Power distribution method and system based on electrochemical energy storage power station

Abstract

The invention discloses a power distribution method and system based on an electrochemical energy storage power station. The method comprises the steps that power grid load demand data and charge state data of all battery units in the energy storage power station are collected in real time; defining a first threshold value and a second threshold value for the peak period and the valley period; constructing a load demand prediction model, and outputting predicted electricity consumption in peak and valley periods in a future time period; calculating target discharge power of the energy storage power station in peak and valley periods; a dynamic power distribution strategy is formulated, wherein the dynamic power distribution strategy comprises the steps of improving charging power and limiting discharging in a low ebb period and covering a load gap with the maximum discharging power in a high ebb period; and monitoring the state of charge of the battery unit in real time, and if the state of charge of any unit deviates from a preset safety interval, triggering a power redistribution strategy. The method has the advantages that through load prediction and dynamic power distribution strategies, maximum discharging is achieved in the peak period, optimal charging is achieved in the valley period, and the efficiency of the energy storage power station is effectively improved.

Description

Technical Field

[0001] The present invention relates to power distribution technology, and in particular to a power distribution method and system based on an electrochemical energy storage power station. Background Art

[0002] Energy storage power plants play a vital role in modern power systems, particularly in addressing the volatility and uncertainty of renewable energy generation. With the widespread adoption of green energy sources like wind and solar, power system stability faces new challenges. Power distribution methods for energy storage power plants hold great promise for applications in smart grids and microgrids.

[0003] The power distribution methods and systems of energy storage power stations currently on the market lack accurate load forecasting and dynamic adjustment capabilities, and often rely on fixed charging and discharging patterns or simple time period divisions. Many existing solutions fail to fully consider the real-time fluctuations in grid load and changes in electricity prices. Therefore, it may not be possible to maximize discharge to meet demand during peak hours, or fail to fully charge during off-peak hours, resulting in inefficient energy storage systems. In addition, traditional methods monitor the charge status of battery cells in a relatively extensive manner and are unable to detect abnormal conditions of individual batteries in real time and make flexible adjustments, which may affect the stability of the system and battery life. The power distribution methods currently on the market generally have deficiencies in accuracy, flexibility, and system protection. Summary of the Invention

[0004] In order to improve the existing methods and systems, a power distribution method and system based on an electrochemical energy storage power station is provided. This method monitors the grid load and battery status in real time, combines load forecasting with a dynamic power distribution strategy, maximizes discharge during peak hours, and optimizes charging during off-peak hours, effectively improving the efficiency of the energy storage power station, protecting the battery, and reducing electricity costs.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is:

[0006] A power distribution method based on an electrochemical energy storage power station, comprising:

[0007] Real-time collection of grid load demand data and state of charge data of all battery units in the energy storage power station;

[0008] Obtaining peak and valley period definition data within the current power dispatch cycle, where the peak period is defined as a continuous period during which the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period during which the grid load demand is lower than a preset second threshold. The first and second thresholds are dynamically updated based on historical load data and electricity price signals;

[0009] Based on the peak and valley period definition data and historical load data, a load demand forecasting model is constructed to output the predicted power consumption during peak periods and valley periods in the future.

[0010] Based on the predicted electricity consumption during peak hours and off-peak hours, the target charging power of the energy storage power station during peak hours and the target discharging power during off-peak hours are calculated.

[0011] Based on the target charging power during peak and off-peak periods, a dynamic power allocation strategy is developed, including increasing charging power during off-peak periods and limiting discharge, and maximizing discharge power during peak periods to cover load gaps.

[0012] The battery cell state of charge is monitored in real time. If the state of charge of any cell deviates from the preset safety range, the power redistribution strategy is triggered.

[0013] Preferably, the acquisition of peak and valley period definition data within the current power scheduling cycle, wherein the peak period is defined as a continuous period during which the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period during which the grid load demand is lower than a preset second threshold, and the first and second thresholds are dynamically updated based on historical load data and electricity price signals, specifically including:

[0014] Collect historical load data of the power grid in real time, obtain load records and real-time electricity price signal data within the most recent dispatch cycle;

[0015] By calculating the dynamic benchmark value based on historical data, the benchmark load mean and benchmark fluctuation range are obtained, and the electricity price influencing factors are generated, including the electricity price sensitivity coefficient and temperature compensation item;

[0016] Based on the above-mentioned benchmark load mean, benchmark fluctuation amplitude, electricity price sensitivity coefficient and temperature compensation term, calculate and obtain first and second thresholds of grid load demand, and the first threshold is greater than the second threshold;

[0017] The period when the grid load demand is higher than a preset first threshold is defined as a peak period, and the period when the grid load demand is lower than a preset second threshold is defined as a valley period.

[0018] Preferably, the construction of a load demand forecasting model based on the peak and valley period definition data and historical load data, and the output of the predicted power consumption during the peak period and the predicted power consumption during the valley period in the future time period specifically include:

[0019] Based on the acquired peak and valley period definition data and historical load data, the peak and valley periods in the historical load data are marked, and feature data is extracted for model training using the LSTM neural network model.

[0020] The prediction task is divided into two subtasks: peak period and off-peak period. Models are trained to predict the load demand during peak period and off-peak period respectively.

[0021] Based on the trained load demand forecasting model, the output obtains the predicted power consumption data during peak hours and off-peak hours in the future time period.

[0022] Preferably, the calculation of the target charging power of the energy storage power station during the peak period and the target discharging power during the valley period based on the predicted power consumption during the peak period and the predicted power consumption during the valley period specifically includes:

[0023] Based on the predicted peak-hour electricity consumption, the minimum of the maximum charging power of the energy storage station and the real-time charging power of the energy storage station is obtained as the target charging power during the peak period, and the actual charging power is corrected according to the charging efficiency of the energy storage station.

[0024] Based on the predicted peak power consumption, the minimum value of the maximum charging power of the energy storage station and the discharge power of the remaining power of the energy storage station during the off-peak period is obtained as the target discharge power during the off-peak period, and the actual discharge power is corrected according to the discharge efficiency of the energy storage station.

[0025] During the charging and discharging process, the energy storage capacity is monitored in real time, and the capacity does not exceed the maximum capacity during charging, and the capacity does not drop below zero during discharging.

[0026] Preferably, the dynamic power allocation strategy is formulated based on the target charging power during peak hours and off-peak hours, including increasing the charging power during off-peak hours and limiting the discharge and maximizing the discharge power during peak hours to cover the load gap. Specifically, the strategy includes:

[0027] Based on the obtained target charging power during peak and off-peak periods, power allocation is performed for each period;

[0028] During peak hours, the discharge power is set to the maximum discharge power and dynamically adjusted based on grid gap demand until the battery power drops to the minimum preset value;

[0029] During peak hours, discharge is prioritized over charging. During peak hours, when the power station load is stable or the electricity price is low, a small amount of charging is performed.

[0030] During the off-peak phase, charging is prioritized over discharging, the charging power is set to the maximum, and the discharging power is kept at the lowest level, with a small amount of discharge.

[0031] Through real-time monitoring of the grid load, the charging and discharging power of the energy storage power station can be adjusted in real time.

[0032] Preferably, the real-time monitoring of the state of charge of the battery cells and triggering the power redistribution strategy if the state of charge of any cell deviates from a preset safety range specifically includes:

[0033] Real-time monitoring of the state of charge of power station battery units, including SOC, temperature, and voltage data, and setting up early warning mechanisms to perform threshold detection and judgment on each data;

[0034] Detect that the SOC of any battery cell deviates from the preset safe range, obtain battery cell data, and record the abnormal status;

[0035] Protect battery cells and restore normal system operation by adjusting the power distribution of the energy storage system.

[0036] Furthermore, a power distribution system based on an electrochemical energy storage power station is proposed, comprising:

[0037] Data acquisition module: The data acquisition module is used to collect real-time grid load demand data and charge status data of all battery units in the energy storage power station;

[0038] Time period definition module: The time period definition module is used to obtain the peak and valley period definition data of the power grid load demand, and dynamically calculate the thresholds of the peak and valley periods based on historical load data and electricity price signals;

[0039] Load demand forecasting module: The load demand forecasting module uses LSTM neural network to predict the power consumption during future peak and off-peak periods based on historical load data and period definition data;

[0040] Target power module: The target power module calculates the target charging power and target discharging power of the energy storage power station based on the predicted peak and off-peak power consumption;

[0041] Dynamic power allocation module: The dynamic power allocation module formulates a dynamic power allocation strategy based on the target charging and discharging power, and makes real-time adjustments based on the grid load demand to ensure maximum discharge during peak hours and priority charging during off-peak hours;

[0042] State of Charge Monitoring Module: The State of Charge Monitoring Module monitors the state of charge of the battery cells in real time, detects whether any cell deviates from the preset safety range, and triggers the power redistribution strategy;

[0043] Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0044] Compared with the prior art, the advantages of the present invention are:

[0045] Real-time collection of grid load demand and battery cell state-of-charge data ensures accurate and efficient power scheduling for energy storage power stations, mitigating the impact of grid load fluctuations on the power station. Secondly, by dynamically adjusting charging and discharging strategies during peak and off-peak periods, the system maximizes discharge during peak periods, alleviating grid pressure, and optimizes charging during off-peak periods, improving energy storage efficiency. Furthermore, a load forecasting model based on an LSTM neural network improves the accuracy of load demand forecasts, enabling more precise power allocation and avoiding power waste. Furthermore, real-time monitoring of battery cell state-of-charge and triggering redistribution strategies effectively protects batteries and extends their lifespan. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of the method proposed in the present invention;

[0047] Figure 2 This is a schematic diagram of the definition of peak and valley time periods proposed by the present invention;

[0048] Figure 3 This is a schematic diagram of the load demand forecasting model proposed by the present invention;

[0049] Figure 4 This is a schematic diagram of the target charge and discharge power proposed by the present invention;

[0050] Figure 5 This is a schematic diagram of the dynamic power allocation strategy proposed by the present invention;

[0051] Figure 6 Schematic diagram of the redistribution strategy proposed by the present invention;

[0052] Figure 7 This is a diagram of the architecture of the electronic equipment in this solution;

[0053] Figure 8 This is a schematic diagram of the computer-readable storage medium structure in this solution. DETAILED DESCRIPTION

[0054] The following description is intended to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are merely examples, and those skilled in the art may conceive of other obvious variations.

[0055] A power distribution system based on an electrochemical energy storage power station, comprising:

[0056] Data acquisition module: The data acquisition module is used to collect real-time grid load demand data and charge status data of all battery units in the energy storage power station;

[0057] Time period definition module: The time period definition module is used to obtain the peak and valley period definition data of the power grid load demand, and dynamically calculate the thresholds of the peak and valley periods based on historical load data and electricity price signals;

[0058] Load demand forecasting module: The load demand forecasting module uses LSTM neural network to predict the power consumption during future peak and off-peak periods based on historical load data and period definition data;

[0059] Target power module: The target power module calculates the target charging power and target discharging power of the energy storage power station based on the predicted peak and off-peak power consumption;

[0060] Dynamic power allocation module: The dynamic power allocation module formulates a dynamic power allocation strategy based on the target charging and discharging power, and makes real-time adjustments based on the grid load demand to ensure maximum discharge during peak hours and priority charging during off-peak hours;

[0061] State of Charge Monitoring Module: The State of Charge Monitoring Module monitors the state of charge of the battery cells in real time, detects whether any cell deviates from the preset safety range, and triggers the power redistribution strategy;

[0062] Processor: The processor is used to process the calculation process of each formula and the construction calculation process of each model.

[0063] See Figure 1 As shown, a power distribution method based on an electrochemical energy storage power station includes:

[0064] Step 1: Real-time collection of grid load demand data and state-of-charge data of all battery cells in the energy storage power station;

[0065] Step 2: Obtain peak and valley period definition data within the current power dispatch cycle, where the peak period is defined as a continuous period during which the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period during which the grid load demand is lower than a preset second threshold. The first and second thresholds are dynamically updated based on historical load data and electricity price signals;

[0066] Step 3: Based on the peak and valley period definition data and historical load data, a load demand forecasting model is constructed to output the predicted power consumption during peak periods and valley periods in the future time period;

[0067] Step 4: Based on the predicted power consumption during peak hours and off-peak hours, calculate the target charging power of the energy storage station during peak hours and the target discharging power during off-peak hours.

[0068] Step 5: Based on the target charging power during peak and off-peak periods, a dynamic power allocation strategy is developed, including increasing charging power during off-peak periods and limiting discharge during peak periods to maximize discharge power to cover the load gap.

[0069] Step 6: Monitor the state of charge of the battery cells in real time. If the state of charge of any cell deviates from the preset safety range, the power redistribution strategy is triggered.

[0070] See Figure 2 As shown, the peak and valley period definition data within the current power scheduling cycle is obtained. The peak period is defined as a continuous period when the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period when the grid load demand is lower than a preset second threshold. The first and second thresholds are dynamically updated based on historical load data and electricity price signals, specifically including:

[0071] Collect historical load data of the power grid in real time, obtain load records and real-time electricity price signal data within the most recent dispatch cycle;

[0072] By calculating the dynamic benchmark value based on historical data, the benchmark load mean and benchmark fluctuation range are obtained, and the electricity price influencing factors are generated, including the electricity price sensitivity coefficient and temperature compensation item;

[0073] Based on the above-mentioned benchmark load mean, benchmark fluctuation amplitude, electricity price sensitivity coefficient and temperature compensation term, calculate and obtain first and second thresholds of grid load demand, and the first threshold is greater than the second threshold;

[0074] The period when the grid load demand is higher than a preset first threshold is defined as a peak period, and the period when the grid load demand is lower than a preset second threshold is defined as a valley period.

[0075] Specifically, the benchmark load mean and benchmark fluctuation range are obtained by analyzing historical load data. The benchmark load mean refers to the average load value within a certain period of time in the historical load data. The benchmark fluctuation range reflects the fluctuation of the historical load data and is expressed by the standard deviation.

[0076] The electricity price sensitivity coefficient reflects the impact of electricity price changes on load demand and is determined by the correlation between electricity price and load in historical data. The temperature compensation term considers the impact of temperature on grid load demand and is usually calculated using the correlation between historical temperature data and load data.

[0077] The first threshold is used to define the peak period, which is usually set to the value of the benchmark load mean plus a certain coefficient multiplied by the benchmark fluctuation range. The second threshold is used to define the off-peak period, which is usually set to the value of the benchmark load mean minus a certain coefficient multiplied by the benchmark fluctuation range.

[0078] See Figure 3As shown in the figure, based on the peak and valley period definition data and historical load data, a load demand forecasting model is constructed to output the predicted power consumption during peak periods and valley periods in the future time period. Specifically, the following are the outputs:

[0079] Based on the acquired peak and valley period definition data and historical load data, the peak and valley periods in the historical load data are marked, and feature data is extracted for model training using the LSTM neural network model.

[0080] The prediction task is divided into two subtasks: peak period and off-peak period. Models are trained to predict the load demand during peak period and off-peak period respectively.

[0081] Based on the trained load demand forecasting model, the output obtains the predicted power consumption data during peak hours and off-peak hours in the future time period.

[0082] Specifically, since the load demand characteristics during peak and off-peak periods may be different, the load forecasting task is divided into two subtasks, including the peak power consumption forecasting path and the off-peak power consumption forecasting path;

[0083] Use the trained peak period LSTM model and input the feature data of the future time period to obtain the corresponding predicted load value. Similarly, use the trained off-peak period LSTM model and input the feature data of the future time period to obtain the corresponding predicted load value.

[0084] See Figure 4 As shown, based on the predicted power consumption during the peak period and the predicted power consumption during the off-peak period, the target charging power of the energy storage power station during the peak period and the target discharging power during the off-peak period are calculated specifically including:

[0085] Based on the predicted peak-hour electricity consumption, the minimum of the maximum charging power of the energy storage station and the real-time charging power of the energy storage station is obtained as the target charging power during the peak period, and the actual charging power is corrected according to the charging efficiency of the energy storage station.

[0086] Based on the predicted peak power consumption, the minimum value of the maximum charging power of the energy storage station and the discharge power of the remaining power of the energy storage station during the off-peak period is obtained as the target discharge power during the off-peak period, and the actual discharge power is corrected according to the discharge efficiency of the energy storage station.

[0087] During the charging and discharging process, the energy storage capacity is monitored in real time, and the capacity does not exceed the maximum capacity during charging, and the capacity does not drop below zero during discharging.

[0088] Specifically, the target charging power is the target charging power of the energy storage station during peak hours. The target power should be the minimum value between the maximum charging power of the energy storage station and the current real-time charging power. The formula is:

[0089]

[0090] in, is the target charging power, is the maximum charging power of the energy storage station, E max is the maximum power of the energy storage station, E current is the current energy storage capacity, T is the duration of the peak period;

[0091] The target discharge power is the target discharge power of the energy storage station during off-peak hours. This target power should be the minimum of the maximum charging power of the energy storage station and the discharge power of the remaining power of the energy storage station during off-peak hours. The formula is:

[0092]

[0093] in, is the target discharge power, is the maximum discharge power of the energy storage station, E current is the current energy storage capacity, T′ is the duration of the valley period;

[0094] By taking the charge and discharge efficiency into consideration, the actual charge and discharge power is corrected.

[0095] See Figure 5 As shown in the figure, based on the target charging power during peak and off-peak periods, a dynamic power allocation strategy is formulated, including increasing charging power during off-peak periods and limiting discharge, and maximizing discharge power during peak periods to cover the load gap. Specifically, the strategy includes:

[0096] Based on the obtained target charging power during peak and off-peak periods, power allocation is performed for each period;

[0097] During peak hours, the discharge power is set to the maximum discharge power and dynamically adjusted based on grid gap demand until the battery power drops to the minimum preset value;

[0098] During peak hours, discharge is prioritized over charging. During peak hours, when the power station load is stable or the electricity price is low, a small amount of charging is performed.

[0099] During the off-peak phase, charging is prioritized over discharging, the charging power is set to the maximum, and the discharging power is kept at the lowest level, with a small amount of discharge.

[0100] Through real-time monitoring of the grid load, the charging and discharging power of the energy storage power station can be adjusted in real time.

[0101] Specifically, during peak hours, the grid load is usually high, so the energy storage power station needs to discharge to fill the grid load gap. During this period, the discharge power should prioritize meeting the grid load demand. Even if the energy storage power station's power begins to decline, it still prioritizes meeting the grid demand until the battery power drops to a preset minimum power level.

[0102] Discharging is prioritized during peak hours. A small amount of charging is performed only when the grid load is relatively stable or the electricity price is low. In this case, the charging power is set to a smaller value than the maximum charging power, and the charging priority is lower than the discharging priority.

[0103] During off-peak hours, the grid load is low, so the energy storage station needs to charge to store electricity for use during peak hours. At this time, charging power takes priority and discharging power is minimized.

[0104] To keep the power of the energy storage station within a safe range, the discharge power should be kept to a minimum during off-peak hours to avoid rapid power consumption.

[0105] The load data of the power grid is obtained in real time and compared with the actual demand of the power grid to determine whether there is a gap in the power grid. If the power grid load is greater than a set benchmark load value, a load gap is generated, and the charging and discharging power of the energy storage power station is dynamically adjusted according to the power grid load gap.

[0106] See Figure 6 As shown, the state of charge of the battery cells is monitored in real time. If the state of charge of any cell deviates from the preset safe range, the power redistribution strategy is triggered, specifically including:

[0107] Real-time monitoring of the state of charge of power station battery units, including SOC, temperature, and voltage data, and setting up early warning mechanisms to perform threshold detection and judgment on each data;

[0108] Detect that the SOC of any battery cell deviates from the preset safe range, obtain battery cell data, and record the abnormal status;

[0109] Protect battery cells and restore normal system operation by adjusting the power distribution of the energy storage system.

[0110] Furthermore, the method according to the embodiment of the present application can also be used with the aid of Figure 7 The electronic device architecture shown in FIG. Figure 7As 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 a 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, may store a power distribution method and system based on an electrochemical energy storage power station provided in this application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 7 One or more components of an electronic device are shown.

[0111] Figure 8 This is a schematic diagram of the computer-readable storage medium structure provided by an embodiment of the present application. Figure 8 As shown, a computer-readable storage medium 600 according to an embodiment of the present application is shown. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by the processor, a power distribution method and system based on an electrochemical energy storage power station according to an embodiment of the present application described with reference to the above figures 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 (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0112] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power distribution method based on an electrochemical energy storage power station, characterized in that: include: Real-time collection of grid load demand data and state of charge data of all battery units in the energy storage power station; Obtaining peak and valley period definition data within the current power dispatch cycle, where the peak period is defined as a continuous period during which the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period during which the grid load demand is lower than a preset second threshold. The first and second thresholds are dynamically updated based on historical load data and electricity price signals; Based on the peak and valley period definition data and historical load data, a load demand forecasting model is constructed to output the predicted power consumption during peak periods and valley periods in the future. Based on the predicted electricity consumption during peak hours and off-peak hours, the target charging power of the energy storage power station during peak hours and the target discharging power during off-peak hours are calculated. Based on the target charging power during peak and off-peak periods, a dynamic power allocation strategy is developed, including increasing charging power during off-peak periods and limiting discharge, and maximizing discharge power during peak periods to cover load gaps. The battery cell state of charge is monitored in real time. If the state of charge of any cell deviates from the preset safety range, the power redistribution strategy is triggered.

2. A power distribution method based on an electrochemical energy storage power station according to claim 1, characterized in that: The obtaining of peak and valley period definition data within the current power dispatch cycle, wherein the peak period is defined as a continuous period during which the grid load demand is higher than a preset first threshold, and the valley period is defined as a continuous period during which the grid load demand is lower than a preset second threshold, wherein the first and second thresholds are dynamically updated based on historical load data and electricity price signals, specifically includes: Collect historical load data of the power grid in real time, obtain load records and real-time electricity price signal data within the most recent dispatch cycle; By calculating the dynamic benchmark value based on historical data, the benchmark load mean and benchmark fluctuation range are obtained, and the electricity price influencing factors are generated, including the electricity price sensitivity coefficient and temperature compensation item; Based on the above-mentioned benchmark load mean, benchmark fluctuation amplitude, electricity price sensitivity coefficient and temperature compensation term, calculate and obtain first and second thresholds of grid load demand, and the first threshold is greater than the second threshold; The period when the grid load demand is higher than a preset first threshold is defined as a peak period, and the period when the grid load demand is lower than a preset second threshold is defined as a valley period.

3. The power distribution method based on the electrochemical energy storage power station according to claim 1, characterized in that: The load demand forecasting model is constructed based on the peak and valley period definition data and historical load data to output the predicted power consumption during the peak period and the predicted power consumption during the valley period in the future time period. Specifically, the following are the steps: Based on the acquired peak and valley period definition data and historical load data, the peak and valley periods in the historical load data are marked, and feature data is extracted for model training using the LSTM neural network model. The prediction task is divided into two subtasks: peak period and off-peak period. Models are trained to predict the load demand during peak period and off-peak period respectively. Based on the trained load demand forecasting model, the output obtains the predicted power consumption data during peak hours and off-peak hours in the future time period.

4. The power distribution method based on an electrochemical energy storage power station according to claim 1, characterized in that: The calculation of the target charging power of the energy storage power station during the peak period and the target discharging power during the valley period based on the predicted power consumption during the peak period and the predicted power consumption during the valley period specifically includes: Based on the predicted peak-hour electricity consumption, the minimum of the maximum charging power of the energy storage station and the real-time charging power of the energy storage station is obtained as the target charging power during the peak period, and the actual charging power is corrected according to the charging efficiency of the energy storage station. Based on the predicted peak power consumption, the minimum value of the maximum charging power of the energy storage station and the discharge power of the remaining power of the energy storage station during the off-peak period is obtained as the target discharge power during the off-peak period, and the actual discharge power is corrected according to the discharge efficiency of the energy storage station. During the charging and discharging process, the energy storage capacity is monitored in real time, and the capacity does not exceed the maximum capacity during charging, and the capacity does not drop below zero during discharging.

5. The power distribution method based on an electrochemical energy storage power station according to claim 1, characterized in that: The dynamic power allocation strategy is formulated based on the target charging power during peak and off-peak periods, including increasing the charging power during off-peak periods and limiting discharge, and maximizing discharge power during peak periods to cover the load gap. Specifically, the strategy includes: Based on the obtained target charging power during peak and off-peak periods, power allocation is performed for each period; During peak hours, the discharge power is set to the maximum discharge power and dynamically adjusted based on grid gap demand until the battery power drops to the minimum preset value; During peak hours, discharge is prioritized over charging. During peak hours, when the power station load is stable or the electricity price is low, a small amount of charging is performed. During the off-peak phase, charging is prioritized over discharging, the charging power is set to the maximum, and the discharging power is kept at the lowest level, with a small amount of discharge. Through real-time monitoring of the grid load, the charging and discharging power of the energy storage power station can be adjusted in real time.

6. A power distribution method based on an electrochemical energy storage power station according to claim 1, characterized in that: The real-time monitoring of the state of charge of the battery cells and triggering a power redistribution strategy if the state of charge of any cell deviates from a preset safety range specifically include: Real-time monitoring of the state of charge of power station battery units, including SOC, temperature, and voltage data, and setting up early warning mechanisms to perform threshold detection and judgment on each data; Detect that the SOC of any battery cell deviates from the preset safe range, obtain battery cell data, and record the abnormal status; Protect battery cells and restore normal system operation by adjusting the power distribution of the energy storage system.

7. A power distribution system based on an electrochemical energy storage power station, used to implement a power distribution method based on an electrochemical energy storage power station according to any one of claims 1 to 6, characterized in that: include: Data acquisition module: The data acquisition module is used to collect real-time grid load demand data and charge status data of all battery units in the energy storage power station; Time period definition module: The time period definition module is used to obtain the peak and valley period definition data of the power grid load demand, and dynamically calculate the thresholds of the peak and valley periods based on historical load data and electricity price signals; Load demand forecasting module: The load demand forecasting module uses LSTM neural network to predict the power consumption during future peak and off-peak periods based on historical load data and period definition data; Target power module: The target power module calculates the target charging power and target discharging power of the energy storage power station based on the predicted peak and off-peak power consumption; Dynamic power allocation module: The dynamic power allocation module formulates a dynamic power allocation strategy based on the target charging and discharging power, and makes real-time adjustments based on the grid load demand to ensure maximum discharge during peak hours and priority charging during off-peak hours; State of Charge Monitoring Module: The State of Charge Monitoring Module monitors the state of charge of the battery cells in real time, detects whether any cell deviates from the preset safety range, and triggers the power redistribution strategy; Processor: The processor is used to process 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 power distribution method based on the electrochemical energy storage power station 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, a power distribution method based on an electrochemical energy storage power station according to any one of claims 1 to 6 is implemented.

Images