Data-driven solar storage and charging energy allocation system and control method

Abstract

The present invention discloses a data-driven photovoltaic storage and charging energy allocation system and control method, which relates to the field of photovoltaic storage and charging energy allocation technology, and includes the following steps: real-time collection of the real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data, and cleaning, normalization and time serialization of the collected data to ensure the accuracy and continuity of the input data. The present invention monitors the load power consumption data in real time, combines the long-term energy prediction model, and dynamically adjusts the energy storage discharge strategy to avoid excessive discharge during non-peak periods, ensure sufficient energy storage during peak periods, reduce dependence on the power grid, and reduce electricity costs. Through load surge detection and adaptive scheduling algorithms, the system can quickly respond to sudden load changes, give priority to ensuring power supply to critical loads, flexibly adjust the discharge mode, improve battery life and system stability, and maximize green energy utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic energy storage and charging allocation, and in particular to a data-driven photovoltaic energy storage and charging allocation system and control method. Background Art

[0002] Data-driven solar-storage-and-charging energy allocation control involves comprehensively collecting and analyzing data from photovoltaic power generation, energy storage systems, and load power consumption, and leveraging machine learning or predictive models to dynamically optimize future energy supply and demand. This allows for efficient coordinated management of photovoltaic power generation, battery energy storage, and grid power. Specifically, using a base station's solar-storage-and-charging system as an example, by analyzing hourly photovoltaic power generation and load power consumption data over the past 15 days, it is possible to predict the amount of energy storage required during the transition from normal times (low electricity prices or low load periods) to peak times (high electricity prices or high load periods). This allows for pre-emptive energy storage when photovoltaic power generation is sufficient, ensuring that peak loads rely primarily on the energy storage system, minimizing curtailment and reducing reliance on the grid. This energy allocation control strategy enables efficient utilization of photovoltaic power without impacting base station operation, reducing overall electricity costs and improving the system's green energy utilization and economic benefits.

[0003] The existing technology has the following deficiencies:

[0004] When allocating energy, existing photovoltaic storage and charging systems tend to overlook the risk of over-discharge of energy storage caused by short-term load surges. Traditional energy allocation usually relies on historical photovoltaic power generation and load power consumption data for prediction. However, in special scenarios, such as base station equipment failure, a surge in emergency communication services, or an interruption in external power grid power supply, the system cannot identify abnormal changes in load in real time. This situation may cause the energy storage system to over-discharge prematurely during normal times, resulting in insufficient power reserves during peak hours, forcing the system to rely on power grid power, increasing electricity costs, and may even cause power outages at base stations, affecting the operation of critical services. To address this problem, a load mutation detection and prediction mechanism can be introduced to monitor load fluctuations in real time, dynamically adjust energy storage strategies, and ensure that the energy storage system has sufficient power reserves in emergency situations, thereby achieving more stable photovoltaic utilization and electricity cost optimization.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide a data-driven photovoltaic energy storage and charging allocation system and control method. By real-time monitoring of load power consumption data and combining it with a long-term energy supply and demand forecasting model, the discharge strategy of the energy storage system is dynamically adjusted to avoid excessive discharge of the energy storage battery during non-peak hours, ensure sufficient energy storage during peak hours, reduce dependence on grid power, and optimize electricity costs. Through a load surge detection mechanism and an adaptive scheduling algorithm, the system can quickly respond to sudden load change scenarios, such as a surge in communication services or a grid outage, automatically adjust the energy storage strategy, ensure continuous power supply to critical loads, and improve battery life by flexibly adjusting the discharge mode, enhance system stability and power supply reliability, and maximize green energy utilization efficiency to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above objectives, the present invention provides the following technical solution: a data-driven solar storage and charging energy allocation control method, comprising the following steps:

[0008] Real-time data collection of photovoltaic power generation system power generation, current power status of energy storage batteries and load power consumption is carried out, and the collected data is cleaned, normalized and time-series processed to ensure the accuracy and continuity of input data;

[0009] Based on historical PV power generation, energy storage system charge and discharge records, and load power usage patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model. This model predicts future PV power generation trends and load demand changes, allowing for the planning of energy storage system charge and discharge strategies.

[0010] Compare real-time monitored load power consumption data with forecast data to detect short-term load surges based on change rate thresholds and time windows;

[0011] Introducing an energy storage strategy optimization algorithm to calculate the optimal charging and discharging strategy for the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status, and load demand forecast;

[0012] Through the anomaly recognition algorithm, the load mutation signal is correlated with the external grid status and analyzed to identify abnormal scenarios. Based on the identification results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the stable operation of the system in emergency situations and the minimization of electricity costs are ensured.

[0013] Preferably, the real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data are collected in real time, and the collected data are cleaned, normalized, and time-series-processed to ensure the accuracy and continuity of the input data. The specific steps are as follows:

[0014] Real-time data collection and transmission of photovoltaic power generation, energy storage battery power, and load power consumption are achieved through sensors and data transmission protocols to ensure data integrity and real-time performance;

[0015] Clean the collected data, remove outliers and supplement missing values, and unify the data frequency through resampling to ensure the continuity and rationality of the data;

[0016] Normalize data from different sources to the same scale to prevent numerical differences between features from affecting the accuracy of model decisions.

[0017] The processed data is arranged in chronological order as time series data to capture periodic and trend changes, providing a time series input basis for load forecasting and scheduling strategies.

[0018] Preferably, based on historical photovoltaic power generation, energy storage system charge and discharge records, and load power consumption patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model to predict future photovoltaic power generation trends and load demand changes, so as to plan the energy storage system's charge and discharge strategy in advance. The specific steps are as follows:

[0019] By selecting key features to construct a time series dataset, we can provide high-quality input data for model training.

[0020] Select a machine learning model suitable for time series data and train the model through cross-validation and parameter adjustment to improve prediction accuracy and robustness;

[0021] Evaluate model performance through various indicators and optimize the model through hyperparameter adjustment and real-time evaluation to adapt it to dynamic data changes;

[0022] The prediction results are used to plan the charging and discharging strategies of the energy storage system, and combined with electricity price optimization and abnormal load identification mechanisms to achieve electricity cost optimization and improve system stability.

[0023] Preferably, the specific steps of comparing the real-time monitored load power consumption data with the predicted data and detecting a short-term load surge based on a change rate threshold and a time window are as follows:

[0024] By comparing the deviation between real-time collected load power consumption data and predicted data, it can identify situations where the actual load exceeds the normal range, providing a basis for sudden increase detection;

[0025] By calculating the rate of change and fluctuation of load data, the trend and instability of load changes in a short period of time can be monitored, thereby providing early warning of sudden increase risks;

[0026] Compare the rate of change with the preset threshold. When the rate of change exceeds the set value, a load mutation signal is triggered, and multiple verifications are performed to improve accuracy.

[0027] After the load mutation signal is triggered, the discharge strategy of the energy storage system is dynamically adjusted according to the photovoltaic power generation, the power status of the energy storage battery and the load demand to ensure continuous and stable power supply to the load.

[0028] Preferably, an energy storage strategy optimization algorithm is introduced to calculate the optimal charging and discharging strategy of the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status and load demand forecast value. The specific steps are as follows:

[0029] First, the current load demand gap is calculated, that is, the difference between the actual load demand and the power provided by photovoltaic power generation. This is used to determine whether the energy storage system needs to be charged or discharged. The calculation expression is as follows:

[0030] ΔP load =P demand -P solar

[0031] , where ΔP load is the load demand gap, P demand is the actual load demand, P solar is the current photovoltaic power generation;

[0032] Based on the calculated load demand gap ΔP load , further calculate the charging and discharging power of the energy storage battery, the calculation expression is as follows:

[0033]

[0034] , where P battery is the charge and discharge power of the energy storage battery, P max is the maximum charge and discharge power of the energy storage battery, max(ΔP load , -P max ) is the maximum limit, indicating that the load gap value must not be less than the negative value of the maximum discharge power of the energy storage battery, min(max(ΔP load , -P max ), P max ) is the minimum value limit, which means that the load gap value must not exceed the maximum charging power of the energy storage battery. SOC is the current state of charge of the energy storage battery, which indicates the charging percentage of the battery.

[0035] Preferably, in order to ensure the long service life of the energy storage battery, the influence of the battery health status on the charge and discharge power is comprehensively considered, and the calculation expression is as follows:

[0036]

[0037] , where P battery_adjustedIt is the charge and discharge power of the energy storage battery after health status correction, SOH is the health status of the energy storage battery;

[0038] When the energy storage system cannot fully meet the load demand, the grid dispatch decision is calculated based on the real-time grid electricity price and the charge and discharge power of the energy storage battery. The decision is whether to purchase electricity from the grid or sell electricity to the grid. The calculation expression is as follows:

[0039] P grid =ΔP load -P battery_adjusted

[0040] , where P grid is the grid dispatching power;

[0041] If P grid >0, then purchase electricity from the grid;

[0042] If P grid <0, then sell electricity to the grid;

[0043] The grid electricity price is adjusted according to the real-time electricity price, and the calculation formula is as follows:

[0044] C cost =P grid ×C grid

[0045] , where C grid is the real-time grid electricity price, C cost It is the cost of purchasing or selling electricity to the power grid.

[0046] Preferably, an abnormality recognition algorithm is used to correlate and analyze load mutation signals with the external grid status to identify abnormal scenarios. Based on the recognition results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the stable operation of the system and the minimization of electricity costs in emergency situations are ensured. The specific steps are as follows:

[0047] First, by correlating and analyzing the real-time monitored load surge signal with the external grid status data, the load sudden change intensity parameter is calculated to quantify the degree of abnormal load change. The calculation expression of the load sudden change intensity parameter is as follows:

[0048]

[0049] , where I LT is the load mutation intensity parameter, ΔL is the load change within the time interval Δt, Δt is the time interval, V dev It is the deviation value of the grid voltage, that is, the difference between the actual voltage and the standard voltage, F devis the deviation value of the grid frequency, that is, the difference between the actual frequency and the standard frequency. α, β, and γ are all weight parameters. α is the weight of the load change rate, which indicates the influence of the load change on the recognition of sudden abnormal scenarios. β is the weight of the voltage deviation value, which indicates the influence of the grid voltage fluctuation on the recognition of sudden abnormal scenarios. γ is the weight of the frequency deviation value, which indicates the influence of the grid frequency fluctuation on the recognition of sudden abnormal scenarios.

[0050] After identifying an abnormal scenario, calculate the priority power supply factor for critical loads to determine the proportion of load power supply that is prioritized in abnormal situations. The calculation expression is as follows:

[0051]

[0052] , where P critical is the priority power supply factor for critical loads, W critical is the total power demand of the critical loads, W total is the sum of the power demands of all loads, and λ is the adjustment coefficient, which is used to control the priority power supply weight of key loads in abnormal scenarios;

[0053] Prioritize power supply factor P according to critical loads critical Based on the current state of charge of the energy storage system, the discharge rate adjustment parameters of the energy storage system are calculated, and the discharge strategy of the energy storage system is dynamically adjusted to ensure stable operation of the energy storage system and minimize electricity costs. The calculation expression is as follows:

[0054]

[0055] , where R discharge is the discharge rate adjustment parameter of the energy storage system, P max is the maximum charge and discharge power of the energy storage battery, SOC is the current state of charge of the energy storage battery, which indicates the charging percentage of the battery, δ is the cost adjustment coefficient, C grid is the real-time grid electricity price, C battery is the unit cost of battery discharge.

[0056] The data-driven solar energy storage and charging energy allocation system includes a data acquisition and preprocessing module, a long-term energy prediction module, a load surge detection and response module, an energy storage strategy optimization module, and an anomaly identification and adaptive scheduling module:

[0057] The data acquisition and preprocessing module collects the real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data in real time, and cleans, normalizes, and time-series the collected data to ensure the accuracy and continuity of the input data;

[0058] The long-term energy forecasting module uses machine learning to build a long-term energy supply and demand forecasting model based on historical photovoltaic power generation, energy storage system charge and discharge records, and load power consumption patterns. This model predicts future photovoltaic power generation trends and load demand changes, allowing for the pre-planning of energy storage system charge and discharge strategies.

[0059] The load surge detection and response module compares real-time monitored load power usage data with predicted data and detects short-term load surges based on the rate of change threshold and time window.

[0060] The energy storage strategy optimization module introduces an energy storage strategy optimization algorithm to calculate the optimal charging and discharging strategy of the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status and load demand forecast value;

[0061] The anomaly identification and adaptive scheduling module uses an anomaly identification algorithm to correlate and analyze load mutation signals with the external grid status, identify abnormal scenarios, and based on the identification results, execute an adaptive scheduling algorithm to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, it ensures the stable operation of the system and minimizes electricity costs in emergency situations.

[0062] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0063] The present invention monitors load power consumption data in real time, combines it with a long-term energy supply and demand forecasting model, and dynamically adjusts the discharge strategy of the energy storage system, thereby effectively avoiding the problem of excessive discharge of energy storage batteries during non-peak periods. Compared with traditional fixed scheduling strategies, this solution can identify load surges in real time and flexibly adjust the discharge rate of energy storage batteries according to the surge signal, ensuring sufficient energy storage during peak periods, reducing dependence on grid power, and lowering overall electricity costs. At the same time, by combining the grid electricity price optimization strategy, the system implements a strategy of storing electricity during low-price periods and discharging during high-price periods, greatly improving the economic benefits of the energy storage system, avoiding the phenomenon of abandoned photovoltaic power generation, and maximizing the utilization efficiency of green energy.

[0064] By introducing a load surge detection mechanism and an adaptive scheduling algorithm, the present invention can automatically trigger the adjustment strategy of the energy storage system when abnormal load changes are detected, and quickly respond to various sudden load change scenarios, such as a surge in communication services, equipment failures, or power grid outages. This automated response mechanism ensures that the energy storage system can prioritize the power supply needs of critical loads when the load fluctuates abnormally, avoiding power outages caused by premature exhaustion of the energy storage battery. At the same time, the system can flexibly adjust the discharge mode according to the duration of the surge, adopting a gradual discharge or partial discharge strategy to further improve the battery life of the energy storage battery, ensure the overall stability of the system and the reliability of power supply, and provide continuous power protection for the user's core business. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0066] Figure 1 This is a flow chart of the data-driven solar storage and charging energy allocation control method of the present invention.

[0067] Figure 2 This is a module schematic diagram of the data-driven solar storage and charging energy allocation system of the present invention. DETAILED DESCRIPTION

[0068] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0069] The present invention provides Figure 1 The data-driven solar energy storage and charging energy allocation control method shown includes the following steps:

[0070] The system collects real-time data on the photovoltaic power generation system's power output, the current state of charge of the energy storage battery, and load power consumption. It also cleans, normalizes, and time-series the collected data to eliminate outliers and missing values, ensuring the accuracy and continuity of the input data.

[0071] The specific steps for collecting real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data are as follows:

[0072] Real-time data collection and transmission of photovoltaic power generation, energy storage battery power, and load power consumption are achieved through sensors and data transmission protocols to ensure data integrity and real-time performance;

[0073] First, sensors collect real-time data from the photovoltaic power generation system, the battery management system (BMS), and smart meters at the load end. This data includes photovoltaic power generation (kWh), the state of charge (SOC) of the energy storage battery, and load power consumption (kWh).

[0074] During the data collection process, to ensure real-time data, data transmission protocols (such as MQTT, Modbus, or HTTP) are used to transmit the collected raw data to the data processing center, minimizing transmission delays from the acquisition end to the processing end. Furthermore, to improve data integrity, the system sets a data collection frequency, such as collecting data once every minute, and automatically generates timestamps, laying the foundation for subsequent time series processing.

[0075] Real-time data collection is the foundation of energy dispatch systems, ensuring they can access the latest status information on the photovoltaic power generation system and loads. The combination of sensors and data transmission protocols enables real-time data transmission and remote monitoring, avoiding data lags and incompleteness.

[0076] Clean the collected data, remove outliers and supplement missing values, and unify the data frequency through resampling to ensure the continuity and rationality of the data;

[0077] After the data is transmitted to the processing center, the system will first clean the collected raw data to eliminate abnormal and erroneous data. For example, during the data cleaning process, values ​​that do not conform to the normal range (such as negative photovoltaic power generation, SOC exceeding 100%, etc.) will be identified and marked as abnormal values. For missing values, the system can use interpolation or moving average methods to supplement missing data to ensure data integrity. In addition, the system will also deal with inconsistent data collection frequencies. For example, if the data collection frequency of a certain period is too high or too low, the data will be unified to the preset sampling frequency (such as every minute or every hour) through resampling to avoid data being too sparse or redundant.

[0078] Data cleaning can significantly improve the quality of input data, preventing abnormal data from impacting the accuracy of subsequent prediction models. For example, in real-world applications, sensors may malfunction, resulting in abnormal or missing data. By cleaning and supplementing data, the system can maintain the continuity and rationality of the data, thereby ensuring the reliability of subsequent analysis and predictions.

[0079] Normalize data from different sources to the same scale to prevent numerical differences between features from affecting the accuracy of model decisions.

[0080] To ensure that data collected from different sources is of the same scale, the system normalizes the data. PV power generation, energy storage battery state of charge (SOC), and load power usage have different units and numerical ranges. To ensure that this data can be input into the same model for analysis, the system uses minimum-maximum normalization or Z-score standardization to scale the data to a range of 0 to 1.

[0081] For example, the data range for photovoltaic power generation may be 0 to 100 kWh, while the range for SOC is 0% to 100%. To ensure that these data have equal influence in the model, normalization converts all data to the same scale. This avoids the situation where a feature with a large value dominates the model decision.

[0082] Normalization is a critical step before data is fed into the model, preventing scale differences between features from influencing the model. This is particularly true in machine learning-based energy allocation systems, where the weights of different features directly impact the accuracy of the allocation strategy. Therefore, normalization can improve the efficiency and accuracy of model training.

[0083] Arrange the processed data into time series data in chronological order to capture periodic and trend changes, providing a time series input basis for load forecasting and scheduling strategies;

[0084] After data cleaning and normalization, the system converts the processed data into time series data. Time series data is arranged in chronological order, ensuring that each data point corresponds to a timestamp, thus providing a temporal basis for subsequent forecasting and scheduling.

[0085] Specifically, the system processes the data in time series according to the data collection interval (such as every minute or every hour) to generate a continuous time series data set. For example, the photovoltaic power generation and load power consumption data for the past 15 days can be sorted by hour to form a time series chart.

[0086] Time-series data structures effectively capture data periodicity and trends, providing fundamental data input for subsequent load forecasting and scheduling algorithms. Furthermore, the system identifies seasonal trends and unusual fluctuations, enabling more accurate predictions for future energy allocation strategies.

[0087] Time series processing helps the system capture data trends and cyclical characteristics. In photovoltaic power generation systems, power generation typically varies on a daily, weekly, or monthly basis. Through time series processing, the system can more accurately predict future power generation trends and load demand, improving the rationality and accuracy of energy allocation.

[0088] Based on historical PV power generation, energy storage system charge and discharge records, and load power usage patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model. This model predicts future PV power generation trends and load demand changes, allowing for the planning of energy storage system charge and discharge strategies.

[0089] Based on historical PV power generation, energy storage system charge and discharge records, and load power usage patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model. This model predicts future PV power generation trends and load demand changes, allowing for pre-planning of the energy storage system's charge and discharge strategies. The specific steps are as follows:

[0090] By selecting key features to construct a time series dataset, we can provide high-quality input data for model training.

[0091] After data cleaning and time series processing, key features are selected from the real-time data of the photovoltaic power generation system, including photovoltaic power generation, the energy storage system's state of charge (SOC), grid electricity prices, weather data (such as temperature and sunshine intensity), and load power consumption. To improve the model's predictive capabilities, the system constructs a training dataset based on these features in a time series format, setting the input window (such as hourly data for the past 15 days) and the prediction target (such as power generation and load demand for the next 24 hours).

[0092] In addition, the dataset needs to be divided into training sets, validation sets, and test sets to ensure that the model performs consistently on different datasets and avoid overfitting or underfitting.

[0093] Feature selection and dataset construction are fundamental to building a predictive model. By rationally selecting key features from historical data, machine learning models can more accurately capture the changing patterns of photovoltaic power generation and load demand. Furthermore, segmenting datasets by time series effectively verifies the model's generalization capabilities and provides high-quality data input for subsequent model training.

[0094] Select a machine learning model suitable for time series data (such as LSTM) and train the model through cross-validation and parameter adjustment to improve prediction accuracy and robustness;

[0095] Based on the data characteristics and forecast requirements, appropriate machine learning models are selected to build long-term energy supply and demand forecasting models. Commonly used models include long short-term memory networks (LSTMs), recurrent neural networks (RNNs), and XGBoost regression models. These models excel at processing time series data and can effectively capture the periodicity and trends of historical data.

[0096] During training, the model continuously adjusts parameters and weights to minimize the error between predicted and actual values. To enhance model robustness, the system employs cross-validation, training and validating the model multiple times to ensure consistent performance across different datasets. Furthermore, to prevent the model from becoming overly dependent on recent data, regularization terms or early stopping mechanisms can be added to prevent overfitting.

[0097] Model selection and training are core components of forecasting model construction. By selecting a deep learning model suitable for time series data, the system can capture complex patterns of change in historical data, thereby improving the accuracy of forecasts for future energy supply and demand. Furthermore, techniques such as cross-validation and regularization can effectively enhance the model's generalization capabilities and reduce forecast errors.

[0098] Evaluate model performance through various indicators and optimize the model through hyperparameter adjustment and real-time evaluation to adapt it to dynamic data changes;

[0099] After completing the initial model training, the performance of the model is evaluated and optimized to ensure the accuracy and stability of the prediction results. Evaluation indicators usually include mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R 2 ) and other indicators. The system judges the model's predictive effectiveness based on these indicators and optimizes its performance by adjusting the model's hyperparameters (such as the learning rate, number of hidden layers, and number of training steps). Furthermore, the system incorporates a real-time evaluation mechanism to compare and analyze the model's predicted results with actual results, continuously revising the model's parameters to improve prediction accuracy. This dynamic optimization approach allows the model to adapt to changes in photovoltaic power generation and load demand, enhancing the reliability of long-term predictions.

[0100] Model optimization and evaluation are key steps in ensuring the effectiveness of predictive models in practical applications. Through multi-dimensional metric evaluation, the system can identify model deficiencies and continuously improve model performance by adjusting hyperparameters. Furthermore, real-time evaluation mechanisms enable the model to adapt to changes in the data environment, maintaining the long-term stability of predictive results.

[0101] The prediction results are used to plan the charging and discharging strategies of the energy storage system. Combined with electricity price optimization and abnormal load identification mechanisms, this can optimize electricity costs and improve system stability.

[0102] After model optimization is complete, the model's predicted future photovoltaic power generation trends and load demand changes are applied to the energy storage system's charge and discharge strategy planning. Based on these predictions, the system dynamically adjusts the energy storage battery's charge and discharge times and power thresholds. For example, if sufficient photovoltaic power generation is predicted, the system will pre-charge the battery and prioritize the energy storage system during high-load periods, thereby reducing reliance on the grid. Furthermore, the system will develop a price optimization strategy based on fluctuations in grid electricity prices, charging during low-price periods and discharging during peak-price periods to minimize electricity costs.

[0103] In addition, to cope with special scenarios (such as equipment failure or sudden load surges), the system will combine real-time monitoring data with prediction results to trigger the abnormal load identification mechanism and dynamically adjust the energy storage strategy to ensure that the energy storage system has sufficient power reserves in emergency situations and guarantee the normal operation of critical loads.

[0104] The application of prediction results is the foundation of energy allocation control, ensuring that the energy storage system can plan charging and discharging strategies based on future supply and demand, thereby improving the utilization rate of photovoltaic power generation and reducing the phenomenon of curtailment. Furthermore, by introducing electricity price optimization and abnormal load identification mechanisms, more flexible energy allocation can be achieved in special scenarios, thereby reducing the overall operating costs of the system.

[0105] Compare real-time monitored load power usage data with forecast data, and detect short-term load surges based on rate-of-change thresholds and time windows. When a load surge exceeding the set threshold is detected, a load mutation signal is triggered, and the energy storage system's discharge strategy is dynamically adjusted to avoid over-discharge during off-peak hours.

[0106] Real-time load power consumption data is compared with forecast data. Short-term load surges are detected based on a rate-of-change threshold and time window. When a load surge exceeding the set threshold is detected, a load mutation signal is triggered and the energy storage system's discharge strategy is dynamically adjusted to avoid excessive discharge during off-peak hours. The specific steps are as follows:

[0107] By comparing the deviation between real-time collected load power consumption data and predicted data, it can identify situations where the actual load exceeds the normal range, providing a basis for sudden increase detection;

[0108] The system first compares real-time load power usage data with load forecasts generated by long-term energy supply and demand forecasting models. To ensure the accuracy of the comparison, the system synchronizes the real-time and forecast data at the same time interval (such as every hour or every minute) to ensure that both have consistent timestamps.

[0109] During the comparison, the system calculates the deviation between actual and predicted load data—that is, subtracting the predicted data from the real-time data—to create a deviation curve. If the deviation continues to increase, it indicates that the actual load is increasingly exceeding the predicted load, potentially leading to a sudden increase. To increase system sensitivity, the system also compares deviation trends within various time windows, such as load changes over the past 5 minutes, 15 minutes, or an hour.

[0110] Comparing real-time data with forecasted data is the foundation of surge detection. By calculating the deviation between the two, the system can quickly identify load conditions exceeding normal ranges. This comparison effectively leverages the results of long-term energy supply and demand forecasting models, avoiding the problem of relying solely on real-time data and ignoring changing trends, thereby improving detection accuracy.

[0111] By calculating the rate of change and fluctuation of load data, the trend and instability of load changes in a short period of time can be monitored, thereby providing early warning of sudden increase risks;

[0112] After the comparison is completed, the system will calculate the rate of change of the deviation value, that is, calculate the speed of change of the load data within a certain time window. The calculation formula of the rate of change is: For example, if the load has changed by 10 kW over the past 5 minutes, the rate of change is 2 kW / min. The system sets multiple time windows (such as 5 minutes, 15 minutes, and 30 minutes) to monitor the rate of change in different time periods and analyze the fluctuation trend of the rate of change. If the rate of change increases rapidly in a short period of time, it indicates a short-term load surge. In addition, the system also introduces a fluctuation analysis algorithm to calculate the fluctuation amplitude of the rate of change. If the fluctuation amplitude exceeds a certain threshold, it indicates that the system load is unstable, and further detection of load mutations is required.

[0113] Rate-of-change calculation and fluctuation analysis can effectively identify sudden increases in load. Compared to simple load data comparison, rate-of-change analysis can more sensitively capture rapid changes in load, providing early warning of sudden increase risks. Furthermore, fluctuation analysis across multiple time windows can effectively avoid false alarms caused by short-term noise or data anomalies, improving detection accuracy and robustness.

[0114] Compare the rate of change with the preset threshold. When the rate of change exceeds the set value, a load mutation signal is triggered, and multiple verifications are performed to improve accuracy.

[0115] The system analyzes the rate of change and fluctuations and compares them with a preset rate of change threshold. If the rate of change exceeds the threshold (for example, more than 5kW / min), the system triggers a load mutation signal, indicating an abnormal load surge.

[0116] Thresholds are typically set based on statistical analysis of historical load data, taking into account the importance of base station services and the stability of the power grid. For example, in scenarios with a surge in communications traffic, a lower threshold can be set to more sensitively detect sudden increases. During normal service, a higher threshold can be set to avoid false triggering. Furthermore, the system performs multiple validation checks on sudden changes to ensure they are not misjudged due to short-term fluctuations or data noise.

[0117] Threshold determination is the core step in triggering a sudden load change signal, directly determining the speed and accuracy of the system's response to a sudden load surge. Proper threshold setting effectively balances system sensitivity and stability, avoiding false positives and false negatives. Furthermore, multiple verification mechanisms further enhance the reliability of sudden load changes, ensuring the system's high fault tolerance in practical applications.

[0118] After triggering a load mutation signal, the energy storage system's discharge strategy is dynamically adjusted based on photovoltaic power generation, energy storage battery power status, and load demand to ensure continuous and stable power supply to the load;

[0119] When a load mutation signal is triggered, the system dynamically adjusts the energy storage system's discharge strategy based on the current photovoltaic power generation, the energy storage battery's state of charge (SOC), and grid electricity prices. Specifically, the system prioritizes reducing the energy storage battery's discharge rate to ensure the energy storage system maintains sufficient power reserves during off-peak periods.

[0120] The system also adjusts its discharge strategy based on the duration of the load surge and the availability of grid power. For example, if the load surge is short-lived, the system will adopt a partial discharge mode to only meet the power needs of critical loads. If the load surge lasts longer, the system will adjust the discharge rate to prevent premature battery depletion. Furthermore, if the load surge exceeds a certain threshold, the system can switch to grid power mode to ensure continuous power supply to the load.

[0121] The ultimate goal of load surge detection is to dynamically adjust the energy storage system's discharge strategy, ensuring stable system operation during unexpected situations. Through dynamic discharge adjustment, the system effectively avoids excessive discharge during off-peak hours, ensuring sufficient battery power during peak hours, optimizing overall electricity costs and improving system reliability.

[0122] An energy storage strategy optimization algorithm is introduced to calculate the optimal charging and discharging strategy for the energy storage system in real time based on the current photovoltaic power generation, energy storage battery charge status, and load demand forecast. This algorithm comprehensively considers grid electricity prices, load demand changes, and the health status of energy storage batteries to achieve dynamic scheduling between photovoltaic power generation, energy storage, and grid power.

[0123] An energy storage strategy optimization algorithm is introduced to calculate the optimal charging and discharging strategy for the energy storage system in real time based on the current photovoltaic power generation, energy storage battery charge status, and load demand forecast. This algorithm comprehensively considers grid electricity prices, load demand changes, and the health status of the energy storage battery. The specific steps for achieving dynamic scheduling between photovoltaic power generation, energy storage, and grid power are as follows:

[0124] First, the current load demand gap is calculated. This is the difference between the actual load demand and the power provided by photovoltaic power generation. This represents the power required to supplement the energy storage system and the grid. This is used to determine whether the energy storage system needs to be charged or discharged. The calculation expression is as follows:

[0125] ΔP load =P demand -P solar

[0126] , where ΔP load is the load demand gap, that is, the load power demand that cannot be met by photovoltaic power generation, P demand is the actual load demand, obtained by the real-time data acquisition system, P solar is the current photovoltaic power generation, which is collected in real time by the sensors of the photovoltaic power generation system;

[0127] When ΔP load When ΔP > 0, it indicates that photovoltaic power generation is insufficient and needs to be supplemented by energy storage system or grid. load When <0, it means that there is a surplus in photovoltaic power generation and the energy storage system can be charged.

[0128] Based on the calculated load demand gap ΔP load , further calculate the charge and discharge power of the energy storage battery. This step takes into account the current state of charge and the maximum charge and discharge power of the energy storage battery to ensure that the battery charge and discharge are within a reasonable range. The calculation expression is as follows:

[0129]

[0130] , where P battery It is the charge and discharge power of the energy storage battery. Positive value indicates discharge, negative value indicates charge. max is the maximum charge and discharge power of the energy storage battery, max(ΔP load , -P max ) is the maximum limit, indicating that the load gap value must not be less than the negative value of the maximum discharge power of the energy storage battery, min(max(ΔP load , -P max ), P max ) is the minimum value limit, indicating that the load gap value must not exceed the maximum charging power of the energy storage battery. SOC is the current state of charge of the energy storage battery, indicating the charging percentage of the battery;

[0131] This step ensures that the charge and discharge power of the energy storage battery does not exceed its maximum limit, and dynamically adjusts the charge and discharge power according to the battery's state of charge (SOC). As the SOC increases, the battery's charging capacity gradually decreases, thus avoiding the risk of overcharging.

[0132] To ensure the long-term service life of energy storage batteries, the impact of the battery's health status on the charge and discharge power is comprehensively considered to measure the battery's remaining life. The lower the health status, the smaller the battery's available charge and discharge capacity. The calculation expression is as follows:

[0133]

[0134] , where P battery_adjusted It is the charge and discharge power of the energy storage battery after health status correction. SOH is the health status of the energy storage battery, which indicates the remaining life percentage of the battery.

[0135] This step dynamically adjusts the charge and discharge power of the energy storage battery to reduce excessive use of batteries in poor health and extend the battery life.

[0136] When the energy storage system cannot fully meet the load demand, the grid dispatch decision is calculated based on the real-time grid electricity price and the charge and discharge power of the energy storage battery. The decision is whether to purchase electricity from the grid or sell electricity to the grid. The calculation expression is as follows:

[0137] P grid =ΔP load -P battery_adjusted

[0138] , where P grid is the grid dispatching power, which represents the power purchased from or sold to the grid;

[0139] If P grid >0, then purchase electricity from the grid;

[0140] If P grid <0, then sell electricity to the grid;

[0141] The grid electricity price is adjusted according to the real-time electricity price, and the calculation formula is as follows:

[0142] C cost =P grid ×C grid

[0143] , where C grid is the real-time grid electricity price, C cost It is the cost of purchasing or selling electricity to the power grid.

[0144] This step combines the grid electricity price to adjust the grid dispatch strategy in real time to minimize electricity costs. When the grid electricity price is low, the system tends to purchase electricity from the grid; when the grid electricity price is high, the system tends to use energy storage batteries to supply power or sell electricity to the grid to obtain income.

[0145] Through an anomaly recognition algorithm, load mutation signals are correlated and analyzed with the external grid status to identify abnormal scenarios. Based on the identification results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the system can ensure stable operation and minimize electricity costs in emergency situations.

[0146] Through an anomaly recognition algorithm, load mutation signals are correlated with external grid status and analyzed to identify abnormal scenarios. Based on the identification results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the system is ensured to operate stably and minimize electricity costs in emergencies. The specific steps are as follows:

[0147] First, by correlating the real-time monitored load surge signal with external grid status data (such as grid frequency, voltage fluctuation, and power outage information), we calculate the load sudden change intensity parameter to quantify the degree of abnormal load change. The load sudden change intensity parameter calculation expression is as follows:

[0148]

[0149] , where I LT is the load mutation intensity parameter, ΔL is the load change within the time interval Δt, Δt is the time interval, V dev It is the deviation value of the grid voltage, that is, the difference between the actual voltage and the standard voltage, F dev is the deviation value of the grid frequency, that is, the difference between the actual frequency and the standard frequency. α, β, and γ are all weight parameters. α is the weight of the load change rate, which indicates the influence of load change on the recognition of sudden abnormal scenarios. If load fluctuation is the main cause of sudden abnormalities, increase the value of α. For example, in communication base stations, load fluctuation is usually a key abnormal signal. β is the weight of the voltage deviation value, which indicates the influence of grid voltage fluctuation on the recognition of sudden abnormal scenarios. When grid voltage instability is the main cause of system abnormalities, increase the value of β. For example, in industrial power scenarios, voltage fluctuations may cause equipment damage. γ is the weight of the frequency deviation value, which indicates the influence of grid frequency fluctuation on the recognition of sudden abnormal scenarios. When grid frequency instability is the main signal of abnormal scenarios, increase the value of γ. For example, in large-scale power grids, frequency fluctuations are usually a manifestation of grid load imbalance.

[0150] By calculating the load sudden change intensity parameter I LT The system can comprehensively consider the load surge signal and the changes in the external grid status to identify the intensity of the current abnormal scenario. For example, when the load surge is accompanied by fluctuations in grid voltage and frequency, the system will identify it as a grid failure or load abnormality scenario and enter adaptive scheduling mode.

[0151] After identifying an abnormal scenario, calculate the priority power supply factor for critical loads to determine the proportion of load power supply that is prioritized in abnormal situations. The calculation expression is as follows:

[0152]

[0153] , where P critical is the priority power supply factor for critical loads, W critical is the total power demand of the critical loads, W total is the sum of the power demands of all loads, and λ is the adjustment coefficient, which is used to control the priority power supply weight of key loads in abnormal scenarios;

[0154] By calculating P critical , the system dynamically adjusts the power supply priority of key loads. The more serious the abnormal scenario (i.e. I LT The higher the value, the greater the system's priority power supply to critical loads, ensuring continuous operation of key services during power shortages or grid failures. For example, in a communication base station, critical loads may include communication core equipment and network transmission equipment.

[0155] Prioritize power supply factor P according to critical loads critical Based on the current state of charge of the energy storage system, the discharge rate adjustment parameters of the energy storage system are calculated, and the discharge strategy of the energy storage system is dynamically adjusted to ensure stable operation of the energy storage system and minimize electricity costs. The calculation expression is as follows:

[0156]

[0157] , where R discharge is the discharge rate adjustment parameter of the energy storage system, P max is the maximum charge and discharge power of the energy storage battery, SOC is the current state of charge of the energy storage battery, which indicates the battery charge percentage, δ is the cost adjustment coefficient, which is used to balance the grid power supply cost and battery discharge cost, C grid is the real-time grid electricity price, C battery is the unit cost of battery discharge.

[0158] By calculating R dischargeThe system can dynamically adjust the energy storage system's discharge rate based on the severity of the abnormal scenario and the current state of the energy storage system. When electricity prices are high or the grid is faulty, the system will prioritize using energy storage batteries for power supply; when electricity prices are low, it will prioritize reducing battery discharge, minimizing energy storage system losses and lowering electricity costs.

[0159] Implementation 1: To prevent the risk of overdischarge of storage batteries during off-peak hours in a solar-powered energy storage and charging system, a dynamic energy storage management solution based on short-term load surge detection is proposed. This solution, centered around real-time data acquisition, load surge detection, and dynamic discharge adjustment, continuously monitors and adjusts the energy storage system's discharge strategy to rapidly respond to abnormal load changes, thereby ensuring efficient system operation and stable power supply.

[0160] The system collects real-time data on photovoltaic power generation, energy storage battery state of charge (SOC), and load power consumption from the photovoltaic power generation system, energy storage battery management system (BMS), and smart meters at the load end. After cleaning, normalization, and time series processing, this data is input into the long-term energy supply and demand forecasting model to generate forecasts of future photovoltaic power generation trends and load demand changes. During actual operation, the system compares the real-time collected load data with the forecasted data and calculates the deviation between the two. If the deviation value continues to increase and the rate of change exceeds the preset threshold, it indicates that the load power consumption has experienced abnormal fluctuations, that is, a short-term load surge.

[0161] The system uses rate-of-change calculation and fluctuation analysis algorithms to dynamically monitor changes in real-time data. By calculating the rate of change of load data over a set time window (e.g., the past 5 minutes, 15 minutes, or 30 minutes), it can identify load fluctuation trends. If the rate of change increases significantly within a short period of time, it indicates a risk of a sudden load surge. To avoid false alarms caused by short-term noise or incidental events, the system performs multiple verifications and analyzes the fluctuation amplitude of the rate of change to ensure the reliability of the load surge signal.

[0162] When the system detects a sudden load surge exceeding a threshold, it immediately triggers a load mutation signal and initiates the energy storage system's dynamic discharge adjustment strategy. During this adjustment, the system dynamically adjusts the energy storage system's discharge rate based on the current photovoltaic power generation, the energy storage battery's charge state, and load demand. For example, when a sudden load surge occurs, the system prioritizes reducing power supply to non-critical loads, preserving more power for critical loads. Simultaneously, the system reduces the energy storage battery's discharge rate to extend its power supply life and prevent premature depletion.

[0163] The advantages of this implementation lie in its strong real-time performance, high sensitivity, and adaptability. By monitoring load changes in real time, the system can quickly respond to sudden load increases and dynamically adjust discharge strategies to avoid over-discharge of the energy storage batteries. This solution also effectively improves system stability and reliability, ensuring the continued stable operation of base stations and key equipment during sudden load fluctuations.

[0164] Implementation 2: To reduce overall electricity costs and improve the economic benefits of the energy storage system, an energy allocation strategy combined with grid price optimization is proposed. This solution dynamically adjusts the energy flow between photovoltaic power generation, energy storage, and grid power, rationally utilizing grid price fluctuations to optimize electricity costs and efficiently utilize energy storage batteries.

[0165] The system accesses the grid's real-time electricity price data interface to obtain current electricity price information, including peak and valley prices, time-of-use prices, and dynamic prices. It then establishes an internal price change model that analyzes historical price data and current price fluctuation trends to predict future price fluctuations. For example, the system can identify daily low and peak price periods and mark these periods as charging and discharging windows for the energy storage system.

[0166] Based on the electricity price fluctuation model, the system dynamically adjusts the energy storage system's charging and discharging strategies. During off-peak periods, the system prioritizes grid power for charging the energy storage batteries, maximizing their reserve capacity. During peak periods, the system prioritizes using the energy storage batteries to power the load, reducing the use of high-priced grid power. This strategy effectively reduces the system's overall electricity costs, while increasing the utilization rate of photovoltaic power generation and preventing curtailment.

[0167] In the event of a sudden load increase, the system prioritizes checking the charge status of the energy storage battery. If the battery's charge level is insufficient to meet the current load demand, the system automatically switches to grid power, avoiding power outages caused by insufficient power. Furthermore, the system selects appropriate grid power hours based on the electricity pricing model, minimizing the use of expensive electricity and reducing electricity costs.

[0168] This solution offers advantages in terms of cost-effectiveness, flexibility, and intelligence. By incorporating an electricity price optimization strategy, the system can optimally allocate energy across different electricity price periods, minimizing electricity costs. Furthermore, in the event of sudden load fluctuations, the system can flexibly switch to the grid, ensuring continuous and stable power supply to critical loads and improving overall system reliability and economic efficiency.

[0169] Implementation 3: To further enhance the intelligence and adaptability of energy storage systems, a machine learning-based adaptive energy storage system charging and discharging strategy optimization solution is proposed. This solution uses a machine learning algorithm to analyze and learn from historical data, continuously optimizing the energy storage system's charging and discharging strategy and achieving adaptive adjustments for different scenarios.

[0170] The system uses long-term data collection and storage, including photovoltaic power generation, energy storage battery charge status, and load power consumption, to model and analyze historical data using machine learning algorithms (such as LSTM and XGBoost) to identify energy supply and demand variations in different scenarios. For example, the system can identify seasonal power generation patterns and power consumption patterns in different time periods, allowing it to proactively adjust energy storage system strategies.

[0171] Based on the model's analysis, the system generates adaptive charging and discharging strategies. During periods of ample photovoltaic power generation, the system pre-charges the energy storage battery based on forecasts. During peak load demand periods, the system prioritizes the use of the energy storage battery, reducing reliance on grid power. Furthermore, in the event of sudden load fluctuations, the system dynamically adjusts the discharge strategy to ensure the energy storage battery's charge level can continuously meet the needs of critical loads.

[0172] The system leverages the anomaly detection capabilities of its machine learning models to identify abnormalities such as equipment failures, external grid outages, and surges in communications traffic. It then automatically adjusts the energy storage system's strategy based on these findings. For example, if a grid outage is detected, the system automatically switches to energy storage power supply mode and adjusts the discharge rate to extend the power supply duration and ensure the normal operation of critical equipment.

[0173] The advantages of this solution lie in its high intelligence, adaptability, and accurate predictions. Through continuous optimization of machine learning algorithms, the system can flexibly adjust energy storage strategies in different scenarios, achieving efficient utilization of photovoltaic power generation and providing reliable power supply during abnormal load fluctuations. Furthermore, the adaptive charging and discharging strategy effectively reduces energy waste in the energy storage system, improving the overall economic efficiency and stability of the system.

[0174] The present invention monitors load power consumption data in real time, combines it with a long-term energy supply and demand forecasting model, and dynamically adjusts the discharge strategy of the energy storage system, thereby effectively avoiding the problem of excessive discharge of energy storage batteries during non-peak periods. Compared with traditional fixed scheduling strategies, this solution can identify load surges in real time and flexibly adjust the discharge rate of energy storage batteries according to the surge signal, ensuring sufficient energy storage during peak periods, reducing dependence on grid power, and lowering overall electricity costs. At the same time, by combining the grid electricity price optimization strategy, the system implements a strategy of storing electricity during low-price periods and discharging during high-price periods, greatly improving the economic benefits of the energy storage system, avoiding the phenomenon of abandoned photovoltaic power generation, and maximizing the utilization efficiency of green energy.

[0175] By introducing a load surge detection mechanism and an adaptive scheduling algorithm, the present invention can automatically trigger the adjustment strategy of the energy storage system when abnormal load changes are detected, and quickly respond to various sudden load change scenarios, such as a surge in communication services, equipment failures, or power grid outages. This automated response mechanism ensures that the energy storage system can prioritize the power supply needs of critical loads when the load fluctuates abnormally, avoiding power outages caused by premature exhaustion of the energy storage battery. At the same time, the system can flexibly adjust the discharge mode according to the duration of the surge, adopting a gradual discharge or partial discharge strategy to further improve the battery life of the energy storage battery, ensure the overall stability of the system and the reliability of power supply, and provide continuous power protection for the user's core business.

[0176] The invention provides Figure 2 The data-driven solar-storage-charging energy allocation system shown in the figure includes a data acquisition and preprocessing module, a long-term energy prediction module, a load surge detection and response module, an energy storage strategy optimization module, and an anomaly identification and adaptive scheduling module:

[0177] The data acquisition and preprocessing module collects the real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data in real time, and cleans, normalizes, and time-series the collected data to eliminate data outliers and missing values, ensuring the accuracy and continuity of the input data;

[0178] The long-term energy forecasting module uses machine learning to build a long-term energy supply and demand forecasting model based on historical photovoltaic power generation, energy storage system charge and discharge records, and load power consumption patterns. This model predicts future photovoltaic power generation trends and load demand changes, allowing for the pre-planning of energy storage system charge and discharge strategies.

[0179] The load surge detection and response module compares real-time monitored load power usage data with predicted data. It detects short-term load surges based on a rate-of-change threshold and a time window. When a load surge exceeding a set threshold is detected, a load mutation signal is triggered and the energy storage system's discharge strategy is dynamically adjusted to avoid over-discharge during off-peak hours.

[0180] The energy storage strategy optimization module introduces an energy storage strategy optimization algorithm. Based on the current photovoltaic power generation, energy storage battery power status and load demand forecast, the optimal charging and discharging strategy of the energy storage system is calculated in real time. The algorithm comprehensively considers the grid electricity price, load demand changes and the health status of the energy storage battery to achieve dynamic scheduling between photovoltaic power generation, energy storage and grid power.

[0181] The anomaly identification and adaptive scheduling module uses an anomaly identification algorithm to correlate and analyze load mutation signals with the external grid status, identify abnormal scenarios, and based on the identification results, execute an adaptive scheduling algorithm to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, it ensures the stable operation of the system and minimizes electricity costs in emergency situations.

[0182] The data-driven photovoltaic storage and charging energy allocation control method provided in an embodiment of the present invention is implemented through the above-mentioned data-driven photovoltaic storage and charging energy allocation system. The specific methods and processes of the data-driven photovoltaic storage and charging energy allocation system are detailed in the embodiment of the above-mentioned data-driven photovoltaic storage and charging energy allocation control method, which will not be repeated here.

[0183] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0184] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0185] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0186] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0187] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0188] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0189] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0190] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0191] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0192] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A data-driven solar energy storage and charging energy allocation control method, characterized in that: The following steps are involved: Real-time data collection of photovoltaic power generation system power generation, current power status of energy storage batteries and load power consumption is carried out, and the collected data is cleaned, normalized and time-series processed to ensure the accuracy and continuity of input data; Based on historical PV power generation, energy storage system charge and discharge records, and load power usage patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model. This model predicts future PV power generation trends and load demand changes, allowing for the planning of energy storage system charge and discharge strategies. Compare real-time monitored load power consumption data with forecast data to detect short-term load surges based on change rate thresholds and time windows; Introducing an energy storage strategy optimization algorithm to calculate the optimal charging and discharging strategy for the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status, and load demand forecast; Through an anomaly recognition algorithm, load mutation signals are correlated and analyzed with the external grid status to identify abnormal scenarios. Based on the identification results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the system can ensure stable operation and minimize electricity costs in emergency situations. The specific steps for comparing real-time monitored load power usage data with predicted data and detecting short-term load surges based on the rate of change threshold and time window are as follows: By comparing the deviation between real-time collected load power consumption data and predicted data, it can identify situations where the actual load exceeds the normal range, providing a basis for sudden increase detection; By calculating the rate of change and fluctuation of load data, the trend and instability of load changes in a short period of time can be monitored, thereby providing early warning of sudden increase risks; Compare the rate of change with the preset threshold. When the rate of change exceeds the set value, a load mutation signal is triggered, and multiple verifications are performed to improve accuracy. After the load mutation signal is triggered, the discharge strategy of the energy storage system is dynamically adjusted according to the photovoltaic power generation, the power status of the energy storage battery and the load demand to ensure continuous and stable power supply to the load.

2. The data-driven solar energy storage and charging energy allocation control method according to claim 1 is characterized in that: The real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data are collected in real time, and the collected data is cleaned, normalized, and time-series processed to ensure the accuracy and continuity of the input data. The specific steps are as follows: Real-time data collection and transmission of photovoltaic power generation, energy storage battery power, and load power consumption are achieved through sensors and data transmission protocols to ensure data integrity and real-time performance; Clean the collected data, remove outliers and supplement missing values, and unify the data frequency through resampling to ensure the continuity and rationality of the data; Normalize data from different sources to the same scale to prevent numerical differences between features from affecting the accuracy of model decisions. The processed data is arranged in chronological order as time series data to capture periodic and trend changes, providing a time series input basis for load forecasting and scheduling strategies.

3. The data-driven solar energy storage and charging energy allocation control method according to claim 1, characterized in that: Based on historical PV power generation, energy storage system charge and discharge records, and load power usage patterns, a machine learning model is used to build a long-term energy supply and demand forecasting model. This model predicts future PV power generation trends and load demand changes, allowing for pre-planning of the energy storage system's charge and discharge strategies. The specific steps are as follows: By selecting key features to construct a time series dataset, we can provide high-quality input data for model training. Select a machine learning model suitable for time series data and train the model through cross-validation and parameter adjustment to improve prediction accuracy and robustness; Evaluate model performance through various indicators and optimize the model through hyperparameter adjustment and real-time evaluation to adapt it to dynamic data changes; The prediction results are used to plan the charging and discharging strategies of the energy storage system, and combined with electricity price optimization and abnormal load identification mechanisms to achieve electricity cost optimization and improve system stability.

4. The data-driven solar energy storage and charging energy allocation control method according to claim 1, characterized in that: The energy storage strategy optimization algorithm is introduced to calculate the optimal charging and discharging strategy of the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status and load demand forecast value. The specific steps are as follows: First, the current load demand gap is calculated, that is, the difference between the actual load demand and the power provided by photovoltaic power generation. This is used to determine whether the energy storage system needs to be charged or discharged. The calculation expression is as follows: , where is the load demand gap, is the actual load demand, is the current photovoltaic power generation; Based on the calculated load demand gap , further calculate the charging and discharging power of the energy storage battery, the calculation expression is as follows: , where is the charging and discharging power of the energy storage battery, is the maximum charge and discharge power of the energy storage battery, It is the maximum value limit, which means that the load gap value shall not be less than the negative value of the maximum discharge power of the energy storage battery. It is the minimum limit, which means that the load gap value must not exceed the maximum charging power of the energy storage battery. It is the current state of charge of the energy storage battery, indicating the battery's charge percentage.

5. The data-driven solar energy storage and charging energy allocation control method according to claim 4 is characterized in that: In order to ensure the long-term service life of the energy storage battery, the impact of the battery's health status on the charge and discharge power is comprehensively considered. The calculation expression is as follows: , where It is the charging and discharging power of the energy storage battery after correction of health status. The health status of the energy storage battery; When the energy storage system cannot fully meet the load demand, the grid dispatch decision is calculated based on the real-time grid electricity price and the charge and discharge power of the energy storage battery. The decision is whether to purchase electricity from the grid or sell electricity to the grid. The calculation expression is as follows: , where is the grid dispatching power; like , then purchase electricity from the grid; like , then sell electricity to the grid; The grid electricity price is adjusted according to the real-time electricity price, and the calculation formula is as follows: , where is the real-time grid electricity price, It is the cost of purchasing or selling electricity to the power grid.

6. The data-driven solar energy storage and charging energy allocation control method according to claim 1, characterized in that: Through an anomaly recognition algorithm, load mutation signals are correlated with external grid status and analyzed to identify abnormal scenarios. Based on the identification results, an adaptive scheduling algorithm is executed to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, the system is ensured to operate stably and minimize electricity costs in emergencies. The specific steps are as follows: First, by correlating and analyzing the real-time monitored load surge signal with the external grid status data, the load sudden change intensity parameter is calculated to quantify the degree of abnormal load change. The calculation expression of the load sudden change intensity parameter is as follows: , where is the load mutation intensity parameter, is in the time interval The load variation within is the time interval, It is the deviation value of the grid voltage, that is, the difference between the actual voltage and the standard voltage. It is the deviation value of the grid frequency, that is, the difference between the actual frequency and the standard frequency. 、 as well as are weight parameters, is the weight of the load change rate, which indicates the impact of load change on the recognition of sudden abnormal scenes. is the weight of the voltage deviation value, which indicates the influence of grid voltage fluctuation on the recognition of sudden abnormal scenes. is the weight of the frequency deviation value, which indicates the influence of the power grid frequency fluctuation on the recognition of sudden abnormal scenarios; After identifying an abnormal scenario, calculate the priority power supply factor for critical loads to determine the proportion of load power supply that is prioritized in abnormal situations. The calculation expression is as follows: , where is the priority power supply factor for critical loads, is the sum of the power demands of the critical loads, is the sum of the power demands of all loads, is the adjustment coefficient, which is used to control the priority power supply weight of key loads in abnormal scenarios; Prioritize power supply factors based on critical loads Based on the current state of charge of the energy storage system, the discharge rate adjustment parameters of the energy storage system are calculated, and the discharge strategy of the energy storage system is dynamically adjusted to ensure stable operation of the energy storage system and minimize electricity costs. The calculation expression is as follows: , where is the discharge rate adjustment parameter of the energy storage system, is the maximum charge and discharge power of the energy storage battery, It is the current state of charge of the energy storage battery, indicating the battery's charge percentage. is the cost adjustment coefficient, is the real-time grid electricity price, is the unit cost of battery discharge.

7. A data-driven solar energy storage and charging energy allocation system, used to implement the data-driven solar energy storage and charging energy allocation control method according to any one of claims 1 to 6, characterized in that: It includes data acquisition and preprocessing module, long-term energy prediction module, load surge detection and response module, energy storage strategy optimization module, and anomaly identification and adaptive scheduling module: The data acquisition and preprocessing module collects the real-time power generation of the photovoltaic power generation system, the current power status of the energy storage battery, and the load power consumption data in real time, and cleans, normalizes, and time-series the collected data to ensure the accuracy and continuity of the input data; The long-term energy forecasting module uses machine learning to build a long-term energy supply and demand forecasting model based on historical photovoltaic power generation, energy storage system charge and discharge records, and load power consumption patterns. This model predicts future photovoltaic power generation trends and load demand changes, allowing for the pre-planning of energy storage system charge and discharge strategies. The load surge detection and response module compares real-time monitored load power usage data with predicted data and detects short-term load surges based on the rate of change threshold and time window. The energy storage strategy optimization module introduces an energy storage strategy optimization algorithm to calculate the optimal charging and discharging strategy of the energy storage system in real time based on the current photovoltaic power generation, energy storage battery power status and load demand forecast value; The anomaly identification and adaptive scheduling module uses an anomaly identification algorithm to correlate and analyze load mutation signals with the external grid status, identify abnormal scenarios, and based on the identification results, execute an adaptive scheduling algorithm to prioritize the power supply needs of critical loads. By adjusting the discharge rate of the energy storage system and the power exchange between the grid, it ensures the stable operation of the system and minimizes electricity costs in emergency situations.

Images