Energy charging and discharging control method and system based on integration of water-light-storage

Abstract

The present application provides an energy charge-discharge control method and system based on integrated water-light-storage, which relates to the technical field of charge-discharge control. The method includes: analyzing historical energy application logs in combination with a predetermined unit cycle to generate a historical energy application amount time series; obtaining the target energy demand of a target cycle; introducing a radiation loss correction function to perform loss analysis on solar energy output characteristic information to obtain a loss correction result, and obtaining a predicted energy output amount; determining whether the predicted energy output amount is greater than the target energy demand to obtain a determination result; and reading a predetermined charge-discharge strategy according to the determination result to perform charge-discharge control. By accurately predicting and comparing the predicted energy output amount and the target energy demand, the energy storage device is activated to perform charge-discharge control, ensuring the balance between energy supply and demand and optimizing energy utilization. The effect of activating the energy storage device to perform charge-discharge control according to the actual situation, ensuring the balance between energy supply and demand, and optimizing energy utilization is achieved.

Description

Technical Field

[0001] This application relates to the technical field of charge and discharge control, and particularly to an energy charge and discharge control method and system based on the integration of water, light, and energy storage. Background Art

[0002] With the continuous growth of global energy demand and the increasing emphasis on environmental protection, the effective utilization of renewable energy and energy management have become an important issue. As a clean and renewable energy source, the output of solar energy is affected by various factors, such as weather conditions, photovoltaic panels, and time. Therefore, accurately predicting solar energy output and grid energy demand and achieving the goal of energy charge and discharge control based on the integration of water, light, and energy storage are of great significance for optimizing energy utilization and reducing costs.

[0003] Energy prediction and control in the prior art are usually based on simple statistical models or empirical rules, lacking in-depth analysis of historical data and accurate prediction of future trends. To improve the accuracy and efficiency of energy prediction, a method that can combine historical data and real-time monitoring information is needed to dynamically adjust energy usage strategies. Summary of the Invention

[0004] The purpose of this application is to provide an energy charge and discharge control method and system based on the integration of water, light, and energy storage, so as to solve the technical problems that the existing traditional energy demand prediction methods may not be able to provide sufficiently accurate prediction results, resulting in low energy management efficiency. At the same time, due to the influence of various factors on solar energy output, it is impossible to quickly and accurately obtain the solar energy output prediction value. Further, without accurate prediction and real-time monitoring, energy charge and discharge control may not be able to achieve optimal operation control, ultimately resulting in low energy utilization efficiency.

[0005] In view of the above problems, this application provides an energy charge and discharge control method and system based on the integration of water, light, and energy storage.

[0006] In a first aspect, the present application provides an energy charge-discharge control method based on integrated water-light-storage. The method is implemented through an energy charge-discharge control system based on integrated water-light-storage. Among them, the energy charge-discharge control method based on integrated water-light-storage includes: analyzing historical energy application logs in combination with a predetermined unit cycle to generate a time series of historical energy application amounts; performing regression fitting analysis on the time series of historical energy application amounts to obtain a polynomial of historical energy application amounts, and predicting the target energy demand for the target cycle according to the polynomial of historical energy application amounts; a solar output monitoring device dynamically monitors solar output characteristic information based on a predetermined output factor dimension; introducing a radiation loss correction function to perform loss analysis on the solar output characteristic information to obtain a loss correction result, and analyzing the loss correction result to obtain a predicted energy output amount; determining whether the predicted energy output amount is greater than the target energy demand to obtain a determination result; reading a predetermined charge-discharge strategy according to the determination result, and activating an energy storage device to perform charge-discharge control according to the predetermined charge-discharge strategy.

[0007] In a second aspect, the present application further provides an energy charge-discharge control system based on integrated water-light-storage, which is used to execute the energy charge-discharge control method based on integrated water-light-storage as described in the first aspect. Among them, the energy charge-discharge control system based on integrated water-light-storage includes: a first generation module, which is used to analyze historical energy application logs in combination with a predetermined unit cycle to generate a time series of historical energy application amounts; a first obtaining module, which is used to perform regression fitting analysis on the time series of historical energy application amounts to obtain a polynomial of historical energy application amounts, and predict the target energy demand for the target cycle according to the polynomial of historical energy application amounts; a second obtaining module, which is used for a solar output monitoring device to dynamically monitor solar output characteristic information based on a predetermined output factor dimension; a third obtaining module, which is used to introduce a radiation loss correction function to perform loss analysis on the solar output characteristic information to obtain a loss correction result, and analyze the loss correction result to obtain a predicted energy output amount; a fourth obtaining module, which is used to determine whether the predicted energy output amount is greater than the target energy demand to obtain a determination result; a first execution module, which is used to read a predetermined charge-discharge strategy according to the determination result, and activate an energy storage device to perform charge-discharge control according to the predetermined charge-discharge strategy.

[0008] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] By analyzing the historical energy application logs in combination with a predetermined unit period, a time series of historical energy application amounts is generated; regression fitting analysis is performed on the time series of historical energy application amounts to obtain a polynomial of historical energy application amounts, and the target energy demand for the target period is predicted based on the polynomial of historical energy application amounts; a solar output monitoring device dynamically monitors solar output characteristic information based on a predetermined output factor dimension; a radiation loss correction function is introduced to perform loss analysis on the solar output characteristic information to obtain a loss correction result, and the loss correction result is analyzed to obtain a predicted energy output amount; it is determined whether the predicted energy output amount is greater than the target energy demand to obtain a determination result; according to the determination result, a predetermined charge-discharge strategy is read, and the energy storage device is activated for charge-discharge control according to the predetermined charge-discharge strategy. That is to say, by analyzing the historical energy application logs to generate time series data of energy application amounts, and then performing regression fitting analysis on these data to obtain a polynomial for predicting the energy demand for the target period. At the same time, the solar output monitoring device dynamically monitors solar output characteristic information and analyzes this information by introducing a radiation loss correction function to obtain the predicted energy output amount. Finally, by comparing the predicted energy output amount and the target energy demand, it is decided whether to activate the energy storage device for charge-discharge control, which depends on the predetermined charge-discharge strategy. Through in-depth analysis and regression fitting of the historical energy application logs, an accurate prediction of future energy demand is achieved. At the same time, by combining the radiation loss correction function to analyze the solar output characteristic information obtained by the solar output monitoring device, an accurate prediction of the solar output amount is obtained. Further, by comparing the predicted energy output amount and the target energy demand, the energy storage device is activated for charge-discharge control to ensure the balance between energy supply and demand and optimize energy utilization. The technical effect of activating the energy storage device for charge-discharge control according to the actual situation to ensure the balance between energy supply and demand and optimize energy utilization is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are given below. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easy to understand through the following description of the specification. Brief Description of the Drawings

[0011] To more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only exemplary. For those of ordinary skill in the art, other accompanying drawings can be obtained according to the provided drawings without creative efforts.

[0012] Figure 1 It is a schematic flowchart of the energy charge and discharge control method based on the integration of water, light and energy storage of the present application;

[0013] Figure 2 It is a schematic structural diagram of the energy charge and discharge control system based on the integration of water, light and energy storage of the present application.

[0014] Explanation of reference numerals:

[0015] The first generation module 11, the first obtaining module 12, the second obtaining module 13, the third obtaining module 14, the fourth obtaining module 15, the first execution module 16. Detailed implementation manners

[0016] By providing the energy charge and discharge control method and system based on the integration of water, light and energy storage, the present application solves the technical problems that the timeliness and accuracy of the existing energy demand and solar energy output prediction are not high, which further leads to the inability to achieve the optimal operation control of energy charge and discharge and is not conducive to the efficient utilization of energy. It achieves the technical effect of activating the energy storage device for charge and discharge control according to the actual situation, ensuring the balance between energy supply and demand, and optimizing the utilization of energy.

[0017] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application. Additionally, it should be noted that for the sake of description, only the parts related to the present application are shown in the accompanying drawings rather than all.

[0018] Embodiment 1. Please refer to the attached Figure 1 , the present application provides an energy charge and discharge control method based on the integration of water, light and energy storage. Among them, the energy charge and discharge control method based on the integration of water, light and energy storage is applied to the energy charge and discharge control system based on the integration of water, light and energy storage. The energy charge and discharge control method based on the integration of water, light and energy storage specifically includes the following steps:

[0019] Step 1: Analyze the historical energy application log in combination with a predetermined unit cycle to generate a historical energy application volume time series.

[0020] Specifically, by analyzing historical energy application logs in combination with a predetermined unit period to generate a time series of historical energy application amounts, the patterns and trends of energy consumption can be revealed, thus better understanding and managing energy use.

[0021] First, it is necessary to collect and organize historical energy application logs. These logs usually contain detailed information such as the time, location, and usage amount of energy use. Then, according to a predetermined unit period, such as every hour, day, or month, these logs are segmented. Next, the energy application amounts within each period are statistically analyzed to generate time series data of energy usage amounts. In addition, other factors, such as weather, season, or specific events, can be combined to further analyze the changes and trends of energy use. Specifically, first, a data collection system needs to be established to ensure accurate recording and storage of energy application logs. Then, data analysis tools, such as time series analysis or machine learning algorithms, are used to process and analyze the collected data. Next, according to the analysis results, a time series chart of energy application amounts is generated to visually display the patterns and trends of energy use. In addition, a prediction function can also be included to analyze future energy use based on historical data, thus providing a basis for energy management and optimization. Finally, through this analysis, the energy use situation can be understood more accurately, potential energy-saving opportunities can be discovered, and efficient use of energy can be achieved.

[0022] Step 2: Perform regression fitting analysis on the time series of the historical energy application amounts to obtain a polynomial of the historical energy application amounts, and predict the target energy demand for the target period according to the polynomial of the historical energy application amounts.

[0023] Specifically, performing regression fitting analysis on the time series of the historical energy application amounts to obtain a polynomial of the historical energy application amounts, and predicting the target energy demand for the target period according to this polynomial helps to improve the accuracy and efficiency of energy management.

[0024] First, collect and organize the time series data of the historical energy application amounts. Then, use regression analysis techniques to fit these data to discover the relationships and trends among the data. Next, according to the fitting results, a polynomial function is generated, which can describe the law of change of energy application amounts over time. In addition, other influencing factors, such as weather, season, or economic activities, can be considered to improve the accuracy of prediction. In the specific implementation process, first determine a suitable regression model, such as linear regression, polynomial regression, or time series analysis, etc. Then, use historical data to train and optimize the model parameters. Next, use the trained model to predict the energy demand for the target period. In addition, to improve the accuracy of prediction, the model can be evaluated and adjusted through methods such as cross-validation. By predicting future energy demand based on historical data, it provides an important reference for energy management and planning.

[0025] Step 3: The solar energy output monitoring device dynamically monitors based on a predetermined output factor dimension to obtain solar energy output characteristic information.

[0026] Specifically, the solar energy output monitoring device dynamically monitors based on a predetermined output factor dimension to obtain solar energy output characteristic information, which can understand the performance and efficiency of solar power generation in real time, thereby providing data support for improving the stability and reliability of solar power generation.

[0027] First of all, it is necessary to install solar energy output monitoring devices, which can dynamically collect the output data of solar panels according to predetermined output factor dimensions, such as time, location, environmental conditions, etc. Then, the collected data is transmitted to the data processing center through the data acquisition system. Next, data analysis algorithms are used to analyze the collected data to extract the characteristic information of solar energy output. In addition, weather forecasts and historical data can be combined to predict and optimize solar energy output. Through dynamic monitoring and analysis, the performance and efficiency of solar power generation can be understood in real time, potential optimization opportunities can be discovered, and the efficient utilization of solar power generation can be achieved.

[0028] Step 4: Introduce a radiation loss correction function to perform loss analysis on the solar energy output characteristic information to obtain a loss correction result, and analyze the loss correction result to obtain a predicted energy output.

[0029] Specifically, introducing a radiation loss correction function to perform loss analysis on the solar energy output characteristic information to obtain a loss correction result, and analyzing this loss correction result to obtain a predicted energy output. By identifying and quantifying the factors affecting the efficiency of solar panels, such as dust, shadows, temperature, etc., the actual output is corrected, so as to more accurately predict the future energy output.

[0030] First, collect the solar energy output characteristic information, including environmental factors such as light intensity, temperature, humidity, etc. Then, introduce a radiation loss correction function, which can estimate the energy loss caused by radiation loss according to these characteristic information. Next, use the correction function to analyze the solar energy output characteristic information to obtain a loss correction result. In addition, historical data and real-time monitoring data can be combined to improve the accuracy of the correction. Through this correction and analysis, the output of solar energy can be predicted more accurately, providing a scientific basis for the planning and scheduling of solar power generation.

[0031] Step 5: Judge whether the predicted energy output is greater than the target energy demand to obtain a judgment result.

[0032] Step 6: Read a predetermined charge and discharge strategy according to the judgment result, and activate the energy storage device for charge and discharge control according to the predetermined charge and discharge strategy.

[0033] Specifically, determine whether the predicted energy output is greater than the target energy demand to obtain a judgment result. According to the judgment result, read the predetermined charge-discharge strategy, and activate the energy storage device for charge-discharge control according to the predetermined charge-discharge strategy. By comparing the predicted solar energy output with the actual energy demand, decide whether it is necessary to use the energy storage device to balance the supply and demand, thereby improving the flexibility and efficiency of energy utilization.

[0034] First, predict the future energy output based on the collected solar energy output characteristic information and historical data. Then, compare the predicted energy output with the target energy demand. Next, according to the comparison result, judge whether it is necessary to activate the energy storage device for charge-discharge. In addition, other factors such as grid load and electricity price fluctuations can also be considered to optimize the charge-discharge strategy. Through this intelligent control method, the charge-discharge of the energy storage device can be automatically adjusted according to the energy supply and demand situation, realizing the efficient utilization and optimized management of energy.

[0035] Further, it includes: the historical energy application amount time series includes multiple cycles with energy application amount identifiers; draw a scatter plot of the historical energy application amount according to the multiple cycles with energy application amount identifiers; use the random sample consensus principle to obtain the first scatter point set in the scatter plot of the historical energy application amount; perform polynomial fitting on the first scatter point set to obtain a first fitting polynomial; read the predetermined test strategy, and perform test analysis on the first fitting curve of the first fitting polynomial based on the predetermined test strategy to obtain a first test result; when the first test result meets the predetermined test constraint, record the first fitting polynomial as the historical energy application amount polynomial.

[0036] Specifically, extract useful information from historical energy application data through data analysis and mathematical modeling to predict future energy demand. First, draw a scatter plot based on the historical energy application amount time series data, and each point represents the energy application amount of a cycle. Then, use the random sample consensus principle to select the first scatter point set from the scatter plot, and this set can represent the characteristics of the overall data. Next, perform polynomial fitting on the first scatter point set to obtain a first fitting polynomial, and this polynomial can describe the change trend of the energy application amount over time. In addition, to ensure the reliability of the fitting result, it is necessary to read the predetermined test strategy and perform test analysis on the fitting curve of the first fitting polynomial.

[0037] Specifically, it is first necessary to determine an appropriate random sampling method to ensure the representativeness and accuracy of the selected scatter point set. Then, select an appropriate polynomial fitting algorithm, such as the least squares method, to fit the scatter point set. Next, evaluate the fitting curve according to a predetermined test strategy, such as goodness-of-fit test or hypothesis test. In addition, it is also necessary to set test constraints, such as a goodness-of-fit threshold, to determine whether the fitting result meets the requirements. Through this kind of analysis and test, a reliable polynomial model can be extracted from historical energy application data for predicting future energy demands. This not only helps to improve the accuracy of energy demand prediction, but also helps to optimize energy management and scheduling, and promote the efficient utilization and sustainable development of energy.

[0038] Further, it includes: obtaining a first test scatter point set based on the predetermined test strategy, where the first test scatter point set refers to the set of scatter points after removing the first scatter point set from the historical energy application scatter plot; obtaining the first spatial distance from a first test scatter point to the first fitting curve, where the first test scatter point refers to any scatter point in the first test scatter point set; determining whether the first spatial distance is within a predetermined distance threshold; if it is within, adding the first test scatter point to the first inlier set, if not, adding the first test scatter point to the first outlier set; calculating the ratio of the number of scatter points in the first inlier set to the number of scatter points in the first outlier set, denoted as the first test ratio; and denoting the first test ratio as the first test result.

[0039] Specifically, the accuracy and reliability of the polynomial fitting model are evaluated through mathematical statistics and geometric analysis. First, according to the predetermined test strategy, the first scatter point set is removed from the historical energy application scatter plot to form a first test scatter point set. Then, calculate the spatial distance from each scatter point in the first test scatter point set to the first fitting curve. Next, according to the predetermined distance threshold, determine whether the spatial distance of each scatter point is within an acceptable range. In addition, according to the judgment result, the scatter points are divided into an inlier set and an outlier set, which respectively represent data points with good and bad fitting effects. Specifically, it is first necessary to determine an appropriate test strategy and distance threshold. Then, use the geometric analysis method to calculate the spatial distance from the scatter points to the fitting curve. Next, classify the scatter points according to the distance threshold. In addition, it is also necessary to calculate the number of scatter points in the inlier set and the outlier set to obtain the first test ratio. Through this kind of analysis and calculation, the first test result, that is, the ratio of the number of scatter points in the inlier set to the number of scatter points in the outlier set, can be obtained, and this ratio can be used as an index to evaluate the accuracy of the polynomial fitting model. This not only helps to evaluate the effectiveness of the model, but also helps to discover possible biases and errors in the model, thereby improving the accuracy and reliability of model prediction.

[0040] Furthermore, it includes: the solar energy output monitoring device includes a radiation monitoring component, a weather monitoring component, and a photovoltaic panel monitoring component; the solar radiation intensity record is dynamically monitored and obtained through the radiation monitoring component; the weather characteristic parameter record is dynamically monitored and obtained through the weather monitoring component, and the weather characteristic parameter record includes a cloud amount record, a temperature record, and a humidity record; the photovoltaic panel characteristic information is monitored and obtained through the photovoltaic panel monitoring component, and the photovoltaic panel characteristic information includes a photovoltaic conversion efficiency and a photovoltaic angle deviation record; the solar radiation intensity record, the cloud amount record, the temperature record, the humidity record, the photovoltaic conversion efficiency, and the photovoltaic angle deviation record constitute the solar energy output characteristic information.

[0041] Specifically, through real-time monitoring and multi-dimensional data collection, the performance and efficiency of the solar power generation system can be comprehensively understood. First, the radiation monitoring component is used to collect data on the solar radiation intensity, which is a key factor in solar energy output. Then, the weather monitoring component is used to obtain weather characteristic parameters such as cloud amount, temperature, and humidity, which will affect the actual output of the solar panels. Next, the photovoltaic panel monitoring component is used to collect the characteristic information of the photovoltaic panels, such as photovoltaic conversion efficiency and angle deviation, which are crucial for evaluating the working state and performance of the photovoltaic panels. In addition, these records are integrated together to form the solar energy output characteristic information, providing comprehensive data support for subsequent data analysis and optimization.

[0042] Specifically, first, it is necessary to ensure the accuracy and stability of the monitoring device to obtain high-quality monitoring data. Then, the data acquisition system is used to transmit the collected data to the data processing center. Next, data analysis algorithms are used to process the data and extract key features. In addition, it may also include data visualization tools to display the analysis results in the form of charts or reports, facilitating user understanding and decision-making. Through this comprehensive monitoring and data collection, the performance and efficiency of the solar power generation system can be understood in real time, potential optimization opportunities can be discovered, and the efficient utilization of solar power generation can be achieved.

[0043] Further, it includes: obtaining a first period, matching a first radiation intensity parameter of the first period in the solar radiation intensity record to obtain a first average radiation intensity; sequentially matching in the cloud cover record, the temperature record, and the humidity record to obtain a first cloud cover parameter, a first temperature parameter, and a first humidity parameter of the first period; sequentially calculating and obtaining a first average cloud cover of the first cloud cover parameter, a first average temperature of the first temperature parameter, and a first average humidity of the first humidity parameter; performing loss correction on the first average cloud cover, the first average temperature, the first average humidity, and the first average radiation intensity according to the radiation loss correction function to obtain a first target average radiation intensity; denoting the first target average radiation intensity as a first loss correction result of the first period, and forming the loss correction result based on the first loss correction result.

[0044] Specifically, through data analysis and correction, the accuracy of solar energy output prediction is improved. First, a first period is determined, and radiation intensity data of this period is extracted from the solar radiation intensity record, and a first average radiation intensity is calculated. Then, data of the first period is sequentially extracted from the cloud cover record, the temperature record, and the humidity record, and a first average cloud cover, a first average temperature, and a first average humidity are calculated. Next, these average parameters are corrected using the radiation loss correction function to estimate the radiation loss caused by environmental factors. In addition, the corrected first target average radiation intensity is used as the loss correction result of the first period, providing a more accurate data basis for subsequent energy output prediction. In the specific implementation process, the length and starting point of the period need to be determined first. Then, data analysis techniques, such as statistical methods, are used to calculate the average value of each parameter. Next, the radiation loss correction function is applied, which can estimate and correct the radiation loss based on factors such as cloud cover, temperature, humidity, and radiation intensity. In addition, the loss correction results of each period need to be recorded and stored for subsequent analysis and prediction. Through this correction and analysis, a more accurate solar energy output prediction can be obtained, thereby improving the efficiency and economy of solar power generation.

[0045] Further, it includes: The expression of the radiation loss correction function is as follows: ; where represents the first period under the first average radiation intensity of the loss correction result, that is, the first target average radiation intensity, represents the first period under the th mean value of weather factor characteristics, represents the th weather factor characteristic for the first average radiation intensity the loss impact coefficient, and .

[0046] Specifically, the expression of the radiation loss correction function is as follows: ; where represents the loss correction result of the first average radiation intensity under the first cycle , that is, the first target average radiation intensity, represents the mean value of the th weather factor feature under the first cycle , represents the loss impact coefficient of the th weather factor feature on the first average radiation intensity , and , that is, the three weather indicators of cloud cover, temperature and humidity.

[0047] Furthermore, it includes: obtaining a predetermined correlation coefficient, and combining the predetermined correlation coefficient with the first target average radiation intensity to obtain a first predicted energy output; summing the first predicted energy outputs to obtain the predicted energy output.

[0048] Specifically, through correlation analysis and mathematical modeling, the output of the solar power generation system is predicted, so as to provide a basis for energy management and optimization. First, a predetermined correlation coefficient is determined, which reflects the correlation between solar radiation intensity and energy output. Then, using this correlation coefficient and the first target average radiation intensity, the first predicted energy output is calculated through a mathematical model. Next, the first predicted energy output is added to the predicted output of other cycles to obtain the total predicted energy output. In addition, this method can also consider other factors, such as weather changes and seasonal impacts, to improve the accuracy of prediction. In the specific implementation process, first, the correlation coefficient needs to be determined according to historical data, which can be achieved through statistical analysis and data mining techniques. Then, using the correlation coefficient and the target average radiation intensity, the predicted energy output is calculated through mathematical formulas or models. Next, the predicted outputs of all cycles are summed to obtain the total predicted energy output. In addition, to improve the accuracy of prediction, the correlation coefficient can be continuously updated and optimized to adapt to environmental changes and system performance changes. Through this correlation analysis and prediction, the total output of the solar power generation system in the future period can be obtained, providing an important reference for energy management and scheduling.

[0049] Further, it includes: according to the judgment result, when the predicted energy output is greater than the target energy demand, activating the energy storage device to conduct charging control for pumped storage. According to the judgment result, when the predicted energy output is less than the target energy demand, activating the energy storage device to conduct discharging control for water release and power generation.

[0050] Specifically, by intelligently controlling the charging and discharging process of the energy storage device, the balance of energy supply and demand is achieved, and the flexibility and efficiency of energy utilization are improved. First, compare the predicted energy output and the target energy demand. Then, according to the comparison result, when the predicted output is greater than the demand, activate the energy storage device for charging to store the excess energy. Next, when the predicted output is less than the demand, activate the energy storage device for discharging to release the stored energy to meet the demand. In the specific implementation process, first, an energy demand prediction model needs to be established to accurately predict the energy demand of the target period. Then, data analysis techniques, such as machine learning algorithms, are used to evaluate the prediction results. Next, according to the evaluation results, appropriate charging and discharging strategies are selected. In addition, an intelligent control system is also required to automatically control the charging and discharging process of the energy storage device according to the selected strategy. Through this intelligent control method, the charging and discharging of the energy storage device can be automatically adjusted according to the energy supply and demand situation, realizing the efficient utilization and optimized management of energy.

[0051] In summary, the energy charging and discharging control method based on integrated water-light-storage provided by this application has the following technical effects:

[0052] By analyzing the historical energy application logs in combination with a predetermined unit cycle, a time series of historical energy application amounts is generated; regression fitting analysis is performed on the time series of historical energy application amounts to obtain a polynomial of historical energy application amounts, and the target energy demand for the target cycle is predicted based on the polynomial of historical energy application amounts; a solar output monitoring device dynamically monitors solar output characteristic information based on a predetermined output factor dimension; a radiation loss correction function is introduced to perform loss analysis on the solar output characteristic information to obtain a loss correction result, and the loss correction result is analyzed to obtain a predicted energy output amount; it is judged whether the predicted energy output amount is greater than the target energy demand to obtain a judgment result; a predetermined charge-discharge strategy is read according to the judgment result, and a energy storage device is activated according to the predetermined charge-discharge strategy to perform charge-discharge control. That is, by analyzing the historical energy application logs to generate time series data of energy application amounts, and then performing regression fitting analysis on these data to obtain a polynomial for predicting the energy demand of the target cycle. At the same time, a solar output monitoring device dynamically monitors solar output characteristic information and analyzes this information by introducing a radiation loss correction function to obtain a predicted energy output amount. Finally, by comparing the predicted energy output amount and the target energy demand, it is decided whether to activate the energy storage device for charge-discharge control, which depends on the predetermined charge-discharge strategy. Through in-depth analysis and regression fitting of the historical energy application logs, an accurate prediction of future energy demand is achieved. At the same time, by combining a radiation loss correction function to analyze the solar output characteristic information obtained by the solar output monitoring device, an accurate prediction of the solar output amount is obtained. Further, by comparing the predicted energy output amount and the target energy demand, the energy storage device is activated for charge-discharge control to ensure the balance between energy supply and demand and optimize energy utilization. The technical effect of activating the energy storage device for charge-discharge control according to the actual situation, ensuring the balance between energy supply and demand, and optimizing energy utilization is achieved.

[0053] Embodiment 2. Based on the same inventive concept as the energy charge-discharge control method based on integrated water-light-energy storage in the foregoing embodiment, the present application further provides an energy charge-discharge control system based on integrated water-light-energy storage. Please refer to the attached Figure 2 , the energy charge-discharge control system based on integrated water-light-energy storage includes:

[0054] The first generation module 11 is configured to analyze the historical energy application logs in combination with a predetermined unit cycle to generate a time series of historical energy application amounts; the first obtaining module 12 is configured to perform regression fitting analysis on the time series of historical energy application amounts to obtain a polynomial of historical energy application amounts, and predict the target energy demand for the target cycle according to the polynomial of historical energy application amounts; the second obtaining module 13 is configured to obtain solar output characteristic information by the solar output monitoring device based on a predetermined output factor dimension; the third obtaining module 14 is configured to introduce a radiation loss correction function to perform loss analysis on the solar output characteristic information to obtain a loss correction result, and analyze the loss correction result to obtain a predicted energy output amount; the fourth obtaining module 15 is configured to determine whether the predicted energy output amount is greater than the target energy demand to obtain a determination result; the first execution module 16 is configured to read a predetermined charge and discharge strategy according to the determination result, and activate the energy storage device for charge and discharge control according to the predetermined charge and discharge strategy.

[0055] Further, the first obtaining module 12 in the energy charge and discharge control system based on integrated water-light-storage is further configured to: the time series of historical energy application amounts includes multiple cycles with energy application amount identifiers; draw a scatter plot of historical energy application amounts according to the multiple cycles with energy application amount identifiers; use the random sample consensus principle to obtain a first scatter point set in the scatter plot of historical energy application amounts; perform polynomial fitting on the first scatter point set to obtain a first fitting polynomial; read a predetermined test strategy, and perform test analysis on the first fitting curve of the first fitting polynomial based on the predetermined test strategy to obtain a first test result; when the first test result meets a predetermined test constraint, record the first fitting polynomial as the polynomial of historical energy application amounts.

[0056] Further, the first obtaining module 12 in the energy charge and discharge control system based on integrated water-light-storage is further configured to: obtain a first test scatter point set based on the predetermined test strategy, where the first test scatter point set refers to a set of scatter points after removing the first scatter point set from the scatter plot of historical energy application amounts; obtain a first spatial distance from a first test scatter point to the first fitting curve, where the first test scatter point refers to any scatter point in the first test scatter point set; determine whether the first spatial distance is within a predetermined distance threshold; if it is within, add the first test scatter point to a first inlier set, if it is not within, add the first test scatter point to a first outlier set; calculate a ratio of the number of scatter points in the first inlier set to the number of scatter points in the first outlier set, denoted as a first test ratio; record the first test ratio as the first test result.

[0057] Further, the second obtaining module 13 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: The solar energy output monitoring device includes a radiation monitoring component, a weather monitoring component, and a photovoltaic panel monitoring component; dynamically monitor and obtain a solar radiation intensity record through the radiation monitoring component; dynamically monitor and obtain a weather characteristic parameter record through the weather monitoring component, where the weather characteristic parameter record includes a cloud amount record, a temperature record, and a humidity record; monitor and obtain photovoltaic panel characteristic information through the photovoltaic panel monitoring component, where the photovoltaic panel characteristic information includes a photovoltaic conversion efficiency and a photovoltaic angle deviation record; the solar radiation intensity record, the cloud amount record, the temperature record, the humidity record, the photovoltaic conversion efficiency, and the photovoltaic angle deviation record constitute the solar energy output characteristic information.

[0058] Further, the third obtaining module 14 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: obtain a first period, and match a first radiation intensity parameter of the first period in the solar radiation intensity record to obtain a first average radiation intensity; sequentially match a first cloud amount parameter, a first temperature parameter, and a first humidity parameter of the first period in the cloud amount record, the temperature record, and the humidity record; sequentially calculate and obtain a first average cloud amount of the first cloud amount parameter, a first average temperature of the first temperature parameter, and a first average humidity of the first humidity parameter; perform loss correction on the first average cloud amount, the first average temperature, the first average humidity, and the first average radiation intensity according to the radiation loss correction function to obtain a first target average radiation intensity; record the first target average radiation intensity as the first loss correction result of the first period, and form the loss correction result based on the first loss correction result.

[0059] Further, the third obtaining module 14 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: The expression of the radiation loss correction function is as follows: ; where represents the first average radiation intensity under the first period of the loss correction result, that is, the first target average radiation intensity, represents the mean of the th weather factor characteristic under the first period, represents the th weather factor characteristic on the first average radiation intensity of the loss impact coefficient, and

[0060] Further, the third obtaining module 14 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: obtain a predetermined correlation coefficient, and combine the predetermined correlation coefficient with the first target average radiation intensity to obtain a first predicted energy output; sum the first predicted energy outputs to obtain the predicted energy output.

[0061] Further, the first execution module 16 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: according to the judgment result, when the predicted energy output is greater than the target energy demand, activate the energy storage device to perform charging control for pumped-storage power generation.

[0062] Further, the first execution module 16 in the energy charging and discharging control system based on integrated water-light-storage is further configured to: according to the judgment result, when the predicted energy output is less than the target energy demand, activate the energy storage device to perform discharging control for water release and power generation.

[0063] The various embodiments in this specification are described in a progressive manner, and the key point of each embodiment is the difference from other embodiments. The Figure 1 energy charging and discharging control method and specific examples in the first embodiment are equally applicable to the energy charging and discharging control system based on integrated water-light-storage in this embodiment. Through the detailed description of the energy charging and discharging control method based on integrated water-light-storage above, those skilled in the art can clearly know the energy charging and discharging control system based on integrated water-light-storage in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be elaborated here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0064] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0065] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is also intended to include these changes and modifications.

Claims

1. An energy charging and discharging control method based on water-photovoltaic-storage integration is characterized in that: include: Analyze historical energy application logs in combination with a predetermined unit period to generate a time series of historical energy application amounts; Performing regression fitting analysis on the historical energy application time series to obtain a historical energy application polynomial, and predicting a target energy demand for a target period based on the historical energy application polynomial; The solar energy output monitoring equipment dynamically monitors the solar energy output characteristic information based on the predetermined output factor dimensions; Introducing a radiation loss correction function to perform loss analysis on the solar energy output characteristic information to obtain a loss correction result, and analyzing the loss correction result to obtain a predicted energy output; Determine whether the predicted energy output is greater than the target energy demand, and obtain a determination result; Reading a predetermined charge and discharge strategy according to the judgment result, and activating the energy storage device to perform charge and discharge control according to the predetermined charge and discharge strategy; The method further comprises: The solar energy output monitoring equipment includes a radiation monitoring component, a weather monitoring component and a photovoltaic panel monitoring component; Dynamically monitor and obtain solar radiation intensity records through the radiation monitoring component; Dynamically monitor and obtain weather characteristic parameter records through the weather monitoring component, wherein the weather characteristic parameter records include cloud cover records, temperature records and humidity records; The photovoltaic panel characteristic information is obtained by monitoring the photovoltaic panel monitoring component, wherein the photovoltaic panel characteristic information includes photovoltaic conversion efficiency and photovoltaic angle deviation records; The solar radiation intensity record, the cloud cover record, the temperature record, the humidity record, the photovoltaic conversion efficiency and the photovoltaic angle deviation record constitute the solar energy output characteristic information; Acquire a first cycle, and match a first radiation intensity parameter of the first cycle in the solar radiation intensity record to obtain a first average radiation intensity; The cloud cover record, the temperature record and the humidity record are matched in sequence to obtain a first cloud cover parameter, a first temperature parameter and a first humidity parameter of the first period; sequentially calculating and acquiring a first average cloud amount of the first cloud amount parameter, a first average temperature of the first temperature parameter, and a first average humidity of the first humidity parameter; Perform loss correction on the first average cloud amount, the first average temperature, the first average humidity and the first average radiation intensity according to the radiation loss correction function to obtain a first target average radiation intensity; Recording the first target average radiation intensity as a first loss correction result of the first period, and forming the loss correction result based on the first loss correction result; The expression of the radiation loss correction function is as follows: ； in, Characterizing the First Cycle The first average radiation intensity under The loss correction result, that is, the average radiation intensity of the first target, Characterizing the First Cycle The next The mean of the weather factor characteristics, Characterizing the The weather factor characteristics have an impact on the first average radiation intensity The loss impact coefficient of ; Obtaining a predetermined correlation coefficient, and combining the predetermined correlation coefficient with the first target average radiation intensity to obtain a first predicted energy output; The first predicted energy output is added to obtain the predicted energy output.

2. According to claim 1, the energy charging and discharging control method based on water-photovoltaic-storage integration is characterized in that: include: The historical energy usage time series includes a plurality of periods with energy usage identifiers; Draw a scatter plot of historical energy usage according to the multiple periods with energy usage identifiers; Obtaining a first scatter point set in the historical energy application amount scatter diagram by using a random sampling consistency principle; Performing polynomial fitting on the first scattered point set to obtain a first fitting polynomial; Reading a predetermined inspection strategy, and performing inspection and analysis on a first fitting curve of the first fitting polynomial based on the predetermined inspection strategy to obtain a first inspection result; When the first inspection result satisfies a predetermined inspection constraint, the first fitting polynomial is recorded as the historical energy application amount polynomial.

3. According to claim 2, the energy charging and discharging control method based on water-photovoltaic-storage integration is characterized in that: include: Based on the predetermined inspection strategy, a first inspection scatter point set is obtained, wherein the first inspection scatter point set refers to a set of scatter points after the first scatter point set is removed from the historical energy application amount scatter point graph; Obtaining a first spatial distance from a first inspection scatter point to the first fitting curve, where the first inspection scatter point refers to any scatter point in the first inspection scatter point set; Determining whether the first spatial distance is within a predetermined distance threshold; If it is, add the first inspection scattered point to the first internal point set; if it is not, add the first inspection scattered point to the first external point set; Calculate the ratio of the number of scattered points in the first internal point set to the number of scattered points in the first external point set, and record it as a first test ratio; The first test ratio is recorded as the first test result.

4. According to claim 1, the energy charging and discharging control method based on water-photovoltaic-storage integration is characterized in that: include: According to the judgment result, when the predicted energy output is greater than the target energy demand, the energy storage device is activated to perform charging control of pumped storage power.

5. The energy charging and discharging control method based on water-photovoltaic-storage integration according to claim 1 is characterized in that: include: According to the judgment result, when the predicted energy output is less than the target energy demand, the energy storage device is activated to perform discharge control for releasing water and electricity.

6. Energy charging and discharging control system based on water-light-storage integration, characterized in that: The steps for implementing the energy charging and discharging control method based on water-photovoltaic storage integration as described in any one of claims 1 to 5, the energy charging and discharging control system based on water-photovoltaic storage integration comprises: A first generating module, the first generating module is used to analyze the historical energy application log in combination with a predetermined unit period to generate a historical energy application amount time series; A first obtaining module, wherein the first obtaining module is used to perform regression fitting analysis on the historical energy application amount time series to obtain a historical energy application amount polynomial, and predict a target energy demand amount for a target period according to the historical energy application amount polynomial; A second obtaining module, wherein the second obtaining module is used for the solar energy output monitoring device to dynamically monitor and obtain solar energy output characteristic information based on a predetermined output factor dimension; a third obtaining module, the third obtaining module is used to introduce a radiation loss correction function to perform loss analysis on the solar energy output characteristic information to obtain a loss correction result, and analyze the loss correction result to obtain a predicted energy output; A fourth obtaining module, the fourth obtaining module is used to determine whether the predicted energy output is greater than the target energy demand, and obtain a determination result; The first execution module is used to read a predetermined charging and discharging strategy according to the judgment result, and activate the energy storage device to perform charging and discharging control according to the predetermined charging and discharging strategy.

Images