Distributed new energy access optimization method and device, computer equipment and medium

Abstract

The invention relates to the technical field of power systems, and provides a distributed new energy access optimization method and device, computer equipment and a medium. The method comprises the following steps: acquiring load information of a net rack to which distributed new energy needs to be accessed; preliminarily planning an access position of the distributed new energy based on the load information by using a particle swarm algorithm; acquiring real-time data of the distributed new energy; key features are extracted from the real-time data; training a support vector machine generating capacity prediction model by using the key features; finely adjusting the access position by using a trained support vector machine generating capacity prediction model to obtain a target access position; and accessing the distributed new energy to the target access position of the net rack. According to the invention, accurate access of new energy can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a distributed new energy access optimization method, device, computer equipment and medium. Background Art

[0002] In modern power systems, the access of distributed new energy sources such as wind power, hydropower and solar power has become a key way to promote energy transformation and improve energy efficiency. These new energy sources are not only abundant and widely distributed, but also can effectively reduce dependence on traditional energy and reduce carbon emissions through rational use.

[0003] However, distributed renewable energy generation is intermittent and uncertain. For example, the fluctuation of natural resources such as wind, hydro, and solar energy leads to the instability of the output power of renewable energy generation. This instability may pose a challenge to the stability and reliability of the existing power grid if it is directly connected to the power grid. Therefore, how to effectively connect distributed renewable energy to the power grid has become an urgent problem to be solved. Summary of the invention

[0004] Based on this, a distributed new energy access optimization method, device, computer equipment and medium are proposed, aiming to solve the technical problem of how to effectively connect distributed new energy to the power grid in the prior art.

[0005] The first aspect of the present application provides a distributed new energy access optimization method, the method comprising:

[0006] Obtain the load information of the grid that needs to be connected to distributed renewable energy;

[0007] Using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information;

[0008] Acquiring real-time data of the distributed new energy;

[0009] extracting key features from the real-time data;

[0010] Using the key features to train a support vector machine power generation prediction model;

[0011] Using the trained support vector machine power generation prediction model to fine-tune the access position to obtain a target access position;

[0012] Connect the distributed new energy to the target access position of the grid.

[0013] Optionally, the load information includes: future load change trend, load bearing capacity and grid area, and the load information of the grid to be connected to the distributed new energy source is obtained including:

[0014] Collect the target user's historical electricity usage time and corresponding historical electricity consumption;

[0015] Predicting future load change trends based on the historical electricity consumption time and the corresponding historical electricity consumption;

[0016] Simulate the power generation of distributed renewable energy after it is connected to the grid;

[0017] determining a load carrying capacity of the power grid according to the power generation;

[0018] According to the future load change trend and the load carrying capacity of the power grid, the grid area that needs to be connected to the distributed new energy is determined.

[0019] Optionally, the using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information includes:

[0020] Initializing a particle swarm, wherein each particle in the particle swarm represents an access location of a distributed new energy source;

[0021] Calculate the current optimal fitness of each particle according to the preset objective function;

[0022] For each particle, compare the current best fitness with the historical best fitness;

[0023] If the current best fitness is better than the historical best fitness, then the historical best position of the particle is updated to the current best position;

[0024] Determine the global best fitness and the corresponding global best position according to the historical best fitness of all particles in the particle swarm;

[0025] Iteratively updating the speed and position of each particle according to the historical best position and the global best position;

[0026] When the iterative update meets the stopping condition, the global optimal position obtained is the initially planned distributed new energy access location.

[0027] Optionally, before acquiring the real-time data of the distributed new energy, the method further includes:

[0028] Determining the source of the distributed new energy data;

[0029] Acquire the distributed new energy data using a connection method matching the source;

[0030] Clean the acquired distributed new energy data;

[0031] Convert the format of the cleaned distributed new energy data;

[0032] The distributed new energy data after format conversion is stored.

[0033] Optionally, the method further includes:

[0034] The power generation is predicted based on the real-time data of distributed renewable energy obtained;

[0035] Distributed renewable energy is dispatched based on the power generation.

[0036] Optionally, the method further includes:

[0037] Determining the energy type of the distributed renewable energy;

[0038] Obtaining monitoring parameters and warning thresholds corresponding to the energy type;

[0039] Acquire a parameter value corresponding to the monitoring parameter from the distributed new energy data;

[0040] comparing the parameter value with a corresponding warning threshold;

[0041] When the parameter value is greater than the corresponding warning threshold, an alarm is issued.

[0042] Optionally, the method further includes:

[0043] The operating status of the distributed new energy and / or the changing trend of the operating status are displayed.

[0044] A second aspect of the present application provides a distributed new energy access optimization device, the device comprising:

[0045] The load acquisition module is used to obtain the load information of the grid that needs to be connected to the distributed new energy;

[0046] A first optimization module, using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information;

[0047] A data acquisition module, used to acquire real-time data of the distributed new energy;

[0048] A feature extraction module, used to extract key features from the real-time data;

[0049] A model training module, used for training a support vector machine power generation prediction model using the key features;

[0050] A second optimization module is used to fine-tune the access position using the trained support vector machine power generation prediction model to obtain a target access position;

[0051] An energy access module is used to connect the distributed new energy to the target access position of the grid.

[0052] The third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the distributed new energy access optimization method when executing the computer program.

[0053] A fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the distributed new energy access optimization method are implemented.

[0054] The present application obtains load information of a grid to which distributed renewable energy sources need to be connected; uses a particle swarm algorithm to preliminarily plan access locations of the distributed renewable energy sources based on the load information; obtains real-time data of the distributed renewable energy sources; extracts key features from the real-time data; uses the key features to train a support vector machine power generation prediction model; uses the trained support vector machine power generation prediction model to fine-tune the access location to obtain a target access location; and connects the distributed renewable energy sources to the target access location of the grid, thereby achieving accurate access to renewable energy sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 It is a flow chart of the distributed new energy access optimization method provided in the embodiment of the present application.

[0057] Figure 2 It is a schematic diagram of the framework of distributed new energy data processing provided in an embodiment of the present application.

[0058] Figure 3 It is a schematic diagram of the framework of real-time monitoring of distributed new energy provided in the embodiment of the present application.

[0059] Figure 4 It is a schematic diagram of the overall framework of real-time monitoring of distributed new energy provided in the embodiment of the present application.

[0060] Figure 5 It is a functional module diagram of a distributed new energy access optimization device provided in an embodiment of the present application.

[0061] Figure 6 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] Compared with traditional centralized power generation systems, distributed renewable energy sources such as wind power, hydropower and solar power are more flexible, efficient and reliable, which can not only improve energy efficiency, but also promote environmental protection and sustainable development. However, distributed renewable energy generation is intermittent and uncertain, and faces many challenges in practical applications.

[0064] Wind power generation captures wind energy through wind rotors and drives generators to generate electricity. It has strong environmental adaptability and can operate efficiently in areas with abundant wind resources such as plateaus, mountains and islands. This method of power generation does not require fuel, does not produce radiation or air pollution, and is a clean and pollution-free renewable energy. Distributed wind power generation systems can also enhance the safety and stability of the power grid, provide continuous power supply when disasters occur, and become an important supplement to the centralized power supply system. However, wind power generation faces the problem of unstable wind speed leading to fluctuations in power generation.

[0065] Hydropower generation uses the potential or kinetic energy of water to convert it into electricity by building dams or other water flow control facilities. This type of power generation relies on river flow and terrain conditions to provide stable power supply. However, fluctuations in hydrological conditions can affect the stability of hydropower generation.

[0066] Photovoltaic power generation mainly refers to solar photovoltaic power generation, which uses solar cells to directly convert sunlight into electrical energy. Although solar photovoltaic power generation has significant advantages in terms of environmental protection and economy, it can reduce the consumption of fossil energy and the emission of harmful gases, while reducing the construction cost and loss of power transmission and distribution networks, but it also faces the problem of unstable power generation caused by weather changes and day and night changes.

[0067] This instability not only affects the utilization efficiency of renewable energy, but also brings challenges to the stable operation of the power grid. How to reasonably plan the access location of distributed renewable energy to optimize the distributed renewable energy grid topology in the distribution network is an urgent problem to be solved.

[0068] At present, some technologies have been tried to solve the problem of distributed renewable energy access. For example, a distributed renewable energy configuration structure optimization based on IACS-IGA first introduces an improved adaptive cuckoo search algorithm (IACS) and combines it with a genetic algorithm (GA) to form a hybrid strategy to improve the accuracy of GA in the later optimization process. The effectiveness and superiority of the improved algorithm in solving the DG configuration structure optimization problem were verified by the IEEE-33 node example and compared with the simulation results under different algorithms. However, when processing distributed renewable energy data, this method fails to fully consider the massiveness and complexity of the data, resulting in low data accuracy; when building a prediction model, it relies on an improved adaptive cuckoo search algorithm, which is difficult to cope with the complex changes in the state of renewable energy power generation.

[0069] Another example is a study on a method for monitoring abnormal power quality when distributed renewable energy is connected to the power grid. By building a model based on the least squares support vector machine and using the particle swarm algorithm to optimize hyperparameters, the missing data of the voltage signal is filled, and the wavelet transform is used to extract the power quality data features and calculate the energy distribution difference. The salp swarm optimization algorithm is introduced to optimize the initial weights and thresholds of the BP neural network, and the difference is input to achieve abnormal monitoring. Although this method introduces the salp swarm optimization algorithm to optimize the initial weights and thresholds of the BP neural network, the accuracy of the prediction model is still subject to certain limitations. At the same time, when processing distributed renewable energy data, it only relies on wavelet transform to extract features and calculate energy distribution differences, and there is no improvement in data accuracy and consistency.

[0070] In addition, neither of the above two methods involves data integration management and abnormal warning, which will lead to insufficient data accuracy, thus affecting the analysis and decision-making of the system. Various potential safety hazards may appear at any time. If these hazards cannot be discovered and handled in time, they will have a serious impact on the stable operation of the power grid.

[0071] Figure 1 A flow chart of a distributed new energy access optimization method provided in an embodiment of the present application is provided. The distributed new energy access optimization method includes the following steps.

[0072] S11, obtaining load information of the grid to which distributed renewable energy sources need to be connected.

[0073] Distributed new energy refers to small-scale power generation facilities scattered at the user end or the end of the power grid, such as solar photovoltaic, wind power generation, hydropower generation, etc. Distributed new energy can generate electricity and directly connect to the power grid.

[0074] The grid refers to the network structure of the power system, including transmission lines, substations, etc.

[0075] The load information includes: future load change trend, load bearing capacity and grid area.

[0076] Determining the load information of the grid is the basis for planning the access location of distributed renewable energy, which helps to ensure the stable operation of the power grid after the access of distributed renewable energy.

[0077] In an optional implementation, the acquiring load information of the grid to be connected to the distributed new energy source includes:

[0078] Collect the target user's historical electricity usage time and corresponding historical electricity consumption;

[0079] Predicting future load change trends based on the historical electricity consumption time and the corresponding historical electricity consumption;

[0080] Simulate the power generation of distributed renewable energy after it is connected to the grid;

[0081] determining a load carrying capacity of the power grid according to the power generation;

[0082] According to the future load change trend and the load carrying capacity of the power grid, the grid area that needs to be connected to the distributed new energy is determined.

[0083] The target users are specific users or user groups in the power grid who need to access distributed renewable energy, such as residents, commercial users or industrial users.

[0084] The electricity usage time (historical electricity usage time) and the corresponding electricity consumption (historical electricity consumption) of the target user in the past period of time (such as one day, one week, one month, etc.) can be obtained through the electricity meter records.

[0085] Based on historical electricity consumption time, historical electricity consumption and other relevant factors (such as weather, holidays, economic activities, etc.), the load change trend of the power grid in the future period is obtained through the prediction model.

[0086] The total amount of electricity (power generation) that distributed renewable energy sources (such as solar photovoltaic panels, wind turbines, etc.) may generate after being connected to the grid can be estimated through physical models or simulation software based on factors such as the type, scale, and weather conditions of distributed renewable energy sources.

[0087] The load carrying capacity of a power grid refers to the maximum load that the grid can withstand under specific conditions.

[0088] According to the future load change trend and the load carrying capacity of the power grid, determine the specific power grid areas or user areas that need to access distributed renewable energy, that is, determine which areas or users need to access distributed renewable energy to meet the load demand of the power grid and ensure the stable operation of the power grid.

[0089] The above optional implementation method, through data collection means, obtains the historical electricity consumption time and corresponding historical electricity consumption of the target user (i.e., the grid user who may access distributed new energy in the future), which helps to understand the user's electricity consumption habits, demand peaks and electricity consumption patterns, and provides accurate historical data support for subsequent load forecasting. According to the historical electricity consumption time and the corresponding historical electricity consumption, the future load change trend can be predicted, and the load demand of the power grid in the future period of time can be foreseen, which provides an important reference for the access location and capacity planning of distributed new energy, and ensures that the access of new energy can meet the actual needs of the power grid. Simulating the power generation of distributed new energy after access to the power grid can evaluate the power generation capacity of new energy under different conditions, provide a basis for the load carrying capacity analysis of the power grid and the selection of the access location of new energy, and ensure that the access of new energy will not cause overload or instability to the power grid. Determine the load carrying capacity of the power grid based on the power generation, which can ensure that the access of new energy will not exceed the carrying range of the power grid, and ensure the safe and stable operation of the power grid. According to the future load change trend and the load carrying capacity of the power grid, determine the grid area that needs to access distributed new energy, which can ensure the rationality of the access location of new energy, and realize the maximum utilization of new energy and the stable operation of the power grid.

[0090] S12, using a particle swarm algorithm to preliminarily plan access locations of the distributed new energy based on the load information.

[0091] Particle swarm optimization is an effective optimization algorithm that can find near-optimal solutions to complex problems.

[0092] Preliminary planning of access locations can provide a basis for subsequent fine-tuning, reduce the amount of calculation and improve optimization efficiency

[0093] Optionally, the using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information includes:

[0094] Initializing a particle swarm, wherein each particle in the particle swarm represents an access location of a distributed new energy source;

[0095] Calculate the current optimal fitness of each particle according to the preset objective function;

[0096] For each particle, compare the current best fitness with the historical best fitness;

[0097] If the current best fitness is better than the historical best fitness, then the historical best position of the particle is updated to the current best position;

[0098] Determine the global best fitness and the corresponding global best position according to the historical best fitness of all particles in the particle swarm;

[0099] Iteratively updating the speed and position of each particle according to the historical best position and the global best position;

[0100] When the iterative update meets the stopping condition, the global optimal position obtained is the initially planned distributed new energy access location.

[0101] Initializing the particle swarm includes: initializing the particle swarm size and initializing the particle position and speed. The particle swarm size is the number of particles contained in the particle swarm, and each particle represents a possible distributed renewable energy access location. The position and speed of each particle are randomly initialized in the search space, and the position of the particle is the specific node or area where the distributed renewable energy accesses the power grid. The particle speed is used to adjust the particle position during the iteration process.

[0102] Based on load information (such as historical power consumption time, power consumption, future load change trend, etc.) and grid conditions, the objective function (also known as fitness function) is defined. The fitness function can reflect the advantages and disadvantages of the access location solution.

[0103] In each iteration, the objective function value of each particle at the current position is calculated according to the fitness function as the current best fitness of the particle. For each particle, its current best fitness is compared with its historical best fitness. If the current best fitness is better than the historical best fitness, the historical best fitness and historical best position of the particle are updated.

[0104] Among the historical best fitness of all particles, find the best one as the global best fitness. The particle position corresponding to the global best fitness is the global best position. According to the historical best position and the global best position, as well as the speed and position update formula, adjust the speed of each particle. Use the updated speed to adjust the position of each particle.

[0105] When the maximum number of iterations is reached or the convergence condition is met, the iteration is stopped and the global optimal position is output, which is the initially planned distributed new energy access location.

[0106] In the above optional implementation, each particle in the particle swarm is set to represent an access position of a distributed new energy source, ensuring that the algorithm can search for the optimal solution in a wide solution space. Through the diversity of particles, the algorithm can explore a variety of possible access positions, increasing the possibility of finding the optimal solution. Calculating the current best fitness can evaluate the pros and cons of each particle (i.e., each access position), providing a clear guidance direction for subsequent iterative updates, and ensuring that the algorithm can evolve towards a better solution. For each particle, its current best fitness is compared with the historical best fitness. If the current best fitness is better, the historical best position of the particle is updated. According to the historical best fitness of all particles in the particle swarm, the global best fitness and its corresponding global best position are determined. The global best fitness and position represent the optimal solution found in the current particle swarm, providing a clear optimization goal for the entire algorithm, ensuring that the algorithm can continuously approach the global optimal solution. According to the historical best position and the global best position, the speed and position of each particle are iteratively updated. When the iterative update meets the preset stop condition, the iteration is stopped, and the global best position at this time is the distributed new energy access position preliminarily planned.

[0107] S13, obtaining real-time data of the distributed new energy.

[0108] Real-time data includes real-time power generation, voltage, current and other data generated by distributed renewable energy during operation.

[0109] In an optional embodiment, refer to Figure 2 As shown, to ensure the accuracy, completeness and availability of real-time data, before obtaining the real-time data of the distributed new energy, the method further includes:

[0110] Determining the source of the distributed new energy data;

[0111] Acquire the distributed new energy data using a connection method matching the source;

[0112] Clean the acquired distributed new energy data;

[0113] Convert the format of the cleaned distributed new energy data;

[0114] The distributed new energy data after format conversion is stored.

[0115] First, it is necessary to determine and identify the sources of distributed new energy data, which may include but are not limited to sensor networks, smart devices, remote monitoring systems, third-party data providers, etc. According to the characteristics of the data source, select the appropriate connection method. The connection method may include API, database interface, file transfer, etc. Different sources may correspond to different connection methods, or they may correspond to the same connection method.

[0116] After obtaining distributed new energy data, cleaning processing is performed, for example, processing missing values, removing outliers, filtering duplicate values, etc., to effectively eliminate data silos and improve data availability and value.

[0117] After the distributed new energy data is cleaned, the data from different sources and formats are converted into a unified format and a unified dimension or range for subsequent processing and analysis.

[0118] According to the characteristics of the data and business needs, choose an appropriate storage method to store distributed new energy data, such as relational databases (such as MySQL, PostgreSQL), non-relational databases (such as MongoDB, Cassandra), time series databases (such as InfluxDB, Prometheus), etc.

[0119] You can also establish a data management system, including data access rights, data update frequency, data backup and recovery strategies, etc.

[0120] The above optional implementation methods, by accessing and managing distributed renewable energy data, can better control the volatility and intermittency of renewable energy, and provide a basis for building distributed renewable energy prediction models and real-time monitoring. This not only enhances the stability and reliability of the power grid, but also promotes the effective integration and utilization of renewable energy.

[0121] S14, extracting key features from the real-time data.

[0122] The key features can reflect the power generation characteristics and laws of distributed renewable energy, and help optimize access locations and power generation scheduling.

[0123] Statistical analysis can be performed on real-time data to calculate statistical quantities such as mean, standard deviation, maximum, minimum, etc. as key features. Key features can also be extracted using machine learning algorithms (such as feature selection, principal component analysis, etc.).

[0124] By extracting key features, the data dimension can be reduced and the efficiency of subsequent analysis and optimization can be improved.

[0125] S14, using the key features to train a support vector machine power generation prediction model.

[0126] First, set the support vector machine kernel function (such as linear kernel, Gaussian kernel, etc.) and parameters.

[0127] The key features are divided into training data set, test data set and validation data set. The training data set is used to train the support vector machine power generation prediction model, and the trained support vector machine power generation prediction model is verified and tested to evaluate its prediction performance.

[0128] By training the support vector machine power generation prediction model, future power generation can be predicted, providing a basis for power generation scheduling and access location optimization.

[0129] S15, using the trained support vector machine power generation prediction model to fine-tune the access position to obtain a target access position.

[0130] Since a group of possible access locations have been preliminarily planned based on load information through the particle swarm algorithm, the support vector machine power generation prediction model is used to predict the power generation at different access locations based on key features, weather conditions, distributed renewable energy types and other relevant factors for each preliminarily selected access location. It is evaluated whether the predicted power generation corresponding to each access location meets the expected goals, such as maximizing power generation, minimizing network losses, and meeting specific load requirements.

[0131] Based on the power generation prediction results, the access position is finely adjusted through iterative optimization algorithms (such as gradient descent, simulated annealing, genetic algorithm, etc.). When the iteration meets the set stop conditions of iterative optimization, such as reaching the maximum number of iterations, the objective function value no longer changes significantly, etc., the training is stopped and the access position with the best objective function value is selected as the target access position.

[0132] S16, connecting the distributed new energy to the target access position of the grid.

[0133] Conduct on-site surveys at the target access location to confirm installation conditions, spatial layout, cable paths, etc. Install distributed new energy equipment, grid-connected equipment, protection devices, etc. at designated locations in accordance with design drawings and installation specifications. Lay cables to electrically connect distributed new energy equipment to the grid. Then, conduct comprehensive commissioning of the grid-connected system, including equipment function testing, protection device verification, grid-connected parameter settings, etc. Ensure that the system can operate normally and meet the safety requirements of the grid.

[0134] This application provides basic data support for the access of distributed new energy by obtaining the load information of the grid that needs to access distributed new energy, ensuring that the access plan can meet the actual load requirements of the grid and avoid overload or underload. First, the particle swarm algorithm is used to preliminarily plan the access location of distributed new energy based on load information, which improves the planning efficiency while ensuring the optimization of the plan in a global scope. Real-time data of distributed new energy is obtained, and key features are extracted from it. The extraction of key features helps to more accurately understand the power generation characteristics and change trends of new energy, and provide a basis for subsequent prediction and adjustment. The support vector machine power generation prediction model is trained using the extracted key features. An accurate power generation prediction model is established to predict the power generation capacity of new energy under different conditions and provide data support for the fine adjustment of the access location. The access location is finely adjusted using the trained support vector machine power generation prediction model to obtain the target access location. Based on the prediction results of the power generation prediction model, the access location is further optimized to ensure that resources can be maximized after the new energy is connected, and the power generation efficiency and grid stability are improved. Finally, the distributed renewable energy will be connected to the target access location of the grid to achieve accurate access of renewable energy, ensure the coordinated operation of renewable energy and the power grid, improve the flexibility and reliability of the power grid, and promote the effective utilization and sustainable development of renewable energy.

[0135] In an optional embodiment, the method further comprises:

[0136] The power generation is predicted based on the real-time data of distributed renewable energy obtained;

[0137] Distributed renewable energy is dispatched based on the power generation.

[0138] Collect all kinds of data of distributed renewable energy in real time, including but not limited to light intensity (for solar energy), wind speed (for wind energy), temperature, humidity and real-time operating parameters of equipment (such as current, voltage, power output, etc.). Use the pre-trained support vector machine power generation prediction model and take the pre-processed real-time data as input to predict power generation.

[0139] Based on the power generation forecast results, combined with the real-time operation status of the power grid, load demand, energy policy and other factors, a scientific and reasonable distributed new energy dispatching strategy is formulated. The dispatching strategy is converted into specific dispatching instructions, and the instructions are sent to the distributed new energy equipment through the remote control system or manually to achieve precise control of its output power, grid connection status, etc. The execution of the dispatching instructions and the actual operation status of the distributed new energy equipment are continuously monitored to ensure the effective implementation of the dispatching strategy.

[0140] The above optional implementation method utilizes the acquired real-time data of distributed renewable energy to predict future power generation through a prediction model, so as to understand in advance the power generation capacity of renewable energy in the future and provide reliable data support for the scheduling of renewable energy. Through accurate power generation prediction, it can ensure that the power generation plan of renewable energy matches the power grid demand, avoid over- or under-generation of power, and improve the utilization rate of renewable energy and the stability of the power grid. Dispatching distributed renewable energy based on power generation can achieve precise control of renewable energy power generation, help balance the supply and demand of the power grid, and ensure the stable operation of the power grid. At the same time, reasonable scheduling can also reduce the impact of renewable energy power generation on the power grid and improve the flexibility and reliability of the power grid.

[0141] In an optional embodiment, refer to Figure 3 As shown, in order to ensure stable and safe operation of the distribution network, the method further includes:

[0142] Determining the energy type of the distributed renewable energy;

[0143] Obtaining monitoring parameters and warning thresholds corresponding to the energy type;

[0144] Acquire a parameter value corresponding to the monitoring parameter from the distributed new energy data;

[0145] comparing the parameter value with a corresponding warning threshold;

[0146] When the parameter value is greater than the corresponding warning threshold, an alarm is issued.

[0147] Energy type refers to the type of distributed renewable energy, such as solar energy, wind energy, and hydropower.

[0148] Since different types of energy have different power generation characteristics and requirements, different management and optimization strategies need to be adopted. Therefore, it is necessary to determine the energy type of distributed renewable energy according to its type and characteristics.

[0149] According to the characteristics of energy type and new energy equipment, determine the parameters that need to be monitored. Monitoring parameters are important parameters that reflect the state of new energy power generation and the operating status of equipment. Consult relevant standards and specifications to determine the warning threshold of each monitoring parameter. The warning threshold is the threshold at which a warning signal needs to be issued. When the parameter value corresponding to the monitoring parameter exceeds the warning threshold, a warning signal is automatically issued.

[0150] For example, for wind power generation, it is necessary to monitor parameters such as wind speed, wind direction, and fan speed in real time. When the values ​​of wind speed, wind direction, and fan speed exceed the warning threshold, a warning signal is automatically issued. For hydropower generation, it is necessary to monitor parameters such as water level, water flow rate, and unit operation status in real time. Once an abnormal situation occurs, such as the water level is too high or too low, the water flow rate is too fast or too slow, or the unit fails, an early warning is issued immediately. For solar power generation, it is necessary to monitor parameters such as light intensity, photovoltaic panel temperature, and output voltage and current in real time. If there is an abnormality, such as a sudden drop in light intensity, excessive photovoltaic panel temperature, and excessive fluctuations in output voltage and current, an alarm is issued in time.

[0151] Through real-time monitoring and early warning, relevant personnel can be reminded to take timely measures, so as to promptly discover and deal with potential safety hazards and ensure the safe and reliable operation of the distribution network system.

[0152] The above optional implementation method first determines the energy type of distributed new energy, which provides a basis for the subsequent selection of monitoring parameters and the setting of warning thresholds, ensuring the pertinence and accuracy of the monitoring and early warning system. Obtain the monitoring parameters and early warning thresholds corresponding to the energy type, obtain the parameter values ​​corresponding to the monitoring parameters from the distributed new energy data, and compare the parameter values ​​with the corresponding early warning thresholds. Through comparison, it is possible to promptly discover whether the parameter values ​​exceed the normal range, providing a basis for judgment for subsequent alarm triggering. When it is found that one or some parameter values ​​exceed the early warning threshold, the alarm mechanism is triggered to issue a warning to the relevant personnel. The alarm mechanism can quickly notify the relevant personnel of abnormal situations, so that they can take timely measures to deal with them, avoiding potential safety hazards and economic losses.

[0153] It should be noted that the above monitoring and early warning require the use of IoT technology to collect real-time data. IoT technology can also be used to realize intelligent scheduling and control of distributed new energy. For example, the operating status of wind turbines and photovoltaic panels can be adjusted according to parameters such as wind speed and light intensity to achieve optimal energy output.

[0154] In an optional embodiment, the method further comprises:

[0155] The operating status of the distributed new energy and / or the changing trend of the operating status are displayed.

[0156] Use graphical interface design tools to create intuitive and easy-to-use graphical interfaces. Through graphical interfaces (such as dashboards, line charts, bar charts, etc.), the operating status of distributed new energy sources, such as power output, voltage, current, temperature, etc., can be displayed in real time.

[0157] The operating status is presented in a dynamically updated manner so that operators can always understand the latest status of the equipment.

[0158] You can use color coding or icons to visually indicate the operating status of the device. For example, green indicates normal operation, yellow indicates warning, and red indicates failure.

[0159] Operators can view detailed information about the device by clicking or hovering to conduct deeper analysis and diagnosis.

[0160] By drawing trend graphs of historical data (such as line graphs, scatter graphs, etc.), the operating status of distributed renewable energy can be shown over time. These trend graphs can help operators identify performance changes, fault precursors or abnormal behaviors of equipment.

[0161] Through visualization technology, complex data and warning information are displayed in an intuitive way, which makes it easier for operation and maintenance personnel to quickly understand the operating status and performance indicators of the equipment, so as to quickly identify which equipment needs attention or action. At the same time, the visualization interface can also provide rich interactive functions to facilitate operation and maintenance personnel to monitor and manage the equipment.

[0162] See also Figure 4 As shown, it is the overall architecture diagram of the distributed new energy real-time monitoring provided in the embodiment of the present application.

[0163] This application will explain how to achieve real-time monitoring of distributed new energy based on a full-dimensional data integration strategy from the following five aspects.

[0164] First, analyze the characteristics of distributed new energy and make preliminary preparations for connecting to the original distribution network.

[0165] Distributed new energy, as an important part of the modern energy system, can not only improve energy efficiency, but also promote environmental protection and sustainable development. Compared with the traditional centralized power generation system, it is more flexible, efficient and reliable. Including wind power generation, hydropower generation, solar power generation and other aspects, each form of energy has its own unique characteristics and challenges. The specific characteristics are as follows:

[0166] (1) Wind power generation: Wind power generation technology captures wind energy through wind rotors and drives generators to generate electricity. It has strong environmental adaptability and can operate efficiently in areas with abundant wind resources such as plateaus, mountains and islands. This method of power generation does not require fuel, does not produce radiation or air pollution, and is a clean and pollution-free renewable energy. Distributed wind power generation systems can also enhance the safety and stability of the power grid, provide continuous power supply when disasters occur, and become an important supplement to the centralized power supply system. However, wind power generation also faces the problem of power generation fluctuations caused by unstable wind speed.

[0167] (2) Hydropower generation: Hydropower generation uses the potential or kinetic energy of water to convert it into electrical energy by building dams or other water flow control facilities. This type of power generation relies on river flow and topographic conditions and can provide stable power supply. However, hydropower generation projects usually require large initial investments and may have an impact on the local ecological environment, such as changing hydrological conditions and ecosystems.

[0168] (3) Photovoltaic power generation: Photovoltaic power generation mainly refers to solar photovoltaic power generation, which uses solar cells to directly convert sunlight into electrical energy. This power generation method has obvious randomness and intermittent characteristics because its output is greatly affected by natural environment and climate factors. Although solar photovoltaic power generation has significant advantages in terms of environmental protection and economy, it can reduce the consumption of fossil energy and the emission of harmful gases, while reducing the construction cost and loss of the power transmission and distribution network, but it also faces the problem of unstable power generation caused by weather changes and the alternation of day and night.

[0169] By analyzing the characteristics and challenges of these distributed renewable energy sources, more flexibility and scalability are provided for the access of distributed renewable energy sources to the original power grid, which is conducive to improving the reliability and stability of the power grid.

[0170] Secondly, based on the characteristics of different types of distributed new energy, optimize the original grid topology.

[0171] This application uses a hybrid intelligent algorithm based on support vector machine and particle swarm algorithm to plan distributed renewable energy, while taking into account the load of the connected lines or grids.

[0172] In the grid structure without the introduction of distributed renewable energy, the power system usually relies on centralized large-scale power plants and long-distance transmission lines. This structure is characterized by its high degree of centralization and scale, which can achieve large-scale power production and transmission. However, due to the mismatch between power demand and supply, energy loss during transmission, and potential grid failure risks; after the introduction of distributed renewable energy, distributed renewable energy such as solar photovoltaic panels and wind turbines are installed on or near the user side, realizing the production and consumption of electricity nearby, which not only improves energy utilization efficiency and reduces energy loss during long-distance transmission, but also enhances the stability and reliability of the power grid. Due to the intermittent nature of distributed renewable energy generation, in order to improve energy utilization efficiency and power supply quality, it is necessary to analyze the load of the connected lines or grids when accessing distributed renewable energy, and it is also necessary to plan the distributed renewable energy.

[0173] (1) Conduct a detailed analysis of the load conditions of the lines or grids to be connected. This includes considering the power consumption patterns of large users, load peak periods, and possible network bottlenecks. Through accurate load analysis, it can be ensured that distributed new energy will not cause excessive burden on the existing power grid after access.

[0174] For example, a factory somewhere needs continuous and uninterrupted electricity, and the power consumption is large. Before the access to distributed new energy, only the electricity transmitted by centralized large power plants was used, and if the circuit fails, it will be affected. Access to distributed new energy can introduce other power sources when a failure occurs. At this time, it is necessary to consider that if a solar power generation power source is connected, it cannot guarantee that the factory will be powered at night when a failure occurs. At this time, you can consider accessing a hydropower power source. The hydropower station can store energy at night (through pumped storage) and release energy to generate electricity during peak demand periods, thereby effectively balancing the supply and demand relationship of the power grid. .

[0175] (2) Planning of distributed renewable energy. This application uses a hybrid intelligent algorithm based on support vector machine (SVM) and particle swarm algorithm (PSO) to plan distributed renewable energy. Support vector machine is used to process high-dimensional data classification and regression problems, while particle swarm algorithm is an optimization algorithm based on swarm intelligence that can efficiently search for the global optimal solution. Combining the two can make full use of their respective advantages to achieve accurate planning of distributed renewable energy.

[0176] First, various parameters of distributed photovoltaic power stations are monitored in real time through sensors and smart devices to collect data such as light intensity, temperature, voltage, and current. Appropriate features are selected from the collected data, which will be used for training and prediction of the SVM model; then the PSO algorithm is used to optimize the preliminary configuration of distributed renewable energy, including the location and capacity of the power source, and the SVM model is used to further fine-tune the configuration of distributed renewable energy; finally, the results of PSO and SVM are combined for comprehensive analysis to determine the final distributed renewable energy planning scheme.

[0177] The third aspect is to access distributed new energy data based on data integration technology.

[0178] Accessing distributed new energy data and using data integration technology to process these data improves data accuracy and provides data support for subsequent predictions of distributed new energy status.

[0179] After optimizing the original grid topology, access to new energy data can better control the volatility and intermittency of new energy, providing a basis for building distributed new energy prediction models and real-time monitoring. This process not only enhances the stability and reliability of the power grid, but also promotes the effective integration and utilization of renewable energy.

[0180] Based on data integration technology, the process of accessing distributed new energy data involves multiple key steps, including cleaning, integrating and analyzing the collected data to ensure the accuracy and consistency of the data. At the same time, data mining technology is used to deeply mine distributed new energy data to extract valuable information and provide support for subsequent applications. Through these steps, data islands can be effectively eliminated and the availability and value of data can be improved.

[0181] Fourthly, build a distributed new energy prediction model.

[0182] The data related to distributed renewable energy is integrated by using full-dimensional data fusion technology for distributed renewable energy prediction modeling and further model training. Finally, the status of distributed renewable energy is monitored in real time, including monitoring anomalies and early warnings. The Internet of Things and visualization technologies are used to provide a visual and intelligent monitoring interface for operation and maintenance personnel, which is more conducive to the management and maintenance of distributed renewable energy and distribution networks containing distributed renewable energy.

[0183] After accessing the distributed new energy data, it is helpful to build a distributed new energy prediction model. Building a distributed new energy prediction model is a complex and crucial process, which involves the use of full-dimensional data fusion technology to integrate multiple types of data. These data include but are not limited to key information such as meteorological data, historical power generation data, and equipment status data. Through this comprehensive data fusion method, the dimension and richness of the data can be improved, and a highly accurate distributed new energy prediction model can be built.

[0184] The random forest algorithm is used to build a distributed new energy prediction model. The random forest algorithm is an integrated learning method that improves the overall prediction performance by building multiple decision trees and averaging or voting their prediction results. The prediction model can predict the power generation in the future based on historical data and current conditions; collect and process current meteorological conditions, equipment status and other data in real time to dynamically adjust the prediction model. The process of building a distributed new energy prediction model using the random forest algorithm is shown in the figure below:

[0185] Fifth, real-time monitoring of the status of distributed new energy, including monitoring of anomalies and early warnings.

[0186] In order to ensure that the distribution network can operate stably and safely after the introduction of distributed renewable energy, it is necessary to monitor the status of distributed renewable energy in real time, analyze the operating data of renewable energy in real time, find potential abnormalities, and issue early warnings. This will help operation and maintenance personnel take timely measures to prevent accidents and ensure the safe and reliable operation of the distribution network system. For different types of distributed renewable energy, set corresponding monitoring parameters and early warning thresholds.

[0187] The above monitoring and early warning require the use of Internet of Things technology and visualization technology. Based on the real-time data collected by Internet of Things technology, intelligent scheduling and control of new energy equipment can be realized. For example, the operating status of wind turbines and photovoltaic panels can be adjusted according to parameters such as wind speed and light intensity to achieve optimal energy output; through visualization technology, complex data and early warning information can be displayed in an intuitive way, which is convenient for operation and maintenance personnel to quickly understand the operating status and performance indicators of the equipment. At the same time, the visualization interface can also provide rich interactive functions to facilitate operation and maintenance personnel to monitor the equipment. Use Internet of Things technology and visualization technology to realize real-time monitoring of distributed new energy status.

[0188] This application improves the reliability and stability of the power grid and promotes the effective use of distributed renewable energy by analyzing the characteristics of distributed renewable energy, optimizing the grid topology, accessing renewable energy data, building a prediction model, and realizing real-time monitoring.

[0189] Figure 5 It is a functional module diagram of the distributed new energy access optimization device provided in the embodiment of the present application.

[0190] In some embodiments, the distributed new energy access optimization device 50 may include multiple functional modules composed of program code segments. The program code of each program segment in the distributed new energy access optimization device 50 may be stored in the memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Function of optimizing access to distributed new energy.

[0191] In this embodiment, the distributed new energy access optimization device 50 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: a load acquisition module 501, a first optimization module 502, a data acquisition module 503, a feature extraction module 504, a model training module 505, a second optimization module 506, an energy access module 507, a data storage module 508, an energy scheduling module 509, a monitoring alarm module 510 and an interface display module 511. The module referred to in this application refers to a series of computer-readable instruction segments that can be executed by at least one processor and can perform fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0192] The load acquisition module 501 is used to acquire the load information of the grid to be connected to the distributed new energy;

[0193] The first optimization module 502 uses a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information;

[0194] The data acquisition module 503 is used to acquire the real-time data of the distributed new energy;

[0195] The feature extraction module 504 is used to extract key features from the real-time data;

[0196] The model training module 505 is used to train a support vector machine power generation prediction model using the key features;

[0197] The second optimization module 506 is used to fine-tune the access position using the trained support vector machine power generation prediction model to obtain a target access position;

[0198] The energy access module 507 is used to connect the distributed new energy to the target access position of the grid.

[0199] The data storage module 508 is used to determine the source of the distributed new energy data; obtain the distributed new energy data using a connection method that matches the source; clean the obtained distributed new energy data; convert the format of the cleaned distributed new energy data; and store the format-converted distributed new energy data.

[0200] The energy scheduling module 509 is used to predict the power generation based on the acquired real-time data of the distributed new energy; and schedule the distributed new energy based on the power generation.

[0201] The monitoring alarm module 510 is used to determine the energy type of the distributed new energy; obtain the monitoring parameters and warning thresholds corresponding to the energy type; obtain parameter values ​​corresponding to the monitoring parameters from the distributed new energy data; compare the parameter values ​​with the corresponding warning thresholds; and issue an alarm when the parameter value is greater than the corresponding warning threshold.

[0202] The interface display module 511 is used to display the operating status of the distributed new energy and / or the changing trend of the operating status.

[0203] It should be understood that the various variations and specific embodiments of the distributed new energy access optimization method provided in the above-mentioned embodiments are also applicable to the distributed new energy access optimization device in this embodiment. Through the detailed description of the aforementioned distributed new energy access optimization method, technical personnel in this field can clearly understand the implementation process of the distributed new energy access optimization device in this embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0204] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, all or part of the steps of the distributed new energy access optimization method are implemented.

[0205] See also Figure 6 FIG. 6 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. In a preferred embodiment of the present application, the computer device 6 includes a memory 601 , at least one processor 602 , and at least one communication bus 603 .

[0206] Those skilled in the art should understand that Figure 6 The structure of the computer device shown does not constitute a limitation of the embodiments of the present application. The computer device 6 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0207] In some embodiments, the computer device 6 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 6 may also include client devices, which include but are not limited to any electronic product that can interact with a client through a keyboard, mouse, remote control, touchpad, or voice-controlled device, such as a personal computer, tablet computer, smart phone, digital camera, etc.

[0208] It should be noted that the computer device 6 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0209] In some embodiments, a computer program is stored in the memory 601, and when the computer program is executed by the at least one processor 602, all or part of the steps in the distributed new energy access optimization method as described are implemented. The memory 601 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data. Further, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, and the like.

[0210] In some embodiments, the at least one processor 602 is the control core (CrolUnit) of the computer device 6, and uses various interfaces and lines to connect the various components of the entire computer device 6, and executes various functions and processes data of the computer device 6 by running or executing the program or module stored in the memory 601, and calling the data stored in the memory 601. For example, when the at least one processor 602 executes the computer program stored in the memory, it implements all or part of the steps of the distributed new energy access optimization method described in the embodiment of the present application; or implements all or part of the functions of the distributed new energy access optimization device. The at least one processor 602 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, and various control chips.

[0211] In some embodiments, the at least one communication bus 603 is configured to realize connection and communication between the memory 601 and the at least one processor 602, etc. Although not shown, the computer device 6 may also include a power supply (such as a battery) for powering each component. Preferably, the power supply may be logically connected to the at least one processor 602 through a power management device, so as to realize functions such as management of charging, discharging, and power consumption management through the power management device. The power supply may also include any components such as one or more DC or AC power supplies, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The computer device 6 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which are not repeated here.

[0212] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the method described in each embodiment of the present application.

[0213] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0214] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A distributed new energy access optimization method, characterized in that: The method comprises: Obtain the load information of the grid that needs to be connected to distributed renewable energy; Using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information; Acquiring real-time data of the distributed new energy; extracting key features from the real-time data; Using the key features to train a support vector machine power generation prediction model; Using the trained support vector machine power generation prediction model to fine-tune the access position to obtain a target access position; Connect the distributed new energy to the target access position of the grid.

2. The distributed new energy access optimization method according to claim 1 is characterized in that: The load information includes: future load change trend, load bearing capacity and grid area. The load information of the grid to be connected to the distributed new energy includes: Collect the target user's historical electricity usage time and corresponding historical electricity consumption; Predicting future load change trends based on the historical electricity consumption time and the corresponding historical electricity consumption; Simulate the power generation of distributed renewable energy after it is connected to the grid; determining a load carrying capacity of the power grid according to the power generation; According to the future load change trend and the load carrying capacity of the power grid, the grid area that needs to be connected to the distributed new energy is determined.

3. The method according to claim 1, characterized in that The using of a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information includes: Initializing a particle swarm, wherein each particle in the particle swarm represents an access location of a distributed new energy source; Calculate the current optimal fitness of each particle according to the preset objective function; For each particle, compare the current best fitness with the historical best fitness; If the current best fitness is better than the historical best fitness, then the historical best position of the particle is updated to the current best position; Determine the global best fitness and the corresponding global best position according to the historical best fitness of all particles in the particle swarm; Iteratively updating the speed and position of each particle according to the historical best position and the global best position; When the iterative update meets the stopping condition, the global optimal position obtained is the access position of the distributed new energy source initially planned.

4. The method according to claim 1, characterized in that: Before acquiring the real-time data of the distributed new energy, the method further includes: Determining the source of the distributed new energy data; Acquire the distributed new energy data using a connection method matching the source; Clean the acquired distributed new energy data; Convert the format of the cleaned distributed new energy data; The distributed new energy data after format conversion is stored.

5. The distributed new energy access optimization method according to claim 1 is characterized in that: The method further comprises: The power generation is predicted based on the real-time data of distributed renewable energy obtained; Distributed renewable energy is dispatched based on the power generation.

6. The distributed new energy access optimization method according to claim 1 is characterized in that: The method further comprises: Determining the energy type of the distributed renewable energy; Obtaining monitoring parameters and warning thresholds corresponding to the energy type; Acquire a parameter value corresponding to the monitoring parameter from the distributed new energy data; comparing the parameter value with a corresponding warning threshold; When the parameter value is greater than the corresponding warning threshold, an alarm is issued.

7. The distributed new energy access optimization method according to claim 1 is characterized in that: The method further comprises: The operating status of the distributed new energy and / or the changing trend of the operating status are displayed.

8. A distributed new energy access optimization device, characterized in that: The device comprises: The load acquisition module is used to obtain the load information of the grid that needs to be connected to the distributed new energy; A first optimization module, using a particle swarm algorithm to preliminarily plan the access location of the distributed new energy based on the load information; A data acquisition module, used to acquire real-time data of the distributed new energy; A feature extraction module, used to extract key features from the real-time data; A model training module, used for training a support vector machine power generation prediction model using the key features; A second optimization module is used to fine-tune the access position using the trained support vector machine power generation prediction model to obtain a target access position; An energy access module is used to connect the distributed new energy to the target access position of the grid.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the distributed new energy access optimization method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the distributed new energy access optimization method as described in any one of claims 1 to 7 are implemented.

Images