Cooperative control method, device and equipment for energy storage system

Abstract

The invention discloses a cooperative control method, device and equipment for an energy storage system. The method comprises the following steps: collecting real-time parameters and historical load data; determining a predicted load rate according to the historical load data; determining a dynamic peak-valley period according to the predicted load rate; according to the real-time parameters, determining a target power for carrying out peak clipping and valley filling on the dynamic peak-valley period; according to the real-time parameters, anti-countercurrent limiting power is determined; and generating a cooperative control instruction for controlling the energy storage system according to at least one of the target power and the anti-countercurrent limiting power. According to the method, the peak-valley time period and the power for peak load shifting are dynamically adjusted, the peak-valley difference reduction rate is increased, meanwhile, peak load shifting and countercurrent prevention are cooperatively controlled, the peak load shifting action is prevented from being interrupted by the countercurrent prevention action, and the loss of energy utilization efficiency is reduced.

Description

Technical Field

[0001] This invention relates to the field of energy storage system scheduling technology, and in particular to a collaborative control method, device and equipment for energy storage systems. Background Technology

[0002] With the large-scale application of distributed energy and energy storage systems, problems such as widening peak-valley differences in the power grid, voltage fluctuations, and reverse power transmission are becoming increasingly prominent. Peak shaving and valley filling, as the core application scenario of energy storage systems, can effectively smooth out grid load fluctuations by discharging during peak electricity demand periods and charging during off-peak periods; while anti-reverse current control can prevent energy storage systems from transmitting power back to the grid, ensuring the safe and stable operation of the power grid.

[0003] In existing technologies, peak shaving and valley filling and backflow prevention control in energy storage systems are mostly independent functional modules: 1) Static peak shaving and valley filling control: By preset fixed peak and valley periods (such as peak 18:00-22:00 and valley 0:00-8:00) and charging and discharging power, the control strategy is executed in a time-triggered manner. It cannot cope with dynamic changes in grid load (such as load surges caused by extreme weather), thus resulting in a decrease in peak shaving and valley filling effect. 2) Independent anti-reverse current control: By detecting the power direction of the grid-side gate meter, when reverse power is detected, the discharge power of the energy storage system is reduced or switched to charging mode.

[0004] Therefore, existing energy storage systems are ineffective at peak shaving and valley filling during fixed peak and valley periods. Furthermore, peak shaving and valley filling operate independently of anti-backflow control, which may interrupt peak shaving and valley filling during anti-backflow action, resulting in energy utilization efficiency loss. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, the present invention aims to provide a collaborative control method, device and equipment for an energy storage system, which can dynamically adjust the peak and valley periods and the power used for peak shaving and valley filling, improve the peak-valley difference reduction rate, and coordinate the control of peak shaving and valley filling and anti-reverse flow to avoid the interruption of peak shaving and valley filling by anti-reverse flow action, thereby reducing the loss of energy utilization efficiency.

[0006] To solve the above problems, the present invention is implemented according to the following solution: A collaborative control method for an energy storage system is provided, including: Collect real-time parameters and historical load data; Based on the historical load data, determine the predicted load factor; Based on the predicted load factor, determine the dynamic peak and valley periods; Based on the real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods; Based on the real-time parameters, determine the backflow prevention limiting power; Based on the target power and at least one of the anti-reverse current limiting power, a coordinated control command for controlling the energy storage system is generated.

[0007] Compared with the prior art, the beneficial effects of the collaborative control method of the energy storage system of the present invention are as follows: by dynamically adjusting the peak and valley periods and the power used for peak shaving and valley filling, the peak-valley difference reduction rate is improved. At the same time, the collaborative control of peak shaving and valley filling and anti-reverse flow avoids interruption of peak shaving and valley filling by anti-reverse flow action, thereby reducing the loss of energy utilization efficiency.

[0008] Optionally, the real-time parameters include real-time grid parameters, real-time energy storage parameters, and real-time electricity prices, wherein the real-time grid parameters include active power and load factor; Collect real-time parameters, including: The grid voltage and grid current are collected at a preset frequency; The initial active power is determined based on the grid voltage and the grid current; Determine the initial load factor based on the initial active power and the rated capacity of the transformer; Initial energy storage parameters and real-time electricity prices are collected at preset time points; High-frequency noise is removed from the initial active power, the initial load factor, and the initial energy storage parameters to obtain the active power, load factor, and real-time energy storage parameters.

[0009] Optionally, determining the predicted load factor based on the historical load data includes: Based on the historical load data, a predicted load curve is generated; Based on the predicted load curve, determine the predicted load power; The predicted load rate is determined based on the predicted load power.

[0010] Optionally, based on the predicted load factor, the dynamic peak and valley periods are determined, including: Peak load factor and off-peak load factor are determined based on K-means clustering. When the predicted load rate is greater than or equal to the peak load rate, the dynamic peak-valley period is the dynamic peak period; When the predicted load rate is less than or equal to the off-peak load rate, the dynamic peak-valley period is the dynamic off-peak period.

[0011] Optionally, based on the real-time parameters, a target power for peak shaving and valley filling during dynamic peak-valley periods is determined, including: When the dynamic peak-valley period is a dynamic peak period, the peak demand power is determined based on the load factor, the peak load factor, the rated power of the energy storage system, and the rated capacity of the transformer. When the dynamic peak-valley period is a dynamic low-valley period, the low-valley demand power is determined based on the load factor, the low-valley load factor, the rated power of the energy storage system, and the rated capacity of the transformer. Based on the real-time electricity price, the peak demand power or the off-peak demand power is adjusted to determine the target power.

[0012] Optionally, based on the real-time electricity price, the peak demand power or the off-peak demand power is adjusted to determine the target power, including: When the real-time electricity price is greater than or equal to the first preset electricity price, the peak demand power is increased by a preset power ratio to determine the target power. When the real-time electricity price is less than or equal to the second preset electricity price, the off-peak demand power is increased by a preset power ratio to determine the target power.

[0013] Optionally, based on the target power and at least one of the anti-reverse current limiting power, a coordinated control command for controlling the energy storage system is generated, including: When the dynamic peak-valley period is a dynamic peak period, the target power and the anti-reverse current limiting power are compared, and the power with the smallest value is taken as the power to be controlled. Based on the power to be controlled, generate coordinated control commands for controlling the energy storage system.

[0014] Optionally, based on the target power and at least one of the anti-reverse current limiting power, a coordinated control command for controlling the energy storage system is generated, including: When the dynamic peak-valley period is a dynamic low-valley period, the target power is taken as the power to be controlled; Based on the power to be controlled, generate coordinated control commands for controlling the energy storage system.

[0015] A collaborative control device for an energy storage system is also provided, which applies the aforementioned collaborative control method for an energy storage system, including: The data acquisition module is used to collect real-time parameters and historical load data; The prediction module is used for: Based on the historical load data, determine the predicted load factor; Based on the predicted load factor, determine the dynamic peak and valley periods; Based on the real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods; Based on the real-time parameters, determine the backflow prevention limiting power; The collaborative control module is used to generate collaborative control commands for controlling the energy storage system based on the target power and at least one of the anti-reverse current limiting power.

[0016] A computer device is also provided, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the processor loads and executes the at least one instruction, at least one program, code set or instruction set to implement the cooperative control method of the energy storage system. Attached Figure Description

[0017] Figure 1 This is a flowchart of the collaborative control method of the present invention; Figure 2 The diagram shows the load curve after being controlled by the collaborative control method of this invention, the uncontrolled load curve, and the load curve independently controlled by existing technology. Detailed Implementation

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0019] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0020] See Figure 1 As shown, a cooperative control method for an energy storage system according to the present invention includes: S1: Collect real-time parameters and historical load data; In one embodiment of the present invention, the real-time parameters include real-time grid parameters, real-time energy storage parameters, and real-time electricity price. The real-time grid parameters include active power and load factor. The acquisition of real-time parameters includes: acquiring grid voltage and grid current at a preset frequency; determining the initial active power based on the grid voltage and grid current; determining the initial load factor based on the initial active power and transformer rated capacity; acquiring the initial energy storage parameters and real-time electricity price at preset time points; and removing high-frequency noise from the initial active power, initial load factor, and initial energy storage parameters to obtain the active power, load factor, and real-time energy storage parameters.

[0021] For three-phase three-wire or three-phase four-wire power grids, the initial active power is calculated using the "three-meter method" or "two-meter method," and the calculation formula is as follows: P_grid=U_A×I_A×cosφ_A+U_B×I_B×cosφ_B+U_C×I_C×cosφ_C Where P_grid represents the initial active power; U_A, U_B, and U_C are all grid voltages, with U_A being the phase voltage of phase A, U_B being the phase voltage of phase B, and U_C being the phase voltage of phase C; I_A, I_B, and I_C are all grid currents, with I_A being the phase current of phase A, I_B being the phase current of phase B, and I_C being the phase current of phase C; cosφ_A, cosφ_B, and cosφ_C are the power factors of phases A, B, and C of the grid, respectively, used to represent the proportion of active power to apparent power; and φ_A, φ_B, and φ_C are the phase differences between voltage and current in phases A, B, and C of the grid.

[0022] For a single-phase power grid, the formula for calculating the initial active power is as follows: P_grid=U×I×cosφ Where P_grid is the initial active power; U is the grid voltage; I is the grid current; cosφ is the grid power factor, which represents the proportion of active power to apparent power; and φ is the phase difference between the grid voltage and the grid current.

[0023] The formula for determining the initial load factor based on the initial active power and the transformer's rated capacity is as follows: Load_rate=P_grid / S_max Where Load_rate is the initial load rate; P_grid is the initial active power; and S_max is the rated capacity of the transformer in the energy storage system.

[0024] S2: Determine the predicted load factor based on historical load data, including: generating a predicted load curve based on historical load data; determining the predicted load power based on the predicted load curve; and determining the predicted load factor based on the predicted load power.

[0025] In one embodiment of the present invention, the historical load data is load data with a time interval of 1 minute in the past 24 hours, which includes a total of 1440 data points; the generation of a predicted load curve based on the historical load data includes: using the historical load data, real-time environmental data including temperature and humidity, and date attributes of weekdays or weekends as input data for the LSTM model, and the LSTM model outputs the predicted load curve for the next 1 hour.

[0026] In one embodiment of the present invention, the formula for calculating the predicted load factor based on the predicted load power is as follows: Load_rate_pred=P_grid_pred / S_max Among them, Load_rate_pred is the predicted load rate, which is the ratio of the predicted load of the power grid to the rated capacity of the transformer at a certain future moment, reflecting the saturation degree of the power grid load in the future period, and the unit is %; P_grid_pred is the predicted load power; and S_max is the rated capacity of the transformer in the energy storage system.

[0027] S3: Determine the dynamic peak and valley periods based on the predicted load rate, including: determining the peak load rate and valley load rate based on K-means clustering; when the predicted load rate is greater than or equal to the peak load rate, the dynamic peak and valley period is the dynamic peak period; when the predicted load rate is less than or equal to the valley load rate, the dynamic peak and valley period is the dynamic valley period.

[0028] In one embodiment of the present invention, the peak load rate is 80% and the valley load rate is 30%. When the predicted load rate Load_rate_pred ≥ 80%, the dynamic peak-valley period is the dynamic peak period; when the predicted load rate Load_rate_pred ≤ 30%, the dynamic peak-valley period is the dynamic valley period. The present invention dynamically adjusts the peak-valley period to dynamically adjust the subsequent peak-shaving and valley-filling power, replacing the traditional fixed peak-valley period. This allows the power grid to better cope with the dynamic changes in power grid load caused by extreme weather and other phenomena, resulting in better peak-shaving and valley-filling effects.

[0029] S4: Based on real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods, including: when the dynamic peak-valley period is a dynamic peak period, determine the peak demand power based on the load factor, peak load factor, rated power of the energy storage system, and rated capacity of the transformer; when the dynamic peak-valley period is a dynamic valley period, determine the valley demand power based on the load factor, valley load factor, rated power of the energy storage system, and rated capacity of the transformer; and adjust the peak demand power or valley demand power based on the real-time electricity price to determine the target power.

[0030] In one embodiment of the present invention, when the dynamic peak-valley period is a dynamic peak period, the calculation formula for determining the peak demand power is as follows, based on the load factor, peak load factor, rated power of the energy storage system, and rated capacity of the transformer: P_peak(t)=min(P_max, (Load_rate - 80%)×S_max) Where P_peak(t) is the peak demand power, Load_rate is the load rate (peak load rate is 80%), P_max is the rated power of the energy storage system, and S_max is the rated capacity of the transformer in the energy storage system.

[0031] In one embodiment of the present invention, when the dynamic peak-valley period is a dynamic low-valley period, the calculation formula for determining the low-valley demand power is as follows, based on the load factor, low-valley load factor, rated power of the energy storage system, and rated capacity of the transformer: P_valley(t)=max(-P_max, (30% - Load_rate)×S_max) Where P_valley(t) is the off-peak demand power, Load_rate is the load rate (30% off-peak load rate), P_max is the rated power of the energy storage system (negative values ​​in this formula indicate that the energy storage system is in a charging state), and S_max is the rated capacity of the transformer.

[0032] In one embodiment of the present invention, the peak demand power or off-peak demand power is adjusted according to the real-time electricity price to determine the target power, including: when the real-time electricity price is greater than or equal to a first preset electricity price, the peak demand power is increased by a preset power ratio to determine the target power; when the real-time electricity price is less than or equal to a second preset electricity price, the off-peak demand power is increased by a preset power ratio to determine the target power; wherein, the first preset electricity price is 1.5 times the benchmark electricity price, the second preset electricity price is 0.5 times the benchmark electricity price, and the preset power ratio is 10%, that is, when the real-time electricity price is ≥ 1.5 times the benchmark electricity price, the peak demand power is increased by 10%; when the real-time electricity price is ≤ 0.5 times the benchmark electricity price, the off-peak demand power is increased by 10%.

[0033] S5: Determine the backflow prevention limit power based on real-time parameters, including real-time load power. The calculation formula for the backflow prevention limit power is as follows: P_grid_max(t) = 0.95×P_load(t) Where P_grid_max(t) is the power limit for preventing backflow, and P_load(t) is the real-time load power, which is ≥5% of the real-time load power on the grid side to avoid backflow.

[0034] In one embodiment of the present invention, real-time load power refers to the total power actually consumed by the power grid at a certain moment, with the unit being kW / MW. The methods for obtaining real-time load power include the following two: 1) Direct calculation method: The active power is calculated using the formula P_load(t) = √3 × U_line × I_line × cosφ. P_grid(t) = P_load(t) - P_storage(t). When P_storage(t) is positive, it is in the discharge state, and when it is negative, it is in the charging state. 2) Data validation method: Compare the real-time load power P_load(t) calculated above with the predicted load power P_load_pred(t). If the deviation is ≥5%, data re-sampling and recalculation will be triggered to ensure accuracy.

[0035] S6: Generate a coordinated control command for controlling the energy storage system based on at least one of the target power and the anti-reverse current limiting power.

[0036] In one embodiment of the present invention, a coordinated control command for controlling the energy storage system is generated based on at least one target power and anti-reverse current limiting power, including: when the dynamic peak-valley period is a dynamic peak period, comparing the target power and the anti-reverse current limiting power, and taking the one with the smallest value as the power to be controlled; and generating a coordinated control command for controlling the energy storage system based on the power to be controlled.

[0037] In one embodiment of the present invention, a coordinated control command for controlling the energy storage system is generated based on at least one target power and anti-reverse current limiting power, including: when the dynamic peak-valley period is a dynamic low-valley period, the target power is used as the power to be controlled; and a coordinated control command for controlling the energy storage system is generated based on the power to be controlled.

[0038] The relationship between grid-side power and reverse current limiting power P_grid_max(t): The grid-side power, i.e., the active power P_grid(t), is the power absorbed by the grid when P_grid(t) ≥ 0, and the reverse flow when P_grid(t) < 0. P_grid_max(t) is its upper limit threshold, P_grid(t) ≤ P_grid_max(t) = 0.95 × P_load(t). The lower limit threshold of the grid-side power is derived as P_load(t) - P_grid_max(t) = 0.05 × P_load(t) (5% of the real-time load power). Therefore, the active power P_grid(t) must satisfy 0.05 × P_load(t) ≤ P_grid(t) ≤ 0.95 × P_load(t) to avoid grid problems caused by excessively high active power P_grid(t) and to prevent reverse flow caused by active power P_grid(t) < 0.

[0039] In one embodiment of the present invention, the method further includes: calculating the revenue deviation based on the actual revenue and the expected revenue, wherein the calculation formula is: revenue deviation = (actual revenue - expected revenue) / expected revenue × 100%; when the peak-valley difference reduction rate is less than 40% or the revenue deviation is greater than or equal to 15%, the LSTM model is modified, specifically by: adding load data from the past week and grid disturbance data during the deviation period (extreme weather / sudden load); adjusting the hidden layer neurons from 64 to 128, the learning rate from 0.01 to 0.005, and the number of iterations from 100 to 200; if the prediction error is ≤5%, the adjusted parameters are saved; otherwise, the adjustment is repeated. Next, the correction factors include: Because the peak demand power P_peak(t) is affected by (Load_rate - 80%), when the peak demand power P_peak(t) is too high, the peak-valley difference reduction rate η will be low. In this case, the power coefficient is adjusted from 1.0 to 0.9 to reduce the power used and achieve the peak shaving effect. If the peak demand power P_peak(t) is too low, the power coefficient is adjusted from 1.0 to 1.1 to increase the power used and achieve the valley filling effect. If the revenue deviation is due to insufficient discharge, and the real-time electricity price is ≥1.5 times the benchmark electricity price, the preset power ratio will be adjusted from 10% to 15%; otherwise, it will be adjusted from 10% to 8%. See Figure 2 The figure shows a load curve controlled by the collaborative control method of the present invention, an uncontrolled load curve, and a load curve independently controlled by existing technology. As can be seen from the figure, the collaborative control method of the present invention can effectively improve the peak-valley difference reduction rate.

[0040] The following section uses a 10MW / 20MWh energy storage system in an industrial park as an example to explain the collaborative control method of the present invention in detail: The grid voltage and current are collected every 1 ms to calculate the active power P_grid; the real-time energy storage parameter SOC (current value 75%) is collected every 500 ms; and the real-time electricity price is received every 5 minutes. For the region where the energy storage system is located, the price is 1.2 yuan / kWh during peak hours and 0.35 yuan / kWh during off-peak hours. Based on the LSTM model, the predicted load factor for 10:00-11:00 is expected to reach 85%, which is the dynamic peak period. The calculated load factor is P_peak(t) = 10MW × (85%-80%) / 20% = 2.5MW. Considering the real-time electricity price of 1.2 yuan / kWh, which is 1.5 times the benchmark electricity price, the load factor is adjusted to 2.75MW. The current P_load is 20MW, and P_grid_max(t) is calculated to be 0.95×20=19MW. The current P_grid is 18MW, so the power to be controlled is P_ref(t)=min(2.75, 19-18)=1MW, ensuring that P_grid≥19×5%=0.95MW. When a brief load drop occurs at 10:15, P_grid instantly drops to 0.8MW (<0.95MW), and within 10ms, the power to be controlled, P_ref(t), is reduced to 0.1MW to avoid reverse flow. At 11:00, the peak-valley difference reduction rate is evaluated to be 49%, and the benefit is 13% higher than that of the static strategy, without the need to optimize the LSTM model parameters.

[0041] After the energy storage system operated continuously for 30 days using the collaborative control method of this invention, the average peak-valley difference reduction rate was 48.2%, while the peak-valley difference reduction rate before using the collaborative control method of this invention was 30.5%, an increase of 17.7 percentage points; the anti-backflow action was executed 12 times, with an average response time of 78ms, and no backflow lasted for more than 100ms; monthly power generation increased by 6200kWh, revenue per kilowatt-hour increased by 0.15 yuan, and monthly revenue increased by about 9300 yuan; on a certain day of extreme high temperature weather, when the load suddenly increased by 20%, the peak period was automatically extended by 3 hours, and the peak-valley difference reduction rate increased to 53.6%.

[0042] This invention improves the peak-valley difference reduction rate by dynamically adjusting the peak-valley time period and the power used for peak shaving and valley filling. At the same time, it coordinates the control of peak shaving and valley filling with anti-reverse current to avoid interruption of peak shaving and valley filling by anti-reverse current action, thereby reducing the loss of energy utilization efficiency.

[0043] The present invention provides a collaborative control device for an energy storage system, which applies the above-described collaborative control method for an energy storage system, comprising: The data acquisition module is used to collect real-time parameters and historical load data; The prediction module is used for: Determine the forecast load factor based on historical load data; Determine dynamic peak and valley periods based on the predicted load factor; Based on real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods; Determine the backflow prevention limiting power based on real-time parameters; The collaborative control module is used to generate collaborative control commands for controlling the energy storage system based on at least one of the target power and the anti-reverse current limiting power.

[0044] The computer device of the present invention includes a processor and a memory. The memory stores at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the above-described cooperative control method.

[0045] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0046] The memory can be used to store the computer programs or modules. The processor implements various functions of the cooperative control method by running or executing the computer programs or modules stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, applications required for at least one function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0047] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A collaborative control method for an energy storage system, characterized in that, include: Collect real-time parameters and historical load data; Based on the historical load data, determine the predicted load factor; Based on the predicted load factor, determine the dynamic peak and valley periods; Based on the real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods; Based on the real-time parameters, determine the backflow prevention limiting power; Based on the target power and at least one of the anti-reverse current limiting power, a coordinated control command for controlling the energy storage system is generated.

2. The collaborative control method for an energy storage system according to claim 1, characterized in that, The real-time parameters include real-time grid parameters, real-time energy storage parameters, and real-time electricity prices. The real-time grid parameters include active power and load factor. Collect real-time parameters, including: The grid voltage and grid current are collected at a preset frequency; The initial active power is determined based on the grid voltage and the grid current; Determine the initial load factor based on the initial active power and the rated capacity of the transformer; Initial energy storage parameters and real-time electricity prices are collected at preset time points; High-frequency noise is removed from the initial active power, the initial load factor, and the initial energy storage parameters to obtain the active power, load factor, and real-time energy storage parameters.

3. The collaborative control method for an energy storage system according to claim 1, characterized in that, Based on the historical load data, the predicted load factor is determined, including: Based on the historical load data, a predicted load curve is generated; Based on the predicted load curve, determine the predicted load power; The predicted load rate is determined based on the predicted load power.

4. The collaborative control method for an energy storage system according to claim 2, characterized in that, Based on the predicted load factor, determine the dynamic peak and valley periods, including: Peak load factor and off-peak load factor are determined based on K-means clustering. When the predicted load rate is greater than or equal to the peak load rate, the dynamic peak-valley period is the dynamic peak period; When the predicted load rate is less than or equal to the off-peak load rate, the dynamic peak-valley period is the dynamic off-peak period.

5. The collaborative control method for an energy storage system according to claim 4, characterized in that, Based on the real-time parameters, the target power for peak shaving and valley filling during dynamic peak-valley periods is determined, including: When the dynamic peak-valley period is a dynamic peak period, the peak demand power is determined based on the load factor, the peak load factor, the rated power of the energy storage system, and the rated capacity of the transformer. When the dynamic peak-valley period is a dynamic low-valley period, the low-valley demand power is determined based on the load factor, the low-valley load factor, the rated power of the energy storage system, and the rated capacity of the transformer. Based on the real-time electricity price, the peak demand power or the off-peak demand power is adjusted to determine the target power.

6. The collaborative control method for an energy storage system according to claim 5, characterized in that, Based on the real-time electricity price, the peak demand power or the off-peak demand power is adjusted to determine the target power, including: When the real-time electricity price is greater than or equal to the first preset electricity price, the peak demand power is increased by a preset power ratio to determine the target power. When the real-time electricity price is less than or equal to the second preset electricity price, the off-peak demand power is increased by a preset power ratio to determine the target power.

7. The collaborative control method for an energy storage system according to claim 4, characterized in that, Based on the target power and at least one of the anti-reverse current limiting power, generate coordinated control commands for controlling the energy storage system, including: When the dynamic peak-valley period is a dynamic peak period, the target power and the anti-reverse current limiting power are compared, and the power with the smallest value is taken as the power to be controlled. Based on the power to be controlled, generate coordinated control commands for controlling the energy storage system.

8. The collaborative control method for an energy storage system according to claim 4, characterized in that, Based on the target power and at least one of the anti-reverse current limiting power, generate coordinated control commands for controlling the energy storage system, including: When the dynamic peak-valley period is a dynamic low-valley period, the target power is taken as the power to be controlled; Based on the power to be controlled, generate coordinated control commands for controlling the energy storage system.

9. A collaborative control device for an energy storage system, employing the collaborative control method for an energy storage system as described in any one of claims 1-8, characterized in that, include: The data acquisition module is used to collect real-time parameters and historical load data; The prediction module is used for: Based on the historical load data, determine the predicted load factor; Based on the predicted load factor, determine the dynamic peak and valley periods; Based on the real-time parameters, determine the target power for peak shaving and valley filling during dynamic peak-valley periods; Based on the real-time parameters, determine the backflow prevention limiting power; The collaborative control module is used to generate collaborative control commands for controlling the energy storage system based on the target power and at least one of the anti-reverse current limiting power.

10. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, at least one program, code set, or instruction set being loaded and executed by the processor to implement a collaborative control method for an energy storage system as described in any one of claims 1 to 8.

Images