Energy storage equipment power balance dynamic load automatic regulation and control method and system

Abstract

The invention discloses an energy storage equipment power balance dynamic load automatic regulation and control method and system, and the method comprises the steps: building a charging power optimization model based on an electricity price policy divided in peak and valley time periods, combining historical electricity demand data, and obtaining the optimal charging power in each time period; the method comprises the following steps: constructing a discharge power dynamic adjustment model through operation state parameters acquired by a real-time environment parameter acquisition device in combination with real-time electricity demand data, and acquiring optimal discharge power in each time period; parameters of the two models are optimized, and the load state based on the optimal charging and discharging power is balanced; based on the historical regulation and control data, the overload condition under the abnormal factors is predicted; and on the basis of a power imbalance condition, preferentially ensuring power supply of a key load according to a power distribution priority and executing energy storage equipment state self-checking. The method has the advantages that the charging power and the discharging power are optimized in combination with the electricity price and the real-time requirement, so that the load state is balanced, the energy cost is reduced, and the equipment overload risk is avoided.

Description

Technical Field

[0001] The present invention relates to load regulation technology, and particularly to a method and system for automatically regulating dynamic loads for power balance of energy storage devices. Background Art

[0002] With the rapid advancement of clean energy and the continuous expansion of the power supply network, means of electrical energy storage have gradually become the core element for ensuring the continuous utilization of green energy. Energy storage devices represented by electrochemical energy storage play a core role in regulating power supply and demand, optimizing energy utilization efficiency, and maintaining the reliable operation of the power grid in the power transmission and distribution network. However, limited by the inherent volatility and randomness characteristics of natural energy such as wind and solar power generation, energy storage units face multi-dimensional operation management problems when dealing with dynamic load regulation.

[0003] Most of the current power load regulation methods for energy storage devices on the market adopt a power distribution strategy based on preset settings, usually relying on simple time period division or fixed charge and discharge modes to regulate the load. These methods usually set fixed charge power and discharge power values to meet different load demands, but this static regulation method is difficult to adapt to complex and dynamic electricity consumption demands. Many methods cannot fully consider the peak-valley electricity price differences of the power grid, and still perform unnecessary charging or discharging during peak hours, resulting in energy waste and increased costs. Traditional energy storage devices do not flexibly adjust power according to real-time environmental parameters (such as temperature, load changes, etc.), resulting in the system being unable to respond in a timely manner when the load changes greatly, and situations such as overload or energy efficiency loss may occur. Summary of the Invention

[0004] In order to improve the existing power load regulation methods and systems for energy storage devices, a method and system for automatically regulating dynamic loads for power balance of energy storage devices are provided. This method optimizes the charge and discharge power to ensure the full utilization of power resources during different time periods, effectively reducing electricity price costs, and balancing the load state during power demand fluctuations. By precisely controlling the charge and discharge power, the system can achieve efficient utilization and optimized scheduling of energy while ensuring the power supply to critical loads.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for automatically regulating dynamic loads for power balance of energy storage devices, comprising:

[0007] Constructing a bidirectional power coupling interface for the energy storage device;

[0008] Based on the electricity price policy divided by peak-valley time periods, combined with historical electricity demand data, constructing a charging power optimization model to obtain the charging power within each time period;

[0009] The operating status parameters obtained by the real-time environmental parameter acquisition device are combined with the real-time electricity demand data to construct a dynamic adjustment model for discharge power, and the discharge power in each time period is obtained.

[0010] Based on the charging power optimization model and the dynamic adjustment model for discharge power, the parameters of the two models are optimized to balance the load status based on the optimal charging and discharging power.

[0011] Based on historical regulation data, the overload situation under abnormal factors is predicted and compared with the real-time monitoring data.

[0012] Based on the power imbalance situation, according to the power distribution priority, the power supply of critical loads is guaranteed first and the self-check of the energy storage device status is performed.

[0013] Preferably, the electricity price policy based on peak-valley period division, combined with historical electricity demand data, constructs a charging power optimization model, and the specific steps for obtaining the charging power in each time period include:

[0014] Obtain the electricity price policy in the area where the energy storage device is located and construct a piecewise linear electricity price function in the time dimension.

[0015] Based on the power supply capacity of the power grid, the currently acceptable charging power of the energy storage device and the safety constraint power, obtain the dynamic charging power fluctuation range.

[0016] Obtain the electricity demand data in different time periods based on historical data.

[0017] Based on the obtained electricity demand data in different time periods, obtain the charging power functions in different time periods.

[0018] Based on the constructed piecewise linear electricity price function and the charging power functions in different time periods, construct a charging power optimization model, and calculate the lowest electricity cost by minimizing the objective function.

[0019] Based on the minimization calculation of the objective function value, obtain the charging power in each time period under the condition of minimizing the electricity cost.

[0020] Preferably, the specific steps for the operating status parameters obtained by the real-time environmental parameter acquisition device, combined with the real-time electricity demand data, to construct a dynamic adjustment model for discharge power and obtain the discharge power in each time period include:

[0021] Obtain the surface temperature distribution of the energy storage device through the temperature sensor array and calculate the temperature gradient field strength.

[0022] Calculate the environmental humidity influence factor through the humidity sensor data.

[0023] Obtain the real-time electricity demand data through the ammeter.

[0024] Based on the acquired real-time electricity demand data, obtain the real-time charging power function;

[0025] Based on the acquired real-time operating state parameter data, construct a discharge power dynamic adjustment model, correct the real-time charging power function, and obtain the discharge power within each time period.

[0026] Preferably, optimizing the parameters of the two models based on the charging power optimization model and the discharge power dynamic adjustment model, and balancing the load status based on the optimal charging and discharging power specifically includes:

[0027] Based on the charging power and discharge power within each time period obtained from the charging power optimization model and the discharge power dynamic adjustment model, obtain the average load of the energy storage device within each time period;

[0028] By adjusting the start time of charging and discharging and the magnitude of the charging and discharging power, obtain several groups of adjusted sample data;

[0029] Based on the adjusted sample data, obtain the load conditions of the energy storage device under various conditions, and obtain the sample parameter data smaller than the average load;

[0030] Based on the sample parameter data smaller than the average load, calculate the corresponding electricity bill data;

[0031] By assigning weights to the load of the energy storage device and the electricity bill, calculate and obtain the sample parameter data with the lowest score, and obtain the optimal charging and discharging power based on the sample parameter data.

[0032] Preferably, predicting the overload situation under abnormal factors based on historical regulation data and comparing it with real-time monitoring data specifically includes:

[0033] Based on historical regulation data, obtain the overload data of the charging and discharging power during large-scale events and holidays;

[0034] Based on the overload data, perform feature extraction, obtain the change trend of the electricity demand of the energy storage device before and after overload, and construct an overload prediction model;

[0035] Substitute the real-time detected operation data of the energy storage device into the overload prediction model, perform real-time matching with the change trend data of the electricity demand before overload through dynamic time warping, align the real-time window data with the historical window data before overload in time series, and calculate the DTW distance to obtain the change trend similarity;

[0036] Based on the obtained change trend similarity, calculate the confidence level of the similarity, and judge whether the current energy storage device will have an overload situation based on the confidence level;

[0037] If there is a conflict between the predicted result and the actual result, the overload prediction model is reconstructed, the parameter model that generates errors is regenerated to obtain the prediction result, and the parameter model is used as the key training parameter.

[0038] Preferably, based on the power imbalance situation, giving priority to ensuring the power supply of critical loads according to the power distribution priority and performing self-check on the state of energy storage devices specifically includes:

[0039] Based on the power imbalance under overload conditions, giving priority to ensuring the power supply of critical loads according to the power distribution priority;

[0040] The specific power distribution priority is as follows:

[0041] The first priority is to ensure the power supply of critical loads, the second priority is the self-maintaining power of the energy storage system, the third priority is the power grid feedback power regulation, and the fourth priority is the scheduling of standby energy storage units;

[0042] The specific implementation of the self-check on the state of energy storage devices includes:

[0043] Checking the remaining power of the energy storage device and evaluating whether it can support the load demand;

[0044] Detecting the charge and discharge state of the energy storage device to confirm whether the device is working properly;

[0045] Evaluating the health state of the energy storage device, including parameters such as the aging degree of the battery, battery voltage and internal resistance;

[0046] Based on the self-check result, the system dynamically adjusts the charge and discharge strategy of the energy storage device to ensure the power supply of priority loads.

[0047] Furthermore, an automatic dynamic load regulation system for power balance of energy storage devices is proposed, including:

[0048] Distributed sensors: The real-time distributed sensors are mainly used to obtain various state data during the operation of energy storage devices;

[0049] Charging module: The charging module is mainly used to obtain electric energy from the power grid;

[0050] Discharging module: The discharging module is mainly used to provide power to the user end;

[0051] Bidirectional power coupling interface: The bidirectional power coupling interface is mainly used to realize the physical layer decoupling of the charging module and the discharging module, allowing the charging circuit and the discharging circuit to operate independently simultaneously throughout the day;

[0052] Model construction module: The model construction module is mainly used to construct a charging power optimization model, a discharging power dynamic adjustment model, and an overload prediction model;

[0053] Optimization module: The optimization module is mainly used to dynamically adjust the load conditions in each time period based on the optimal charging power and the optimal discharging power;

[0054] Overload prediction module: The overload prediction module is mainly used to compare the real-time operation data based on the historical regulation data and predict the trend of overload;

[0055] Status self-check module: The status self-check module is mainly used to self-check the energy storage device after overload occurs;

[0056] Database module: The database module is mainly used to store the operation status data of the energy storage device, power overload abnormal data, etc.;

[0057] Processor: The processor is mainly used for the calculation process of each formula and the construction and calculation process of each model.

[0058] Compared with the prior art, the advantages of the present invention are as follows:

[0059] By constructing a bi-directional power coupling interface, the two can operate independently in all-weather periods, thereby improving the flexibility and stability of the energy storage system. With the support of the charging power optimization model, combined with the peak-valley electricity price policy and historical electricity demand data, the charging power in each time period can be accurately calculated, effectively reducing the energy cost and improving the charging efficiency of the system. At the same time, through the real-time environmental parameter acquisition device, combined with the electricity demand data, a dynamic adjustment model of the discharging power is constructed to achieve precise adjustment of the discharging power and ensure the discharging power output under different load conditions. By optimizing the charging and discharging power, the load status can be balanced, energy waste can be reduced, and while ensuring the efficient operation of the energy storage system, equipment overload caused by power imbalance can be avoided. This method can not only predict and timely respond to the overload risk under abnormal factors, but also give priority to ensuring the power supply of key loads when power imbalance occurs, improving the reliability and safety of the system. The introduction of the energy storage device status self-check function also provides real-time guarantee for system maintenance, ensuring the stability and sustainable operation of the energy storage system under various working conditions. Brief Description of the Drawings

[0060] Figure 1 It is a schematic diagram of the method proposed by the present invention;

[0061] Figure 2 It is a schematic diagram of obtaining the charging power proposed by the present invention;

[0062] Figure 3 It is a schematic diagram of obtaining the discharging power proposed by the present invention;

[0063] Figure 4 It is a schematic diagram of load balancing proposed by the present invention;

[0064] Figure 5 Schematic diagram of overload prediction proposed by the present invention;

[0065] Figure 6 Schematic diagram of imbalance regulation and self - inspection proposed by the present invention;

[0066] Figure 7 Architecture diagram of the electronic device in this solution;

[0067] Figure 8 Schematic diagram of the structure of the computer - readable storage medium in this solution. Detailed implementation manners

[0068] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0069] The power balance dynamic load automatic regulation system for energy storage devices includes:

[0070] Distributed sensors: The real - time distributed sensors are mainly used to obtain various state data during the operation of energy storage devices;

[0071] Charging module: The charging module is mainly used to obtain electric energy from the power grid;

[0072] Discharging module: The discharging module is mainly used to provide power to the usage end;

[0073] Bidirectional power coupling interface: The bidirectional power coupling interface is mainly used to achieve physical - layer decoupling of the charging module and the discharging module, allowing the charging loop and the discharging loop to operate independently simultaneously throughout the day;

[0074] Model construction module: The model construction module is mainly used to construct a charging power optimization model, a discharging power dynamic adjustment model, and an overload prediction model;

[0075] Optimization module: The optimization module is mainly used to dynamically adjust the load conditions in each time period based on the optimal charging power and the optimal discharging power;

[0076] Overload prediction module: The overload prediction module is mainly used to compare the real - time operation data based on historical regulation data and predict the trend of overload occurrence;

[0077] Status self - inspection module: The status self - inspection module is mainly used to self - inspect the energy storage device after overload occurs;

[0078] Database module: The database module is mainly used to store the operation status data of energy storage devices, power overload abnormal data, etc.;

[0079] Processor: The processor is mainly used for the calculation processes of various formulas and the construction and calculation processes of various models.

[0080] Refer to Figure 1 As shown, the dynamic load automatic regulation method for power balance of energy storage devices includes:

[0081] Step 1: Construct a bidirectional power coupling interface for the energy storage device;

[0082] Step 2: Based on the electricity price policy divided by peak and valley periods, combined with historical electricity demand data, construct a charging power optimization model to obtain the charging power in each time period;

[0083] Step 3: Through the operating state parameters obtained by the real-time environmental parameter acquisition device, combined with the real-time electricity demand data, construct a discharge power dynamic adjustment model to obtain the discharge power in each time period;

[0084] Step 4: Based on the charging power optimization model and the discharge power dynamic adjustment model, optimize the parameters of the two models and balance the load status based on the optimal charging and discharging power;

[0085] Step 5: Based on historical regulation data, predict the overload situation under abnormal factors and compare it with the real-time monitoring data;

[0086] Step 6: Based on the power imbalance situation, preferentially ensure the power supply of critical loads according to the power distribution priority and perform a self-check on the status of the energy storage device.

[0087] Refer to Figure 2 As shown, based on the electricity price policy divided by peak and valley periods, combined with historical electricity demand data, constructing a charging power optimization model to obtain the charging power in each time period specifically includes:

[0088] Obtain the electricity price policy of the area where the energy storage device is located and construct a piecewise linear electricity price function in the time dimension;

[0089] Obtain the dynamic charging power fluctuation range based on the grid's available power supply, the currently acceptable charging power of the energy storage device, and the safety constraint power;

[0090] Obtain the electricity demand data in different time periods based on historical data;

[0091] Based on the obtained electricity demand data in different time periods, obtain the charging power functions in different time periods;

[0092] Based on the constructed piecewise linear electricity price function and the charging power functions in different time periods, construct a charging power optimization model and calculate the lowest electricity cost by minimizing the objective function;

[0093] Based on the minimization calculation of the objective function value, the charging power in each time period under the condition of minimizing the electricity cost is obtained.

[0094] It can be understood that the power supply capacity of the power grid may fluctuate due to regional differences, seasonal changes or emergencies, resulting in the system being unable to continuously provide stable electric energy. To address the problem of unstable power grid supply, a dynamic adjustment mechanism can be designed to dynamically adjust the charging power according to the real-time load situation of the power grid (for example, real-time load monitoring data). When the power supply capacity of the power grid is low, the charging power can be automatically reduced to ensure the stability of the power grid.

[0095] Refer to Figure 3 As shown, obtaining the specific discharge power in each time period by constructing a discharge power dynamic adjustment model based on the operating state parameters obtained by the real-time environmental parameter acquisition device and combining the real-time power consumption demand data specifically includes:

[0096] Obtain the surface temperature distribution of the energy storage device through the temperature sensor array and calculate the temperature gradient field strength;

[0097] Calculate the environmental humidity influence factor through the humidity sensor data;

[0098] Obtain the real-time power consumption demand data through the ammeter;

[0099] Based on the obtained real-time power consumption demand data, obtain the real-time charging power function;

[0100] Based on the obtained real-time operating state parameter data, construct a discharge power dynamic adjustment model, correct the real-time charging power function, and obtain the discharge power in each time period.

[0101] It can be understood that when the environmental humidity deviates from the optimal operating humidity, the air thermal conductivity and convective heat transfer ability change significantly. In a high-humidity environment, moisture adsorption may exacerbate the insulation aging of the device surface, while low humidity leads to a risk of static electricity accumulation. Therefore, it is necessary to introduce the humidity influence factor into the dynamic correction of the temperature rise range, and adjust the temperature rise tolerance in real time through humidity to achieve double safety boundary control.

[0102] Refer to Figure 4 As shown, based on the charging power optimization model and the discharge power dynamic adjustment model, optimizing the two model parameters and balancing the load state based on the optimal charge and discharge power specifically includes:

[0103] Based on the charging power and discharge power in each time period obtained from the charging power optimization model and the discharge power dynamic adjustment model, obtain the average load of the energy storage device in each time period;

[0104] By adjusting the start time of charging and discharging and the magnitude of the charging and discharging power, obtain several groups of adjustment sample data;

[0105] By adjusting the sample data, obtain the load conditions of the energy storage device under various conditions, and obtain the sample parameter data with values less than the load average value among them;

[0106] Based on the sample parameter data with values less than the load average value, calculate the corresponding electricity cost data;

[0107] By assigning weights to the load and electricity cost of the energy storage device, calculate and obtain the sample parameter data with the lowest score, and based on the sample parameter data, obtain the optimal charge and discharge power.

[0108] Refer to Figure 5 As shown, based on historical regulation data, predict the overload situation under abnormal factors and compare it with real-time monitoring data. Specifically include:

[0109] Based on historical regulation data, obtain the charge and discharge power overload data during large-scale events and holidays;

[0110] Based on the overload data, perform feature extraction, obtain the changing trend of the electricity demand of the energy storage device before and after overload, and construct an overload prediction model;

[0111] Substitute the operation data of the energy storage device obtained by real-time detection into the overload prediction model, perform real-time matching with the changing trend data of the electricity demand before overload through dynamic time warping, align the real-time window data and the historical window data before overload in time series, and calculate the DTW distance to obtain the similarity of the changing trend;

[0112] Based on the obtained similarity of the changing trend, calculate the confidence level of this similarity, and judge whether the current energy storage device will have an overload situation based on the confidence level;

[0113] If the prediction result conflicts with the actual result, reconstruct the overload prediction model, regenerate the prediction result for the parameter model that generates errors, and use the parameter model as the key training parameter.

[0114] Specifically, when constructing the overload prediction model, feature extraction needs to take into account the spatio-temporal correlation of historical overload events and the multi-dimensional coupling characteristics of the device operation state, including: modeling the regional load distribution and the correlation of charge and discharge periods through a spatio-temporal attention mechanism, and extracting the spatio-temporal propagation characteristics under the topological constraints of the power grid nodes; for the operation state of the energy storage device, decompose multi-source time series data such as current, voltage, and temperature through wavelet transform, construct a composite feature vector reflecting the coupling relationship between the battery health (SOH), remaining capacity (SOC), and power fluctuation, and at the same time introduce an external event driving factor as a covariate input.

[0115] Refer to Figure 6As shown, based on the power imbalance situation, the power supply to critical loads is preferentially ensured according to the power distribution priority, and the self-check of the energy storage device status is performed, which specifically includes: extracting external features such as date tags, event scale (such as population density, regional power consumption increment), and duration of large-scale events / holidays, and mapping them to potential impact factors of the power load. Statistical quantities (mean, variance, skewness), frequency-domain energy distribution (the proportion of high-frequency fluctuation energy obtained through wavelet decomposition), and dynamic features such as the power change rate are extracted from the charge-discharge power time-series data. Multidimensional cross features are constructed by combining grid-side data and energy storage device parameters.

[0116] Based on the power imbalance under overload, the power supply to critical loads is preferentially ensured according to the power distribution priority;

[0117] The specific power distribution priority is as follows:

[0118] The first priority is the power supply guarantee for critical loads, the second priority is the self-maintenance power of the energy storage system, the third priority is the grid feedback power regulation, and the fourth priority is the scheduling of standby energy storage units;

[0119] The specific implementation of the self-check of the energy storage device status includes:

[0120] Check the remaining power of the energy storage device and evaluate whether it can support the load demand;

[0121] Detect the charge-discharge status of the energy storage device and confirm whether the device is working properly;

[0122] Evaluate the health status of the energy storage device, including parameters such as the aging degree of the battery, battery voltage, and internal resistance;

[0123] Based on the self-check results, the system dynamically adjusts the charge-discharge strategy of the energy storage device to ensure the power supply to priority loads.

[0124] Furthermore, the method according to the embodiment of the present application can also be implemented by means of Figure 7 the architecture of the electronic device shown. As Figure 7 shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to the network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store the method and system for automatically regulating the dynamic load of the energy storage device power balance provided by the present application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 the architecture shown is only exemplary. When implementing different devices, one or more components in the electronic device shown may be omitted according to actual needs. Figure 7 shown in the electronic device.

[0125] Figure 8 It is a schematic structural diagram of a computer-readable storage medium provided by an embodiment of the present application. As Figure 8 shown, it is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are run by a processor, the power balance dynamic load automatic regulation method and system according to the embodiment of the present application described with reference to the above drawings can be executed. The storage medium 600 includes but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0126] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0128] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for automatic control of dynamic load of power balance of energy storage equipment, characterized in that: include: Construct a bidirectional power coupling interface for energy storage devices; Based on the electricity price policy divided into peak and valley periods, combined with historical electricity demand data, a charging power optimization model is constructed to obtain the charging power in each time period; The operating status parameters obtained by the real-time environmental parameter acquisition device are combined with the real-time power demand data to build a dynamic adjustment model for discharge power and obtain the discharge power in each time period; Based on the charging power optimization model and the discharging power dynamic adjustment model, the two model parameters are optimized to balance the load state based on the optimal charging and discharging power; Based on historical control data, predict overload conditions under abnormal factors and compare them with real-time monitoring data; Based on the power imbalance, the power supply to critical loads is prioritized according to the power allocation priority and the energy storage device status self-check is performed.

2. The method for automatic control of power balance dynamic load of energy storage equipment according to claim 1, characterized in that: The electricity price policy based on peak and valley time periods is combined with historical electricity demand data to build a charging power optimization model to obtain the charging power in each time period. Specifically, it includes: Obtain the electricity price policy of the region where the energy storage equipment is located, and construct a piecewise linear electricity price function in the time dimension; The dynamic charging power fluctuation range is obtained based on the power available from the power grid, the currently acceptable charging power of the energy storage device and the safety constraint power; Obtain electricity demand data for different periods based on historical data; Based on the electricity demand data obtained in different time periods, the charging power function in different time periods is obtained; Based on the constructed piecewise linear electricity price function and the charging power function in different time periods, a charging power optimization model is constructed to calculate the minimum electricity fee by minimizing the objective function; Based on the minimization calculation of the objective function value, the charging power in each time period under the condition of minimizing the electricity fee is obtained.

3. The method for automatic control of power balance dynamic load of energy storage equipment according to claim 1, characterized in that: The operating state parameters obtained by the real-time environmental parameter acquisition device are combined with the real-time power demand data to construct a dynamic adjustment model for discharge power. The discharge power in each time period is obtained specifically including: The surface temperature distribution of the energy storage device is obtained through the temperature sensor array, and the temperature gradient field strength is calculated; Calculate the environmental humidity impact factor through humidity sensor data; Obtain real-time electricity demand data through current meters; Based on the acquired real-time electricity demand data, a real-time charging power function is acquired; Based on the acquired real-time operating status parameter data, a discharge power dynamic adjustment model is constructed to correct the real-time charging power function and obtain the discharge power in each time period.

4. The method for automatic control of power balance dynamic load of energy storage equipment according to claim 1, characterized in that: The optimization of the two model parameters based on the charging power optimization model and the discharging power dynamic adjustment model and balancing the load state based on the optimal charging and discharging power specifically include: Based on the charging power optimization model and the discharging power dynamic adjustment model, the charging power and discharging power in each time period are obtained, and the average load of the energy storage device in each time period is obtained; By adjusting the starting time of charging and discharging and the power of charging and discharging, several groups of adjustment sample data are obtained; The load conditions of the energy storage device under various conditions are obtained by adjusting the sample data, and sample parameter data that is less than the load mean is obtained; Based on the sample parameter data that is less than the load average, the corresponding electricity fee data is calculated; By assigning weights to the energy storage device load and electricity charges, the sample parameter data with the lowest score is calculated and obtained, and the optimal charging and discharging power is obtained based on the sample parameter data.

5. The method for automatic control of power balance dynamic load of energy storage equipment according to claim 1, characterized in that: The prediction of overload conditions under abnormal factors based on historical control data and comparison with real-time monitoring data specifically include: Based on historical control data, obtain charging and discharging power overload data during large-scale events and holidays; Based on the overload data, feature extraction is performed to obtain the changing trend of the power demand of the energy storage equipment before and after the overload, and an overload prediction model is constructed; The energy storage equipment operation data obtained through real-time detection is substituted into the overload prediction model, and the data of power demand change trend before the overload is matched in real time through dynamic time warping. The real-time window data is aligned with the historical window data before the overload in time series, and the DTW distance is calculated to obtain the similarity of the change trend. Based on the obtained similarity of the change trend, the confidence of the similarity is calculated, and based on the confidence, it is determined whether the current energy storage device will be overloaded; If the prediction result conflicts with the actual result, the overload prediction model is reconstructed, the parameter model that generates the error is used to regenerate the prediction result, and the parameter model is used as the key training parameter.

6. The method for automatic control of power balance dynamic load of energy storage equipment according to claim 1, characterized in that: Based on the power imbalance situation, the method of ensuring the power supply of key loads and performing the energy storage device status self-check according to the power allocation priority specifically includes: Based on the power imbalance in overload conditions, power supply to critical loads is prioritized according to power allocation priorities; The power allocation priorities are specifically: The first priority is to ensure the power supply of critical loads, the second priority is the self-sustaining power of the energy storage system, the third priority is the grid feedback power regulation, and the fourth priority is the scheduling of backup energy storage units; The performing of the energy storage device status self-check specifically includes: Check the remaining power of the energy storage device to assess whether it can support the load demand; Detect the charging and discharging status of the energy storage device to confirm whether the device is working normally; Evaluate the health status of energy storage equipment, including parameters such as battery aging, battery voltage and internal resistance; Based on the self-test results, the system dynamically adjusts the charging and discharging strategies of the energy storage equipment to ensure power supply to priority loads.

7. Combined with the energy storage device power balance dynamic load automatic control method, it is used to implement the energy storage device power balance dynamic load automatic control system as claimed in any one of claims 1 to 6, characterized in that: include: Distributed sensors: Real-time distributed sensors are mainly used to obtain various status data during the operation of energy storage equipment; Charging module: The charging module is mainly used to obtain electrical energy from the power grid; Discharge module: The discharge module is mainly used to provide power to the user end; Bidirectional power coupling interface: The bidirectional power coupling interface is mainly used to achieve physical layer decoupling of the charging module and the discharging module, allowing the charging circuit and the discharging circuit to operate independently at the same time during all weather periods; Model construction module: The model construction module is mainly used to construct a charging power optimization model, a discharge power dynamic adjustment model, and an overload prediction model; Optimization module: The optimization module is mainly used to dynamically adjust the load conditions in each time period based on the optimal charging power and the optimal discharging power; Overload prediction module: The overload prediction module is mainly used to compare the real-time operation data based on the historical control data to predict the overload trend; Status self-check module: The status self-check module is mainly used to perform self-check on the energy storage device after overload occurs; Database module: The database module is mainly used to store the operating status data of the energy storage device, power overload abnormal data, etc.; Processor: The processor is mainly used for the calculation process of each formula and the construction calculation process of each model.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for automatic control of dynamic load of power balance of energy storage equipment as described in any one of claims 1-6.

9. A computer-readable storage medium storing computer-readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the method for automatic control of dynamic load of power balance of energy storage equipment described in any one of claims 1-6 is implemented.

Images