A Community Microgrid Scheduling Method Considering Photovoltaic Energy Storage

Abstract

The present invention provides a community microgrid scheduling method and system considering photovoltaic energy storage, which relates to the technical field of data processing. The method includes: collecting photovoltaic energy storage data in the community; identifying trends and periodicities in the data through time series analysis based on the photovoltaic energy storage data to obtain the results of time series analysis; constructing a neural network architecture according to the results of time series analysis, and predicting future photovoltaic energy storage data based on the neural network architecture to obtain prediction results; determining the scheduling strategy of power equipment according to the prediction results and the current operating state of the distribution network. By comprehensively applying technical means such as time series analysis, neural network prediction, linear programming, and cutting plane method, the present invention improves the utilization efficiency of the photovoltaic energy storage system, reduces the power cost, and improves the stability of the power system.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a community microgrid scheduling method considering photovoltaic energy storage. Background Technique

[0002] Photovoltaic power generation, as a clean and renewable energy form, has the characteristics of environmental protection, sustainability, and distribution. The output of photovoltaic power generation is affected by factors such as weather, season, and sunlight intensity, and has instability and intermittency. This leads to problems such as power source fluctuations and power fluctuations in the community microgrid in the photovoltaic power generation system, posing certain challenges to the operation of the power grid. A community microgrid is a small-scale power system composed of renewable energy power generation devices (such as photovoltaics), energy storage systems, traditional power generation devices (such as diesel generators), and load devices. It can operate independently or be connected to the main power grid, and has a high degree of autonomy and controllability. In order to ensure the stable operation of the community microgrid and improve energy utilization efficiency, effective scheduling methods need to be adopted.

[0003] Energy storage technology is an effective means to solve the instability and intermittency of photovoltaic power generation. By storing the excess photovoltaic power generation into energy storage devices and releasing it when needed, the difference between the power grid load and supply can be balanced, and the reliability and economy of the power grid can be improved. In the community microgrid, the scheduling method considering photovoltaic energy storage can optimize the power generation efficiency and improve the reliability and economy of the power grid. By predicting the output of photovoltaic power generation and combining the charge and discharge strategies of the energy storage system, a reasonable power generation scheduling plan can be formulated to ensure the stable operation of the microgrid under different operating modes. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a community microgrid scheduling method considering photovoltaic energy storage, which improves the utilization efficiency of the photovoltaic energy storage system, reduces the power cost, and improves the stability of the power system by comprehensively applying technical means such as time series analysis, neural network prediction, linear programming, and cutting plane method.

[0005] To solve the above technical problem, the technical solution of the present invention is as follows:

[0006] In the first aspect, a community microgrid scheduling method considering photovoltaic energy storage, the method includes:

[0007] Collect photovoltaic energy storage data in the community;

[0008] According to the photovoltaic energy storage data, identify the trends and periodicities in the data through time series analysis to obtain the results of time series analysis;

[0009] According to the results of time series analysis, construct a neural network architecture, and predict future photovoltaic energy storage data according to the neural network architecture to obtain the prediction results;

[0010] Determine the scheduling strategy of power equipment according to the prediction results and the current operation status of the distribution network;

[0011] Perform linear programming on the power distribution according to the scheduling strategy of the power equipment to obtain the distribution result;

[0012] According to the distribution result, the scheduling plan is adjusted in real time by the cutting plane method to realize the scheduling of the community microgrid.

[0013] Furthermore, by arranging corresponding sensors and data acquisition devices at the key nodes of the community microgrid and performing calibration and initialization settings;

[0014] After the device initialization is completed, start real-time data acquisition, and the collected raw data is transmitted to the central data processing unit in real time by wired or wireless means;

[0015] After the central data processing unit receives the data, it is stored in the high-speed data storage system, and the system will perform data verification before data storage to obtain the photovoltaic energy storage data in the community.

[0016] Furthermore, by collecting and sorting out the photovoltaic energy storage data, observe the change of the data over time;

[0017] By observing the change of the data over time, arrange them in chronological order, and analyze the change speed of the trend and the length of the cycle;

[0018] Combine the trend and periodic analysis results to comprehensively analyze the change characteristics of the data;

[0019] According to the trend and periodic change characteristics, obtain the result of time series analysis.

[0020] Furthermore, according to the result of time series analysis, construct a recurrent neural network architecture, including an input layer, a hidden layer, an output layer, and an activation function;

[0021] Train the neural network architecture to obtain the trained neural network architecture;

[0022] According to the trained neural network architecture, predict the future photovoltaic energy storage data to obtain the prediction result.

[0023] Furthermore, set the objective function and constraint conditions, where the objective function includes minimizing the power generation cost and minimizing the load power shortage rate or voltage deviation;

[0024] Through real number coding or binary coding, each gene represents the output power of a device, and an initial chromosome is randomly generated to form an initial population;

[0025] Calculate the objective function value of each scheduling plan;

[0026] According to roulette wheel selection, the parental chromosomes are selected according to the fitness values. Chromosomes with high fitness are preferentially selected to retain excellent genes. Single-point crossover or multi-point crossover is performed on the selected parents to generate offspring chromosomes, and some gene values of the offspring chromosomes are randomly changed with a certain probability to increase the population diversity;

[0027] The newly generated offspring population is merged with the parental population, and the M chromosomes with the highest fitness are selected as the next generation population. When the maximum number of iterations is reached, the final solution is obtained;

[0028] The decoding of the global final solution is used to determine the scheduling strategy of the power equipment.

[0029] Furthermore, the calculation formula of the objective function is:

[0030] ;

[0031] where is the minimum total optimization objective value, , is the weight coefficient, is the total number of generators, is the th linear power generation cost coefficient of the generator, is the th output power of the generator, is the th quadratic power generation cost coefficient of the generator, is the scheduling time interval, is the total number of power purchase nodes, is the th electricity price of the power purchase node, is the th power purchase power of the power purchase node, is the total number of load nodes, is the number of load subsets, is the th power shortage of the load node, is the th total demand power of the load node, is the weight coefficient of the load power shortage rate, is the total number of distribution network nodes, is the th actual voltage of the node, is the th rated voltage of the node, is the weight coefficient of the voltage deviation, is the th expected voltage of the node, and It is an index.

[0032] Furthermore, according to the scheduling strategy and historical data of power equipment, predict the power load demand to obtain a prediction result;

[0033] Construct a linear programming framework based on the prediction result;

[0034] Convert the scheduling problem into a linear programming problem to determine the decision variables, objective function, and constraint conditions of the linear programming framework;

[0035] Calculate the objective function to obtain the final solution;

[0036] Convert the final solution into a power allocation plan to obtain an allocation result.

[0037] In a second aspect, a community microgrid scheduling system considering photovoltaic energy storage includes:

[0038] An acquisition module for collecting photovoltaic energy storage data in the community; based on the photovoltaic energy storage data, identify trends and periodicity in the data through time series analysis to obtain the result of time series analysis;

[0039] A prediction module for constructing a neural network framework according to the result of time series analysis and predicting future photovoltaic energy storage data based on the neural network framework to obtain a prediction result; determine the scheduling strategy of power equipment according to the prediction result and the current operation status of the distribution network;

[0040] An allocation module for formulating a scheduling plan according to the scheduling strategy of power equipment, performing linear programming on power allocation to obtain an allocation result; and adjusting the scheduling plan in real time through the cutting plane method according to the allocation result to achieve the scheduling of the community microgrid.

[0041] In a third aspect, a computing device includes:

[0042] One or more processors;

[0043] A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the described method.

[0044] In a fourth aspect, a computer-readable storage medium stores a program that implements the described method when executed by a processor.

[0045] The above solution of the present invention has at least the following beneficial effects:

[0046] By collecting and analyzing photovoltaic energy storage data in real time, it is possible to predict future photovoltaic energy storage situations, thereby optimizing the scheduling strategy of power equipment. This helps to make full use of renewable energy, reduce dependence on traditional energy, and improve energy utilization efficiency. Through time series analysis and neural network prediction, it is possible to predict power load demand and generation costs, and then formulate a more economical scheduling strategy, which helps to reduce generation costs, reduce electricity purchase expenses, and minimize the load power outage rate, thereby reducing the overall operating cost. Through the application of linear programming and cutting plane method, the system can stabilize the voltage and reduce voltage deviation while meeting the power demand. Enhancing the stability of the distribution network and improving power supply reliability, it can collect the operation data of the microgrid in real time and adjust the scheduling plan according to the real-time deviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 FIG. is a schematic flow chart of a community microgrid scheduling method considering photovoltaic energy storage provided by an embodiment of the present invention.

[0048] Figure 2 FIG. is a schematic diagram of a community microgrid scheduling system considering photovoltaic energy storage provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0050] As Figure 1 shown, an embodiment of the present invention proposes a community microgrid scheduling method considering photovoltaic energy storage, and the method includes the following steps:

[0051] Step 12, collecting photovoltaic energy storage data in the community;

[0052] Step 13, according to the photovoltaic energy storage data, identifying trends and periodicities in the data through time series analysis to obtain the results of time series analysis;

[0053] Step 14, according to the results of time series analysis, constructing a neural network architecture, and predicting future photovoltaic energy storage data according to the neural network architecture to obtain prediction results;

[0054] Step 15, determining the scheduling strategy of power equipment according to the prediction results and the current operating state of the distribution network;

[0055] Step 16, performing linear programming on the power distribution according to the scheduling strategy of the power equipment to obtain the distribution results;

[0056] Step 17, according to the allocation result, the scheduling plan is adjusted in real time by the cutting plane method to realize the scheduling of the community microgrid.

[0057] In the embodiment of the present invention, the above step 12 may include:

[0058] Step 121, by arranging corresponding sensors and data acquisition devices at the key nodes of the community microgrid and performing calibration and initialization settings;

[0059] Step 122, after the device initialization is completed, start real-time data acquisition, and the collected raw data is transmitted to the central data processing unit in real time by wired or wireless means.

[0060] Step 123, after the central data processing unit receives the data, it is stored in the high-speed data storage system. Before data storage, the system will perform data verification to obtain the photovoltaic energy storage data in the community.

[0061] In the embodiment of the present invention, by carefully arranging and calibrating sensors and data acquisition devices at the key nodes of the community microgrid, the collected raw data is reliable. After the device initialization is completed, the real-time data acquisition mechanism is immediately started, and the data is transmitted to the central data processing unit in real time by wired or wireless means. This enables the system to monitor the operation status of the microgrid in real time, promptly detect abnormalities or potential problems, and respond quickly, ensuring the stable operation of the microgrid and the continuity of power supply. After the central data processing unit receives the data, it stores it in the high-speed data storage system.

[0062] In a specific embodiment of the present invention, the specific steps include:

[0063] Step 121, in the community microgrid, according to the key paths and nodes of the power flow and information flow, select the specific positions where sensors and data acquisition devices need to be arranged. These positions may include the output end of the photovoltaic power station, the input and output ends of the energy storage system, the nodes of the key distribution lines, etc. According to the selected nodes, install the corresponding sensors and data acquisition devices, and use a standard signal source or a device with a known accurate value to calibrate the sensors, and the measurement error of the sensors is within an acceptable range.

[0064] Step 122, after the initialization settings are completed, start the data acquisition device and start real-time acquisition of relevant data of the photovoltaic energy storage system. The data acquisition device transmits the collected raw data to the central data processing unit in real time by wired means. During the transmission process, ensure the integrity and security of the data to prevent data loss or tampering.

[0065] Step 123, after the central data processing unit receives the data, it stores the data in the high-speed data storage system. Before storing the data, the central data processing unit verifies the data. For the verified data, the central data processing unit performs further processing and conversion. The data after the above processing and conversion is the valid data of the photovoltaic energy storage system in the community.

[0066] In an embodiment of the present invention, the above step 13 may include:

[0067] Step 131, by collecting and sorting out the photovoltaic energy storage data, observing the change of the data over time;

[0068] Step 132, by observing the change of the data over time, arranging it in chronological order, and analyzing the change speed of the trend and the length of the period;

[0069] Step 133, combining the trend and periodic analysis results, and comprehensively analyzing the change characteristics of the data;

[0070] Step 134, according to the trend and periodic change characteristics, to obtain the result of time series analysis.

[0071] In an embodiment of the present invention, by collecting and sorting out the photovoltaic energy storage data and observing the change of these data over time, the operation status and performance of the photovoltaic energy storage system can be understood more deeply. This helps to identify abnormal behaviors, potential problems or improvement spaces in the system. By observing the change of the data over time and arranging it in chronological order, the trend and periodic characteristics in the data can be accurately captured. Trend analysis can reveal the long-term development direction and speed of the data, while periodic analysis can identify the recurring patterns or cycles in the data. Combining the trend and periodic analysis results and conducting comprehensive analysis can comprehensively reveal the change characteristics of the data. This comprehensive analysis discovers the hidden laws, correlations or anomalies in the data, providing strong support for subsequent decision-making and optimization. The result of time series analysis can provide an important basis for the prediction and planning of the photovoltaic energy storage system. By understanding the trend and periodic characteristics of the data, the future system performance, demand changes or potential problems can be predicted, so as to formulate effective plans and strategies.

[0072] In a specific embodiment of the present invention, the specific steps include:

[0073] Step 131, obtain the historical data of the photovoltaic energy storage system from the central data processing unit or the data storage system, and use statistical tools to observe the change trend and pattern of the data over time.

[0074] Step 132: Observe the changing trend of the data over time, determine whether it is rising, falling, or remaining stable, identify the periodic variations in the data, such as daily, weekly, monthly cycles, etc., select a start time point as the starting point of the cycle, select an end time point as the end point of the cycle, and calculate the length of the cycle.

[0075] Step 133: Combine the results of the trend analysis and the periodic analysis, comprehensively consider the long-term trend and short-term fluctuations in the data, and conduct a comprehensive analysis of the overall change characteristics of the data. Identify the outliers, turning points, or trend changes in the data to provide a basis for subsequent decision-making and optimization.

[0076] Step 134: Present the results of the time series analysis in the form of charts, reports, or data tables, interpret and explain the analysis results, elaborate on the trends, periodic characteristics in the data and their possible causes or impacts, and formulate corresponding strategies or measures based on the results of the time series analysis.

[0077] In the embodiment of the present invention, the above step 14 may include:

[0078] Step 141: According to the results of the time series analysis, construct a recurrent neural network architecture, including an input layer, a hidden layer, an output layer, and an activation function;

[0079] Step 142: Train the neural network architecture to obtain a trained neural network architecture;

[0080] Step 143: According to the trained neural network architecture, predict the future photovoltaic energy storage data to obtain a prediction result.

[0081] In the embodiment of the present invention, the recurrent neural network is good at processing time series data, can capture the time-dependent relationships and long-term trends in the data, thereby improving the prediction accuracy of photovoltaic energy storage data. The neural network model has a strong adaptive ability and can learn and adjust according to new data to adapt to the changing photovoltaic energy storage environment. By automating the prediction process, the dependence on manual experience and judgment is reduced, and the prediction efficiency is improved. The prediction results can provide strong support for the optimal scheduling and decision-making of the photovoltaic energy storage system, and improve the overall operation efficiency of the system.

[0082] In a specific embodiment of the present invention, the specific steps include:

[0083] Step 141: Conduct time series analysis on historical photovoltaic energy storage data to identify features such as trends, seasonality, and periodicity in the data, as well as the dimension and format of the input data. Input layer: Design an input layer for receiving time series data, where the number of neurons in the input layer matches the feature dimension of the input data. Hidden layer: Plan the number of hidden layers and the number of neurons in each layer. The hidden layer is the core of the RNN and is responsible for capturing the temporal dependencies in the time series. Output layer: Design the output layer to generate predicted values for future photovoltaic energy storage data. The number of neurons in the output layer is determined according to the prediction target. Activation function: Select an appropriate activation function to enhance the nonlinear expression ability of the model.

[0084] Step 142: Divide the historical photovoltaic energy storage data into a training set, a validation set, and a test set. Preprocess the data, such as normalization or standardization, to improve the training efficiency. The input data enters the RNN through the input layer and is passed layer by layer to the hidden layer and the output layer. At each time step, the hidden layer calculates a new hidden state based on the current input and the hidden state of the previous time step, and the output layer calculates the prediction result based on the current hidden state. Monitor the value of the loss function during the training process, adjust hyperparameters such as the learning rate and batch size to optimize the training effect, and use the validation set to evaluate the performance of the model to prevent overfitting. Evaluate the prediction performance of the trained RNN model on the test set, using the metric mean squared error , where n is the total number of samples, is the true value of the q-th sample, is the predicted value of the q-th sample, and q is the index.

[0085] Step 143: Collect the latest photovoltaic energy storage data, perform the same preprocessing operations on the new data as on the training data, input the preprocessed new data into the trained RNN model. The model generates predicted values for future photovoltaic energy storage data based on the input data and the learned temporal dependencies, and perform post-processing on the prediction results, such as inverse normalization or inverse standardization, to obtain practically interpretable prediction results. Use the prediction results for the scheduling and management of the photovoltaic energy storage system, optimize the energy storage strategy, improve the system efficiency, monitor the difference between the actual data and the predicted data, and adjust the prediction model in a timely manner to adapt to system changes.

[0086] In the embodiment of the present invention, the above step 15 may include:

[0087] Step 151: Set the objective function and constraint conditions, where the objective function includes minimizing the power generation cost and minimizing the load power shortage rate or voltage deviation;

[0088] Step 152: Through real number coding or binary coding, each gene represents the output power of a device, randomly generate an initial chromosome to form an initial population;

[0089] Step 153, calculate the objective function value of each scheduling scheme;

[0090] Step 154, according to roulette wheel selection, select the parental chromosomes according to the fitness value, preferentially select the chromosomes with high fitness, retain the excellent genes, perform single-point crossover or multi-point crossover on the selected parents to generate offspring chromosomes, and randomly change some gene values of the offspring chromosomes with a certain probability to increase the population diversity;

[0091] Step 155, merge the newly generated offspring population with the parental population, select the M chromosomes with the highest fitness as the next-generation population, reach the maximum number of iterations, and obtain the final solution;

[0092] Decode the global final solution to determine the scheduling strategy of the power equipment.

[0093] In the embodiment of the present invention, clear objective functions and constraint conditions are set, providing an optimization direction and scope for the genetic algorithm. Represent the output power of the equipment by real number coding or binary coding, and randomly generate the initial population, providing a starting point for searching the optimal solution. Calculate the objective function value of each scheduling scheme to evaluate the advantages and disadvantages of the scheduling scheme. Generate a new offspring population through selection, crossover, and mutation operations, increasing the population diversity and search scope. At the same time, check the constraint conditions of the mutated chromosomes to ensure that the generated scheduling scheme meets the actual requirements. By merging the parental and offspring populations and selecting the individuals with the highest fitness as the next-generation population, gradually approach the optimal solution. The finally decoded optimal scheduling strategy can guide the actual operation of the power equipment.

[0094] In a specific embodiment of the present invention, the specific steps include:

[0095] Step 151, the objective function, which is an important economic indicator in power dispatching, aims to reduce the power generation cost by optimizing equipment scheduling. The load power shortage rate reflects the degree to which the system cannot meet the load demand, while the voltage deviation affects the normal operation of power equipment and the stability of the power grid. Equipment operation constraints, such as the maximum and minimum output power limits of the equipment, the start-stop time limits of the equipment, etc., grid safety constraints, such as the limits of electrical parameters such as voltage, current, and power factor, to ensure the safe operation of the power grid, and load demand constraints: meet the load demand within a specific time period to ensure the adequacy of power supply.

[0096] Step 152, real number coding, each gene is represented by a real number, such as the output power of the equipment can be directly represented by a real number, and binary coding, discretize continuous variables such as the output power of the equipment into binary strings. Randomly generate a group of chromosomes, and each chromosome represents a possible scheduling scheme. The length of the chromosome is determined by the number of equipment and the coding method.

[0097] Step 153, evaluate each chromosome, and obtain the final solution by

[0098] calculating its corresponding objective function value, where, is the minimum total optimization objective value, , is the weight coefficient, is the total number of generators, is the linear power generation cost coefficient of the th generator, is the output power of the th generator, is the quadratic power generation cost coefficient of the th generator, is the scheduling time interval, is the total number of power purchase nodes, is the electricity price of the th power purchase node, is the power purchase amount of the th power purchase node, is the total number of load nodes, is the number of load subsets, is the power shortage of the th load node, is the total demand power of the th load node, is the weight coefficient of the load power shortage rate, is the total number of distribution network nodes, is the actual voltage of the th node, is the rated voltage of the th node, is the weight coefficient of the voltage deviation, is the expected voltage of the and are indices.

[0099] Step 154, selection operation, select the parent chromosomes according to the roulette wheel selection method based on the fitness value. Chromosomes with higher fitness values have a greater probability of being selected to retain excellent genes. Crossover operation, perform single-point or multi-point crossover on the selected parent chromosomes to generate offspring chromosomes. The crossover operation helps to combine the excellent genes of the parent chromosomes to generate a new scheduling plan. Mutation operation, randomly change some gene values of the offspring chromosomes with a certain probability to increase the population diversity. The mutation operation helps to jump out of the local optimal solution and explore a broader solution space. Check the constraint conditions for the mutated chromosomes to ensure that they meet all the constraint conditions. If they do not meet the constraint conditions, perform necessary repair operations.

[0100] Step 155: Merge the populations. Combine the newly generated offspring population with the parent population to form a new population. Select the optimal solution. Select the M chromosomes with the highest fitness values according to the fitness values as the next-generation population. Repeat the above process until the maximum number of iterations is reached or other stopping conditions are met to obtain the final solution. After reaching the maximum number of iterations, select the chromosome with the highest fitness value as the final solution. Decode the global final solution to determine the scheduling strategy of the power equipment.

[0101] In the embodiment of the present invention, the above step 16 may include:

[0102] Step 161: Predict the power load demand based on the scheduling strategy of the power equipment and historical data to obtain a prediction result;

[0103] Step 162: Construct a linear programming framework according to the prediction result;

[0104] Step 163: Convert the scheduling problem into a linear programming problem to determine the decision variables, objective function, and constraint conditions of the linear programming framework;

[0105] Step 164: Calculate the objective function to obtain the final solution;

[0106] Step 165: Convert the final solution into a power allocation plan to obtain an allocation result.

[0107] In the embodiment of the present invention, by minimizing the power generation cost and power purchase cost, the operating cost of the power enterprise is reduced, and the economic benefit is improved. By optimizing the power scheduling plan, the load power outage rate and voltage deviation are reduced, and the power supply quality and reliability are improved. By constructing a linear programming framework, the scheduling problem is converted into a mathematical optimization problem, which is convenient for solving using algorithms, and the flexibility and adaptability of the system are improved. Provide a scientific power scheduling plan for power enterprises, support decision-making, and improve the management level. By optimizing power scheduling, resource waste and environmental pollution are reduced.

[0108] In a specific embodiment of the present invention, the specific steps include:

[0109] Step 161: Use multi-source data such as historical power load data, weather conditions, holiday information, and economic activity indicators, combined with the current power equipment scheduling strategy, and adopt methods such as time series analysis, machine learning algorithms, or neural network models to predict the future power load demand. The prediction result should give the power load curve or load volume within a certain period in the future, which is the basis for subsequent linear programming.

[0110] Step 162: Based on the load forecasting results, determine the basic framework of linear programming, including the selection of decision variables, the setting of the objective function, and the construction of constraint conditions. The decision variables usually include the output power of the generating units, the power purchase power of the power purchase nodes, etc. The objective function and constraint conditions will be set according to specific optimization objectives.

[0111] Step 163: Specify the decision variables in the linear programming framework. For example, let be the output power of the th generator, be the power purchase power of the jth power purchase node, etc. Set the objective function. For example, the total optimization objective value Z needs to be minimized, and its expression may include the weighted sum of multiple aspects such as power generation cost, power purchase cost, load power shortage rate, voltage deviation, etc. Construct constraint conditions, such as the supply-demand balance constraint (i.e., the power generation and power purchase should meet the load demand), the equipment operation constraints (such as the output power limit and start-stop time limit of the generating units), voltage and current limits, etc.

[0112] Step 164: Solve the objective function to obtain the optimal solution that satisfies the constraint conditions.

[0113] Step 165: According to the obtained final solution, formulate a specific power allocation plan. The power allocation plan should clarify the power generation plans of each generating unit (including power generation time, power generation quantity, etc.), the power purchase plans of each power purchase node (including power purchase time, power purchase quantity, etc.), and the power transmission plan of the distribution network.

[0114] In the embodiment of the present invention, the above step 17 may include:

[0115] Step 171: According to the allocation result, collect the operation data of the microgrid in real time and identify the deviation from the initial allocation result;

[0116] Step 172: According to the real-time deviation, construct a cutting plane to exclude the current infeasible scheduling schemes;

[0117] Step 173: According to the cutting plane, adjust the scheduling plan to obtain the adjusted scheduling plan;

[0118] Step 174: Transmit the adjusted scheduling plan to each power generation unit in the microgrid to achieve the scheduling of the community microgrid.

[0119] In the embodiments of the present invention, the operation data of the microgrid is collected in real time and compared with the initial allocation result, so as to timely detect deviations and ensure that the dispatching plan conforms to the actual operation status. By constructing cutting planes to exclude infeasible solutions, the system can more flexibly respond to changes in the microgrid, improve the adaptability and reliability of dispatching. Adjusting the dispatching plan according to the cutting planes can more reasonably allocate resources in the microgrid, improve the resource utilization efficiency, and timely transmit the adjusted dispatching plan to each power generation unit. The rapid execution of dispatching instructions can improve the dispatching efficiency of the entire microgrid.

[0120] In a specific embodiment of the present invention, the specific steps include:

[0121] Step 171, use devices such as sensors and smart meters to collect in real time the output power, status information, and load demand data of each power generation unit (such as solar photovoltaic panels, wind turbines, energy storage batteries, etc.) in the microgrid. Ensure the accuracy and timeliness of data collection to timely reflect the actual operation status of the microgrid.

[0122] Compare the operation data collected in real time with the initial allocation result to identify the differences or deviations between the actual operation status and the plan. The deviations may include fluctuations in the output power of power generation units, sudden changes in load demand, etc.

[0123] Step 172, analyze the identified deviations, and evaluate the degree and scope of their impact on the dispatching plan. Whether the deviations will make the dispatching scheme infeasible or inefficient. According to the results of the deviation analysis, construct cutting planes to exclude those dispatching schemes that cannot be executed or are inefficient under the current conditions.

[0124] Step 173, adjust the initial dispatching plan according to the constructed cutting planes to adapt to the actual operation status of the microgrid. The adjustments may include changing the output plan of power generation units, adjusting the charge and discharge strategies of energy storage devices, reallocating loads, etc. Verify the adjusted dispatching plan to meet the operation constraints and conditions of the microgrid, and further optimize the dispatching plan to improve its efficiency and reliability.

[0125] Step 174, convert the adjusted dispatching plan into specific dispatching instructions and transmit them to each power generation unit in the microgrid through the communication network. Ensure the accurate transmission and timely execution of dispatching instructions so that each power generation unit can operate according to the plan. Each power generation unit adjusts and operates according to the received dispatching instructions to achieve the overall dispatching goal of the microgrid.

[0126] As Figure 2 shown, the embodiments of the present invention also provide a community microgrid dispatching system considering photovoltaic energy storage, including:

[0127] An acquisition module, configured to collect photovoltaic energy storage data within a community; based on the photovoltaic energy storage data, identify trends and periodicity in the data through time series analysis to obtain the result of the time series analysis;

[0128] A prediction module, configured to construct a neural network architecture according to the result of the time series analysis, and predict future photovoltaic energy storage data based on the neural network architecture to obtain a prediction result; determine a scheduling strategy for power equipment according to the prediction result and the current operating state of the distribution network;

[0129] An allocation module, configured to formulate a scheduling plan according to the scheduling strategy of the power equipment, perform linear programming on the power allocation to obtain an allocation result; adjust the scheduling plan in real time through the cutting plane method according to the allocation result to achieve the scheduling of the community microgrid.

[0130] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art of the present technology, without departing from the principle described in the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A community microgrid scheduling method considering photovoltaic energy storage, characterized in that, The method includes: Collecting photovoltaic energy storage data within the community; Based on the photovoltaic energy storage data, identifying trends and periodicity in the data through time series analysis to obtain the results of time series analysis; Based on the results of time series analysis, constructing a neural network architecture and, according to the neural network architecture, predicting future photovoltaic energy storage data to obtain a prediction result; Based on the prediction result and the current operating state of the distribution network, to determine the scheduling strategy for power equipment, including: setting an objective function and constraints, where the objective function includes minimizing the power generation cost and minimizing the load power shortage rate or voltage deviation; through real number coding or binary coding, each gene represents the output power of a device, randomly generating an initial chromosome to form an initial population; calculating the objective function value of each scheduling plan; according to roulette wheel selection, selecting parental chromosomes according to the fitness value, preferentially selecting chromosomes with high fitness, retaining excellent genes, performing single-point crossover or multi-point crossover on the selected parents to generate offspring chromosomes, randomly changing some gene values of the offspring chromosomes to increase population diversity; merging the newly generated offspring population with the parental population, selecting the M chromosomes with the highest fitness as the next generation population, reaching the maximum number of iterations to obtain the final solution; decoding the global final solution to determine the scheduling strategy for power equipment; the calculation formula of the objective function is: ； Among them, is the total optimization objective value, which needs to be minimized, , is the weight coefficient, is the total number of generators, is the linear power generation cost coefficient of the th generator, is the output power of the th generator, is the quadratic power generation cost coefficient of the th generator, is the scheduling time interval, is the total number of power purchase nodes, is the electricity price of the th power purchase node, is the purchased power of the th power purchase node, is the total number of load nodes, is the power shortage of the th load node, is the total demand power of the th load node, is the weight coefficient of the load power shortage rate, is the total number of distribution network nodes, is the actual voltage of the th node, is the rated voltage of the th node, and the weight coefficient of the voltage deviation is obtained to get the final solution; According to the scheduling strategy of power equipment, performing linear programming on the power distribution to obtain a distribution result; According to the distribution result, making real-time adjustments to the scheduling plan through the cutting plane method to achieve the scheduling of the community microgrid, including: according to the distribution result, collecting the operating data of the microgrid in real time and identifying the deviation from the initial distribution result; according to the real-time deviation, constructing a cutting plane to exclude the current infeasible scheduling plan; according to the cutting plane, adjusting the scheduling plan to obtain an adjusted scheduling plan; transmitting the adjusted scheduling plan to each power generation unit in the microgrid to achieve the scheduling of the community microgrid.

2. The community microgrid scheduling method considering photovoltaic energy storage according to claim 1, characterized in that Collecting photovoltaic energy storage data within the community, including: By arranging corresponding sensors and data acquisition devices at key nodes of the community microgrid and performing calibration and initialization settings; After the device initialization is completed, starting real-time data acquisition, and the collected raw data is transmitted to the central data processing unit in real time by wired or wireless means; After receiving the data, the central data processing unit stores it in the high-speed data storage system, and the system will perform data verification before data storage to obtain the photovoltaic energy storage data within the community.

3. A community microgrid scheduling method considering photovoltaic energy storage according to claim 2, characterized in that, Based on the photovoltaic energy storage data, identifying trends and periodicity in the data through time series analysis to obtain the results of time series analysis, including: By collecting and organizing the photovoltaic energy storage data, observing the changes in the data over time; By observing the changes in the data over time, arranging them in chronological order, and analyzing the change speed of the trend and the length of the period; Combining the results of trend and periodicity analysis and comprehensively analyzing the change characteristics of the data; Based on the change characteristics of the trend and periodicity, to obtain the results of time series analysis.

4. A community microgrid scheduling method considering photovoltaic energy storage according to claim 3, characterized in that, Based on the results of time series analysis, constructing a neural network architecture and, according to the neural network architecture, predicting future photovoltaic energy storage data to obtain a prediction result, including: Construct a recurrent neural network architecture, including an input layer, a hidden layer, an output layer, and an activation function, based on the results of time series analysis. Train the neural network architecture to obtain a trained neural network architecture. Predict future photovoltaic energy storage data based on the trained neural network architecture to obtain a prediction result.

5. A community microgrid scheduling method considering photovoltaic energy storage according to claim 4, characterized in that Perform linear programming on the power allocation according to the scheduling strategy of power equipment to obtain an allocation result, including: Predict the power load demand according to the scheduling strategy of power equipment and historical data to obtain a prediction result. Construct a linear programming architecture based on the prediction result. Convert the scheduling problem into a linear programming problem to determine the decision variables, objective function, and constraint conditions of the linear programming architecture. Calculate the objective function to obtain the final solution. Convert the final solution into a power allocation plan to obtain an allocation result.

6. A community microgrid scheduling system considering photovoltaic energy storage, which implements the method described in any one of claims 1 to 5, characterized in that, Including: An acquisition module for collecting photovoltaic energy storage data in the community. Identify the trends and periodicities in the data through time series analysis based on the photovoltaic energy storage data to obtain the results of time series analysis. A prediction module for constructing a neural network architecture based on the results of time series analysis, predicting future photovoltaic energy storage data according to the neural network architecture to obtain a prediction result, and determining the scheduling strategy of power equipment according to the prediction result and the current operating state of the distribution network. An allocation module for formulating a scheduling plan according to the scheduling strategy of power equipment, performing linear programming on the power allocation to obtain an allocation result. Real-time adjust the scheduling plan through the cutting plane method according to the allocation result to achieve the scheduling of the community microgrid.

7. A computing device, characterized in that, Including: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images