Energy storage management system and energy storage management method

Abstract

An energy storage management system and an energy storage management method are provided. The energy storage management method includes: obtaining the current energy storage capacity through a capacity analysis module, and calculating a first capacity and a second capacity based on the current energy storage capacity and system parameters; inputting multiple historical electricity price data from a historical database into a prediction model through a charging scheduling module to obtain predicted electricity price data; scheduling a charging process based on the predicted electricity price data, the first capacity, and system parameters through the charging scheduling module, and executing the charging process, wherein the charging process includes performing a charging operation based on a first power during a first time period; inputting multiple historical load data from a historical database into a prediction model through a discharging scheduling module to obtain predicted load data; and scheduling a discharging process based on the predicted load data, the second capacity, and system parameters through the discharging scheduling module, and executing the discharging process, wherein the discharging process includes performing a discharging operation based on a second power during a second time period.

Description

Technical Field

[0001] This invention relates to the field of energy management, and more particularly to an energy storage management system and energy storage management method. Prior Technology

[0002] With the global energy transition, the penetration rate of renewable energy (such as solar and wind power) is increasing. However, the intermittent and fluctuating nature of renewable energy poses significant challenges to electrical grids.

[0003] Therefore, the conventional approach is to balance electricity supply and demand through the charging and discharging strategies of energy storage systems. However, conventional energy storage systems mostly execute charging and discharging processes based on fixed schedules, without taking into account electricity price fluctuations and load changes, resulting in problems such as low energy utilization and high operating costs. Summary of the Invention

[0004] In view of this, the present invention provides an energy storage management system and an energy storage management method, which can effectively improve energy utilization and economic benefits by dynamically optimizing charging and discharging strategies.

[0005] This invention provides an energy storage management system, including a storage medium and a processor. The storage medium stores a historical database and multiple modules. The historical database stores multiple historical electricity price data and multiple historical load data. The processor is coupled to the storage medium and accesses and executes the multiple modules. The multiple modules include a capacity analysis module, a charging scheduling module, and a discharging scheduling module. The capacity analysis module is used to obtain the current energy storage capacity and calculate a first capacity and a second capacity based on the current energy storage capacity and system parameters. The charging scheduling module is used to input multiple historical electricity price data into a prediction model to obtain predicted electricity price data. The charging scheduling module is also used to schedule a charging process based on the predicted electricity price data, the first capacity, and system parameters, and execute the charging process, wherein the charging process includes performing a charging operation based on a first power during a first time period. The discharging scheduling module is used to input multiple historical load data into the prediction model to obtain predicted load data. The discharge scheduling module is also used to schedule the discharge process based on the predicted load data, the second capacity, and the system parameters, and to execute the discharge process, wherein the discharge process includes the discharge operation performed based on the second power during the second time period.

[0006] This invention provides an energy storage management method. The method includes: obtaining the current energy storage capacity through a capacity analysis module, and calculating a first capacity and a second capacity based on the current energy storage capacity and system parameters; inputting multiple historical electricity price data from a historical database into a prediction model through a charging scheduling module to obtain predicted electricity price data; scheduling a charging process based on the predicted electricity price data, the first capacity, and system parameters through the charging scheduling module, and executing the charging process, wherein the charging process includes performing a charging operation based on a first power during a first time period; inputting multiple historical load data from a historical database into the prediction model through a discharging scheduling module to obtain predicted load data; and scheduling a discharging process based on the predicted load data, the second capacity, and system parameters through the discharging scheduling module, and executing the discharging process, wherein the discharging process includes performing a discharging operation based on a second power during a second time period.

[0007] Based on the above, the energy storage management system and energy storage management method of the present invention can achieve the effect of improving energy utilization and economic benefits by intelligently and dynamically adjusting the charging and discharging strategy. Simple Explanation of the Diagram

[0008] Figure 1 illustrates a schematic diagram of an energy storage management system according to an embodiment of the present invention. Figure 2 illustrates a flowchart of an energy storage management method according to an embodiment of the present invention. Figure 3 illustrates a flowchart of an energy storage management method according to an embodiment of the present invention. Implementation

[0009] Some embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Component symbols used in the following description are considered identical or similar when the same component symbol appears in different drawings. These embodiments are only a part of the present invention and do not disclose all possible implementations of the invention. More precisely, these embodiments are merely examples within the scope of the present invention's patent application.

[0010] Figure 1 illustrates a schematic diagram of an energy storage management system according to an embodiment of the present invention. Referring to Figure 1, the energy storage management system 100 includes a processor 110, a storage medium 120, and a transceiver 130. The processor 110 is coupled to the storage medium 120 and the transceiver 130.

[0011] The processor 110 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose microcontroller (MCU), microprocessor, digital signal processor (DSP), programmable controller, application-specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar elements or combinations thereof.

[0012] Storage medium 120 may be any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), or similar elements or combinations thereof, used to store multiple modules, prediction model 125, and historical database 126 accessible and executable by processor 110, to implement the energy storage management method of the present invention. The multiple modules include a capacity analysis module 121, a charging scheduling module 122, a discharging scheduling module 123, and an auxiliary discharging module 124. In this embodiment, prediction model 125 may be, for example, a recurrent neural network (RNN) model, a convolutional neural network (CNN), or a combination of both.

[0013] Transceiver 130 transmits and receives signals wirelessly or via a wired connection. Transceiver 300 can also perform operations such as low-noise amplification, impedance matching, mixing, up or down frequency conversion, filtering, amplification, and similar functions.

[0014] Figure 2 illustrates a flowchart of an energy storage management method according to an embodiment of the present invention. Please refer to Figures 1 and 2 simultaneously. The energy storage management system 100 can intelligently and dynamically adjust the charging and discharging strategy using the energy storage management method shown in Figure 2, thereby improving energy utilization efficiency and economic benefits simultaneously.

[0015] In step S201, the capacity analysis module 121 obtains the current energy storage capacity and calculates the first capacity and the second capacity based on the current energy storage capacity and system parameters. In this embodiment, the system parameters include the first system capacity and the second system capacity. The first system capacity indicates the maximum energy storage capacity that the energy storage management system 100 can allow. That is, the first system capacity indicates the upper limit of charging of the energy storage management system 100. The second system capacity indicates the minimum energy storage capacity that the energy storage management system 100 can allow. That is, the second system capacity indicates the lower limit of discharging of the energy storage management system 100. It should be noted that during the discharge operation, the energy storage capacity of the energy storage management system 100 must not be lower than the second system capacity to avoid damaging the internal components of the energy storage management system 100, such as the battery (not shown), thereby affecting the service life of the energy storage management system 100.

[0016] In this embodiment, the first capacity indicates the rechargeable capacity of the energy storage management system 100. The capacity analysis module 121 can calculate the first capacity based on the current energy storage capacity and the first system capacity. For example, the capacity analysis module 121 can calculate the difference between the first system capacity and the current energy storage capacity to obtain the first capacity of the energy storage management system 100. Additionally, in this embodiment, the second capacity indicates the dischargeable capacity of the energy storage management system 100. The capacity analysis module 121 can calculate the second capacity based on the current energy storage capacity and the second system capacity. For example, the capacity analysis module 121 can calculate the difference between the current energy storage capacity and the second system capacity to obtain the second capacity of the energy storage management system 100.

[0017] Next, the energy storage management system 100 can formulate an optimized charging and discharging strategy. It is worth mentioning that, in addition to the charging and discharging strategies, the energy storage management system 100 of this invention also provides an auxiliary discharging strategy, which can more effectively improve economic efficiency. Generally, the energy storage management system 100 will sign a contracted load with the power company. When the load of the energy storage management system 100 exceeds this contracted load, the energy storage management system 100 needs to pay an over-contract penalty to the power company.

[0018] For the charging strategy, please refer to steps S202 to S205. For the discharging strategy, please refer to steps S206 to S209. For the auxiliary discharging strategy, please refer to steps S206, S210, and S211. These three strategies will be described separately below.

[0019] Regarding the charging strategy, in step S202, the charging scheduling module 122 can input multiple historical electricity price data into the prediction model 125 to obtain predicted electricity price data. In this embodiment, the historical database 126 is used to store multiple historical electricity price data. The charging scheduling module 122 can input multiple historical electricity price data from the historical database 126 into the pre-trained prediction model 125 to obtain predicted electricity price data. The predicted electricity price data may, for example, include multiple predicted electricity prices.

[0020] The function used by prediction model 125 to generate the predicted electricity price can be, for example, shown by function (1).

[0021] …function (1)

[0022] in, For time Forecasted electricity prices For prediction model functions, For time interval and The number of historical data points used for prediction.

[0023] In step S203, the charging scheduling module 122 can schedule the charging process based on the predicted electricity price data, the first capacity, and system parameters, and then execute the charging process. In this embodiment, the system parameters also include the first system power. Specifically, the first system power may be, for example, the highest charging power that the energy storage management system 100 can use.

[0024] In this embodiment, the predicted electricity price data includes, but is not limited to, multiple predicted electricity prices and their corresponding time periods. The predicted electricity price data may be as shown in Table 1, for example. Please refer to Table 1. Time period Forecast electricity prices 00:00-05:00 0.3 05:00-17:00 1.0 17:00-24:00 1.8 Table 1

[0025] Specifically, the charging scheduling module 122 may, for example, select the lowest predicted electricity price (also referred to as the first predicted electricity price) from multiple predicted electricity prices, and take the time period corresponding to the lowest predicted electricity price (i.e., 00:00-05:00) as the charging time period (also referred to as the first time period), and calculate the charging power (also referred to as the first power) based on the first time period, the first capacity, and the first system power. That is to say, the charging scheduling module 122 can calculate the charging power used by the energy storage management system 100 during the charging time period based on the charging time period and the rechargeable capacity and maximum charging power of the energy storage management system 100. The formula for calculating the charging power can be, for example, shown in formula (1).

[0026] …Formula (1)

[0027] in, The first power (meaning, charging power) This refers to the first system power (i.e., the highest charging power). For the first capacity (i.e., rechargeable capacity) and The first time period (i.e., the charging period) is longer. The units for the first power and the first system power can be, for example, kilowatts (kW), the unit for the first time period can be, for example, hours (h), and the unit for the first capacity can be, for example, kilowatt-hours (kWh).

[0028] After calculating the first power, the charging scheduling module 122 can execute the charging process. In this embodiment, the charging process includes, but is not limited to, performing a charging operation based on the first power during a first time period. Specifically, the charging scheduling module 122 can perform a charging operation based on the first power during the time period from 00:00 to 05:00.

[0029] Furthermore, in step S204, the capacity analysis module 121 can obtain real-time status data during the execution of the charging process. Specifically, the capacity analysis module 121 can obtain real-time status data of the storage management system 100 during the execution of the charging process (i.e., the first time period 00:00-05:00). For example, the capacity analysis module 121 can periodically obtain real-time status data during the first time period and optimize the charging process based on the real-time status data.

[0030] In step S205, the charging scheduling module 122 may adjust the first power and / or the first time period based on real-time status data. In this embodiment, the real-time status data may include the current energy storage capacity and the current time. For example, the charging scheduling module 122 may calculate the optimal charging power based on the real-time status data. The formula for calculating the optimal charging power may be, for example, shown in formula (2).

[0031] …Formula (2)

[0032] in, For the current time Optimal charging power This refers to the first system power (i.e., the highest charging power). The first system capacity (i.e., the maximum energy storage capacity) of the energy storage management system 100. For the energy storage management system 100 at the current time Current energy storage capacity and This is the end time of the first time period.

[0033] Accordingly, the charging scheduling module 122 can calculate the optimal charging power based on real-time status data and adjust the charging power used in the charging process (i.e., the first power) to the optimal charging power to optimize the charging process.

[0034] In one embodiment, the real-time status data may also include the current electricity price. The charging scheduling module 122 can adjust the charging power and / or charging time period according to the current electricity price to avoid increased charging costs and waste. For example, when the current electricity price is higher than the predicted electricity price corresponding to the current time, the charging scheduling module 122 can reduce the charging power and / or charging time period. The formula for calculating charging costs may be, for example, shown in formula (3).

[0035] …Formula (3)

[0036] in, For charging costs, The start time of the first period The end time of the first period In time Optimal charging power In time The current electricity price.

[0037] In one embodiment, the real-time status data may further include the current load. The charging scheduling module 122 may adjust the charging power and / or charging period according to the current load. For example, if the current load is below a threshold, the charging scheduling module 122 may correspondingly increase the charging power and / or change the charging period.

[0038] Based on the above, the charging strategy of the present invention can schedule the charging process using the predicted electricity price data predicted by the artificial intelligence model (i.e., prediction model 125), and optimize the charging process based on real-time status data during the execution of the charging process, dynamically adjusting the charging strategy to achieve the effect of improving energy utilization and economic benefits at the same time.

[0039] On the other hand, regarding the discharge strategy, in step S206, the discharge scheduling module 123 can input multiple historical load data points into the prediction model 125 to obtain predicted load data. In this embodiment, the historical database 126 is also used to store multiple historical load data points. The discharge scheduling module 123 can input multiple historical load data points from the historical database 126 into the pre-trained prediction model 125 to obtain predicted load data.

[0040] In step S207, the discharge scheduling module 123 can schedule the discharge process based on the predicted load data, the second capacity, and system parameters, and execute the discharge process. In this embodiment, the system parameters also include the second system power. Specifically, the second system power may be, for example, the highest discharge power that the energy storage management system 100 can use.

[0041] In this embodiment, the predicted load data includes, but is not limited to, multiple predicted loads and their corresponding time periods. The predicted load data may be as shown in Table 2, for example. Please refer to Table 2. Time period Predicted load 06:00-20:00 900 20:00-22:00 800 22:00-06:00 500 Table 2

[0042] Specifically, the discharge scheduling module 123 can select the highest predicted load (also known as the first predicted load) from multiple predicted loads, and take the time period corresponding to the highest predicted load (i.e., 08:00-20:00) as the discharge time period (also known as the second time period), and calculate the discharge power (also known as the second power) based on the second time period, the second capacity, and the first system power. That is to say, the discharge scheduling module 123 can calculate the discharge power used by the energy storage management system 100 during the discharge time period based on the discharge time period, the dischargeable capacity of the energy storage management system 100, and the highest discharge power. The calculation function for the discharge power can be, for example, shown by formula (4).

[0043] …Formula (4)

[0044] in, The second power (i.e., the discharge power) This refers to the second system power (i.e., the highest discharge power). For the second capacity (i.e., the discharge capacity) and The second time period (i.e., the discharge period) is longer. The units for the second power and the second system power can be, for example, kilowatts (kW), the unit for the second time period can be, for example, hours (h), and the unit for the second capacity can be, for example, kilowatt-hours (kWh).

[0045] After calculating the second power, the discharge scheduling module 123 can execute the discharge process. In this embodiment, the discharge process includes, but is not limited to, performing a discharge operation based on the second power during a second time period. Specifically, the discharge scheduling module 123 can perform a discharge operation based on the second power during the time period from 08:00 to 20:00.

[0046] Furthermore, in step S208, the capacity analysis module 121 can acquire real-time status data during the discharge process. Specifically, the capacity analysis module 121 can acquire real-time status data of the storage management system 100 during the discharge process (i.e., the second time period 08:00-20:00). For example, the capacity analysis module 121 can periodically acquire real-time status data during the second time period and optimize the discharge process based on the real-time status data.

[0047] In step S209, the discharge scheduling module 123 may also be used to adjust the second power and / or the second time period based on real-time status data. In this embodiment, the real-time status data may include the current energy storage capacity and the current time. For example, the discharge scheduling module 123 may calculate the optimal discharge power based on the real-time status data. The formula for calculating the optimal discharge power may be, for example, shown in formula (5).

[0048] …Formula (5)

[0049] in, For the current time Optimal discharge power This refers to the second system power (i.e., the highest charging power). This refers to the second system capacity (i.e., the minimum energy storage capacity) of the energy storage management system 100. For the energy storage management system 100 at the current time Current energy storage capacity and This is the end time of the second period.

[0050] In this way, the discharge scheduling module 123 can calculate the optimal discharge power based on real-time status data and adjust the discharge power (i.e., the second power) used in the discharge process to the optimal discharge power to optimize the discharge process.

[0051] In one embodiment, the real-time status data may also include the current electricity price. For example, the discharge scheduling module 123 may adjust the charging power and / or charging period according to the current electricity price to improve discharge efficiency. For example, if the current electricity price is high, the discharge scheduling module 123 may correspondingly increase the discharge power and / or change the discharge period. The formula for calculating discharge efficiency may be, for example, shown in formula (6).

[0052] …Formula (6)

[0053] in, For discharge efficiency, The start time of the second period The end time of the second period In time Optimal discharge power In time The current electricity price.

[0054] In one embodiment, the real-time status data may also include the current load. For example, if the current load is higher than the predicted load corresponding to the current time, the discharge scheduling module 123 may correspondingly increase the discharge power. For example, if the current load is higher than the threshold load, the discharge scheduling module 123 may execute an auxiliary discharge process to avoid paying over-limit penalties.

[0055] Based on the above, the discharge strategy of the present invention schedules the discharge process using predicted load data predicted by an artificial intelligence model (i.e., prediction model 125), and optimizes the discharge process based on real-time status data during the execution of the discharge process, thereby dynamically adjusting the discharge strategy to improve energy utilization and economic efficiency at the same time.

[0056] Regarding the auxiliary discharge strategy, in step S210, the auxiliary discharge module 124 can determine whether each predicted load is greater than the threshold load. If at least one predicted load is greater than the threshold load, then proceed to step S211. Otherwise, the auxiliary discharge module 124 does not schedule the auxiliary discharge process. In this embodiment, the threshold load is associated with the contract load. For example, the threshold load may be lower than the contract load. For example, the threshold load may be equal to the contract load. After the prediction model 125 predicts the predicted load data, the auxiliary discharge module 124 can determine whether each predicted load is greater than the threshold load.

[0057] For example, suppose the contracted load of the energy storage management system 100 is 800 kW and the threshold load is 750 kW. Taking Table 2 as an example, the predicted load during 06:00-20:00 (i.e., 900 kW) and the predicted load during 20:00-22:00 (i.e., 800 kW) are greater than the threshold load.

[0058] Accordingly, in step S211, the auxiliary discharge module 124 can execute an auxiliary discharge process. In this embodiment, the auxiliary discharge process includes, but is not limited to, performing an auxiliary discharge operation during at least one time period corresponding to at least one predicted load greater than the threshold load, to reduce at least one load to the threshold load. That is, the auxiliary discharge module 124 can perform an auxiliary discharge operation during 06:00-20:00 to reduce a predicted load of up to 900 kW to the threshold load of 750 kW. Similarly, the auxiliary discharge module 124 can perform an auxiliary discharge operation during 20:00-22:00 to reduce a predicted load of up to 800 kW to the threshold load of 750 kW. In this way, the energy storage management system 100 can avoid paying over-limit penalties by using the auxiliary discharge process.

[0059] It is worth mentioning that during the execution of the auxiliary discharge process, the capacity analysis module 121 can obtain real-time status data, thereby enabling the auxiliary discharge module 124 to optimize the auxiliary discharge process based on the real-time status data.

[0060] Based on the above, the auxiliary discharge strategy of the present invention can prevent the load of the energy storage management system 100 from exceeding the contracted load, thereby maintaining economic efficiency.

[0061] Figure 3 illustrates a flowchart of an energy storage management method according to an embodiment of the present invention, wherein the energy storage management method can be implemented by the energy storage management system 100 as shown in Figure 1. Please refer to Figures 1 and 3 simultaneously. In step S301, the current energy storage capacity is obtained through the capacity analysis module 121, and a first capacity and a second capacity are calculated based on the current energy storage capacity and system parameters. In step S302, multiple historical electricity price data from the historical database 126 are input into the prediction model 125 through the charging scheduling module 122 to obtain predicted electricity price data. In step S303, the charging scheduling module 122 schedules the charging process according to the predicted electricity price data, the first capacity, and system parameters, and executes the charging process, wherein the charging process includes performing charging operations based on a first power during a first time period. In step S304, multiple historical load data from the historical database 126 are input into the prediction model 125 through the discharging scheduling module 123 to obtain predicted load data. In step S305, the discharge scheduling module 123 schedules the discharge process according to the predicted load data, the second capacity and system parameters, and executes the discharge process, wherein the discharge process includes performing a discharge operation based on the second power during the second time period.

[0062] The implementation details of steps S301 to S305 have been described in detail in the foregoing embodiments, and therefore will not be repeated here. Furthermore, the execution order of steps S302 to S303 in the charging process and steps S304 to S305 in the discharging process can be interchanged or performed simultaneously; this invention does not impose any limitation on this.

[0063] In summary, the energy storage management system and energy storage management method provided by the embodiments of the present invention can formulate charging strategies, discharging strategies and auxiliary discharging strategies in an intelligent manner, and dynamically adjust the above-mentioned charging and discharging strategies according to the actual situation (i.e., real-time status data), thereby improving energy utilization and economic benefits.

[0064] Although the present invention has been disclosed above by way of embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make some modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0065] 100: Energy Storage Management System 110: Processor 120: Storage Media 121: Capacity Analysis Module 122: Charging scheduling module 123: Discharge scheduling module 124: Auxiliary Discharge Module 125: Predictive Model 126: Historical Database 130: Transceiver S201, S202, S203, S204, S205, S206, S207, S208, S209, S210, S211, S301, S302, S303, S304, S305: Steps

Claims

1. An energy storage management system, comprising: Storage media for storing historical databases and multiple modules, wherein the historical database stores multiple historical electricity price data and multiple historical load data; and a processor, coupled to the storage medium, for accessing and executing the modules, wherein the modules include: a capacity analysis module for obtaining the current energy storage capacity and calculating a first capacity and a second capacity based on the current energy storage capacity and system parameters; A charging scheduling module is used to input the historical electricity price data into the prediction model to obtain predicted electricity price data, and to schedule and execute the charging process based on the predicted electricity price data, the first capacity, and the system parameters, wherein the charging process includes performing a charging operation based on a first power during a first time period; and a discharging scheduling module is used to input the historical load data into the prediction model to obtain predicted load data, and to schedule and execute the discharging process based on the predicted load data, the second capacity, and the system parameters, wherein the discharging process includes performing a discharging operation based on a second power during a second time period.

2. The energy storage management system as claimed in claim 1, wherein during the execution of the charging process, the capacity analysis module is further configured to obtain real-time status data, and the charging scheduling module is further configured to adjust at least one of the first power and the first time period based on the real-time status data.

3. The energy storage management system as claimed in claim 1, wherein during the execution of the discharge process, the capacity analysis module is further configured to obtain real-time status data, and the discharge scheduling module is further configured to adjust at least one of the second power and the second time period based on the real-time status data.

4. The energy storage management system as described in claim 2 or 3, wherein the real-time status data includes the current energy storage capacity, current time, current electricity price, and current load.

5. The energy storage management system as claimed in claim 1, wherein the first capacity is used to indicate the rechargeable capacity of the energy storage management system.

6. The energy storage management system as claimed in claim 1, wherein the second capacity is used to indicate the dischargeable capacity of the energy storage management system.

7. The energy storage management system as claimed in claim 1, wherein the system parameters include a first system capacity, a second system capacity, a first system power, and a second system power.

8. The energy storage management system as described in claim 7, wherein the predicted electricity price data includes multiple predicted electricity prices and their corresponding multiple time periods.

9. The energy storage management system as claimed in claim 8, wherein the charging scheduling module is further configured to select a first predicted electricity price from the predicted electricity prices, and designate the time period corresponding to the first predicted electricity price as the first time period, and calculate the first power based on the first time period, the first capacity, and the first system power.

10. The energy storage management system as claimed in claim 7, wherein the predicted load data includes multiple predicted loads and their corresponding multiple time periods.

11. The energy storage management system as claimed in claim 10, wherein the discharge scheduling module is further configured to select a first predicted load from the predicted loads, and designate the time period corresponding to the first predicted load as the second time period, and calculate the second power based on the second time period, the second capacity, and the second system power.

12. The energy storage management system as claimed in claim 10, wherein the modules further include: An auxiliary discharge module is used to determine whether each of the predicted loads is greater than the threshold load. In response to at least one predicted load being greater than the threshold load, the auxiliary discharge module is also used to execute an auxiliary discharge process, wherein the auxiliary discharge process includes performing an auxiliary discharge operation during at least one time period corresponding to the at least one predicted load to reduce the at least one load to the threshold load.

13. An energy storage management method, comprising: The current energy storage capacity is obtained through the capacity analysis module, and the first capacity and the second capacity are calculated based on the current energy storage capacity and system parameters. The charging scheduling module inputs multiple historical electricity price data from the historical database into the prediction model to obtain predicted electricity price data. The charging scheduling module then schedules and executes a charging process based on the predicted electricity price data, the first capacity, and the system parameters. This charging process includes a first time period during which charging operations are performed based on a first power level. The discharging scheduling module inputs multiple historical load data from the historical database into the prediction model to obtain predicted load data. The discharging scheduling module then schedules and executes a discharging process based on the predicted load data, the second capacity, and the system parameters. This discharging process includes a second time period during which discharging operations are performed based on a second power level.

Images