Dynamic optimization scheduling algorithm for photovoltaic energy storage system

Abstract

The invention relates to the technical field of dynamic scheduling, in particular to a dynamic optimization scheduling algorithm for a photovoltaic energy storage system, which is characterized in that based on a working environment of the photovoltaic energy storage system, environment illumination intensity data is acquired in real time, average power generation under the same illumination intensity is extracted, and weather conditions in a future time period of a current region are received through weather forecast data; and predicting the generating capacity in a future period to obtain generating capacity evaluation information. According to the invention, by capturing the environment illumination condition in real time and combining the historical power generation data, the future power generation condition of the photovoltaic system is effectively predicted, the load change of the power grid is monitored in real time, and the influence brought by specific activities is considered, so that timely response can be made when the demand of the power grid fluctuates, and the supply and scheduling of electric energy are optimized; according to the invention, continuous monitoring and abnormity processing are carried out on the power generation equipment, and the abnormal condition of the equipment is handled by correcting the discharge capacity in real time, so that the risk in operation of the energy storage system is reduced, and solid technical support is provided for stable operation of a power grid.

Description

Technical Field

[0001] The present invention relates to the field of dynamic scheduling technology, and in particular to a dynamic optimization scheduling algorithm for a photovoltaic energy storage system. Background Art

[0002] The field of dynamic dispatch technology involves technologies used to manage and optimize various resources in real time or near real time. In the context of photovoltaic energy storage systems, dynamic dispatch focuses on maximizing the efficiency of power generation and storage facilities, especially in the field of renewable energy. The core content of this technology field involves the dynamic matching of energy demand and supply, including load balancing, energy storage management and grid stability. Dynamic dispatch technology not only supports forecast-based dispatch strategies, but also adapts to real-time data feedback to optimize system performance and improve energy utilization.

[0003] Among them, the photovoltaic energy storage system dynamic optimization scheduling algorithm uses methods and control strategies to adjust and optimize the working state of the photovoltaic system and energy storage equipment to achieve the optimal distribution and utilization of electricity. This algorithm covers the charge and discharge control of energy storage equipment, the output regulation of photovoltaic power generation, and the dynamic balance between the two, including the use of power scheduling strategies to accurately control photovoltaic output and energy storage status to meet the needs of the power grid and power supply safety requirements, ensuring that the photovoltaic energy storage system can maintain high efficiency and stable performance under various operating conditions.

[0004] Traditional dispatching algorithms lack sufficiently flexible prediction and adjustment mechanisms, and have obvious deficiencies in response speed and accuracy when dealing with environmental changes. For example, traditional dispatching algorithms are only executed based on preset modes or limited historical data, making it difficult to adapt to rapidly changing market demands and environmental conditions. In addition, traditional algorithms lack effective real-time monitoring and immediate response mechanisms when dealing with equipment anomalies. Once equipment failure occurs or the external environment changes drastically, the stability and security of traditional algorithms are difficult to guarantee, which will make it difficult to adjust the discharge efficiency in real time, leading to power supply interruptions, power supply instability, and even power grid accidents, bringing serious consequences to users and power supply safety. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a dynamic optimization scheduling algorithm for a photovoltaic energy storage system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a photovoltaic energy storage system dynamic optimization scheduling algorithm, comprising the following steps: S1: Based on the working environment of the photovoltaic energy storage system, the ambient light intensity data is collected in real time, the average power generation under the same light intensity is extracted, and the weather conditions in the future period of the current area are received through weather forecast data, the power generation in the future period is estimated, and the power generation evaluation information is obtained; S2: Based on the grid load data, extract the grid load records within the target time period, evaluate the grid load fluctuation within the target time period according to the load changes within the target time period, and evaluate the grid load fluctuation degree in the future time period according to the impact of activities in the future time period to obtain load fluctuation evaluation information; S3: Based on the power generation assessment information and the load fluctuation assessment information, the available power of the photovoltaic energy storage system in the future period is assessed according to the current storage capacity of the energy storage device, and the discharge power of the energy storage device is adjusted in combination with the real-time load demand and load fluctuation degree of the power grid to obtain real-time discharge adjustment information; S4: Based on the real-time discharge adjustment information, monitor the working status of the power generation equipment of the photovoltaic energy storage system in real time, analyze the deviation of the power generation equipment from the normal working condition, evaluate the abnormality of the photovoltaic power generation equipment, cut off the abnormal photovoltaic power generation equipment, and correct the real-time discharge amount of the energy storage equipment according to the expected power generation of the abnormal photovoltaic power generation equipment to obtain abnormal condition response information.

[0007] The present invention is improved in that the step of obtaining the power generation evaluation information is: S111: Based on the working environment of the photovoltaic energy storage system, the ambient light intensity data is collected in real time through the light intensity sensor, and the average power generation under the same light intensity is extracted through the power generation record of the photovoltaic energy storage system to obtain the power generation reference data; S112: Receive weather forecast data for the future period of the current area, analyze the expected light intensity change, and obtain future light intensity prediction data; S113: Based on the power generation reference data and the future light intensity prediction data, the formula: ; Calculate the power generation expected in the future period and obtain power generation assessment information; in, To estimate the power generation in the future, is the historical average power generation, is the predicted light intensity, is the historical average light intensity, and is the adjustment factor.

[0008] The present invention is improved in that the step of evaluating the power grid load fluctuation within the target time period is: S211: Based on the power grid load data, collect power grid load records within a target time period to obtain a load record data set; S212: Performing statistical analysis based on the load record data set, calculating the average value of the load in the target period, and obtaining load average value information; S213: Based on the load average value information and the load record data set, the formula: ; Calculate the standard deviation of the grid load, and evaluate the grid load fluctuation within the target period based on the size of the standard deviation of the grid load; in, is the number of data points, It is The load value of the data point, is the load average, Represents the standard deviation of the grid load.

[0009] The present invention is improved in that the steps of acquiring the load fluctuation assessment information are as follows: S221: Based on the information of large-scale events in the future period, including concerts, ball games and sports events, the flow of people and time of the events are extracted to generate event impact data; S222: Analyze the impact of the activity on the grid load based on the activity impact data, evaluate the increase in grid load during the activity, and obtain predicted load increase data; S223: Based on the predicted load increase data and the standard deviation of the grid load, the formula: ; Calculate the grid load fluctuation index, evaluate the grid load fluctuation degree in the future period, and obtain load fluctuation evaluation information; in, is the grid load fluctuation index, is the predicted load increase due to the activity, is the historical load average, is the adjustment factor, Represents the standard deviation of the grid load.

[0010] The present invention is improved in that the step of evaluating the available power of the photovoltaic energy storage system in the future period is: S311: extracting the current storage capacity of the energy storage device based on the real-time operation data of the energy storage device, analyzing the charge and discharge cycle efficiency of the energy storage device, and obtaining effective storage capacity data; S312: Based on the effective power storage data and power generation evaluation information, the formula: ; Calculate the available power and obtain the available power analysis results; in, is the current storage capacity of the energy storage device, It is the power consumption of daily operation and maintenance. Represents available power. Represents the expected power generation in the future period.

[0011] The present invention is improved in that the step of acquiring the real-time discharge adjustment information is: S321: Based on the available power analysis result and the load fluctuation assessment information, according to the real-time operation data of the power grid, extract the real-time load demand of the power grid to obtain discharge-related data; S322: Based on the discharge-related data, by formula: ; Calculate the adjusted discharge power and obtain real-time discharge adjustment information; in, represents the length of the target period, is the adjustment coefficient, represents the adjusted discharge power, Represents available power. Represents the real-time load demand of the power grid, Represents the grid load fluctuation index.

[0012] The present invention is improved in that the step of cutting off the abnormal photovoltaic power generation equipment is: S411: Based on the real-time discharge adjustment information, real-time operating parameters of the power generation equipment are monitored in real time to obtain real-time monitoring data of the power generation equipment; S412: Based on the real-time monitoring data of the power generation equipment, the real-time monitoring data is compared with the normal working condition, the deviation between the current working parameter and the normal working condition is evaluated, and the deviation data of the power generation equipment is obtained; S413: Based on the power generation equipment deviation data, the formula: ; Calculate the abnormal index of photovoltaic power generation equipment, compare it with the preset abnormal threshold, cut off the photovoltaic power generation equipment whose abnormal index exceeds the preset abnormal threshold, and implement abnormal notification to the staff to obtain the abnormal equipment cut-off result: in, Represents the abnormal index of photovoltaic power generation equipment, Represents the current Item operation parameters, Represents the standard Item operation parameters, It is The weight coefficient of the operating parameters, is the total number of parameter items.

[0013] The present invention is improved in that the step of obtaining the abnormal situation response information is: S421: Based on the abnormal equipment cut-off result and according to the number of abnormal photovoltaic power generation equipment, the estimated power generation loss of the abnormal photovoltaic power generation equipment is counted to obtain power generation loss data; S422: Based on the lost power generation data and the real-time discharge adjustment information, the formula: ; Calculate the corrected discharge power and obtain the information on dealing with abnormal conditions; in, is the correction factor, represents the corrected discharge power, represents the adjusted discharge power, represents the expected power generation loss, Represents the length of the target period.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by real-time collection of ambient light intensity data and grid load data, timely adjustment of the discharge power of the energy storage device and monitoring of the power generation equipment, the response speed and adaptability of the photovoltaic energy storage system are improved. By real-time capture of ambient light conditions and combining historical power generation data, the future power generation of the photovoltaic system is effectively predicted. The grid load changes are monitored in real time and the impact of specific activities is taken into account. When the grid demand fluctuates, timely response can be made to optimize the supply and dispatch of electric energy. Continuous monitoring and abnormal processing of power generation equipment ensure the continuity and safety of the energy storage system. By real-time correction of the discharge amount to cope with equipment abnormalities, the risk in the operation of the energy storage system is reduced, providing solid technical support for the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of the method of the present invention; Figure 2 A flow chart for obtaining power generation assessment information for the present invention; Figure 3 A flow chart of evaluating power grid load fluctuations within a target period of time according to the present invention; Figure 4 A flow chart for obtaining load fluctuation assessment information according to the present invention; Figure 5 A flow chart for evaluating the amount of electricity available to the photovoltaic energy storage system in a future period of time for the present invention; Figure 6 A flow chart of obtaining real-time discharge adjustment information according to the present invention; Figure 7 A flow chart for cutting off abnormal photovoltaic power generation equipment according to the present invention; Figure 8 The present invention is a flow chart for obtaining abnormal situation response information. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The present invention provides a technical solution: a photovoltaic energy storage system dynamic optimization scheduling algorithm, comprising the following steps: S1: Based on the working environment of the photovoltaic energy storage system, the light intensity sensor collects the ambient light intensity data in real time, and extracts the average power generation under the same light intensity through the power generation record of the photovoltaic energy storage system. The weather forecast data is used to receive the weather conditions in the future period of the current area. According to the weather changes, the power generation in the future period is estimated to obtain the power generation evaluation information; S2: Based on the grid load data, extract the grid load records within the target time period, evaluate the grid load fluctuation within the target time period according to the load changes within the target time period, and evaluate the grid load fluctuation degree in the future time period according to the impact of activities in the future time period to obtain load fluctuation evaluation information; S3: Based on the power generation assessment information and load fluctuation assessment information, according to the current storage capacity of the energy storage device, the available power of the photovoltaic energy storage system in the future period is assessed, and the discharge power of the energy storage device is adjusted in combination with the real-time load demand and load fluctuation degree of the power grid to obtain real-time discharge adjustment information; S4: Based on the real-time discharge adjustment information, monitor the working status of the power generation equipment of the photovoltaic energy storage system in real time, analyze the deviation between the power generation equipment and the normal working condition, evaluate the abnormality of the photovoltaic power generation equipment, cut off the abnormal photovoltaic power generation equipment, and correct the real-time discharge of the energy storage equipment according to the expected power generation of the abnormal photovoltaic power generation equipment to obtain abnormal condition response information.

[0019] The power generation assessment information includes the predicted maximum power generation, minimum power generation and average power generation; the load fluctuation assessment information includes the expected load during peak hours, the expected load during off-peak hours and the average load during normal hours; the real-time discharge adjustment information includes the adjusted discharge start time, discharge end time and discharge power; the abnormal situation response information includes the expected missing power generation of the cut-off equipment and the adjusted energy storage discharge strategy.

[0020] See also Figure 2 , the steps for obtaining power generation assessment information are: S111: Based on the working environment of the photovoltaic energy storage system, the ambient light intensity data is collected in real time through the light intensity sensor, and the average power generation under the same light intensity is extracted through the power generation record of the photovoltaic energy storage system to obtain the power generation reference data; Based on the working environment of the photovoltaic energy storage system, real-time light intensity data is collected through environmental monitoring equipment. The environmental monitoring equipment can capture light changes through photosensors. The sensors are installed on photovoltaic panels and can monitor real-time changes in sunlight intensity. The monitoring data is updated every minute and transmitted to the central processing unit. The central processing unit records and analyzes the data. Through time series analysis, the average power generation of historical data under the same lighting conditions is calculated. The calculation process involves normalization of the data and removal of outliers. For example, if the data of a certain minute deviates significantly from the average by more than two standard deviations, the data point is considered an anomaly and is removed from the analysis. The statistical analysis of historical data is based on the Pandas library in Python, and its DataFrame structure is used to store and operate time series data to ensure the efficiency and accuracy of data processing, and obtain the average power generation data under each light intensity.

[0021] S112: Receive weather forecast data for the future period in the current area, analyze the expected change in light intensity, and obtain future light intensity prediction data; Receive weather forecast data for the current area in the future. The data is provided by the regional meteorological station and contains hourly weather forecasts for the next few days, including light intensity, temperature, cloud cover and other information. The data is automatically obtained from the server of the meteorological station using the data interface. The obtained data is processed by analysis software. The software can analyze the changing trend of the expected light intensity and predict the future light intensity based on statistical methods such as moving average or exponential smoothing. The prediction model is trained with historical weather data to ensure the accuracy and practicality of the prediction. Through analysis, the predicted data of future light intensity is obtained.

[0022] S113: Based on the reference data of power generation and the predicted data of future light intensity, the formula is: ; Calculate the power generation expected in the future period and obtain power generation assessment information; in, To estimate the power generation in the future period, is the historical average power generation, is the predicted light intensity, is the historical average light intensity, and is the adjustment factor; formula: ; The benefit of the formula is that by adjusting the coefficients and , can flexibly adapt to the power generation prediction under different environmental conditions, so that the model can more accurately reflect the sensitivity of the actual light changes to power generation.

[0023] Detailed explanation of the formula and the process of formula calculation and derivation: In the formula, To estimate the power generation in the future period, is the average power generation calculated based on historical data, is the future light intensity predicted based on weather forecast data, is the average light intensity calculated from historical light data. Adjustment factor and Determined by regression analysis of historical data, for example, the two parameters can be fitted according to historical power generation and light intensity data using the least squares method.

[0024] The specific calculation process of the formula is as follows: Assume that we get from the data , , , , ,but: ; The results show that considering the increase in future sunlight intensity, the power generation is expected to increase slightly compared to the historical average, which is consistent with the purpose of the forecast model, which is to accurately predict the power generation based on future sunlight conditions.

[0025] See also Figure 3 ,The steps to evaluate the grid load fluctuation during the target period are: S211: Based on the power grid load data, collect power grid load records within a target time period to obtain a load record data set; Based on the grid load data, the grid load records within the target time period are collected. The grid operation status is monitored in real time through the grid monitoring equipment to obtain the grid load data set. The monitoring equipment records data at fixed intervals, including the current and voltage information of each connection point. The collected data is first transmitted to the data processing center. The data processing center uses automated software to perform preliminary cleaning and sorting on the collected data to remove obvious erroneous readings or duplicate data entries. For the grid load records, special attention is paid to the load fluctuations during peak and trough periods in order to more accurately evaluate the operation efficiency and stability of the grid and obtain the load record data set.

[0026] S212: Perform statistical analysis based on the load record data set, calculate the average value of the load in the target period, and obtain load average value information; Based on the load record data set, statistical analysis is performed to calculate the power grid load value of each recording point in the target time period, and the average of the load value is calculated using statistical software. The calculation process includes the calculation of the arithmetic mean and the analysis of the distribution characteristics of the data, such as calculating the median and mode, as well as the skewness and peak state of the data. Through statistical analysis, more comprehensive information on the average power grid load is obtained, which helps power grid operators evaluate the operating efficiency of the power grid in different time periods.

[0027] S213: Based on the load average information and the load record data set, the formula: ; Calculate the standard deviation of the grid load, and evaluate the grid load fluctuation within the target period based on the size of the standard deviation of the grid load; in, is the number of data points, It is The load value of the data point, is the load average, Represents the standard deviation of grid load; formula: ; The benefit of the formula is that by calculating the standard deviation of grid load data, the volatility of grid load can be effectively evaluated, which helps grid operators to conduct better load management and risk assessment.

[0028] Detailed explanation of the formula and the process of formula calculation and derivation: in, is the number of data points, It is The load value of the data point, is the load average, Represents the standard deviation of the grid load. Assume that 3 data points were collected during the monitoring period, and the load values ​​of the data points were 120MW, 150MW, and 180MW. Calculate the load average of these data points, and then use the average to calculate the standard deviation: Calculate the average : ; Calculate the squared deviation for each data point: ; ; ; Compute the mean of the squared deviations: ; Calculate standard deviation : ; Calculation results, standard deviation of grid load It is 24.49MW, which shows that during the target period, the fluctuation of grid load is relatively small, and the load values ​​are roughly concentrated around the average value of 150MW, with only a small fluctuation amplitude. The calculation results are helpful for grid operators to evaluate the stability of grid load and optimize grid management strategies accordingly to ensure the stable operation of the grid under different load conditions.

[0029] See also Figure 4 ,The steps for obtaining load fluctuation assessment information are: S221: Based on the information of large-scale events in the future period, including concerts, ball games and sports events, the flow of people and time of the events are extracted to generate event impact data; Based on the information of large-scale events in the future period, including concerts, ball games and sports events, the event data is provided by the Urban Event Management Bureau. The data of each event includes the type of event, the expected number of participants, the date and time of the event. The information is entered into the central database, which can automatically classify and organize the data and generate detailed information about future events. The information plays a key role in predicting the flow of people in the city. By analyzing the historical flow data of different types of activities, a flow prediction model is established to predict the flow of people that may be generated by each type of activity. The model uses linear regression analysis to predict the flow of people according to the scale and type of the activity and generate activity impact data.

[0030] S222: Analyze the impact of the activity on the grid load based on the activity impact data, evaluate the increase in grid load during the activity, and obtain predicted load increase data; Based on the activity impact data, the impact of the activity on the grid load is analyzed. Data analysis is performed. The activity impact data is received and combined with the historical load data of the grid. Machine learning methods are used to analyze the potential increase in grid load during the activity. The evaluation model predicts the increase in load based on the flow of people at the activity and the historical grid load data for the same period. The model is trained with historical data and can automatically adjust its parameters to adapt to the impact of different types of activities on the grid load, and outputs predicted load increase data.

[0031] S223: Based on the predicted load increase data and the standard deviation of the grid load, the formula: ; Calculate the grid load fluctuation index, evaluate the grid load fluctuation degree in the future period, and obtain load fluctuation evaluation information; in, is the grid load fluctuation index, is the predicted load increase due to the activity, is the historical load average, is the adjustment factor, Represents the standard deviation of grid load; formula: ; The benefit of the formula is that by adjusting the coefficients This can be used to precisely adjust the impact of the predicted load increment caused by specific activities on the grid standard deviation, thereby more accurately assessing grid load fluctuations.

[0032] Detailed explanation of the formula and the process of formula calculation and derivation: in, is the standard deviation of the grid load, is the predicted load increase due to the activity, is the historical load average, is the adjustment coefficient. , , , , the calculation formula is as follows: ; The results show that the load fluctuation level of the power grid will increase slightly during the predicted large-scale events, which is an important reference information for power grid operators to help with risk assessment and resource allocation to ensure the stable operation of the power grid during the event.

[0033] See also Figure 5 , the steps to evaluate the available power of the photovoltaic energy storage system in the future period are: S311: extracting the current storage capacity of the energy storage device based on the real-time operation data of the energy storage device, analyzing the charge and discharge cycle efficiency of the energy storage device, and obtaining effective storage capacity data; Based on the real-time operation data of the energy storage device, the status of the energy storage device is monitored in real time. Through the sensors connected to the energy storage device, the voltage, current, temperature and other data of the battery are collected in real time. After the data is initially processed, the current storage capacity is calculated, and then the charge and discharge cycle efficiency of the energy storage device is analyzed. The analysis includes calculating the loss rate of battery energy in each charge and discharge cycle, using the energy loss rate formula, taking into account the aging factor of the battery, and periodically calibrating the measurement tool to ensure the accuracy of the data, thereby obtaining the effective storage capacity data. The effective storage capacity is the actual available power after considering the loss. The data is of great significance for predicting the operating efficiency and life of the energy storage equipment.

[0034] S312: Based on the effective power storage data and power generation assessment information, the formula: ; Calculate the available power and obtain the available power analysis results; in, is the current storage capacity of the energy storage device, It is the power consumption of daily operation and maintenance. Represents available power. Represents the expected power generation in the future period; formula: ; The benefit of the formula is that by integrating the expected future power generation, the effective storage capacity of energy storage equipment and operation and maintenance consumption, the available electricity can be accurately calculated, thus providing decision support for power system operations.

[0035] Detailed explanation of the formula and the process of formula calculation and derivation: in, is the current storage capacity of the energy storage device, It is the power consumption of daily operation and maintenance. Represents available power. Represents the expected power generation in the future period. , , , and calculate: ; The results show that after considering operation and maintenance consumption, 1250 kWh of electricity will be available for deployment in the future period, which will help power system operators optimize resource allocation and improve system operation efficiency and reliability.

[0036] See also Figure 6, the steps for obtaining real-time discharge adjustment information are: S321: Based on the available power analysis results and the load fluctuation assessment information, according to the real-time operation data of the power grid, extract the real-time load demand of the power grid to obtain discharge-related data; Based on the available power analysis results and load fluctuation assessment information, the grid load is monitored in real time. The current and voltage data are recorded in real time by sensors installed at key nodes of the grid. The real-time data is transmitted to the central control room. The total load demand of the grid is calculated using these real-time data. Through comparative analysis of historical data, load fluctuations caused by specific activities or time periods are identified. The analysis helps operators understand the performance of the grid in specific time periods, so as to make scheduling decisions and obtain discharge-related data. The discharge-related data not only includes the current load demand, but also predicts the load changes in the next few hours, providing important decision-making support for grid operation and maintenance.

[0037] S322: Based on the discharge-related data, the formula: ; Calculate the adjusted discharge power and obtain real-time discharge adjustment information; in, represents the length of the target period, is the adjustment coefficient, represents the adjusted discharge power, Represents available power. Represents the real-time load demand of the power grid, Represents the grid load fluctuation index; formula: The benefit of the formula is that it optimizes the operating efficiency and stability of the power grid by dynamically adjusting power generation and discharge strategies to cope with grid load demand and fluctuations.

[0038] Detailed explanation of the formula and the process of formula calculation and derivation: in, represents the length of the target period (in hours), is the regulation coefficient, which is used to adjust the power demand changes caused by load fluctuations. represents the adjusted discharge power, Represents available power. Represents the real-time load demand of the power grid, Represents the grid load fluctuation index. Hour, , , , : ; The results show that, considering the real-time load and load fluctuation of the power grid, the system will discharge at a power of 1002.547kW in the next hour to meet the actual needs of the power grid, which helps to balance the supply and demand of the power grid and improve the operation efficiency and reliability of the power grid.

[0039] See also Figure 7 , the steps to cut off abnormal photovoltaic power generation equipment are: S411: Based on the real-time discharge adjustment information, real-time operating parameters of the power generation equipment are monitored in real time to obtain real-time monitoring data of the power generation equipment; Based on real-time discharge adjustment information, the working parameters of the power generation equipment are monitored in real time. Key parameters such as temperature, voltage and current are collected in real time through multiple sensors connected to the power generation equipment. The data is uploaded to the central database and processed in real time. The processing process includes data cleaning, standardization and anomaly detection. By comparing the real-time data with the set working parameter thresholds, any parameters that exceed the normal operating range can be immediately identified to ensure that the power generation equipment can operate in the best state and obtain real-time monitoring data of the power generation equipment. The real-time monitoring data not only provides the operation and maintenance team with first-hand equipment operating status, but also provides a basis for performance analysis and maintenance decisions.

[0040] S412: Based on the real-time monitoring data of the power generation equipment, the data is compared with the normal working condition, the deviation between the current working parameters and the normal working condition is evaluated, and the deviation data of the power generation equipment is obtained; Based on the real-time monitoring data of power generation equipment, it is compared with the normal working conditions. The deviation between the current working parameters and the set standard working parameters is analyzed through the data analysis system. The analysis includes calculating the percentage difference between the real-time value and the standard value of each key parameter, automatically calculating the deviation using a preset formula, and evaluating whether the deviation will affect power generation efficiency or safe operation. In this way, the operation and maintenance team can quickly respond to any potential equipment problems, make adjustments or repairs in time to avoid greater equipment failures or losses, and obtain the deviation data of power generation equipment. Accurate analysis of deviation data helps the maintenance team optimize equipment performance and extend equipment life.

[0041] S413: Based on the deviation data of the power generation equipment, the formula: ; Calculate the abnormal index of photovoltaic power generation equipment, compare it with the preset abnormal threshold, cut off the photovoltaic power generation equipment whose abnormal index exceeds the preset abnormal threshold, and implement abnormal notification to the staff to obtain the abnormal equipment cut-off result: in, Represents the abnormal index of photovoltaic power generation equipment, Represents the current Item operation parameters, Represents the standard Item operation parameters, It is The weight coefficient of the operating parameters, is the total number of parameter items; formula: ; The benefit of the formula is that it combines the deviations of multiple operating parameters through weighted summation to form a single anomaly index, which makes the assessment of the overall health status of the equipment more intuitive and easier to manage.

[0042] Detailed explanation of the formula and the process of formula calculation and derivation: in, Represents the abnormal index of photovoltaic power generation equipment, Represents the current Item operation parameters, Represents the standard Item operation parameters, It is The weight coefficient of the operating parameters, is the total number of parameter items. , , , , , , , , , , and calculate: ; The results show that the abnormality index of photovoltaic power generation equipment is 0.08. If this value exceeds the preset abnormality threshold, such as 0.1, the equipment needs to be cut off and subsequent inspection and maintenance must be carried out. The application of this formula ensures the reliability and efficiency of equipment operation.

[0043] See also Figure 8 , the steps to obtain abnormal situation response information are: S421: based on the abnormal equipment cut-off result and according to the number of abnormal photovoltaic power generation equipment, the estimated power generation loss of the abnormal photovoltaic power generation equipment is counted to obtain the power generation loss data; Based on the results of abnormal equipment disconnection, the number of photovoltaic power generation equipment that has been disconnected due to abnormalities is counted, including the model, location and abnormal time of each device. The power generation of the equipment under normal working conditions is predicted through a pre-set model. By comparing the model prediction value with the actual power generation, the lost power generation of each device is calculated, and the lost power generation of all abnormal equipment is summarized to obtain the lost power generation data. The lost power generation data provides a basis for decision-making, such as whether it is necessary to temporarily increase other power generation resources or adjust the power grid operation strategy to ensure the stable operation of the power grid and the continuity of power supply.

[0044] S422: Based on the lost power generation data and the real-time discharge adjustment information, the formula: ; Calculate the corrected discharge power and obtain the information on dealing with abnormal conditions; in, is the correction factor, represents the corrected discharge power, represents the adjusted discharge power, represents the expected power generation loss, represents the length of the target period; formula: ; The benefit of the formula is that by considering the impact of lost power generation on discharge power, the discharge strategy is dynamically adjusted to ensure the stability and reliability of power supply to the grid.

[0045] Detailed explanation of the formula and the process of formula calculation and derivation: in, is a correction factor used to adjust the discharge power to compensate for the effect of lost power generation, represents the corrected discharge power, represents the adjusted discharge power, represents the expected power generation loss, Represents the length of the target period in hours. , , , : ; The results show that after considering the impact of lost power generation, it will be discharged at a power of 927.547 kW in the next hour, which will help balance the supply and demand of the power grid and reduce the risk of instability due to abnormal power generation equipment.

[0046] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A photovoltaic energy storage system dynamic optimization scheduling algorithm, characterized in that: The following steps are involved: S1: Based on the working environment of the photovoltaic energy storage system, the ambient light intensity data is collected in real time, the average power generation under the same light intensity is extracted, and the weather conditions in the future period of the current area are received through weather forecast data, the power generation in the future period is estimated, and the power generation evaluation information is obtained; S2: Based on the grid load data, extract the grid load records within the target time period, evaluate the grid load fluctuation within the target time period according to the load changes within the target time period, and evaluate the grid load fluctuation degree in the future time period according to the impact of activities in the future time period to obtain load fluctuation evaluation information; S3: Based on the power generation assessment information and the load fluctuation assessment information, the available power of the photovoltaic energy storage system in the future period is assessed according to the current storage capacity of the energy storage device, and the discharge power of the energy storage device is adjusted in combination with the real-time load demand and load fluctuation degree of the power grid to obtain real-time discharge adjustment information; S4: Based on the real-time discharge adjustment information, monitor the working status of the power generation equipment of the photovoltaic energy storage system in real time, analyze the deviation of the power generation equipment from the normal working condition, evaluate the abnormality of the photovoltaic power generation equipment, cut off the abnormal photovoltaic power generation equipment, and correct the real-time discharge amount of the energy storage equipment according to the expected power generation of the abnormal photovoltaic power generation equipment to obtain abnormal condition response information.

2. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 1 is characterized in that: The steps for obtaining the power generation evaluation information are as follows: S111: Based on the working environment of the photovoltaic energy storage system, the ambient light intensity data is collected in real time through the light intensity sensor, and the average power generation under the same light intensity is extracted through the power generation record of the photovoltaic energy storage system to obtain the power generation reference data; S112: Receive weather forecast data for the future period in the current area, analyze the expected change in light intensity, and obtain future light intensity prediction data; S113: Based on the power generation reference data and the future light intensity prediction data, the formula: ； Calculate the power generation expected in the future period and obtain power generation assessment information; in, To estimate the power generation in the future period, is the historical average power generation, is the predicted light intensity, is the historical average light intensity, and is the adjustment factor.

3. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 1 is characterized in that: The steps of evaluating the power grid load fluctuation during the target period are as follows: S211: Based on the power grid load data, collect power grid load records within a target time period to obtain a load record data set; S212: Performing statistical analysis based on the load record data set, calculating the average value of the load in the target period, and obtaining load average value information; S213: Based on the load average value information and the load record data set, the formula: ； Calculate the standard deviation of the grid load, and evaluate the grid load fluctuation within the target period based on the size of the standard deviation of the grid load; in, is the number of data points, It is The load value of the data point, is the load average, Represents the standard deviation of the grid load.

4. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 3 is characterized in that: The steps for acquiring the load fluctuation assessment information are as follows: S221: Based on the information of large-scale events in the future period, including concerts, ball games and sports events, the flow of people and time of the events are extracted to generate event impact data; S222: Analyze the impact of the activity on the grid load based on the activity impact data, evaluate the increase in grid load during the activity, and obtain predicted load increase data; S223: Based on the predicted load increase data and the standard deviation of the grid load, the formula: ； Calculate the grid load fluctuation index, evaluate the grid load fluctuation degree in the future period, and obtain load fluctuation evaluation information; in, is the grid load fluctuation index, is the predicted load increase due to the activity, is the historical load average, is the adjustment factor, Represents the standard deviation of the grid load.

5. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 1 is characterized in that: The steps for evaluating the available power of the photovoltaic energy storage system in the future period are: S311: extracting the current storage capacity of the energy storage device based on the real-time operation data of the energy storage device, analyzing the charge and discharge cycle efficiency of the energy storage device, and obtaining effective storage capacity data; S312: Based on the effective power storage data and power generation evaluation information, the formula: ； Calculate the available power and obtain the available power analysis results; in, is the current storage capacity of the energy storage device, It is the power consumption of daily operation and maintenance. Represents available power. Represents the expected power generation in the future period.

6. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 5 is characterized in that: The step of acquiring the real-time discharge adjustment information is as follows: S321: Based on the available power analysis result and the load fluctuation assessment information, according to the real-time operation data of the power grid, extract the real-time load demand of the power grid to obtain discharge-related data; S322: Based on the discharge-related data, by formula: ； Calculate the adjusted discharge power and obtain real-time discharge adjustment information; in, represents the length of the target period, is the adjustment coefficient, represents the adjusted discharge power, Represents available power. Represents the real-time load demand of the power grid, Represents the grid load fluctuation index.

7. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 1 is characterized in that: The steps of cutting off abnormal photovoltaic power generation equipment are: S411: Based on the real-time discharge adjustment information, real-time operating parameters of the power generation equipment are monitored in real time to obtain real-time monitoring data of the power generation equipment; S412: Based on the real-time monitoring data of the power generation equipment, the real-time monitoring data is compared with the normal working condition, the deviation between the current working parameter and the normal working condition is evaluated, and the deviation data of the power generation equipment is obtained; S413: Based on the power generation equipment deviation data, the formula: ； Calculate the abnormal index of photovoltaic power generation equipment, compare it with the preset abnormal threshold, cut off the photovoltaic power generation equipment whose abnormal index exceeds the preset abnormal threshold, and implement abnormal notification to the staff to obtain the abnormal equipment cut-off result: in, Represents the abnormal index of photovoltaic power generation equipment, Represents the current Item operation parameters, Represents the standard Item operation parameters, It is The weight coefficient of the operating parameters, is the total number of parameter items.

8. The photovoltaic energy storage system dynamic optimization scheduling algorithm according to claim 7 is characterized in that: The steps for obtaining the abnormal situation response information are as follows: S421: Based on the abnormal equipment cut-off result and according to the number of abnormal photovoltaic power generation equipment, the estimated power generation loss of the abnormal photovoltaic power generation equipment is counted to obtain power generation loss data; S422: Based on the lost power generation data and the real-time discharge adjustment information, the formula: ； Calculate the corrected discharge power and obtain the information on dealing with abnormal conditions; in, is the correction factor, represents the corrected discharge power, represents the adjusted discharge power, represents the expected power generation loss, Represents the length of the target period.

Images