New energy delivery section adjustment control system based on energy storage

Abstract

The invention discloses a new energy sending section adjustment control system based on energy storage, and relates to the technical field of energy storage control, and the system comprises the steps: collecting and obtaining a new energy power generation data set, and building a new energy power generation prediction network; determining new energy power generation prediction parameters; obtaining new energy power generation fluctuation parameters; acquiring power regulation demand parameters of the power grid; performing charging and discharging analysis on the energy storage unit based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and determining an energy storage charging and discharging strategy parameter scheme; and dynamically adjusting and controlling the energy storage charging and discharging strategy parameter scheme through the power operation feedback parameters. The technical problems that in the prior art, new energy power output fluctuation is difficult to respond in time, so that charging and discharging control of an energy storage system is not efficient and accurate enough, and the energy storage utilization efficiency is low are solved, and the technical effects of improving the energy storage utilization efficiency, the charging and discharging control accuracy and the power output stability are achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to energy storage control, and specifically to a new energy transmission section adjustment and control system based on energy storage. Background Art

[0002] With the continuous increase in global energy demand and the increasingly severe climate change problem, the demand for clean and renewable new energy technologies is constantly rising, and the proportion of new energy power generation is rapidly increasing. Among them, new energy such as wind energy and solar energy will not produce greenhouse gas emissions during the power generation process, and is an important development direction for the future power system to achieve low carbon and green. However, the significant characteristics of new energy power generation are volatility and instability. Especially in the scenario where meteorological factors such as wind energy and solar energy have a greater impact, the fluctuation of its power output has brought great challenges to the grid dispatching and the stable operation and balanced dispatching of the power system. How to effectively regulate the matching degree of these power generation resources with the grid load to ensure the stability of power output has become a key issue for the stable operation of the power system. The traditional power system design is usually based on the stability of the load, and the regulation measures mainly rely on the start and stop of conventional thermal power units, rotating standby and other means, but these traditional means have a relatively slow response speed. It is difficult to achieve rapid regulation when the output of new energy power generation changes rapidly, which easily leads to fluctuations in grid frequency and voltage, affecting the safety of the grid. In addition, the randomness and intermittency of new energy power generation also make it difficult to accurately predict power dispatching, thereby increasing the complexity of grid dispatching.

[0003] Therefore, at the current stage, there are technical problems in the new energy energy storage regulation and control related technologies that make it difficult to respond to fluctuations in new energy power output in a timely manner, resulting in inefficient and inaccurate charging and discharging control of the energy storage system and low energy storage utilization efficiency. Summary of the invention

[0004] The present application provides a new energy transmission section adjustment and control system based on energy storage, thereby solving the technical problems in the prior art that it is difficult to respond in a timely manner to fluctuations in new energy power output, resulting in insufficient efficiency and accuracy in the charging and discharging control of the energy storage system and low energy storage utilization efficiency, thereby achieving the technical effect of improving energy storage utilization efficiency, charging and discharging control accuracy and power output stability.

[0005] The present application provides a new energy transmission section regulation and control system based on energy storage, and the system includes: a power generation prediction network establishment module, which is used to collect and obtain a new energy power generation data set, and use a recurrent neural network to train and optimize the new energy power generation data set to establish a new energy power generation prediction network; a power generation prediction parameter determination module, which is used to perform power generation prediction for a preset time window based on the new energy power generation prediction network, and determine the new energy power generation prediction parameters; a power generation fluctuation parameter acquisition module, which is used to monitor and obtain new energy power generation output data and power grid load demand parameters through power sensing equipment, and perform power generation fluctuation evaluation based on the new energy power generation output data to obtain new energy power generation fluctuation parameters. a power regulation demand parameter acquisition module, used to compare and analyze the new energy power generation prediction parameters and the power grid load demand parameters to obtain the power grid power regulation demand parameters; an energy storage charging and discharging strategy parameter scheme determination module, used to analyze the charging and discharging of the energy storage unit based on the new energy power generation fluctuation parameters and the power grid power regulation demand parameters, and determine the energy storage charging and discharging strategy parameter scheme; a power operation feedback parameter output module, used to perform power regulation control monitoring on the new energy transmission section based on the energy storage charging and discharging strategy parameter scheme, output power operation feedback parameters, and dynamically adjust and control the energy storage charging and discharging strategy parameter scheme through the power operation feedback parameters.

[0006] In a possible implementation, the power generation prediction network establishment module also performs the following processing: obtaining a data preprocessing step chain, the data preprocessing step chain including data cleaning, data normalization and format standardization; performing data preprocessing on the new energy power generation data set based on the data preprocessing step chain to obtain a standard new energy power generation data set; arranging and sequence-dividing the standard new energy power generation data set according to time series information to obtain a new energy power generation sample set; defining structural parameter information of a recurrent neural network, performing cyclic supervised training on the new energy power generation sample set based on the structural parameter information of the recurrent neural network to generate a basic power generation prediction network; using a model optimizer to verify and optimize the basic power generation prediction network to establish the new energy power generation prediction network.

[0007] In a possible implementation, the power generation prediction network establishment module also performs the following processing: obtaining model performance evaluation indicators, using the model performance evaluation indicators to perform multi-dimensional performance evaluation on the basic power generation prediction network, and obtaining prediction network performance parameter information; selecting the model optimizer based on the prediction network performance parameter information; using the model optimizer to search and tune the model parameter information of the basic power generation prediction network to determine the prediction network structure parameters; and performing configuration optimization training on the basic power generation prediction network based on the prediction network structure parameters to obtain the new energy power generation prediction network.

[0008] In a possible implementation, the power regulation demand parameter acquisition module also performs the following processing: obtaining information on factors affecting power grid load demand, performing power grid load data mining and prediction training based on the information on power grid load demand influencing factors, and obtaining a power grid load demand impact prediction network; performing load impact prediction on the preset time window based on the power grid load demand impact prediction network, and outputting power grid load factor impact parameters; performing incremental profit and loss calculation on the power grid load demand parameters according to the power grid load factor impact parameters, and obtaining power grid load correction demand parameters; performing supply and demand balance comparison analysis on the new energy power generation prediction parameters and the power grid load correction demand parameters, and determining the power grid power regulation demand parameters.

[0009] In a possible implementation, the energy storage charging and discharging strategy parameter scheme determination module further performs the following processing: performing charging and discharging strategy analysis based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and constructing a charging and discharging strategy parameter solution space; obtaining characteristic parameter information of the energy storage unit, and using the characteristic parameter information as a constraint parameter to perform constraint division on the charging and discharging strategy parameter solution space, and obtaining a charging and discharging strategy parameter search database; constructing a charging and discharging evaluation index set, performing weight allocation fitting on the charging and discharging evaluation index set, and establishing a charging and discharging effect evaluation fitness function; and using the charging and discharging effect evaluation fitness function to perform global optimization in the charging and discharging strategy parameter search database to determine the energy storage charging and discharging strategy parameter scheme.

[0010] In a possible implementation, the energy storage charging and discharging strategy parameter scheme determination module further performs the following processing: performing charging and discharging strategy analysis based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and determining a charging and discharging strategy parameter selection threshold; randomly selecting multiple charging and discharging strategy parameters within the charging and discharging strategy parameter selection threshold, and evaluating the multiple charging and discharging strategy parameters through the charging and discharging effect evaluation fitness function to obtain multiple strategy parameter fitnesses; optimizing the multiple charging and discharging strategy parameters according to the multiple strategy parameter fitnesses to obtain multiple superior strategy parameters; performing cross-variation growth based on the multiple superior strategy parameters, and expanding the multiple charging and discharging strategy parameters through the grown strategy parameters to construct the charging and discharging strategy parameter solution space.

[0011] In a possible implementation, the energy storage charging and discharging strategy parameter scheme determination module further performs the following processing: performing parameter search in the charging and discharging strategy parameter search database according to the global search step to obtain a global charging and discharging strategy parameter set; evaluating the global charging and discharging strategy parameter set using the charging and discharging effect evaluation fitness function to obtain a global parameter fitness set; performing gradient ascent calculation optimization on the global parameter fitness set to obtain a search direction parameter set in the maximum gradient ascent direction, performing evaluation and comparison optimization based on the search direction parameter set to determine the energy storage charging and discharging strategy parameter scheme.

[0012] In a possible implementation, the energy storage charging and discharging strategy parameter scheme determination module also performs the following processing: performing power regulation effect optimization analysis on the power operation feedback parameters and setting parameter variation optimization rules; performing variation optimization on the energy storage charging and discharging strategy parameter scheme based on the parameter variation optimization rules to obtain a charging and discharging optimization strategy parameter scheme and dynamically adjusting and controlling the new energy transmission section.

[0013] The proposed application proposes a new energy transmission section regulation and control system based on energy storage, collects and acquires new energy power generation data sets, establishes a new energy power generation prediction network; determines new energy power generation prediction parameters; obtains new energy power generation fluctuation parameters; obtains power grid power regulation demand parameters; analyzes the energy storage unit charging and discharging based on the new energy power generation fluctuation parameters and the power grid power regulation demand parameters, determines the energy storage charging and discharging strategy parameter scheme; and dynamically regulates and controls the energy storage charging and discharging strategy parameter scheme through power operation feedback parameters. It solves the technical problem that it is difficult to respond to the fluctuation of new energy power output in a timely manner in the prior art, resulting in the inefficient and inaccurate charging and discharging control of the energy storage system and the low efficiency of energy storage utilization, and achieves the technical effect of improving the efficiency of energy storage utilization, the accuracy of charging and discharging control, and the stability of power output. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a new energy transmission section adjustment control system based on energy storage provided in an embodiment of the present application;

[0016] Figure 2A schematic diagram of the execution process of an energy storage charging and discharging strategy parameter scheme determination module in a new energy transmission section regulation control system based on energy storage provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: power generation prediction network establishing module 10, power generation prediction parameter determining module 20, power generation fluctuation parameter obtaining module 30, power regulation demand parameter obtaining module 40, energy storage charging and discharging strategy parameter scheme determining module 50, power operation feedback parameter output module 60. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The embodiment of the present application provides a new energy transmission section adjustment control system based on energy storage, such as Figure 1 As shown, the system comprises:

[0022] The power generation prediction network establishment module 10 is used to collect and acquire a new energy power generation data set, train and optimize the new energy power generation data set using a recurrent neural network, and establish a new energy power generation prediction network.

[0023] Preferably, a new energy power generation data set is collected and acquired, and a recurrent neural network (RNN) is used to analyze, learn and predict the new energy power generation data to establish a prediction model that can accurately predict future power generation conditions. Specifically, the new energy power generation data set includes historical power generation records, real-time power generation, weather data (such as light intensity, wind speed, temperature, etc.) and other external environmental data that affect power generation. The collected data may contain outliers or missing values, and the data is preprocessed (such as removing outliers, filling missing values, data normalization, etc.) to ensure data quality, and then the preprocessed data is input into the recurrent neural network for training to learn the fluctuation pattern and trend of new energy power generation, wherein the recurrent neural network ( RNN is a special neural network structure that is good at processing sequence data and can remember previous input information. It is very suitable for time series prediction. The basic unit includes hidden layer, input layer and output layer. By learning from past power generation data, RNN can identify the time dependency and regularity. The training process continuously adjusts the weight parameters of the model through the back propagation algorithm to minimize the prediction error, and finally establishes a new energy power generation prediction network to predict future new energy power generation. After inputting meteorological data or real-time power grid data, the new energy power generation prediction network can output power generation prediction data for a period of time in the future, including the changing trend and fluctuation range of power generation.

[0024] The power generation prediction parameter determination module 20 is used to perform power generation prediction for a preset time window based on the new energy power generation prediction network and determine the new energy power generation prediction parameters.

[0025] Preferably, the preset time window refers to a time period, such as one hour, one day or one week. The specific length can be set according to the demand frequency of the power grid and the fluctuation of new energy. The preset time window determines the time span of the prediction to understand the changes in new energy power generation within the time period. Specifically, the power generation data and meteorological conditions (such as light, wind speed, temperature, etc.) of the preset time window are input into the power generation prediction network. The new energy power generation prediction network predicts the power generation in the future time window based on these input data and outputs the power generation prediction results, which mainly include the power generation change curve, power generation fluctuation amplitude, power generation peak and valley values, etc. in the future time window, which can show the short-term fluctuation characteristics of new energy power generation, and then determine multiple new energy power generation prediction parameters, which may include but are not limited to predicted power generation, that is, the power generation value predicted by the model in the future time window, usually including the predicted power generation value at each time point; power generation volatility, the fluctuation amplitude or change rate of power generation during the prediction period, which measures the intensity of changes in new energy power generation; predicted peak and valley values, the maximum and minimum power generation in the prediction time window; predicted trend parameters, such as the trend of gradual increase, decrease or periodic fluctuation of power generation.

[0026] The power generation fluctuation parameter acquisition module 30 is used to monitor and acquire the new energy power generation output data and the grid load demand parameters through the power sensing device, and to evaluate the power generation fluctuation based on the new energy power generation output data to obtain the new energy power generation fluctuation parameters.

[0027] Preferably, the power sensing device is used to monitor and obtain the new energy power generation output data and the power grid load demand parameters in real time. Specifically, the power sensing device is a monitoring device installed on new energy power generation facilities (such as wind farms, photovoltaic power stations, etc.) and key nodes of the power grid, such as smart meters, load sensors, voltage and current sensors, etc. These power sensing devices are used to obtain the new energy power generation data in real time to reflect the current power generation status, such as power generation, power generation frequency, output power, etc., and the power grid load demand parameters, that is, the load demand value of the power grid at the current moment, in real time, reflecting the actual demand of the power grid for power supply; then the power generation output data of the new energy is analyzed for power generation volatility, and the stability and fluctuation of power generation are evaluated. Specifically, the power generation output within a period of time is analyzed. Time series analysis is performed on power data to observe the changing pattern of power generation, calculate the average fluctuation range, and use statistical methods to calculate the fluctuation rate of power generation, that is, the rate of power change per unit time. For example, if the power generation changes significantly in a short period of time, the fluctuation rate is higher. Finally, the intensity of fluctuation is quantified by calculating the standard deviation and variance of power output data. High standard deviation and variance values ​​indicate large power generation fluctuations, while low standard deviation and variance values ​​indicate relatively stable power generation. The fluctuation parameters of new energy power generation are then generated, which may include fluctuation intensity parameters, indicating the fluctuation intensity of power output; fluctuation frequency parameters, that is, the frequency of power generation fluctuations, such as high-frequency fluctuations or low-frequency fluctuations; and fluctuation trend parameters, reflecting the trend of fluctuations, such as whether fluctuations are gradually increasing or decreasing.

[0028] The power regulation demand parameter acquisition module 40 is used to compare and analyze the new energy power generation prediction parameters and the power grid load demand parameters to obtain the power grid power regulation demand parameters.

[0029] Preferably, the prediction parameters of renewable energy power generation are compared and analyzed with the parameters of grid load demand. Specifically, the difference between the predicted power supply of renewable energy power generation and the grid load demand in a specific time window is calculated. A positive difference indicates that the power generation is higher than the demand, and the energy storage system can be considered to be charged; a negative difference indicates that the power generation is lower than the demand, and the energy storage system needs to be discharged. Then, the change trend between the power generation prediction curve and the load demand curve is analyzed to determine the timeliness and continuity of the supply and demand difference, so as to determine when and at what power the energy storage system should be adjusted. In the case of large power generation fluctuations, the matching of the predicted power generation fluctuations and the grid load demand is analyzed. For example, when the load demand is at a peak and the power generation fluctuates greatly, The system may need more energy storage to smooth the difference between supply and demand; ultimately generate grid power regulation demand parameters to guide the energy storage system on how to adjust power output to ensure grid stability. Grid power regulation demand parameters may include charging and discharging demand, which refers to the power value that the energy storage system needs to charge or discharge in the case of an imbalance between supply and demand, to ensure that renewable energy power generation matches grid load demand; adjust frequency and duration, define the frequency and duration of charging and discharging required by the energy storage system, especially in the case of frequent power generation fluctuations, to ensure the continuity of power supply; backup power requirements, when the difference between power supply and demand is large, the energy storage system may be required to provide a certain amount of backup power to cope with sudden load fluctuations or power generation fluctuations.

[0030] The energy storage charging and discharging strategy parameter scheme determination module 50 is used to analyze the charging and discharging of the energy storage unit based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and determine the energy storage charging and discharging strategy parameter scheme.

[0031] Preferably, based on the fluctuation parameters of renewable energy power generation (such as power generation fluctuation rate, fluctuation intensity, etc.) and the power grid power regulation demand parameters (such as load demand changes, standby power demand, etc.), the demand for energy storage units is analyzed for charging and discharging. Specifically, the charging or discharging power required by the energy storage unit at a specific moment is determined to meet the supply and demand balance of power generation and load demand. According to the fluctuation frequency and grid regulation demand, it is determined how quickly the energy storage unit needs to respond to the charging and discharging operation. When the fluctuation frequency is high, a higher response speed is required. The current power level of the energy storage unit is evaluated to ensure that it will not be over-discharged or fully charged during the expected charging and discharging operation. Based on the analysis of electricity demand, formulate energy storage charging and discharging strategy parameter schemes, including setting the charging power or discharging power of the energy storage unit according to the difference between supply and demand and power generation fluctuations. For example, when the power generation is greater than the load demand, set a higher charging power to store the excess power; on the contrary, when the load demand is greater than the power generation, set the discharge power to fill the demand; set the charging and discharging duration of the energy storage unit, for example, when the peak load demand is expected to last for a period of time, the energy storage system sets a longer discharge time to stabilize the power supply; determine the charging and discharging frequency of the energy storage system, especially when the power generation fluctuates frequently, frequent charging and discharging can better adapt to fluctuating demand. In order to effectively respond to the sharp fluctuations in grid load or abnormal power generation in emergencies, the energy storage strategy must also include priority and backup strategies. The priority parameter can ensure that the critical load demand is met first when the power is insufficient, while the backup strategy ensures that the energy storage system has sufficient power reserves when responding to emergency needs.

[0032] The power operation feedback parameter output module 60 is used to perform power regulation control monitoring on the new energy transmission section based on the energy storage charging and discharging strategy parameter scheme, output power operation feedback parameters, and dynamically adjust and control the energy storage charging and discharging strategy parameter scheme through the power operation feedback parameters.

[0033] Preferably, the output section of the renewable energy power generation is controlled in real time through the energy storage charging and discharging strategy parameter scheme, the effect is continuously monitored, and the strategy is dynamically adjusted according to the monitoring feedback. Specifically, the energy storage unit is controlled to perform charging and discharging operations according to the energy storage charging and discharging strategy parameter scheme to adjust the power output of the renewable energy sending section. The system maintains a balance between the renewable energy output power and the grid load, thereby ensuring the stability of the power flow on the sending section. In the process of performing the charging and discharging operation, the output fluctuation of the power sending section is monitored in real time to ensure a relatively stable power output under the condition of power generation and load fluctuations. The actual charging and discharging effect of the energy storage system is monitored to confirm whether the charging or discharging is carried out as expected and whether the energy storage unit meets the regulation requirements. Then, power operation feedback parameters are generated to reflect the actual effect of the current energy storage regulation operation, including real-time power balance parameters. It reflects the supply and demand balance between the current renewable energy power generation and the grid load demand; the energy storage state parameters record the current energy storage system's power state, charging and discharging rate, remaining energy storage capacity, etc.; the power flow stability, such as output fluctuation amplitude and frequency, determines the stability of the current power flow; finally, the power operation feedback parameters are analyzed, and the energy storage charging and discharging strategy is dynamically adjusted according to the actual situation to optimize power regulation and control. For example, if the feedback parameters show that the current power flow fluctuates greatly, the energy storage discharge power is increased according to demand. If the load demand decreases or renewable energy power generation increases, the charging and discharging power is reduced; when the fluctuation frequency of power generation or load demand changes, the frequency and duration of charging and discharging are adjusted accordingly to better adapt to the actual fluctuations; when there are extreme fluctuations in load demand or power generation, the backup capacity of the energy storage system is dynamically adjusted to ensure that it can cope with sudden changes in power demand. Through real-time monitoring and dynamic adjustment, a closed-loop control process is formed, that is, the system continuously optimizes the energy storage charging and discharging strategy according to the actual monitoring results, so that the power output of the new energy transmission section is more stable, and the regulation effect of the energy storage system is gradually optimized, ensuring that energy storage can accurately and efficiently complete power regulation when responding to fluctuations in new energy power generation and changes in grid load demand, thereby ensuring the stability and reliability of the grid energy storage system.

[0034] According to an embodiment of the present invention, a new energy transmission section regulation and control system based on energy storage is used to solve the technical problem that it is difficult to respond to the fluctuation of new energy power output in time in the prior art, resulting in the insufficient efficiency and accuracy of the charge and discharge control of the energy storage system and the low efficiency of energy storage utilization, thereby achieving the technical effect of improving the efficiency of energy storage utilization, the accuracy of charge and discharge control and the stability of power output. A new energy transmission section regulation and control system based on energy storage includes: a power generation prediction network establishment module 10, a power generation prediction parameter determination module 20, a power generation fluctuation parameter acquisition module 30, a power regulation demand parameter acquisition module 40, an energy storage charge and discharge strategy parameter scheme determination module 50, and a power operation feedback parameter output module 60.

[0035] The specific configuration of the power generation prediction network establishment module 10 will be described in detail below. The power generation prediction network establishment module 10 may further include: obtaining a data preprocessing step chain, the data preprocessing step chain including data cleaning, data normalization and format standardization; performing data preprocessing on the new energy power generation data set based on the data preprocessing step chain to obtain a standard new energy power generation data set; arranging and dividing the standard new energy power generation data set according to the time series information to obtain a new energy power generation sample set; defining the structural parameter information of the recurrent neural network, performing cyclic supervised training on the new energy power generation sample set based on the structural parameter information of the recurrent neural network, and generating a basic power generation prediction network; using a model optimizer to verify and optimize the basic power generation prediction network, and establishing the new energy power generation prediction network.

[0036] Preferably, the original renewable energy power generation data set is preprocessed, including data cleaning, data normalization and data format standardization. The renewable energy power generation data set is preprocessed according to the data preprocessing step chain to obtain a clear, standardized and unified data format to form a standard renewable energy power generation data set. The standardized data set is then arranged in chronological order and divided into a series of input-output data pairs based on the chronological order to form a renewable energy power generation sample set. The time series information ensures that the model can identify time dependency during training, which helps to capture the dynamic change law of renewable energy power generation and construct effective input-output sample pairs. Then, a recurrent neural network (RNN) suitable for time series is established, including defining the structural parameters of the RNN, such as the number of hidden layers, the number of hidden units, the learning rate, etc. The renewable energy power generation sample set is input into RNN. The NN model undergoes cyclic supervised training. Through supervised training, the model predicts the power generation data and compares the predicted results with the real data. After calculating the error, it back-propagates and updates the model parameters. The weights are continuously adjusted to capture the timing rules of renewable energy power generation, thereby generating a basic power generation prediction network. Finally, the model optimizer is used to further verify and optimize the basic power generation prediction network, that is, to continuously adjust the model weights and structural parameters to reduce the prediction error and improve the prediction accuracy, such as regularization to avoid model overfitting and improve generalization ability. The early stopping mechanism stops training when the verification error no longer decreases to avoid overtraining. Hyperparameter tuning finds the optimal hyperparameter configuration through cross-validation to further improve the model accuracy and obtain the final renewable energy power generation prediction network, which can predict future power generation under given input conditions.

[0037] The specific configuration of the power generation prediction network establishment module 10 will be described in detail below. The power generation prediction network establishment module 10 may further include: obtaining a model performance evaluation index, using the model performance evaluation index to perform a multi-dimensional performance evaluation on the basic power generation prediction network, and obtaining prediction network performance parameter information; selecting the model optimizer according to the prediction network performance parameter information; using the model optimizer to search and tune the model parameter information of the basic power generation prediction network to determine the prediction network structure parameters; performing configuration optimization training on the basic power generation prediction network based on the prediction network structure parameters to obtain the new energy power generation prediction network.

[0038] Preferably, performance evaluation indicators for evaluating the basic power generation prediction network are selected and defined, such as mean square error, mean absolute error, root mean square error, etc., which are used to measure the prediction effect of the model in multiple dimensions. The above evaluation indicators are used to perform multi-dimensional performance evaluation on the basic power generation prediction network, examine the performance of the model from multiple angles, identify the accuracy, stability and applicability of the model in different scenarios, ensure that the basic model has a certain prediction ability, and obtain comprehensive performance parameter information about the current state of the model through multi-dimensional performance evaluation, that is, predictive network performance parameter information; select a model optimizer, such as random search or grid search, for hyperparameter adjustment based on the predictive network performance parameter information, and make tentative adjustments within a specific parameter range to find the optimal configuration; use The Bayesian theory dynamically adjusts the parameters to find the global optimal value of the model; then the model optimizer is used to search and tune the model parameters of the basic power generation prediction network to determine the prediction network structure parameters, including learning rate, number of hidden layers, activation function, regularization coefficient, etc. Finally, based on the obtained prediction network structure parameters, the basic power generation prediction network is reconfigured and optimization training is started. For example, the basic model is reconstructed using the newly optimized structural parameters to ensure that the model adapts to the updated parameter settings. The network is re-supervised and trained under the optimized configuration. The model further improves in prediction accuracy and stability, and finally generates a new energy power generation prediction network. The network performs well in multi-dimensional evaluation indicators and can predict new energy power generation more accurately and stably.

[0039] The specific configuration of the power regulation demand parameter acquisition module 40 will be described in detail below. The power regulation demand parameter acquisition module 40 may further include: acquiring information on factors affecting power grid load demand, performing power grid load data mining and prediction training based on the information on factors affecting power grid load demand, and obtaining a power grid load demand impact prediction network; performing load impact prediction on the preset time window based on the power grid load demand impact prediction network, and outputting power grid load factor impact parameters; performing incremental profit and loss calculation on the power grid load demand parameters according to the power grid load factor impact parameters, and obtaining power grid load correction demand parameters; performing supply and demand balance comparison analysis on the new energy power generation prediction parameters and the power grid load correction demand parameters, and determining the power grid power regulation demand parameters.

[0040] Preferably, information on the main factors affecting the load demand of the power grid is collected and identified, including climate (such as temperature, humidity, wind speed, precipitation, etc.), time factors (different seasons, weekdays or holidays have different load demands), social activities (population density, industrial production, commercial activities, etc.) and electricity price fluctuations. Climate change usually has a significant impact on electricity demand. For example, extremely high and low temperatures will increase the load of air conditioning and heating equipment. A load demand impact prediction model is constructed based on regression models, time series models (such as ARIMA or LSTM) or neural networks. According to the information on the factors affecting load demand, the historical power grid is analyzed. The load data is mined and analyzed, and the model is trained to obtain a grid load demand impact prediction network, which can predict the changing trend of the grid load and analyze the specific impact of various factors on the load demand; then based on the load demand impact prediction network, the load impact prediction is carried out within the preset time window, and the grid load factor impact parameters are output to quantify the expected effect of different influencing factors on the load demand within a specific time window in the future. For example, a temperature rise in the next week may lead to a 5% increase in load demand, weekday demand is 10% higher than weekends, and the inhibitory effect of rising electricity prices on load is expected to be around 3%.

[0041] Preferably, the incremental profit and loss calculation of the load demand of the power grid is performed according to the load factor influencing parameters to generate the power grid load correction demand parameters, wherein the incremental profit and loss calculation refers to adjusting the original load demand parameters to accurately reflect the effects of the predicted influencing factors. For example, if the incremental effect of temperature rise on the load demand is 5%, then the load demand is increased by 5% on the original demand; if the incremental effect of the arrival of holidays on the load demand is -10%, then the original demand is reduced by 10%; finally, the new energy power generation prediction parameters and the power grid load correction demand parameters are compared and analyzed for supply and demand balance to determine the differences between the processes, and then the power grid power regulation demand parameters are generated. Specifically, the calculation Correct the difference between load demand and power generation forecast value in order to clarify the regulation demand of energy storage system, compare the matching degree between load peak period and power generation peak period, if there is insufficient power supply during load peak, it is necessary to formulate a discharge strategy for energy storage system, if there is excess power generation, energy storage charging is carried out, the system dynamically updates the charging and discharging strategy of energy storage system according to load forecast changes and fluctuations in new energy power generation, so that the grid load and power generation are more matched; the grid power regulation demand parameters include the charging and discharging power, duration and response speed required by the energy storage system, which are used to guide the regulation of energy storage system, ensure the balance of power supply and demand, reduce the impact of load fluctuations on the grid, and achieve stable operation of the power system.

[0042] The specific configuration of the energy storage charging and discharging strategy parameter scheme determination module 50 will be described in detail below. Figure 2 As shown, the energy storage charging and discharging strategy parameter scheme determination module 50 may further include: performing charging and discharging strategy analysis based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and constructing a charging and discharging strategy parameter solution space; obtaining characteristic parameter information of the energy storage unit, and using the characteristic parameter information as a constraint parameter to constrain the charging and discharging strategy parameter solution space to obtain a charging and discharging strategy parameter search database; constructing a charging and discharging evaluation index set, performing weight distribution fitting on the charging and discharging evaluation index set, and establishing a charging and discharging effect evaluation fitness function; using the charging and discharging effect evaluation fitness function to perform global optimization in the charging and discharging strategy parameter search database to determine the energy storage charging and discharging strategy parameter scheme.

[0043] Preferably, based on the fluctuation parameters of renewable energy power generation (such as the fluctuation amplitude and frequency of power generation) and the power regulation demand parameters of the power grid (such as the specific demands of peak and valley load demands), the charging and discharging strategies of the energy storage system are analyzed to generate possible charging and discharging strategy parameters, including charging and discharging power, duration, frequency, etc. These parameter combinations form a charging and discharging strategy parameter solution space, that is, all possible charging and discharging strategy combinations; characteristic parameter information of the energy storage unit is obtained, such as energy storage capacity, maximum charging and discharging rate, charging and discharging efficiency, durability, temperature sensitivity, etc., reflecting the physical and operational limitations of the energy storage system, and then these characteristic parameters are used as constraints and applied to the charging and discharging strategy parameter solution space, and strategy combinations that do not meet the characteristic constraints of the energy storage unit are eliminated to avoid charging and discharging strategies that are actually infeasible. After constraint division, the remaining feasible parameter combinations form a charging and discharging strategy parameter search database; a database for evaluating the effectiveness of charging and discharging strategies is constructed. A set of evaluation indicators of the results is used to measure the advantages and disadvantages of the charging and discharging strategies. Common indicators include energy utilization rate, response speed, battery life, etc. By assigning weights to each evaluation indicator, a charging and discharging strategy that adapts to the current scenario needs is constructed, and then the weights of each indicator are fitted to form a charging and discharging effect evaluation fitness function. The influence of all evaluation indicators is integrated and their effects are quantified to evaluate how different charging and discharging strategies can optimize the performance of the energy storage system while meeting the supply and demand balance; finally, in the charging and discharging strategy parameter search database, the charging and discharging effect evaluation fitness function is used for global optimization, that is, by evaluating the fitness value of each feasible strategy, the best charging and discharging strategy combination is selected, such as using genetic algorithms, particle swarm optimization algorithms, etc. to ensure that the optimal solution is found in all possible parameter combinations, and finally the energy storage charging and discharging strategy parameter scheme is determined, which maximizes the efficiency and life of the energy storage system while meeting the power regulation needs.

[0044] The specific configuration of the energy storage charging and discharging strategy parameter scheme determination module 50 will be described in detail below. The energy storage charging and discharging strategy parameter scheme determination module 50 may further include: performing charging and discharging strategy analysis based on the new energy generation fluctuation parameter and the power grid power regulation demand parameter, and determining the charging and discharging strategy parameter selection threshold; randomly selecting multiple charging and discharging strategy parameters within the charging and discharging strategy parameter selection threshold, and evaluating the multiple charging and discharging strategy parameters through the charging and discharging effect evaluation fitness function to obtain multiple strategy parameter fitness; optimizing the multiple charging and discharging strategy parameters according to the multiple strategy parameter fitness to obtain multiple superior strategy parameters; performing cross-variation growth based on the multiple superior strategy parameters, and expanding the multiple charging and discharging strategy parameters through the grown strategy parameters to construct the charging and discharging strategy parameter solution space.

[0045] Preferably, the charging and discharging strategy is analyzed according to the fluctuation parameters of the new energy power generation and the power regulation demand parameters of the power grid, and the threshold for selecting the charging and discharging strategy parameters is determined, which is used to screen and limit the parameter range of the charging and discharging strategy, such as the upper and lower limits of the strategy parameters such as the charging power, the discharging power, and the duration. By setting the selection threshold, it is ensured that the charging and discharging strategy within the range can better meet the grid regulation demand. Within the determined threshold range, a plurality of charging and discharging strategy parameter combinations are randomly selected to represent different charging and discharging operation schemes, such as different charging and discharging powers, durations, etc. The randomly selected strategy parameters represent the initial candidate solutions in the charging and discharging strategy parameter space; the randomly generated charging and discharging strategy parameter combination is evaluated by the charging and discharging effect evaluation fitness function, that is, the fitness value of each strategy combination is calculated based on multiple evaluation indicators (such as energy efficiency, response speed, life impact, etc.). The higher the fitness of the strategy parameter, the better its performance in achieving the system goals. The fitness corresponding to the plurality of strategy parameter combinations is generated. According to the fitness value sorting, the charging and discharging strategy parameters are optimized, and multiple strategy parameters with the highest fitness values ​​are selected as the superior strategy parameters, representing the strategy combination that best meets the system requirements at the current stage. Then, based on the multiple superior strategy parameters selected, crossover and mutation operations are performed to expand the solution space. Specifically, the superior strategy parameters are crossovered to exchange some elements in two or more strategy parameter combinations to generate new strategy combinations. For example, the charging and discharging power and time of two charging and discharging schemes can be partially exchanged to form a new scheme. Under a certain probability, some values ​​in the superior strategy parameters are randomly fine-tuned or mutated to generate a variety of candidate strategy combinations to ensure the diversity of the parameter solution space and avoid the algorithm from falling into the local optimal solution. The new strategy parameter combination generated by crossover and mutation is added to the charging and discharging strategy parameter solution space to expand the size and diversity of the solution space, and the charging and discharging strategy parameter solution space is obtained, including the original candidate solution and the solution generated by its crossover and mutation, forming a richer charging and discharging strategy parameter library.

[0046] The specific configuration of the energy storage charging and discharging strategy parameter scheme determination module 50 will be described in detail below. The energy storage charging and discharging strategy parameter scheme determination module 50 may further include: performing parameter search in the charging and discharging strategy parameter search database according to the global search step length to obtain a global charging and discharging strategy parameter set; evaluating the global charging and discharging strategy parameter set using the charging and discharging effect evaluation fitness function to obtain a global parameter fitness set; performing gradient ascent calculation optimization on the global parameter fitness set to obtain a search direction parameter set in the maximum gradient ascent direction, performing evaluation comparison and optimization based on the search direction parameter set to determine the energy storage charging and discharging strategy parameter scheme.

[0047] Preferably, in the charge and discharge strategy parameter search database, a global search step is set to gradually scan all possible charge and discharge strategy parameter combinations. Specifically, the global search step refers to the parameter range at each search, and different parameter combinations are gradually explored in the database to generate a global charge and discharge strategy parameter set, which includes all possible charge and discharge strategy parameter combinations. The fitness function for charging and discharging effect evaluation is used to evaluate the global charge and discharge strategy fitness of the global charge and discharge strategy parameter set, that is, the fitness of each strategy combination is calculated according to system requirements and constraints (such as energy efficiency, response speed, life impact, etc.). The higher the fitness of the strategy combination, the better its performance in achieving system goals. The evaluation result forms a global parameter fitness set, including the fitness value corresponding to each parameter combination; then the global parameter fitness set is evaluated. Perform gradient ascent calculation, and determine the direction in which the fitness value rises fastest, i.e., the direction of maximum gradient ascent, by finding the maximum direction of fitness value change. Gradient ascent is an optimization method. By calculating the rate of change of fitness value in parameter space, the direction in which fitness is maximized is found. Selecting the parameter combination in this direction can effectively improve fitness and represent the optimal charging and discharging strategy combination. Based on the maximum gradient ascent direction, generate a search direction parameter set, which includes parameter combinations that meet the gradient ascent direction, and represents the preferred area in the charging and discharging strategy parameter space. Finally, evaluate and compare the parameters in the search direction parameter set to find the best solution, and select the parameter combination with the highest fitness value as the optimal energy storage charging and discharging strategy parameter solution, which can fully adapt to the fluctuation of new energy power generation and the changes in grid load demand, and provide efficient and stable charging and discharging operation guidance for the energy storage system.

[0048] The specific configuration of the energy storage charging and discharging strategy parameter scheme determination module 50 will be described in detail below. The energy storage charging and discharging strategy parameter scheme determination module 50 may further include: performing power regulation effect optimization analysis on the power operation feedback parameters, setting parameter variation optimization rules; performing variation optimization on the energy storage charging and discharging strategy parameter scheme based on the parameter variation optimization rules, obtaining a charging and discharging optimization strategy parameter scheme, and dynamically adjusting and controlling the new energy transmission section.

[0049] Preferably, by analyzing the real-time feedback data of power regulation, the charging and discharging strategy parameters are mutated and optimized, and the energy storage charging and discharging operations are dynamically adjusted to adapt to the real-time changes in power demand. Specifically, the regulation effect is continuously monitored and analyzed through the power operation feedback parameters, the shortcomings of the current charging and discharging strategy are identified, and the direction for optimization is found, for example, insufficient power output at certain times, over-discharge of the energy storage system, slow response time, etc.; based on the feedback analysis results, parameter variation optimization rules are defined. The variation optimization rules are a set of adjustment criteria for the control strategy, which are mainly used to generate new charging and discharging strategy parameter combinations to improve the regulation effect, including adjusting the step size, making small changes to parameters such as charging and discharging power, duration, and response time, and exploring better parameter configurations; parameter limiting, constraining the parameter range during the variation process to avoid excessive variation causing the energy storage system operation to deviate from the target; goal-oriented variation, according to the specific problems identified in the feedback parameters (such as Insufficient power output or slow response time), the relevant parameters are adjusted first; then, based on the variation optimization rules, the existing energy storage charging and discharging strategy parameter scheme is mutated and adjusted to generate a new parameter combination, such as a slight random adjustment of the parameter value; certain parameters are increased or decreased in a targeted manner, such as increasing the discharge power, reducing the charging duration, etc.; with a certain probability, the key parameters in the strategy are adjusted significantly to cope with sudden changes in load demand or power generation fluctuations; and then a charging and discharging optimization strategy parameter scheme is generated, which can more flexibly adapt to the real-time fluctuations of renewable energy power generation and changes in grid load demand, and provide a stable power regulation effect under conditions of large load fluctuations. Finally, based on the optimized charging and discharging strategy parameter scheme, the renewable energy transmission section is dynamically adjusted and controlled to maintain a smooth output of power flow, that is, the charging and discharging strategy is dynamically adjusted according to the latest load demand and power generation conditions to achieve stability and efficiency of the power system.

[0050] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0051] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A new energy transmission section adjustment control system based on energy storage, characterized in that: The system comprises: A power generation prediction network establishment module is used to collect and acquire a new energy power generation data set, train and optimize the new energy power generation data set using a recurrent neural network, and establish a new energy power generation prediction network; A power generation prediction parameter determination module, used to perform power generation prediction for a preset time window based on the new energy power generation prediction network and determine new energy power generation prediction parameters; A power generation fluctuation parameter acquisition module is used to obtain new energy power generation output data and power grid load demand parameters through power sensing equipment monitoring, and to evaluate power generation fluctuations based on the new energy power generation output data to obtain new energy power generation fluctuation parameters; A power regulation demand parameter acquisition module is used to compare and analyze the new energy power generation prediction parameters and the power grid load demand parameters to obtain the power grid power regulation demand parameters; An energy storage charging and discharging strategy parameter scheme determination module is used to analyze the charging and discharging of the energy storage unit based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and determine the energy storage charging and discharging strategy parameter scheme; The power operation feedback parameter output module is used to perform power regulation control and monitoring on the new energy transmission section based on the energy storage charging and discharging strategy parameter scheme, output power operation feedback parameters, and dynamically adjust and control the energy storage charging and discharging strategy parameter scheme through the power operation feedback parameters.

2. A new energy transmission section adjustment control system based on energy storage as claimed in claim 1, characterized in that: The establishment of a new energy generation prediction network includes: Obtaining a chain of data preprocessing steps, the chain of data preprocessing steps including data cleaning, data normalization, and format standardization; Performing data preprocessing on the new energy power generation data set based on the data preprocessing step chain to obtain a standard new energy power generation data set; Arranging and dividing the standard new energy power generation data set according to time series information to obtain a new energy power generation sample set; Defining structural parameter information of a recurrent neural network, performing cyclic supervised training on the new energy power generation sample set based on the structural parameter information of the recurrent neural network, and generating a basic power generation prediction network; The basic power generation prediction network is verified and optimized using a model optimizer to establish the new energy power generation prediction network.

3. A new energy transmission section adjustment control system based on energy storage as claimed in claim 2, characterized in that: The establishing of the new energy generation prediction network comprises: Obtaining a model performance evaluation index, using the model performance evaluation index to perform a multi-dimensional performance evaluation on the basic power generation prediction network, and obtaining prediction network performance parameter information; Selecting the model optimizer according to the predicted network performance parameter information; The model optimizer is used to search and optimize the model parameter information of the basic power generation prediction network to determine the prediction network structure parameters; The basic power generation prediction network is configured and optimized based on the prediction network structure parameters to obtain the new energy power generation prediction network.

4. A new energy transmission section adjustment control system based on energy storage as claimed in claim 1, characterized in that: The obtaining of power grid power regulation demand parameters includes: Obtaining information on factors influencing power grid load demand, performing power grid load data mining and prediction training based on the information on factors influencing power grid load demand, and obtaining a power grid load demand impact prediction network; Based on the power grid load demand impact prediction network, load impact prediction is performed on the preset time window, and power grid load factor impact parameters are output; Performing incremental profit and loss calculation on the grid load demand parameter according to the grid load factor influencing parameter to obtain a grid load correction demand parameter; A supply-demand balance comparison analysis is performed on the new energy power generation prediction parameters and the power grid load correction demand parameters to determine the power grid power regulation demand parameters.

5. A new energy transmission section adjustment control system based on energy storage as claimed in claim 1, characterized in that: The scheme for determining energy storage charging and discharging strategy parameters includes: Based on the new energy power generation fluctuation parameters and the power grid power regulation demand parameters, a charging and discharging strategy is analyzed to construct a charging and discharging strategy parameter solution space; Acquire characteristic parameter information of the energy storage unit, use the characteristic parameter information as a constraint parameter to constrain partitioning of the charge-discharge strategy parameter solution space, and obtain a charge-discharge strategy parameter search database; Constructing a charge and discharge evaluation index set, performing weight distribution fitting on the charge and discharge evaluation index set, and establishing a charge and discharge effect evaluation fitness function; The charging and discharging effect evaluation fitness function is used to perform global optimization in the charging and discharging strategy parameter search database to determine the energy storage charging and discharging strategy parameter scheme.

6. A new energy transmission section adjustment control system based on energy storage as claimed in claim 5, characterized in that: The construction of the charging and discharging strategy parameter solution space includes: Performing charge-discharge strategy analysis based on the new energy power generation fluctuation parameter and the power grid power regulation demand parameter, and determining a charge-discharge strategy parameter selection threshold; Randomly selecting multiple charge and discharge strategy parameters within the charge and discharge strategy parameter selection threshold, evaluating the multiple charge and discharge strategy parameters by using the charge and discharge effect evaluation fitness function, and obtaining multiple strategy parameter fitness; Optimizing the multiple charging and discharging strategy parameters according to the multiple strategy parameter adaptabilities to obtain multiple optimal strategy parameters; Based on the multiple superior strategy parameters, cross-mutation growth is performed, and the multiple charge and discharge strategy parameters are expanded through the grown strategy parameters to construct the charge and discharge strategy parameter solution space.

7. A new energy transmission section adjustment control system based on energy storage as claimed in claim 5, characterized in that: The method of determining the energy storage charging and discharging strategy parameter scheme includes: Performing parameter search in the charge-discharge strategy parameter search database according to the global search step length to obtain a global charge-discharge strategy parameter set; Using the charging and discharging effect evaluation fitness function to evaluate the global charging and discharging strategy parameter set, to obtain a global parameter fitness set; The global parameter fitness set is optimized by gradient ascent calculation to obtain a search direction parameter set in the maximum gradient ascent direction, and an evaluation comparison is performed based on the search direction parameter set to determine the energy storage charging and discharging strategy parameter scheme.

8. A new energy transmission section adjustment control system based on energy storage as claimed in claim 6, characterized in that: The dynamically adjusting and controlling the energy storage charging and discharging strategy parameter scheme by the power operation feedback parameter includes: Performing power regulation effect optimization analysis on the power operation feedback parameters and setting parameter variation optimization rules; Based on the parameter variation optimization rule, the energy storage charging and discharging strategy parameter scheme is variably optimized to obtain a charging and discharging optimization strategy parameter scheme, and the new energy transmission section is dynamically adjusted and controlled.

Images