Power scheduling method for micro-grid, program product, medium and computer device

Abstract

The application provides a kind of micro-grid power scheduling method, program product, medium and computer equipment, relate to power supply system field.Energy scheduling method includes: obtaining the historical power supply dataset of each of the multiple energy generation systems in micro-grid;Obtain the historical environmental data set of the operation process of micro-grid;Based on the historical power supply dataset and historical environmental data set of multiple energy generation systems, correlation analysis is carried out to obtain the environmental influence characteristic set of at least one energy generation system;Obtain the operating state data of micro-grid;According to the operating state data and environmental influence characteristic set, generate the power scheduling optimization scheme of micro-grid, and control micro-grid to execute power scheduling optimization scheme.The scheme of the application can comprehensively consider the energy generation state, environmental factors and current operating state, realize the reasonable scheduling of power by means of artificial intelligence and other information technology means, improve the rationality of power scheduling, so that micro-grid can operate more efficiently and stably.

Description

Technical Field

[0001] This invention relates to the field of power supply and distribution systems, and in particular to a power dispatching method, program product, medium, and computer equipment for a microgrid. Background Technology

[0002] A microgrid is a self-sufficient small-scale power network composed of multiple energy generation systems, which can use renewable energy, energy storage devices, and traditional fossil fuels as power sources. With the rapid development of renewable energy, microgrids, as a flexible, efficient, and environmentally friendly power supply solution, are gradually gaining attention. One of their core challenges is how to rationally optimize dispatching based on changing external environments and internal conditions.

[0003] Existing technologies typically optimize dispatch based on historical data. However, historical data cannot accurately reflect future extreme weather or sudden changes in demand, which leads to insufficient accuracy in microgrid dispatch schemes. Specifically, dispatch optimization based on historical data ignores drastic fluctuations in future weather conditions and electricity demand. As a result, when weather conditions and electricity demand deviate from historical data, the dispatch scheme may not be able to adapt in time, leading to energy waste or insufficient power supply.

[0004] Furthermore, microgrid systems employ multiple power generation systems, simultaneously utilizing various energy types. These different energy types are affected by different environmental factors, with varying degrees of impact. Introducing environmental factors into the control process for each type of power generation system cannot guarantee that the overall power dispatch requirements of the microgrid will be met. This presents greater technical challenges for microgrid power dispatch. Summary of the Invention

[0005] One object of the present invention is to provide a power dispatching method for microgrids that at least solves any of the above-mentioned technical problems.

[0006] A further objective of this invention is to prevent the efficiency of microgrid power dispatch schemes from decreasing or even failing due to changes in the operating environment.

[0007] Another further objective of this invention is to improve the operational stability of microgrids.

[0008] Specifically, this invention provides a power dispatching method for microgrids. The method includes:

[0009] Obtain historical power supply datasets for various energy generation systems in a microgrid, classifying the energy generation systems according to the type of energy source they generate;

[0010] Obtain historical environmental datasets of the microgrid operation process;

[0011] Correlation analysis was conducted on historical power supply datasets and historical environmental datasets of multiple energy power generation systems to obtain environmental impact characteristic sets of at least one type of energy power generation system.

[0012] Acquire microgrid operational status data, which includes power generation data from various energy generation systems, microgrid operating environment data, and microgrid electricity load forecast data.

[0013] Based on the operating status data and the environmental impact feature set, a power dispatch optimization scheme for the microgrid is generated, and the microgrid is controlled to execute the power dispatch optimization scheme.

[0014] Optionally, the steps for generating a power dispatch optimization scheme for the microgrid based on operating status data and environmental impact feature sets include:

[0015] Obtain the historical scheduling record sets for each of the various energy generation systems. The historical scheduling record sets are used to store the scheduling actions of the energy generation systems, the execution results of the scheduling actions, and the operating status data during the scheduling actions.

[0016] The microgrid's operational status data and environmental impact feature set are matched against the historical dispatch record set.

[0017] An initial power dispatch scheme is generated based on the matching results;

[0018] Evaluate whether the initial power dispatch scheme meets the preset dispatch requirements; if so, the initial power dispatch scheme shall be used as the optimized power dispatch scheme.

[0019] Optionally, the step of generating an initial power dispatch scheme based on the matching results includes:

[0020] Multiple power dispatch alternatives that meet the set constraints are identified from the matching results;

[0021] The scheduling effects of multiple power dispatching alternatives are ranked, and the one with the best scheduling effect is selected as the initial power dispatching scheme.

[0022] Optionally, the steps for evaluating whether the initial power dispatch scheme meets the preset dispatch requirements include:

[0023] An initial power dispatch scheme is executed in a virtual model pre-built for a microgrid to obtain dispatch simulation results data;

[0024] The scheduling simulation results are evaluated based on a preset evaluation function to obtain the evaluation results;

[0025] Determine whether the evaluation results meet the scheduling requirements.

[0026] Optionally, the step of evaluating the scheduling simulation results data based on a preset evaluation function includes:

[0027] The evaluation function is invoked to quantify the multidimensional evaluation factors into evaluation results. The multidimensional evaluation factors include: economic cost dimension, system stability dimension, security dimension, energy utilization rate dimension, grid dependence dimension, and equipment loss dimension.

[0028] The quantitative values ​​of multidimensional evaluation factors are calculated based on the scheduling simulation results, operation status data, and environmental impact feature set.

[0029] The evaluation results are obtained by calculating the quantitative values ​​of the multidimensional evaluation factors using the evaluation function.

[0030] Optionally, if the initial power dispatch scheme does not meet the dispatch requirements, it also includes:

[0031] Generate scheduling parameter constraints based on multiple power dispatching alternatives;

[0032] Based on satisfying the constraints of the scheduling parameters, the initial power dispatch scheme is iteratively optimized;

[0033] The iterative optimization schemes are evaluated, and the iterative optimization schemes whose evaluation results meet the scheduling requirements are taken as the power dispatch optimization schemes.

[0034] Optionally, the steps for performing correlation analysis based on historical power supply datasets and historical environmental datasets from multiple energy generation systems include:

[0035] The historical power supply dataset and historical environment dataset of each type of energy generation system are time-aligned to ensure that the two correspond in the time dimension.

[0036] Correlation analysis was performed on the historical power supply dataset and the historical environmental dataset for each type of energy generation system during the same period.

[0037] Data with a correlation greater than a preset correlation coefficient threshold is selected from historical environmental datasets to obtain relevant environmental data;

[0038] By extracting and organizing the features of relevant environmental data, an environmental impact feature set for this type of energy power generation system is obtained.

[0039] Optionally, after the step of controlling the microgrid to execute the power dispatch optimization scheme, the following may be included:

[0040] Monitor the power supply and power consumption data of the microgrid;

[0041] The microgrid's dispatch evaluation is generated based on the power supply side data and power consumption side data.

[0042] Optionally, the step of generating a dispatch evaluation of the microgrid includes:

[0043] Determine whether the dispatch evaluation meets the power dispatch expectations of the microgrid;

[0044] If the conditions are met, the scheduling information of various energy generation systems will be recorded and added to the historical scheduling record set.

[0045] If the conditions are not met, identify the abnormal subsystems in the microgrid and make targeted adjustments to them.

[0046] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the steps of the power dispatching method for any of the above-described microgrids.

[0047] According to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the power dispatching method for any of the above-described microgrids.

[0048] According to another aspect of the present invention, a computer device is also provided, which includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the power dispatching method for any of the above-described microgrids.

[0049] The microgrid power dispatching method of this invention acquires historical power supply datasets from multiple energy generation systems and historical environmental datasets from the microgrid's operation process. Correlation analysis is then performed to obtain an environmental impact feature set. Combined with operational status data, a power dispatching optimization scheme is generated and executed. This method comprehensively considers energy generation status, environmental factors, and the current operational status to achieve rational power dispatching of the microgrid, improving the rationality of power dispatching and enabling the microgrid to operate more efficiently and stably. For different types of energy generation systems in the microgrid, such as traditional fossil fuel power generation, renewable energy power generation (solar, wind, etc.), and new power generation methods (hydrogen, waste incineration, geothermal), historical power supply datasets are acquired and environmental impact feature sets are determined. Using information technology such as artificial intelligence, the correlation between each power generation method and environmental factors is accurately identified. When generating the power dispatching optimization scheme, power generation tasks can be more rationally arranged based on real-time operational status data to meet the overall power dispatching requirements of the microgrid.

[0050] Furthermore, the power dispatching method for microgrids in this invention accumulates historical dispatching information under different operating conditions through historical dispatching record sets for various energy generation systems. By matching current operating state data with environmental impact feature sets, a matching dispatching scheme can be quickly determined from historical experience data as a reference, thereby greatly improving the efficiency of generating dispatching schemes and reducing the time cost and computational resource consumption of scheme generation. Evaluating the initial power dispatching scheme ensures that the optimized power dispatching scheme can meet the various needs of the current microgrid operation.

[0051] Furthermore, historical environmental datasets can include ambient weather data, thereby revealing the performance characteristics of different types of energy generation systems under varying weather conditions, thus improving the practical operability of dispatching schemes. Microgrid load forecasting data provides accurate demand predictions for subsequent energy dispatching, enabling early prediction of electricity demand fluctuations, ensuring accurate matching of energy supply and avoiding energy shortages or surpluses due to sudden increases in demand.

[0052] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0053] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0054] Figure 1 This is a schematic diagram of the system architecture of a microgrid according to an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of a power dispatching method for a microgrid according to an embodiment of the present invention;

[0056] Figure 3 This is a schematic diagram illustrating the generation of an optimized power dispatch scheme in a power dispatch method for a microgrid according to an embodiment of the present invention;

[0057] Figure 4 This is a schematic diagram illustrating the evaluation of an initial power dispatch scheme in a power dispatch method for a microgrid according to an embodiment of the present invention;

[0058] Figure 5 This is a schematic diagram illustrating the correlation analysis between historical power supply dataset and historical environmental dataset in a microgrid power dispatching method according to an embodiment of the present invention.

[0059] Figure 6This is a schematic diagram illustrating the steps of a microgrid power dispatching method according to an embodiment of the present invention after executing a power dispatching optimization scheme;

[0060] Figure 7 This is a schematic diagram of a computer program product according to an embodiment of the present invention;

[0061] Figure 8 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention;

[0062] Figure 9 This is a schematic block diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0063] Those skilled in the art should understand that the embodiments described below are merely a part of the embodiments of the present invention, and not all of the embodiments of the present invention. These partial embodiments are intended to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention. Based on the embodiments provided by the present invention, all other embodiments obtained by those skilled in the art without creative effort should still fall within the scope of protection of the present invention.

[0064] Figure 1 This is a schematic diagram of a microgrid system architecture according to an embodiment of the present invention. The microgrid generally includes multiple types of energy generation systems 110, which are classified according to the type of energy source they generate. For example, they include traditional fossil fuel power generation (coal, oil, gas, etc.), renewable energy power generation (hydropower, wind power, photovoltaic, biomass energy, geothermal energy, tidal energy), other new energy (hydrogen energy) power generation, and energy storage (mechanical energy, electrochemical batteries, electromagnetic energy storage) power generation. Different types of energy generation systems are affected differently by environmental factors. For example, for solar power systems, environmental factors such as sunlight intensity and weather conditions have a significant impact on their power generation; for wind power systems, environmental factors such as wind speed and wind direction have a significant impact on their power generation; for hydropower, watershed precipitation and runoff have a significant impact on power generation; and for traditional fossil fuels, their control methods are usually relatively mature, and they are less affected by environmental factors.

[0065] Microgrids can also include various types of power systems 120, such as power equipment systems (various motors, such as water pumps, fans, compressors, machine tools), electric heating equipment systems (such as electric furnaces, electric water heaters, air conditioners), electronic information equipment systems (such as computers, servers, network equipment, communication equipment), charging equipment systems (such as electronic device chargers, electric vehicle charging equipment), and lighting equipment (various lamps).

[0066] Microgrids can also include various measurement and detection devices 130, such as smart meters, various sensors, etc., to acquire electrical data such as power load data, power generation data, voltage and current, power quality, and power factor, as well as environmental data such as temperature, humidity, wind force, wind direction, solar irradiance, and weather.

[0067] Microgrids may also include various communication devices 140, which can interact with external devices through various communication methods, such as obtaining weather forecast data from weather platforms and obtaining power grid data such as electricity prices and dispatch information from public power grid service platforms.

[0068] The microgrid may also include a control center 150. The control center 150 may include one or more of the following: local device control equipment, edge-side control equipment, and network-side platform control equipment. The control center 150 interacts with the aforementioned multi-energy generation system 110, multi-electricity consumption system 120, measurement and detection equipment 130, and communication equipment 140 to perform functions such as data analysis and scheduling scheme formulation.

[0069] The microgrid power dispatching method in this embodiment achieves reasonable dispatching of microgrid power by comprehensively considering energy generation status, environmental factors, and current operating status through data analysis. Figure 2 This is a schematic diagram of a power dispatching method for a microgrid according to an embodiment of the present invention. The power dispatching method for the microgrid generally includes:

[0070] Step S201: Obtain historical power supply datasets for each of the various energy generation systems in the microgrid. The energy generation systems are categorized according to the type of energy source they generate. The historical power supply dataset records power generation data, power output, power generation equipment operating status data, and energy storage charging / discharging status, organized chronologically. Power generation data and power output reflect the power generation capacity (or production capacity) of each type of energy generation system. Power generation equipment operating status data reflects the operating status of the power generation system and may include parameters such as fuel consumption rate, steam pressure, and generator speed for traditional fossil fuel power generation equipment; the rotational speed and yaw angle of wind turbine blades for wind power generation equipment; and the temperature, output voltage, and current of photovoltaic panels for photovoltaic power generation equipment.

[0071] Step S202: Obtain the historical environmental dataset of the microgrid operation process. The historical environmental dataset is used to record external environmental data that affects the power generation and power consumption systems in the microgrid. This environmental data may include: meteorological environmental data (sunlight, temperature, humidity, wind speed, wind force, weather conditions, precipitation, etc.), climate characteristics, and geographical location characteristics (altitude, climate, etc.).

[0072] Historical power supply datasets and historical environment datasets can be time-aligned, meaning the data is organized chronologically. After time alignment, the historical power supply dataset and historical environment dataset achieve a precise correspondence in the time dimension, providing a reliable data foundation for subsequent analyses such as correlation analysis.

[0073] Step S203: Based on the historical power supply dataset and historical environmental dataset of multiple energy power generation systems, perform correlation analysis to obtain the environmental impact feature set of at least one type of energy power generation system.

[0074] Step S204: Obtain the microgrid's operational status data, which includes power generation data from various energy generation systems, microgrid operating environment data, and microgrid load forecast data. The operational status data reflects the current operational status and forecast data of the microgrid. The microgrid load forecast data can be obtained based on historical data using time series analysis or regression analysis. Alternatively, in some embodiments, artificial intelligence-based forecasting methods such as artificial neural networks can be used.

[0075] Step S205: Generate a power dispatch optimization scheme for the microgrid based on the operating status data and the environmental impact feature set, and control the microgrid to execute the power dispatch optimization scheme.

[0076] Figure 3 This is a schematic diagram illustrating the generation of an optimized power dispatch scheme in a power dispatch method for a microgrid according to an embodiment of the present invention. The generation of the optimized power dispatch scheme for the microgrid in step S205 may include:

[0077] Step S301: Obtain the historical dispatch record sets for each of the various energy generation systems. These historical dispatch record sets are used to store dispatch actions, execution results, and operational status data during the dispatch actions. Dispatch actions can include internal dispatch actions within the energy generation system, such as starting and stopping power generation equipment and adjusting power output, as well as adjustments in power generation output and energy distribution between energy generation systems. Execution results of dispatch actions can include changes in power generation, stability indicators of power supply (e.g., voltage and frequency fluctuations), energy utilization efficiency, and changes in power generation costs. Operational status data during the dispatch actions can include operational status parameters of power generation equipment and overall electrical parameters of the microgrid (voltage, current, power, frequency, power factor).

[0078] Step S302 involves matching the microgrid's operational status data and environmental impact feature set against the historical dispatch record set. The operational status data and environmental impact feature set can be standardized and encoded to form a data feature sequence with a predetermined format, while the historical dispatch record set can be pre-cleaned and standardized to achieve vectorization. The matching process can utilize a suitable vector distance matching algorithm, such as Euclidean distance or cosine similarity, to find similar data based on the distance between vectors, serving as the matching result.

[0079] Step S303: Generate an initial power dispatch scheme based on the matching results. In some embodiments, the process of generating the initial power dispatch scheme may be as follows: identify multiple power dispatch candidate schemes that meet the set constraints from the matching results; rank the dispatch effects of the multiple power dispatch candidate schemes, and select the one with the best dispatch effect as the initial power dispatch scheme.

[0080] Step S304: Evaluate whether the initial power dispatch plan meets the preset dispatch requirements. Constraints can be set according to the microgrid's operational requirements, such as the power generation ratio requirements of each energy generation system, power generation cost requirements, and power load control requirements. If the initial power dispatch plan meets the preset dispatch requirements, proceed to step S305; if the initial power dispatch plan does not meet the preset dispatch requirements, proceed to step S306.

[0081] In step S305, the initial power dispatch scheme is used as the optimized power dispatch scheme.

[0082] Step S306: Generate scheduling parameter constraints based on multiple alternative power dispatch schemes. These constraints may include: power supply and demand balance conditions (e.g., the total power generation of all energy generation systems within the microgrid must be equal to or greater than the sum of the microgrid's power load plus line losses and other power consumption, and the balance requirements for energy storage charging and discharging); power generation equipment operation constraints (e.g., minimum and maximum power limits for power generation equipment, and limits on the rate of change of power generation); power consumption equipment demand constraints (e.g., the size of different levels of power load, and the adjustable range of load); electrical parameter constraints (e.g., power quality requirements, voltage deviation limits, and frequency deviation limits); economic cost constraints (e.g., power generation costs and electricity purchase costs); and safety constraints (e.g., limits on reserve capacity, failure rate limits, and maintenance time).

[0083] Step S307: Based on satisfying the scheduling parameter constraints, the initial power dispatch scheme is iteratively optimized. The optimization process can use nonlinear programming algorithms, such as adjusting variable values ​​by calculating the gradient (or Hessian matrix) of the objective function to gradually approach the optimal solution. Alternatively, in some embodiments, the optimization process can also be implemented using a genetic algorithm, encoding the initial power dispatch scheme as chromosomes. By calculating the fitness value of each chromosome (dispatch scheme) (related to the objective function, such as lower power generation costs and higher system stability corresponding to higher fitness values), chromosomes with high fitness are selected for genetic operations (crossover and mutation) to generate new offspring chromosomes, i.e., new dispatch schemes. After multiple generations of evolution, the chromosomes in the population gradually approach the optimal solution. In other embodiments, the optimization process can also be implemented through perturbation analysis, for example, by subjecting the parameters of the initial power dispatch scheme to small perturbations, determining the amount of change after the perturbation, selecting sensitive parameters based on the magnitude of the change caused by the perturbation of each parameter, and achieving optimization by adjusting the sensitive parameters.

[0084] Step S308: Evaluate the iterative optimization schemes and select the iterative optimization schemes whose evaluation results meet the scheduling requirements as the power dispatch optimization schemes.

[0085] Figure 4 This is a schematic diagram illustrating the evaluation of an initial power dispatch scheme in a power dispatch method for a microgrid according to an embodiment of the present invention. Step S304 above, evaluating the initial power dispatch scheme, may include:

[0086] Step S401: Execute the initial power dispatch scheme in a pre-constructed virtual model for the microgrid to obtain dispatch simulation result data. The virtual model, through abstraction and digitization of the microgrid, utilizes mathematical and computer technologies to simulate and model the microgrid's operating characteristics and behavior, yielding dispatch simulation result data that closely approximates the actual dispatch results. Using a virtual model to simulate the dispatch process allows for the evaluation of the dispatch scheme's effectiveness before its actual execution, avoiding the risks associated with direct execution on the actual microgrid and improving the accuracy and reliability of dispatch scheme evaluation.

[0087] Step S402: Invoke the evaluation function. The evaluation function quantifies the multi-dimensional evaluation factors into evaluation results. These multi-dimensional evaluation factors include: economic cost dimension, system stability dimension, safety dimension, energy utilization rate dimension, grid dependence dimension, and equipment loss dimension. The evaluation function can be a weighted summation method, for example, assigning weights to each evaluation factor according to control requirements, and calculating the evaluation result through weighted summation. The weights of the multi-dimensional evaluation factors can be determined using the analytic hierarchy process (AHP).

[0088] Alternatively, considering the potentially complex interactions between the evaluation factors, a nonlinear combination of evaluation functions can be used. For example, a neural network can be used to construct the evaluation function, taking the multidimensional evaluation factors as input, and outputting the evaluation results after nonlinear transformation through hidden layers.

[0089] Step S403: Quantitative values ​​of multidimensional evaluation factors are calculated based on the scheduling simulation results, operational status data, and environmental impact feature set. Different evaluation factors can be calculated using corresponding methods, such as principal component analysis, fuzzy comprehensive evaluation, and entropy weight method.

[0090] Step S404 involves calculating the quantified values ​​of the multidimensional evaluation factors using the evaluation function to obtain the evaluation results. Steps S402 to S404 above evaluate the scheduling simulation result data based on a preset evaluation function to obtain the evaluation results.

[0091] Step S405: Determine whether the initial power dispatch scheme meets the dispatch requirements based on the evaluation results.

[0092] Figure 5 This is a schematic diagram illustrating the correlation analysis of historical power supply dataset and historical environment dataset in a microgrid power dispatching method according to an embodiment of the present invention. The correlation analysis in step S203 above may include:

[0093] Step S501: Perform time alignment processing on the historical power supply dataset and historical environment dataset of each type of energy power generation system to ensure that the two correspond in the time dimension.

[0094] Step S502: Perform correlation analysis on the historical power supply dataset and the historical environmental dataset for each type of energy power generation system during the same period.

[0095] Step S503: Filter out data with a correlation greater than a preset correlation coefficient threshold from the historical environmental dataset to obtain relevant environmental data.

[0096] Step S504: Extract and organize the features of relevant environmental data to obtain the environmental impact feature set of this type of energy power generation system.

[0097] Figure 6 This is a schematic diagram illustrating the steps of a microgrid power dispatching method according to an embodiment of the present invention after executing a power dispatching optimization scheme. After controlling the microgrid to execute the power dispatching optimization scheme, the method of this embodiment may further include:

[0098] Step S601: Monitor the power supply side data and power consumption side data of the microgrid.

[0099] Step S602: Generate a dispatch evaluation of the microgrid based on the power supply side data and power consumption side data of the microgrid.

[0100] Step S603: Determine whether the dispatch evaluation meets the microgrid's power dispatch expectations. If the dispatch evaluation meets the microgrid's power dispatch expectations, proceed to step S604; if the dispatch evaluation does not meet the microgrid's power dispatch expectations, proceed to step S605.

[0101] Step S604: Record the scheduling information of various energy generation systems to add them to the historical scheduling record set, thereby providing data support for subsequent scheduling.

[0102] Step S605: Identify abnormal subsystems in the microgrid and make targeted adjustments to them. An abnormal subsystem refers to a device or combination of devices whose operating state deviates from the normal range, causing the microgrid's state to not meet the expectations of power dispatch. By correcting the state of the abnormal subsystems, the microgrid can operate stably and reliably.

[0103] Taking a microgrid with an M-type energy power generation system as an example, the M-type energy power generation system pre-records M sets of historical power supply datasets and pre-aligns them with historical environmental datasets (historical weather data, etc.) to ensure that the power supply data at each point in time corresponds to the corresponding environmental data. If the time granularity of the data is different, it is necessary to interpolate or aggregate the data with a longer time granularity.

[0104] Impact analysis based on M sets of historical power supply and environmental datasets yields N sets of environmental impact characteristics, where N ≤ M. This indicates the existence of energy generation systems less affected by weather, such as traditional fossil fuel power generation systems. These N sets of environmental impact characteristics represent the influence of environmental factors on N types of energy generation systems. Different types of energy generation systems are affected by different environmental factors.

[0105] Microgrids can use smart meters, sensors and other detection devices to collect historical electricity consumption data from each electricity user. The historical electricity consumption data can be recorded at different time granularities such as hour, day and month. The data content includes time series information of electricity consumption, and the variables involved include total electricity consumption, electricity load curve, peak load period, etc.

[0106] Historical electricity consumption data is used for electricity consumption trend analysis. For example, time series models are used to analyze electricity consumption data to predict future electricity consumption; patterns such as seasonal fluctuations and differences in electricity consumption between weekdays and weekends are identified; and abnormal patterns in historical electricity consumption, such as equipment failures, peak consumption, and abnormal loads, are identified through data analysis. Electricity load forecasting data will be used in subsequent scheduling to adjust energy dispatching schemes to ensure sufficient power supply during specific periods.

[0107] Microgrids can obtain weather forecast information and public power grid information by interacting with meteorological facilities and the public power grid.

[0108] The microgrid combines N sets of environmental impact features, weather forecast information, and electricity load forecast data to conduct energy dispatch analysis on M-type energy generation systems, generating an initial power dispatch plan. The N sets of environmental impact features reflect the impact of different environments on the energy generation system, the weather forecast information reflects the weather data of the microgrid's location in the future, and the electricity load forecast data reflects the electricity demand.

[0109] By applying multi-constraint optimization to the initial power dispatch scheme, an optimized power dispatch scheme can be obtained. The constraints of multi-constraint optimization include dispatch economic cost, dispatch stability, energy utilization efficiency, and dispatch losses. By optimizing the initial power dispatch scheme, a more accurate and efficient optimized energy dispatch scheme can be obtained.

[0110] The virtual model of the microgrid can execute alternative power dispatch schemes and obtain dispatch simulation result data. Based on the dispatch fitness evaluation function, the dispatch fitness of the dispatch simulation result data is evaluated, and dispatch fitness evaluation coefficients are generated. If the dispatch fitness evaluation coefficients do not meet the preset fitness threshold, optimization instructions are generated to perform multi-constraint optimization on the initial power dispatch scheme.

[0111] The dispatch fitness evaluation function is used to assess the effectiveness of energy dispatch schemes. The evaluation dimensions include economic cost, system stability, security, energy utilization rate, grid dependence, and equipment losses. The evaluation results reflect the dispatch effectiveness and serve as a basis for adjusting the dispatch scheme.

[0112] The scheduling fitness evaluation function is a weighted average of multiple preset evaluation indicators, including scheduling economic cost, scheduling stability, energy utilization efficiency, and scheduling losses. The weighting coefficients are set according to the specific objectives of the microgrid. For example, if the system's objective is to prioritize economic efficiency, a higher weight can be assigned to the economic cost indicator; if the system has high stability requirements, a higher weight can be assigned to scheduling stability. In practical applications, the weighting coefficients can be dynamically adjusted based on feedback from the scheduling scheme and actual needs to achieve better system performance.

[0113] The process of conducting impact analysis on the historical power supply dataset of M-type energy power generation system may include: randomly extracting the first historical power supply dataset of the first energy type based on the historical power supply dataset; randomly extracting the first historical weather dataset of the first weather feature based on the historical environmental dataset; aligning the first historical power supply dataset and the first historical weather dataset in time and performing correlation analysis to obtain the first correlation coefficient; if the first correlation coefficient is greater than the correlation coefficient threshold, then adding the first weather feature to the first weather impact index set of the first energy type.

[0114] Correlation analysis can help assess the relationship between weather conditions and power supply. For example, the Pearson correlation coefficient is used to measure the linear correlation between two variables. The value ranges from -1 to 1. A value close to 1 indicates a positive correlation, a value close to -1 indicates a negative correlation, and a value close to 0 indicates no linear correlation. The first correlation coefficient obtained through correlation analysis reflects the strength and direction of the relationship between power supply data and weather variables.

[0115] If the calculated correlation coefficient is greater than the correlation coefficient threshold, it indicates a significant correlation between the weather type and the energy type, suggesting that the weather factor has a significant impact on energy. The threshold can be adjusted according to actual needs. Typically, the correlation coefficient threshold can be set to 0.5, 0.7, etc., meaning that only when the correlation coefficient exceeds these thresholds is the weather condition considered to have a significant impact on energy output. The first weather impact index set includes all weather factors that have a significant impact on the first energy type. These weather factors will serve as key inputs in subsequent scheduling analysis to help optimize energy scheduling schemes.

[0116] The process of conducting energy dispatch analysis for M-type energy generation systems and developing an initial energy dispatch plan may include: retrieving the historical dispatch record set of the M-type energy generation system; traversing and matching the historical dispatch record set based on weather forecast information and electricity consumption prediction results, and obtaining Q energy dispatch candidate plans that meet preset matching constraints based on the matching results; evaluating the adaptability of the Q energy dispatch candidate plans based on a set of N weather impact indicators, and selecting the optimal plan based on the evaluation results to obtain the initial energy dispatch plan.

[0117] The historical dispatch record set includes historical weather information, historical electricity consumption information, and historical energy dispatch schemes. The historical weather information is weather data for historical periods, such as temperature, wind speed, and sunshine. The historical electricity consumption information is the electricity demand for historical periods, including specific load data. The historical energy dispatch schemes are dispatch strategies that have been adopted based on historical weather and electricity consumption conditions, such as the power generation allocation of each energy generation system.

[0118] The weather forecast information is matched with historical weather information, and the target power consumption prediction results are matched with historical power consumption information to ensure that the matching degree between the two is as high as possible. By traversing and matching historical records, a set of Q power dispatch alternatives that meet the target conditions are obtained.

[0119] A set of N weather impact indicators reflects the influence of different weather factors on various energy generation systems. Each power dispatching alternative is evaluated for its adaptability based on these weather impact indicators. The evaluation criteria include: energy output adaptability (whether the output capacity of the energy generation system meets electricity demand under different weather conditions) and energy supply balance (whether the output of different energy sources can be balanced under fluctuating weather conditions). By evaluating Q power dispatching alternatives, the dispatching scheme with the best adaptability score is selected as the initial power dispatching scheme. This scheme is the optimal choice to meet the predetermined objectives and can provide the most suitable energy dispatching strategy under the target weather conditions and electricity demand.

[0120] Multi-constraint optimization of the initial power dispatch scheme may include: generating a multi-dimensional parameter constraint space based on Q power dispatch candidate schemes; performing multi-dimensional parameter mutation on the initial power dispatch scheme within the multi-dimensional parameter constraint space generated by the Q power dispatch candidate schemes to obtain a set of mutated energy dispatch schemes; evaluating the dispatch fitness of the set of mutated energy dispatch schemes based on the dispatch fitness evaluation function to generate a set of mutated dispatch fitness evaluation coefficients; determining whether there are mutated dispatch fitness evaluation coefficients in the set of mutated dispatch fitness evaluation coefficients that satisfy a preset fitness threshold; if so, outputting the corresponding mutated energy dispatch scheme as the optimized energy dispatch scheme; if not, performing iterative optimization until a mutated energy dispatch scheme whose mutated dispatch fitness evaluation coefficients satisfy the preset fitness threshold is determined.

[0121] Based on Q alternative energy dispatch schemes, a multi-dimensional parameter constraint space is constructed by integrating different parameters in the dispatch schemes. This space represents the range and constraints of all possible variables of the dispatch scheme, providing a reasonable spatial framework for mutation operations. Within the multi-dimensional parameter constraint space, multi-dimensional parameter mutation is performed to explore new energy dispatch schemes. The mutation operation simulates the mutation mechanism in natural selection, aiming to explore potential optimal schemes by adjusting certain parameters. For example, energy output can be randomly adjusted, such as randomly increasing or decreasing the output of wind power and solar power, or the combination ratio of multiple energy generation systems can be adjusted to optimize the overall dispatch scheme. By performing mutation operations within the multi-dimensional parameter constraint space, a new set of mutated energy dispatch schemes is obtained. The set of mutated energy dispatch schemes is evaluated based on the dispatch fitness evaluation function to quantify the merits of each mutated scheme. After fitness evaluation, a set of mutated dispatch fitness evaluation coefficients is generated, where the fitness coefficient of each scheme reflects its comprehensive performance under preset evaluation indicators.

[0122] The fitness threshold reflects the performance of an ideal scheduling scheme. The fitness evaluation coefficient of each mutated scheduling scheme is compared with the preset fitness threshold to determine if a suitable scheme exists. If a mutated scheme has a fitness evaluation coefficient greater than or equal to the preset threshold, that scheme is output as the optimal power dispatching scheme. If no mutated scheme has a fitness evaluation coefficient that meets the preset threshold, the mutation operation is repeated. This means that the current mutation operation has not yet found a suitable scheme, and further adjustments to the parameter space are needed for new mutations and evaluations. This process is iterative until an optimal scheduling scheme is found.

[0123] When microgrid dispatching is carried out according to the optimized energy dispatching scheme, microgrid dispatching status monitoring can also be performed to obtain power supply side monitoring datasets and power consumption side monitoring datasets; based on these two datasets, microgrid dispatching status evaluation is performed, and dispatching anomaly information is generated according to the evaluation results; feedback adjustments to the optimized energy dispatching scheme are executed according to the dispatching anomaly information.

[0124] When implementing optimized energy dispatching schemes, microgrid dispatching status monitoring is conducted. This involves real-time monitoring of both the power supply and consumption sides of the microgrid to acquire various key data. Based on the collected power supply and consumption monitoring datasets, a comprehensive evaluation of the microgrid's operational status is performed. Specifically, this involves assessing the balance between power generation and demand, identifying any power surplus or shortage; evaluating the grid's stability, monitoring for power fluctuations and voltage instability; and evaluating energy efficiency based on actual energy production and consumption, identifying any energy waste or excessive waste of traditional energy sources. During the evaluation process, any unexpected situations, such as power shortages, equipment failures, or dispatching schemes unsuitable for current needs, generate dispatching anomaly information.

[0125] Based on anomaly information, the energy dispatch scheme is adjusted in response to feedback. For example, if some power generation units fail to reach their expected output, their operating parameters can be adjusted based on weather forecasts and real-time monitoring data, or the output of backup energy can be adjusted. If there are anomalies on the demand side, such as a sudden increase in load, load balancing adjustments can be made based on historical data and current demand, and resources can be reconfigured to avoid over-reliance on a single energy source. If the grid load fluctuates significantly, energy storage systems can be used to regulate the load by charging or discharging, reducing the risk of system instability. Feedback adjustment is a cyclical process. After each adjustment, the system status needs to be monitored again to ensure that the new dispatch scheme can effectively solve the original problems.

[0126] The method in this embodiment acquires historical power supply datasets from multiple energy generation systems and historical environmental datasets from the microgrid's operation process. Correlation analysis is then performed to obtain an environmental impact feature set. This, combined with operational status data, generates and executes an optimized power dispatch scheme. This approach comprehensively considers energy generation status, environmental factors, and the current operational status, enabling rational power dispatching within the microgrid and improving its efficiency and stability. For different types of energy generation systems within the microgrid, such as traditional fossil fuel power generation, renewable energy power generation (solar, wind, etc.), and new power generation methods (hydrogen, waste incineration, geothermal), historical power supply datasets are acquired and environmental impact feature sets are determined. This allows for accurate identification of the correlation between each power generation method and environmental factors. When generating an optimized power dispatch scheme, real-time operational status data can be used to more rationally arrange power generation tasks.

[0127] This embodiment also provides a computer program product 810, a computer-readable storage medium 820, and a computer device 830. Figure 7 This is a schematic diagram of a computer program product according to an embodiment of the present invention. Figure 8 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention. Figure 9 This is a schematic block diagram of a computer device according to an embodiment of the present invention.

[0128] Computer program product 810 includes computer program 811, which, when executed by processor 831, implements the steps of the power dispatching method for the microgrid according to any of the above embodiments. Computer-readable storage medium 820 stores the computer program 811 thereon, which, when executed by processor 831, implements the steps of the power dispatching method for the microgrid according to any of the above embodiments. Computer device 830 may include memory 832, processor 831, and computer program 811 stored in memory 832 and running on processor 831.

[0129] The computer program 811 used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages.

[0130] Computer program 811 may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, to perform aspects of the invention, electronic circuits including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may execute computer-readable program instructions to personalize the electronic circuits by utilizing state information of computer-readable program instructions.

[0131] For the purposes of this embodiment, computer program product 810 is a related product that includes computer program 811.

[0132] For the purposes of this embodiment, a computer-readable storage medium 820 is a tangible device capable of holding and storing a computer program 811. It can be any device capable of containing, storing, communicating, propagating, or transmitting the computer program 811 for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium 820 include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical encoding device, and any suitable combination thereof.

[0133] Therefore, those skilled in the art should recognize that although numerous exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications conforming to the principles of the present invention can be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Thus, the scope of the present invention should be understood and construed as covering all such other variations or modifications.

Claims

1. A power dispatching method for a microgrid, characterized in that... include: The historical power supply datasets of various energy generation systems in the microgrid are obtained, and the energy generation systems are classified according to the type of energy generated. Obtain the historical environmental dataset of the microgrid's operation process; Based on the historical power supply dataset and the historical environmental dataset of the various energy power generation systems, a correlation analysis is performed to obtain at least one environmental impact feature set of the energy power generation systems. The microgrid's operating status data is obtained, including power generation data of the multi-energy power generation system, operating environment data of the microgrid, and power load forecast data of the microgrid. Obtain the historical dispatch record sets of each of the various energy generation systems, and match the microgrid's operating status data and the environmental impact feature set in the historical dispatch record sets; generate an initial power dispatch scheme based on the matching results; The initial power dispatch scheme is executed in a virtual model pre-built for the microgrid to obtain dispatch simulation result data; The scheduling simulation results data are evaluated based on a preset evaluation function to obtain an evaluation result; it is then determined whether the evaluation result meets the scheduling requirements. If the initial power dispatch scheme does not meet the dispatch requirements, dispatch parameter constraints are generated based on multiple alternative power dispatch schemes; and the initial power dispatch scheme is iteratively optimized based on the dispatch parameter constraints. The iterative optimization scheme is evaluated, and the iterative optimization scheme whose evaluation result meets the scheduling requirements is taken as the power dispatch optimization scheme. The evaluation function is used to quantify multi-dimensional evaluation factors into evaluation results. The multi-dimensional evaluation factors include: economic cost dimension, system stability dimension, security dimension, energy utilization rate dimension, grid dependence dimension, and equipment loss dimension. Control the microgrid to execute the power dispatch optimization scheme.

2. The power dispatching method for microgrids according to claim 1, characterized in that, The historical scheduling record set is used to store the scheduling actions of the energy generation system, the execution results of the scheduling actions, and the operating status data during the scheduling actions; If the initial power dispatch scheme meets the dispatch requirements, then the initial power dispatch scheme shall be used as the optimized power dispatch scheme.

3. The power dispatching method for microgrids according to claim 2, characterized in that, The step of generating an initial power dispatch scheme based on the matching results includes: Multiple power dispatch alternatives that meet the set constraints are identified from the matching results; The scheduling effects of the multiple power dispatching alternatives are ranked, and the one with the best scheduling effect is taken as the initial power dispatching scheme.

4. The power dispatching method for microgrids according to claim 1, characterized in that, The steps for evaluating the scheduling simulation results data based on a preset evaluation function include: Call the evaluation function; The quantitative values ​​of the multidimensional evaluation factors are calculated based on the scheduling simulation results, the operating status data, and the environmental impact feature set. The evaluation result is obtained by calculating the quantitative values ​​of the multidimensional evaluation factors using the evaluation function.

5. The power dispatching method for microgrids according to claim 1, characterized in that, The steps for performing correlation analysis based on the historical power supply dataset and the historical environment dataset of the various energy power generation systems include: The historical power supply dataset of each type of energy generation system is time-aligned with the historical environment dataset to ensure that the two correspond in the time dimension. Correlation analysis was performed on the historical power supply dataset of each type of energy generation system and the data from the same period in the historical environmental dataset. Data with a correlation greater than a preset correlation coefficient threshold are selected from the historical environmental dataset to obtain relevant environmental data; By extracting and organizing the features of the relevant environmental data, an environmental impact feature set for this type of energy power generation system is obtained.

6. The power dispatching method for microgrids according to claim 1, characterized in that, Following the step of controlling the microgrid to execute the power dispatch optimization scheme, the following is included: Monitor the power supply side data and power consumption side data of the microgrid; The dispatch evaluation of the microgrid is generated based on the power supply side data and power consumption side data of the microgrid.

7. The power dispatching method for microgrids according to claim 6, characterized in that, The step of generating the dispatch evaluation of the microgrid includes: Determine whether the scheduling evaluation meets the power dispatch expectations of the microgrid; If the conditions are met, the scheduling information of each type of energy generation system is recorded and added to the historical scheduling record set; If the conditions are not met, identify the abnormal subsystems in the microgrid and make targeted adjustments to the abnormal subsystems.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the power dispatching method for the microgrid as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that... When the computer program is executed by the processor, it implements the steps of the power dispatching method for the microgrid according to any one of claims 1 to 7.

10. A computer device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the power dispatching method for the microgrid according to any one of claims 1 to 7.

Images