damage. In the latter case, the energy storage SOC is limited to avoid overcharging or over-discharging, which would reduce battery life and improve equipment reliability.

[0041] Environmental constraints are established based on policy compliance, such as daily limits on total carbon emissions and total sulfur emissions. These emissions can then be further converted into the power generation and time of corresponding power generation facilities to facilitate compliance with these constraints.

[0042] Furthermore, it may include constraints on the number of times equipment can be started and stopped, in order to limit the frequent start and stop of power generation facilities and avoid damage to the hardware; and power quality constraints, to limit the voltage and frequency deviations of the microgrid (for example, the deviations shall not exceed 5%), in order to avoid damage to electrical equipment and related loads.

[0043] In one embodiment, the step of acquiring in real-time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and inputting them into the model includes: S31: Select high-quality configuration schemes from historical data as the initial population input model; S32: Use the data of the day as the correction input model.

[0044] Specifically, in step S31, the initial population refers to the initial configuration schemes used for screening and fusion, which can be determined based on historical data or experience. The selection of high-quality configuration schemes can be based on fitness values. In addition to historical data and experience, the initial population can also randomly generate a portion of configuration schemes that meet the constraints to avoid falling into local optima. The fitness of each individual in the initial population is evaluated, and high-quality individuals are selected based on fitness (e.g., the top 50% of individuals by fitness). These individuals are then cross-matched to replace some variables to form a new generation population, corresponding to evolution and reproduction in HEOA. The fitness of this new generation population is then evaluated, screened, and cross-matched again. This process is repeated until a predetermined number of iterations is reached or the fitness reaches a predetermined value, at which point the iteration terminates. In this embodiment, the preset number of iterations is 400 to achieve a balance between computational speed and result accuracy.

[0045] In step S32, the daily data may include the peak and off-peak electricity prices for the day, the output plan of the power generation facilities, the load forecast for the day, and hardware parameters. This data is used to replace outdated data in the model, correct the fitness calculation formula, and ensure that the optimal configuration scheme evaluated in the final assessment conforms to the actual operating conditions of the day. In particular, real-time monitoring of hardware parameters can further align the analysis with the current hardware health status and avoid biases in the results caused by using outdated hardware parameters.

[0046] In one embodiment, after the step of the model outputting an optimal configuration scheme, which includes the optimal values ​​for each device at each time period, the following steps are included: S50: Store the optimal configuration scheme according to the preset labels and iterate through historical data, and use it to correct the model.

[0047] Preset labels can include the day's load level, the day's weather (sunny or rainy), and the deviation between predicted and actual loads. These labels are used to annotate past optimal configuration schemes. Subsequent classification analysis can be performed based on these labels to obtain commonalities and correct relevant parameters in the model, such as the objective function, fitness function, and constraints. This allows the model to better fit actual working conditions and improves the accuracy of the obtained optimal configuration scheme.

[0048] In one embodiment, the step of acquiring in real-time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and inputting them into the model includes: S33: Set thresholds for each data point. When data exceeds the threshold outside of a fixed time in each cycle, reprocess and input the real-time data, and obtain the updated optimal configuration scheme through the model.

[0049] Specifically, in this embodiment, a cycle is defined as one day. At a fixed time each day (10 PM), the optimal configuration scheme for the following day is predicted and output, and then sent to each facility node for setup. However, during the remaining time, various data are continuously monitored. When a data point exceeds a threshold, it is considered a significant data fluctuation. Correspondingly, the threshold range should be relatively large to avoid misjudgments caused by small data fluctuations. At this point, all data should be immediately checked and processed, and then input into the model to output a corrected configuration scheme for the remainder of the day. This addresses sudden changes and fluctuations in data, improves control accuracy, and prevents damage to facility hardware.

[0050] In one embodiment, the model outputs an optimal configuration scheme based on the objective function and constraints, and the microgrid executes the optimal configuration scheme, including the following steps: S41: The model selects individuals based on the evaluation results of each individual using the fitness function, and obtains a new generation of population through cross-pollination. After iterating several times, the optimal configuration scheme is obtained.

[0051] Specifically, new individuals are generated through crossover. In this embodiment, the population is divided into five groups on average. The top 10% of individuals with the highest fitness in each of the five groups are selected. The optimal variable values ​​of the decision variables in each group are analyzed, and these optimal variable values ​​are then used to crossover with individuals from other groups to obtain a new generation of individuals. Dividing the population into multiple groups aims to avoid local optima caused by uneven weighting of some variables. It also facilitates adjustments to the weights of different objectives based on the degree of difference between groups during subsequent analysis and review, thereby further refining the model.

[0052] In one embodiment, the model selects individuals based on the evaluation results of each individual using a fitness function, and obtains a new generation of individuals through cross-pollination, iterating several times to obtain the optimal configuration scheme. This process includes: S42: Iterate several times until the fitness result of an individual fluctuates below a preset value, then stop the iteration and select the individual of that generation as the optimal configuration scheme for output.

[0053] Specifically, the number of iterations and fitness result thresholds can be preset. When the number of iterations is greater than the preset value and the difference in fitness result changes is less than the threshold, the iteration is terminated and the result of this event is taken as the optimal configuration scheme and output.

[0054] The above is an explanation of a microgrid optimization configuration method based on HEOA in the embodiments of this application. The following describes a microgrid optimization configuration system 10 based on HEOA in the embodiments of this application. Please refer to... Figure 2A microgrid optimization configuration system 10 based on HEOA, applicable to a microgrid optimization configuration method based on HEOA as described above, includes: Quantization module 11 is used to obtain optimization targets based on the needs of the microgrid and convert the optimization targets into quantitative indicators; Modeling module 12 is used to build a model based on HEOA. The model includes an objective function based on quantitative indicators and constraints based on power balance and equipment capacity. The data acquisition module 13 is used to acquire in real time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and input them into the model; The calculation module 14 is used to output the optimal configuration scheme of the model, which includes the optimal values ​​of each device at each time period.

[0055] Since the system implementations correspond to the method implementations described above, please refer to the method implementations above for an introduction to the HEOA-based microgrid optimization configuration system provided by this invention. It will not be repeated here, as it has the same beneficial effects as the HEOA-based microgrid optimization configuration method described above.

[0056] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A microgrid optimization configuration method based on HEOA, characterized in that, include: S10: Based on the needs of the microgrid, obtain the optimization target and convert the optimization target into quantitative indicators; S20: Construct a model based on HEOA, the model including an objective function based on the quantified index and constraints based on power balance and equipment capacity; S30: Real-time acquisition of the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and input them into the model; S40: The model outputs an optimal configuration scheme based on the objective function and the constraints, and the microgrid executes the optimal configuration scheme.

2. The microgrid optimization configuration method based on HEOA according to claim 1, characterized in that, The steps of obtaining optimization objectives based on the needs of microgrids and converting the optimization objectives into quantitative indicators include: S11: Based on the needs of the microgrid, obtain economic, reliability, and environmental objectives; S12: Prioritize and quantify the economic objectives, reliability objectives, and environmental objectives to obtain quantitative indicators.

3. The microgrid optimization configuration method based on HEOA according to claim 1, characterized in that, The model constructed based on HEOA, which includes the steps of an objective function based on the quantified index and constraints based on power balance and equipment capacity, includes: S21: Based on the HEOA definition, the decision variables of the configuration scheme are treated as individuals, a fitness function is constructed according to the quantitative indicators, and the individuals are assigned tasks according to the results of the fitness function.

4. The microgrid optimization configuration method based on HEOA according to claim 3, characterized in that, The HEOA-based model construction method includes steps such as an objective function based on the quantified index and constraints based on power balance and device hardware, including: S22: Construct power balance constraints based on the fact that the total output and total load are equal at any given time, and construct equipment hardware constraints based on equipment capacity, equipment power, and grid-connected power; S23: Apply the constraints to each of the individuals.

5. A microgrid optimization configuration method based on HEOA according to claim 3, characterized in that, The step of acquiring in real-time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan of the microgrid, and inputting them into the model, includes: S31: Select a high-quality configuration scheme from historical data as the initial population input to the model; S32: Use the data of the day as the correction input to the model.

6. A microgrid optimization configuration method based on HEOA according to claim 5, characterized in that, The model outputs an optimal configuration scheme, which includes the optimal values ​​for each device at each time period. Following this step, the optimal configuration scheme includes: S50: Store the optimal configuration scheme according to preset labels and iterate through historical data, and use it to correct the model.

7. A microgrid optimization configuration method based on HEOA according to claim 3, characterized in that, The step of acquiring in real time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan of the microgrid, and inputting them into the model, includes: S33: Set thresholds for each data point. When the data exceeds the threshold outside a fixed time in each cycle, reorganize and input the real-time data, and obtain the updated optimal configuration scheme through the model.

8. A microgrid optimization configuration method based on HEOA according to claim 3, characterized in that, The model outputs an optimal configuration scheme based on the objective function and the constraints. The microgrid executes the optimal configuration scheme in the following steps: S41: The model filters each individual based on the evaluation results of each individual using the fitness function, and obtains a new generation of individuals through cross-pollination. After iterating several times, the optimal configuration scheme is obtained.

9. A microgrid optimization configuration method based on HEOA according to claim 8, characterized in that, The model filters individuals based on the evaluation results of the fitness function, cross-selects a new generation of individuals, and iterates several times to obtain the optimal configuration scheme. The steps include: S42: Iterate several times until the fitness result of the individual fluctuates below a preset value, then stop the iteration and select the individual of that generation as the output of the optimal configuration scheme.

10. A microgrid optimization configuration system based on HEOA, applicable to the microgrid optimization configuration method based on HEOA as described in any one of claims 1 to 9, characterized in that, include: The quantization module is used to obtain optimization targets based on the needs of the microgrid and convert the optimization targets into quantitative indicators. A modeling module is used to build a model based on HEOA, the model including an objective function based on the quantification index and constraints based on power balance and equipment capacity; The data acquisition module is used to acquire in real time the electricity price table, power generation device operation plan, power generation device hardware parameters, and energy storage device operation plan in the microgrid, and input them into the model; The calculation module is used to output the optimal configuration scheme of the model, which includes the optimal values ​​of each device at each time period.

Images