A multi-mode coordinated control method and system based on a wind-solar-storage new energy power station

Abstract

The application relates to the technical field of power regulation, and discloses a multi-mode coordinated control method and system based on a wind-solar-storage new energy power station, which comprises the following steps: acquiring real-time operation data of wind power, photovoltaic power generation and an energy storage system; predicting power grid load and wind power, photovoltaic power generation in a future period of time; recommending an energy scheduling scheme set by using a collaborative recommendation algorithm; determining an optimal energy scheduling scheme by using an improved Bayesian optimization algorithm based on an immune mechanism; and performing corresponding control operations on wind energy, light energy and energy storage equipment according to the obtained optimal energy scheduling scheme, so that efficient collaborative work of various energies is realized; and the application further discloses a multi-mode coordinated control system based on the wind-solar-storage new energy power station. The application can quickly find the optimal energy scheduling scheme, efficiently realize coordinated control of the wind-solar-storage new energy power station, better meet the power grid load demand, and maximize the energy utilization efficiency.

Description

Technical Field

[0001] This invention relates to the field of power regulation technology, and more specifically, to a multi-mode coordinated control method and system based on wind, solar and energy storage power plants. Background Technology

[0002] With the rapid depletion of fossil fuels such as coal, oil, and natural gas, and the continued deterioration of the ecological environment, especially the increasingly serious global climate change caused by greenhouse gas emissions, the sustainable development of human society is facing unprecedented threats. Therefore, energy technologies are gradually shifting towards low-carbon and carbon-free development. Against this backdrop, the power system, as an aspect closely related to human life, also faces a series of challenges.

[0003] A smart grid is a widely distributed and highly automated energy exchange system characterized by the bidirectional flow of electricity and information. To promote the development of smart grids, numerous demonstration projects are being conducted globally. To truly realize a smart grid, the goals of reliability, security, economy, efficiency, environmental protection, and safe use must be achieved across all stages, including power generation, transmission, distribution, consumption, energy storage, and microgrids. Therefore, accelerating the construction of a multi-level smart grid energy system with bidirectional interaction across all stages, including power generation, transmission, distribution, and consumption, is a crucial stage and foundation for my country's comprehensive advancement of smart grid construction.

[0004] In recent years, my country's new energy industry has developed rapidly, playing a vital role in improving the energy structure, protecting the environment, and promoting economic development. However, wind power and photovoltaic (PV) power generation are intermittent and volatile. Large-scale use of new energy power generation can lead to significant fluctuations in grid voltage and frequency, posing challenges to stable operation. Therefore, introducing large-capacity energy storage systems is an important method to ensure the stable operation of large-scale grid-connected new energy power generation. Combining energy storage systems with wind and PV power generation systems to construct integrated wind-solar-storage systems can coordinate the power output of wind and PV power generation and mitigate their output fluctuations. This control scheme is gaining increasing attention and is a crucial means to ensure the stable operation of large-scale grid-connected new energy power generation; this approach is becoming a research hotspot.

[0005] However, the traditional operation mode of wind, solar and energy storage power plants is relatively simple and extensive, lacking mutual coordination and system optimization. Therefore, this invention proposes a multi-mode coordinated control method and system based on wind, solar and energy storage power plants. Summary of the Invention

[0006] To address the problems in related technologies, this invention proposes a multi-mode coordinated control method and system based on wind, solar, and energy storage power plants, in order to overcome the aforementioned technical problems existing in the current related technologies.

[0007] Therefore, the specific technical solution adopted by the present invention is as follows:

[0008] According to one aspect of the present invention, a multi-mode coordinated control method based on a wind-solar-storage new energy power station is provided, the method comprising the following steps:

[0009] S1. Obtain real-time operation data of wind power, photovoltaic power generation and energy storage systems through external protocol access;

[0010] S2. Use real-time operational data and weather data to predict the grid load and wind and solar power generation in the future period.

[0011] S3. Use the collaborative recommendation algorithm to recommend energy scheduling schemes based on the prediction data to obtain a set of energy scheduling schemes;

[0012] S4. Based on the power generation capacity, energy storage capacity and grid load demand of the power plant, the optimal energy dispatch scheme is determined from the energy dispatch scheme set using an improved Bayesian optimization algorithm based on an immune mechanism.

[0013] S5. Based on the obtained optimal energy dispatch scheme, corresponding control operations are performed on wind power, solar power, and energy storage equipment to achieve efficient collaborative operation of various energy sources.

[0014] Preferably, the method of using real-time operational data combined with weather data to predict the grid load and wind and photovoltaic power generation in the future includes the following steps:

[0015] S21. Obtain historical operating data of wind power generation, photovoltaic power generation, and energy storage systems from the database, as well as corresponding weather data;

[0016] S22. Construct a power grid load forecasting model using historical load data and corresponding time and weather data, and use the trained power grid load forecasting model to predict the power grid load in the future.

[0017] S23. Construct a wind power generation prediction model based on historical wind power generation operation data, and use the trained wind power generation prediction model to predict wind power generation data in the future period.

[0018] S24. Construct a photovoltaic power generation prediction model using historical photovoltaic power generation operation data, and use the trained photovoltaic power generation prediction model to predict photovoltaic power generation data for a future period of time.

[0019] Preferably, the power grid load forecasting model, wind power generation forecasting model, and photovoltaic power generation forecasting model are all any one of time series models, regression models, machine learning models, deep learning models, or ensemble learning models.

[0020] Preferably, the step of using a collaborative recommendation algorithm to recommend energy scheduling schemes based on prediction data to obtain a set of energy scheduling schemes includes the following steps:

[0021] S31. Acquire historical and forecast data and preprocess them. Historical data includes energy data, load demand data and weather conditions. Forecast data includes power grid load forecast data, wind power generation forecast data and photovoltaic power generation forecast data.

[0022] S32. Construct a time-load demand and energy type scoring matrix based on the acquired historical and forecast data;

[0023] S33. Use clustering algorithm to calculate the rating matrix of time-load demand and energy type to obtain several different categories, and cut the rating matrix in the time-load demand dimension to obtain several rating matrices of time-load demand and energy type.

[0024] S34. Using the similarity metric method, find the nearest neighbor time-load demand of the target time-load demand in each category based on the clustering results, and analyze to obtain the recommended energy type set for the time-load demand in that category;

[0025] S35. Based on the recommended energy types across all categories, sort the predicted scores and select a preset number of recommended energy types as the energy dispatch scheme set recommended by the predicted data, according to the sorting results from high to low.

[0026] Preferably, the step of using a clustering algorithm to calculate the time-load demand and energy type scoring matrix to obtain several different categories, and then cutting the scoring matrix along the time-load demand dimension to obtain several time-load demand and energy type scoring matrices includes the following steps:

[0027] S331. Construct a sample feature matrix by taking each time-load demand and each energy type score in the time-load demand and energy type score matrix as a separate sample and sample feature;

[0028] S332. Set the number of cluster centers k, and randomly select k samples from the sample feature matrix as the initial cluster centers;

[0029] S333. Based on the initial cluster centers, the Euclidean distance calculation method is used to calculate the distance between two time-load demand samples, and the samples are assigned to the nearest category.

[0030] S334. After one round of clustering, find the new center of each category and define the coordinates of the new cluster center as the centroid of that category.

[0031] S335. Repeat S333 and S334. When the distance between the latest cluster center and the original cluster center is less than or equal to the preset distance threshold, the clustering is completed and k different categories are obtained.

[0032] S336. Segment the rating matrix along the time-load demand dimension, extract the rating corresponding to the sample of each category, and obtain k new rating matrices.

[0033] Preferably, the formula for calculating the predicted score is:

[0034]

[0035] In the formula, P(u,i) represents the predicted score of target time-load demand u on energy type i;

[0036] Sim(u,v) represents the similarity between the target time-load demand u and the nearest neighbor time-load demand v;

[0037] R(v,i) represents the actual score of the nearest-neighbor time-load demand v for energy type i.

[0038] Preferably, the step of determining the optimal energy dispatch scheme from the energy dispatch scheme set using an improved Bayesian optimization algorithm based on an immune mechanism, based on the power plant's power generation capacity, energy storage capacity, and grid load demand, includes the following steps:

[0039] S41. Obtain data on the power generation capacity, energy storage capacity, and grid load demand of the power plant, encode them, and create an initial set of energy dispatch schemes;

[0040] S42. Set a fitness function based on the power plant's power generation cost, environmental impact, grid load matching degree, grid demand satisfaction degree, and energy consumption.

[0041] S43. By analyzing the initial set of energy scheduling schemes, a Bayesian network is established to predict the fitness of new energy scheduling schemes.

[0042] S44. Calculate the conditional probability of each node in the Bayesian network using the maximum likelihood estimation algorithm combined with the energy scheduling scheme set, and use the conditional probability of the node as the parameter of the Bayesian network.

[0043] S45. Sample the Bayesian network based on its conditional probabilities to generate new energy scheduling schemes.

[0044] S46. Select the energy scheduling scheme individual with the highest fitness value to make a vaccine, vaccinate the newly generated energy scheduling scheme individuals, and select the next generation energy scheduling scheme set according to the fitness of the energy scheduling scheme individuals.

[0045] S47. Determine whether the number of iterations has reached the maximum number of iterations or whether the fitness of the new energy scheduling scheme individual has reached the preset threshold. If so, output the current energy scheduling scheme as the best energy scheduling scheme. Otherwise, return to S42 and continue iterating.

[0046] Preferably, the fitness function is calculated using the following formula:

[0047] y=ω1C1+ω2C2+ω3C3+ω4C4-ω5C5

[0048] ω1+ω2+ω3+ω4+ω5=1;

[0049] In the formula, y represents the fitness value, C1 represents the standardized carbon dioxide emissions, ω1 represents the weight of the standardized carbon dioxide emissions, C2 represents the standardized generation cost, ω2 represents the weight of the standardized generation cost, C3 represents the standardized grid load matching degree, ω3 represents the weight of the standardized grid load matching degree, C4 represents the standardized grid demand satisfaction degree, ω4 represents the weight of the standardized grid demand satisfaction degree, C5 represents the standardized energy consumption, and ω5 represents the weight of the standardized energy consumption.

[0050] Preferably, the process of selecting the energy scheduling scheme individual with the highest fitness value to make a vaccine, inoculating the newly generated energy scheduling scheme individuals, and selecting the next generation of energy scheduling schemes based on the fitness of the energy scheduling scheme individuals includes the following steps:

[0051] S461. Select the energy scheduling scheme individual with the highest fitness value, and randomly select several characteristic gene loci from the energy scheduling scheme individual. Use the information of the extracted characteristic gene loci to make a vaccine.

[0052] S462. Several individuals with energy scheduling schemes are randomly selected based on the vaccination probability and vaccinated. The information on the characteristic gene loci of the selected individuals with energy scheduling schemes is mutated according to the information of the vaccine.

[0053] S463. Test the energy scheduling scheme individuals that have been vaccinated. If their affinity is less than that of the parent energy scheduling scheme individuals, then the energy scheduling scheme individuals are replaced by the parent energy scheduling scheme individuals. Conversely, if the affinity of the energy scheduling scheme individuals after vaccination is greater than that of the parent energy scheduling scheme individuals, then the energy scheduling scheme individuals replace the parent energy scheduling scheme individuals in the next generation of the population.

[0054] According to another aspect of the present invention, a multi-mode coordinated control system based on wind, solar and energy storage new energy power plants is provided. The system includes an operation data acquisition module, an information prediction module, an energy dispatch scheme recommendation module, an energy dispatch scheme determination module and a multi-mode coordinated control module.

[0055] The operation data acquisition module is used to acquire real-time operation data of wind power, photovoltaic power generation and energy storage systems through external protocol access.

[0056] The information prediction module is used to predict the power grid load and wind power and photovoltaic power generation in the future period by combining real-time operation data with weather data.

[0057] The energy scheduling scheme set recommendation module is used to recommend energy scheduling schemes based on prediction data using a collaborative recommendation algorithm, thereby obtaining an energy scheduling scheme set.

[0058] The energy dispatch scheme determination module is used to determine the optimal energy dispatch scheme from the energy dispatch scheme set based on the power plant's power generation capacity, energy storage capacity and grid load demand using an improved Bayesian optimization algorithm based on an immune mechanism.

[0059] The multi-mode coordinated control module is used to perform corresponding control operations on wind power, solar power and energy storage equipment according to the obtained optimal energy dispatch scheme, so as to realize the efficient coordinated operation of various energy sources.

[0060] Compared with existing technologies, this invention provides a multi-mode coordinated control method and system based on wind, solar, and energy storage power plants, which has the following beneficial effects:

[0061] (1) This invention can accurately predict the grid load and wind and photovoltaic power generation in the future based on real-time operation data of wind power, photovoltaic power generation and energy storage systems combined with weather data. Based on the prediction results, an energy dispatch scheme set can be obtained. The optimal energy dispatch scheme can be determined efficiently and quickly from the energy dispatch scheme set according to the power generation capacity, energy storage capacity and grid load demand of the power station. The optimal energy dispatch scheme can then be used to precisely control wind power, solar power and energy storage equipment, achieve efficient coordination between various energy sources, better meet the grid load demand and maximize the energy utilization efficiency.

[0062] (2) By using a collaborative recommendation algorithm to recommend a set of energy scheduling schemes based on the predicted data, a set of energy scheduling schemes corresponding to the target time or load demand can be recommended based on the similarity algorithm before determining the optimal energy scheduling scheme. This allows the optimal energy scheduling scheme to be determined by analyzing the recommended set of energy scheduling schemes. Since the schemes in the recommended set are already relatively good candidate solutions, the optimal energy scheduling scheme can be determined by searching within a smaller set. Compared with the traditional global search method, this invention can effectively reduce the search space, improve search efficiency, and find the optimal energy scheduling scheme faster, thereby achieving efficient coordinated control of wind, solar and energy storage power plants.

[0063] (3) Compared with traditional optimization algorithms, this invention can use an improved Bayesian optimization algorithm based on immune mechanism to determine the optimal energy dispatch scheme based on the power generation capacity, energy storage capacity and grid load demand of the power station. This can effectively reduce the amount of calculation, shorten the operation time, and find the optimal energy dispatch scheme more quickly. Furthermore, by comprehensively considering factors such as the power generation cost, environmental impact, grid load matching degree, grid demand satisfaction degree and energy consumption of the power station, a more optimized energy dispatch scheme under multiple objectives can be found. Then, the operation of the wind, solar and energy storage power station can be automatically controlled according to the determined optimal energy dispatch scheme, reducing manual intervention and achieving efficient and continuous operation. Attached Figure Description

[0064] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0065] Figure 1 This is a flowchart of a multi-mode coordinated control method for a wind, solar, and energy storage power station according to an embodiment of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] According to an embodiment of the present invention, a multi-mode coordinated control method and system based on wind, solar and energy storage power plants is provided.

[0068] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1As shown, according to an embodiment of the present invention, a multi-mode coordinated control method and system based on a wind-solar-storage new energy power station is provided. The method includes the following steps:

[0069] S1. Obtain real-time operation data of wind power, photovoltaic power generation and energy storage systems through external protocol access;

[0070] The real-time operational data includes:

[0071] Wind power data: Information such as wind turbine rotation speed, power generation, wind speed, and wind direction.

[0072] Photovoltaic power generation data: information such as the current, voltage, and power of the photovoltaic panels, as well as ambient temperature and light intensity.

[0073] Energy storage system data includes information such as the voltage, current, status (e.g., charging, discharging, standby), and remaining energy of the energy storage device.

[0074] Other shared data: In addition to the specific operational data mentioned above, some shared data can also be obtained, such as information on the voltage, frequency, and load of the power grid;

[0075] S2. Use real-time operational data and weather data to predict the grid load and wind and solar power generation in the future period.

[0076] Power grid load forecasting: Common influencing parameters include historical load data, time (such as season, day of the week, time of day, etc.), weather factors (such as temperature, humidity, etc.), and special events (such as holidays, large-scale events, etc.). These all affect users' electricity consumption behavior, thereby affecting the power grid load.

[0077] Prediction of wind power generation: The main influencing factors are climatic conditions such as wind speed, wind direction, air density, and humidity, as well as the technical parameters and real-time operating status of the wind turbine.

[0078] Forecasting photovoltaic power generation: The main influencing factors are weather factors such as solar radiation intensity, temperature, sunshine duration, cloud cover, and rainfall, as well as the angle, orientation, and cleanliness of the photovoltaic panels, and the configuration of the photovoltaic array.

[0079] The method of using real-time operational data combined with weather data to predict the grid load and wind and solar power generation in the future includes the following steps:

[0080] S21. Obtain historical operating data of wind power generation, photovoltaic power generation, and energy storage systems from the database, as well as corresponding weather data;

[0081] S22. Construct a power grid load forecasting model using historical load data and corresponding time and weather data, and use the trained power grid load forecasting model in combination with real-time operation data and weather data to predict the power grid load in the future period.

[0082] S23. Construct a wind power generation prediction model based on historical wind power generation operation data, and use the trained wind power generation prediction model in combination with real-time operation data and weather data to predict wind power generation data in the future period.

[0083] S24. Construct a photovoltaic power generation prediction model using historical photovoltaic power generation operation data, and use the trained photovoltaic power generation prediction model in combination with real-time operation data and weather data to predict photovoltaic power generation data for a future period of time.

[0084] Specifically, there are various models for predicting grid load, wind power, and photovoltaic power generation; different models can be selected depending on the specific circumstances. Below are some commonly used models:

[0085] Time series models, such as the Autoregressive Moving Average (ARIMA) model and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model, are primarily used to predict data with time correlation.

[0086] Regression models, such as linear regression, multiple linear regression, ridge regression, and Lasso regression, can be used to predict continuous numerical variables.

[0087] Machine learning models, such as Support Vector Machines (SVM), Random Forest, and Gradient Boosting Decision Trees (GBDT), can handle non-linear, high-dimensional data.

[0088] Deep learning models, such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and other neural networks, can handle complex, non-linear standard and non-standard problems.

[0089] Ensemble learning models, such as Bagging, Boosting, and Stacking, improve prediction accuracy by integrating multiple models together.

[0090] Optimization algorithm models, such as genetic algorithms and particle swarm optimization. These models are mainly used to solve optimization problems, but can also be used for prediction.

[0091] When selecting a model, factors such as data characteristics, problem complexity, and computational resource limitations need to be considered. Furthermore, model selection is not a one-time event; it requires continuous experimentation and optimization in practical applications.

[0092] S3. Use the collaborative recommendation algorithm to recommend energy scheduling schemes based on the prediction data to obtain a set of energy scheduling schemes;

[0093] The step of using a collaborative recommendation algorithm to recommend energy scheduling schemes based on predicted data to obtain a set of energy scheduling schemes includes the following steps:

[0094] S31. Acquire historical and forecast data and preprocess them. Historical data includes energy data, load demand data, and weather conditions. Forecast data includes grid load forecast data, wind power forecast data, and photovoltaic power forecast data. Clean these data, remove missing values, outliers, and noisy data, and perform data transformations such as normalization or standardization.

[0095] S32. In the energy dispatching scenario, "users" can be viewed as different time periods or different load demands, and "items" can be viewed as different energy types. Based on historical and forecast data, a user-item rating matrix is ​​constructed, where each element represents the effect or benefit of using a certain energy source under a certain time period or load demand. Specifically, a time-load demand and energy type rating matrix is ​​constructed based on the acquired historical and forecast data. The rows of this matrix can be different time periods or load demands, and the columns can be different energy types. Each element of the matrix represents the efficiency or satisfaction of using a certain energy source under a certain time period or load demand.

[0096] S33. Calculate the time-load demand and energy type rating matrix using a clustering algorithm to obtain several different categories, and then cut the rating matrix along the time-load demand dimension to obtain several time-load demand and energy type rating matrices. The purpose of this step is to find similar time-load demand patterns based on historical data for subsequent recommendations.

[0097] Specifically, the process of using a clustering algorithm to calculate the time-load demand and energy type rating matrix to obtain several different categories, and then segmenting the rating matrix along the time-load demand dimension to obtain several time-load demand and energy type rating matrices, includes the following steps:

[0098] S331. Construct a sample feature matrix by taking each time-load demand and each energy type score in the time-load demand and energy type score matrix as a separate sample and sample feature;

[0099] Specifically, the time-load demand and energy type rating matrix is ​​constructed as input data suitable for clustering algorithms. Each time-load demand can be regarded as a sample, and each energy type rating as a sample feature, thus constructing a sample feature matrix.

[0100] S332. Set the number of cluster centers k, and randomly select k samples from the sample feature matrix as the initial cluster centers;

[0101] S333. Based on the initial cluster centers, the Euclidean distance calculation method is used to calculate the distance between two time-load demand samples, and the samples are assigned to the nearest category.

[0102] S334. After one round of clustering, find the new center of each category and define the coordinates of the new cluster center as the centroid of that category.

[0103] S335. Repeat S333 and S334. When the distance between the latest cluster center and the original cluster center is less than or equal to the preset distance threshold, the clustering is completed and k different categories are obtained.

[0104] S336. Segment the rating matrix along the time-load demand dimension, extract the rating corresponding to the sample of each category, and obtain k new rating matrices.

[0105] S34. Using similarity metrics (such as cosine similarity, Pearson correlation coefficient, etc.), find the nearest time-load demand of the target time-load demand in each category based on the clustering results, and analyze to obtain the recommended energy type set for the time-load demand in that category; the purpose of this step is to find out which energy types have higher usage efficiency or satisfaction under similar circumstances.

[0106] S35. Based on the recommended energy types across all categories, sort the predicted scores and select a preset number of recommended energy types as the energy dispatch scheme set recommended by the predicted data, according to the sorting results from high to low.

[0107] Specifically, the formula for calculating the predicted score is as follows:

[0108]

[0109] In the formula, P(u,i) represents the predicted score of target time-load demand u on energy type i;

[0110] Sim(u,v) represents the similarity between the target time-load demand u and the nearest neighbor time-load demand v;

[0111] R(v,i) represents the actual score of the nearest-neighbor time-load demand v for energy type i.

[0112] S4. Based on the power generation capacity, energy storage capacity and grid load demand of the power plant, the optimal energy dispatch scheme is determined from the energy dispatch scheme set using an improved Bayesian optimization algorithm based on an immune mechanism.

[0113] The step of determining the optimal energy dispatch scheme from the energy dispatch scheme set using an improved Bayesian optimization algorithm based on an immune mechanism, based on the power plant's power generation capacity, energy storage capacity, and grid load demand, includes the following steps:

[0114] S41. Obtain data on the power generation capacity, energy storage capacity, and grid load demand of the power plant, encode them, and create an initial set of energy dispatch schemes;

[0115] S42. Set a fitness function based on the power plant's power generation cost, environmental impact, grid load matching degree, grid demand satisfaction degree, and energy consumption.

[0116] Specifically, the roles of each influencing factor in this fitness function are as follows:

[0117] Generation cost: This refers to the total cost required to implement a certain energy dispatch scheme, including fuel costs, maintenance costs, equipment depreciation costs, etc. The lower the generation cost, the better the economic efficiency of the energy dispatch scheme.

[0118] CO2 emissions: This refers to the amount of carbon dioxide emitted by implementing a particular energy dispatch scheme, used to measure the environmental friendliness of the scheme. The lower the CO2 emissions, the smaller the environmental impact of the energy dispatch scheme.

[0119] Grid load matching degree: This refers to the degree of matching between the actual load of the power grid and the load predicted in the energy dispatch scheme. The higher the matching degree, the more accurate the load prediction of the power grid by the energy dispatch scheme, and the better the stability of the power grid operation.

[0120] Grid demand satisfaction: This refers to the degree of matching between the actual power supply and grid demand. A higher demand satisfaction rate indicates that the energy dispatch scheme can better meet the grid's load demand.

[0121] Energy consumption: This refers to the total amount of energy required to implement a certain energy dispatch scheme. The lower the energy consumption, the higher the energy efficiency of the energy dispatch scheme, and the more energy-saving it is.

[0122] The fitness function is calculated using the following formula:

[0123] y=ω1C1+ω2C2+ω3C3+ω4C4-ω5C5

[0124] ω1+ω2+ω3+ω4+ω5=1;

[0125] In the formula, y represents the fitness value, C1 represents the standardized carbon dioxide emissions, ω1 represents the weight of the standardized carbon dioxide emissions, C2 represents the standardized generation cost, ω2 represents the weight of the standardized generation cost, C3 represents the standardized grid load matching degree, ω3 represents the weight of the standardized grid load matching degree, C4 represents the standardized grid demand satisfaction degree, ω4 represents the weight of the standardized grid demand satisfaction degree, C5 represents the standardized energy consumption, and ω5 represents the weight of the standardized energy consumption.

[0126] Wherein, standardized power generation cost = (power generation cost - minimum power generation cost) / (maximum power generation cost - minimum power generation cost);

[0127] Standardized CO2 emissions = (CO2 emissions - minimum CO2 emissions) / (maximum CO2 emissions - minimum CO2 emissions);

[0128] Standardized grid load matching degree = (grid load matching degree - minimum matching degree) / (maximum matching degree - minimum matching degree);

[0129] Standardized power grid demand satisfaction = (Actual power supply - Minimum power supply) / (Power grid demand - Minimum power supply);

[0130] Standardized energy consumption = (energy consumption - minimum energy consumption) / (maximum energy consumption - minimum energy consumption).

[0131] S43. By analyzing the initial set of energy scheduling schemes, a Bayesian network is established to predict the fitness of new energy scheduling schemes.

[0132] S44. Calculate the conditional probability of each node in the Bayesian network using the maximum likelihood estimation algorithm combined with an energy scheduling scheme set, and use the conditional probability of the nodes as parameters of the Bayesian network. Specifically, this includes:

[0133] Calculate conditional probabilities: Use the maximum likelihood estimation algorithm to calculate the conditional probability of each node. For a node with a parent node, calculate the conditional probability of that node given the parent node's state.

[0134] Specifically, if the parent node of a node A is B, then the conditional probability P(A|B) of A can be calculated by the following formula: P(A|B)=P(A,B) / P(B);

[0135] Here, P(A,B) is the probability that nodes A and B occur simultaneously, and P(B) is the probability that node B occurs. Both probabilities can be calculated using data from a statistical energy scheduling scheme set.

[0136] Determine the parameters: Finally, we use the calculated conditional probability of each node as the parameters of the Bayesian network;

[0137] S45. Sample the Bayesian network based on its conditional probabilities to generate new energy scheduling schemes.

[0138] S46. Select the energy scheduling scheme individual with the highest fitness value to make a vaccine, vaccinate the newly generated energy scheduling scheme individuals, and select the next generation energy scheduling scheme set according to the fitness of the energy scheduling scheme individuals.

[0139] Specifically, the process of selecting the energy scheduling scheme individual with the highest fitness value to make a vaccine, inoculating newly generated energy scheduling scheme individuals, and selecting the next generation of energy scheduling schemes based on the fitness of the energy scheduling scheme individuals includes the following steps:

[0140] S461. Select the energy scheduling scheme individual with the highest fitness value, and randomly select several characteristic gene loci (i.e. key information, such as specific energy ratio, scheduling time, etc.) from the energy scheduling scheme individual. Use the information of the extracted characteristic gene loci to make a vaccine.

[0141] S462. Several individuals with energy scheduling schemes are randomly selected based on the vaccination probability and vaccinated. The information on the characteristic gene loci of the selected individuals with energy scheduling schemes is mutated according to the information of the vaccine.

[0142] S463. Test the energy scheduling scheme individuals that have been vaccinated. If their affinity is less than that of the parent energy scheduling scheme individuals, then the energy scheduling scheme individuals are replaced by the parent energy scheduling scheme individuals. Conversely, if the affinity of the energy scheduling scheme individuals after vaccination is greater than that of the parent energy scheduling scheme individuals, then the energy scheduling scheme individuals replace the parent energy scheduling scheme individuals in the next generation of the population.

[0143] S47. Determine whether the number of iterations has reached the maximum number of iterations or whether the fitness of the new energy scheduling scheme individual has reached the preset threshold. If so, output the current energy scheduling scheme as the best energy scheduling scheme. Otherwise, return to S42 and continue iterating.

[0144] S5. Based on the obtained optimal energy dispatch scheme, corresponding control operations are performed on wind power, solar power, and energy storage equipment to achieve efficient collaborative operation of various energy sources.

[0145] The step of controlling wind power, solar power, and energy storage equipment according to the obtained optimal energy dispatch scheme is to achieve efficient synergistic operation of various energy sources, including:

[0146] Wind energy control operations: Adjust the operating status of wind turbines according to the optimal energy dispatch plan. For example, if the plan recommends increasing wind energy utilization, the wind turbine speed can be increased; if the plan recommends reducing wind energy utilization, the wind turbine speed can be reduced or the wind turbines can be partially shut down.

[0147] Solar energy control operation: Adjusting the operating status of the photovoltaic power generation system according to the optimal energy dispatch scheme. For example, if the scheme recommends increasing the utilization rate of solar energy, the operating status of the photovoltaic array can be optimized through maximum power point tracking (MPPT) technology; if the scheme recommends reducing the utilization rate of solar energy, the power generation can be reduced by changing the tilt angle of the photovoltaic array or partially shading the photovoltaic array.

[0148] Energy storage device control operation: Adjust the charging and discharging strategies of energy storage devices according to the optimal energy dispatch plan. For example, if the plan recommends that the energy storage device discharge to meet the grid load, the energy storage device can be controlled to discharge; if the plan recommends that the energy storage device charge to store excess wind or solar energy, the energy storage device can be controlled to charge.

[0149] Coordinated control: The control operations of wind power, solar power, and energy storage devices need to be carried out in a coordinated manner to ensure the overall operating efficiency and stability of the power plant. For example, when wind and solar power are abundant, they can be used simultaneously to generate electricity, and the energy storage devices can be controlled to charge. When wind and solar power are insufficient, wind, solar, and energy storage devices can be used simultaneously to discharge electricity to meet the grid load.

[0150] According to an embodiment of the present invention, a multi-mode coordinated control system based on wind, solar and energy storage new energy power plants is provided. The system includes an operation data acquisition module, an information prediction module, an energy dispatch scheme recommendation module, an energy dispatch scheme determination module and a multi-mode coordinated control module.

[0151] The operation data acquisition module is used to acquire real-time operation data of wind power, photovoltaic power generation and energy storage systems through external protocol access.

[0152] The information prediction module is used to predict the power grid load and wind power and photovoltaic power generation in the future period by combining real-time operation data with weather data.

[0153] The energy scheduling scheme set recommendation module is used to recommend energy scheduling schemes based on prediction data using a collaborative recommendation algorithm, thereby obtaining an energy scheduling scheme set.

[0154] The energy dispatch scheme determination module is used to determine the optimal energy dispatch scheme from the energy dispatch scheme set based on the power plant's power generation capacity, energy storage capacity and grid load demand using an improved Bayesian optimization algorithm based on an immune mechanism.

[0155] The multi-mode coordinated control module is used to perform corresponding control operations on wind power, solar power and energy storage equipment according to the obtained optimal energy dispatch scheme, so as to realize the efficient coordinated operation of various energy sources.

[0156] In summary, by utilizing the technical solutions described above, the grid load and wind and solar power generation status over a future period can be accurately predicted based on real-time operational data of wind power, solar power, and energy storage systems combined with weather data. Based on the prediction results, an energy dispatch scheme set can be obtained. This allows for the efficient and rapid determination of the optimal energy dispatch scheme from the set, considering the power plant's generation capacity, energy storage capacity, and grid load demand. Furthermore, the optimal energy dispatch scheme can be used to precisely control wind, solar, and energy storage equipment, achieving efficient coordination among various energy sources. This better meets grid load demands while maximizing energy utilization efficiency.

[0157] Furthermore, by utilizing a collaborative recommendation algorithm to recommend a set of energy scheduling schemes based on predicted data, a similarity algorithm can be used to recommend a set of energy scheduling schemes corresponding to the target time or load demand before determining the optimal energy scheduling scheme. This allows the subsequent determination of the optimal energy scheduling scheme to be obtained only from the recommended set of energy scheduling schemes. Since the schemes in the recommended set are already relatively excellent candidate solutions, the search for the optimal energy scheduling scheme can be conducted within a smaller set. Compared with the traditional global search method, this invention can effectively reduce the search space, improve search efficiency, and find the optimal energy scheduling scheme faster, thereby enabling efficient coordinated control of wind, solar, and energy storage power plants.

[0158] Furthermore, compared to traditional optimization algorithms, this invention can utilize an improved Bayesian optimization algorithm based on an immune mechanism to determine the optimal energy dispatch scheme based on the power plant's power generation capacity, energy storage capacity, and grid load demand. This effectively reduces computational load, shortens computation time, and finds the optimal energy dispatch scheme more quickly. By comprehensively considering factors such as the power plant's power generation cost, environmental impact, grid load matching degree, grid demand satisfaction degree, and energy consumption, a more optimized energy dispatch scheme under multiple objectives can be found. Subsequently, the operation of wind, solar, and energy storage power plants can be automatically controlled based on the determined optimal energy dispatch scheme, reducing manual intervention and achieving efficient and continuous operation.

[0159] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes the steps described in the above methods. The storage medium may be, for example, ROM / RAM, magnetic disk, optical disk, etc.

[0160] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A multi-mode coordinated control method based on a wind-solar-storage new energy power station, characterized in that, The method comprises the following steps: S1, obtaining real-time operation data of wind power, photovoltaic power generation and energy storage system through external protocol access; S2, predicting the power grid load and wind power, photovoltaic power generation in a future period of time respectively by using real-time operation data combined with weather data; S3, using a collaborative recommendation algorithm to recommend an energy scheduling scheme according to the prediction data, and obtaining an energy scheduling scheme set; S4, determining the best energy scheduling scheme from the energy scheduling scheme set according to the power generation capacity, energy storage capacity and power grid load demand of the power station by using an improved Bayesian optimization algorithm based on an immune mechanism; S5, performing corresponding control operations on wind energy, light energy and energy storage equipment according to the obtained best energy scheduling scheme, so as to realize efficient collaborative work of various energies; The method comprises the following steps: S31, obtaining historical data and prediction data and preprocessing, the historical data including energy data, load demand data and weather conditions, the prediction data including power grid load prediction data, wind power prediction data and photovoltaic power prediction data; S32, constructing a time-load demand and energy type scoring matrix according to the obtained historical data and prediction data; S33, using a clustering algorithm to calculate the time-load demand and energy type scoring matrix, obtaining several different categories, and cutting the scoring matrix in the time-load demand dimension to obtain several time-load demand and energy type scoring matrices; S34, using a similarity measurement method to find the neighbor time-load demand of the target time-load demand in each category according to the clustering result, and analyzing to obtain a recommended energy type set of the time-load demand in the category; S35, synthesizing the recommended energy types in all categories, sorting the predicted scores, and taking the preset number of recommended energy types as the energy scheduling scheme set recommended by the prediction data according to the sorting results from high to low; The calculation formula of the predicted score is: In the formula, P(u, i) represents the predicted score of the target time-load demand u to the energy type i; Sim(u, v) represents the similarity between the target time-load demand u and the neighbor time-load demand v; R(v, i) represents the actual score of the neighbor time-load demand v to the energy type i. 2.The multi-mode coordinated control method based on a wind-solar-storage new energy power station according to claim 1, characterized in that, The method comprises the following steps: S21, obtaining historical operation data of wind power generation, photovoltaic power generation and energy storage system and corresponding weather data in the database; S22, constructing a power grid load prediction model by using historical load data and corresponding time and weather data, and predicting the power grid load in a future period of time by using the trained power grid load prediction model; S23, constructing a wind power prediction model based on historical wind power operation data, and predicting the wind power data in a future period of time by using the trained wind power prediction model; S24, constructing a photovoltaic power generation prediction model by using historical photovoltaic power generation operation data, and predicting photovoltaic power generation data in a future period of time by using the trained photovoltaic power generation prediction model.

3. The multi-mode coordinated control method based on wind-solar-storage new energy power station according to claim 2, characterized in that, The power grid load prediction model, the wind power generation prediction model and the photovoltaic power generation prediction model are any one of a time series model, a regression model, a machine learning model, a deep learning model or an ensemble learning model. 4.The multi-mode coordinated control method based on a wind-solar-storage new energy power station of claim 1, characterized in that, The method for calculating the score matrix of time-load demand and energy type by using a clustering algorithm, obtaining a plurality of different categories, and cutting the score matrix in the time-load demand dimension to obtain a plurality of score matrices of time-load demand and energy type comprises the following steps: S331, constructing a sample feature matrix by taking the score of each time-load demand and each energy type in the score matrix of time-load demand and energy type as a separate sample and sample feature, respectively; S332, setting the number of clustering centers k, and randomly selecting k samples from the sample feature matrix as initial clustering centers; S333, calculating the distance between two time-load demand samples based on the initial clustering centers by using the Euclidean distance calculation method, and classifying the samples into the nearest category; S334, when a round of clustering is completed, a new center of each category is calculated, and the coordinates of the new cluster center are defined as the centroid of the category; S335, repeating S333 and S334, and when the distance between the latest clustering center and the original clustering center is less than or equal to a preset distance threshold, the clustering is completed, and k different categories are obtained; S336, cutting the score matrix in the time-load demand dimension, extracting the scores corresponding to the samples of each category, and obtaining k new score matrices.

5. The multi-mode coordinated control method based on wind-solar-storage new energy power station according to claim 1, characterized in that, The method for determining the optimal energy scheduling scheme from the energy scheduling scheme set based on the improved Bayesian optimization algorithm based on the immune mechanism according to the power generation capacity, energy storage capacity and power grid load demand of the power station comprises the following steps: S41, obtaining the data of the power generation capacity, energy storage capacity and power grid load demand of the power station, encoding and creating an initial energy scheduling scheme set; S42, setting an adaptability function based on the power generation cost, environmental impact, power grid load matching degree, power grid demand satisfaction degree and energy consumption of the power station; S43, analyzing the initial energy scheduling scheme set to establish a Bayesian network for predicting the adaptability of new energy scheduling schemes; S44, calculating the conditional probability of each node in the Bayesian network by using the maximum likelihood estimation algorithm combined with the energy scheduling scheme set, and taking the conditional probability of the node as the parameter of the Bayesian network; S45, sampling the Bayesian network according to the conditional probability of the Bayesian network to generate new energy scheduling scheme individuals; S46, selecting the energy scheduling scheme individual with the highest adaptability value to make a vaccine, inoculating the newly generated energy scheduling scheme individuals, and selecting the next generation of energy scheduling scheme set according to the adaptability of the energy scheduling scheme individuals. S47, judge whether the iteration number reaches the maximum iteration number or whether the fitness of the new energy scheduling scheme individual reaches the preset threshold value, if yes, output the current energy scheduling scheme as the optimal energy scheduling scheme, otherwise, return to S42 and continue iteration.

6. The multi-mode coordinated control method based on wind-solar-storage new energy power station according to claim 5, characterized in that, The calculation formula of the fitness function is: In the formula, y represents the fitness value, C1 represents the normalized carbon dioxide emission, ω1 represents the weight of the normalized carbon dioxide emission, C2 represents the normalized power generation cost, ω2 represents the weight of the normalized power generation cost, C3 represents the normalized power grid load matching degree, ω3 represents the weight of the normalized power grid load matching degree, C4 represents the normalized power grid demand satisfaction degree, ω4 represents the weight of the normalized power grid demand satisfaction degree, C5 represents the normalized energy consumption, and ω5 represents the weight of the normalized energy consumption.

7. The multi-mode coordinated control method based on wind-solar-storage new energy power station according to claim 5, characterized in that, The energy scheduling scheme individual with the highest fitness value is selected to make a vaccine, the newly generated energy scheduling scheme individual is inoculated, and the next generation of energy scheduling scheme set is obtained by selection according to the fitness of the energy scheduling scheme individual, including the following steps: S461, select the energy scheduling scheme individual with the highest fitness value, and randomly select a plurality of characteristic gene sites from the energy scheduling scheme individual, and make the information of the extracted characteristic gene sites into a vaccine; S462, a plurality of energy scheduling scheme individuals are randomly selected for vaccination by a vaccination probability, and the information on the characteristic gene sites in the selected energy scheduling scheme individuals is mutated according to the information of the vaccine; S463, detect the energy scheduling scheme individual after vaccination, if the affinity is less than the affinity of the parent energy scheduling scheme individual, the energy scheduling scheme individual is replaced by the parent energy scheduling scheme individual, otherwise, if the affinity of the energy scheduling scheme individual after vaccination is greater than the affinity of the parent energy scheduling scheme individual, the energy scheduling scheme individual replaces the parent energy scheduling scheme individual to enter the next generation population.

8. A multi-mode coordinated control system based on a wind-solar-storage new energy power station, used to implement the steps of the multi-mode coordinated control method based on a wind-solar-storage new energy power station in any of claims 1-7, characterized in that, The system comprises a running data acquisition module, an information prediction module, an energy scheduling scheme set recommendation module, an energy scheduling scheme determination module and a multi-mode coordinated control module. The running data acquisition module is configured to acquire real-time running data of wind power, photovoltaic power generation and energy storage system through external protocol access. The information prediction module is configured to predict the power grid load and the wind power and photovoltaic power generation in a future period of time respectively by using the real-time running data and weather data. The energy scheduling scheme set recommendation module is configured to recommend an energy scheduling scheme according to the predicted data by using a collaborative recommendation algorithm to obtain an energy scheduling scheme set. The energy scheduling scheme determination module is configured to determine an optimal energy scheduling scheme from the energy scheduling scheme set by using an improved Bayesian optimization algorithm based on an immune mechanism according to the power generation capacity, energy storage capacity and power grid load demand of the power station. The multi-mode coordinated control module is configured to control the wind energy, light energy and energy storage equipment according to the obtained optimal energy scheduling scheme, so as to realize efficient collaborative work of various energies.

Images