Electric energy control method, device, equipment and medium

Abstract

The invention discloses an electric energy control method and device, equipment and a medium, and relates to the technical field of electric power. According to the scheme, the fluctuation and change of the state of the energy storage system in the historical period, the electricity price in the peak, flat and valley period and the user production load are considered, namely, the parameter change of the energy storage system in various random scenes is fully considered; according to the three parameters, the accumulated cost value in the historical time period is determined in combination with the electric energy distribution scheme and the decision moment in the historical time period, so that the historical cost value is used as an iterative learning basis for selecting the electric energy distribution scheme in the future time period; and finally, the target electric energy distribution scheme executed in the future time period is determined in all the to-be-selected electric energy distribution schemes in the preset strategy space, so that charging and discharging power control by using fixed parameters is avoided. Compared with an expert experience method, the scheme has higher optimal strategy adaptability to various random scenes, and the system performance is improved.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to an electric energy control method, device, equipment and medium. Background Art

[0002] The charging and discharging control of industrial and commercial energy storage peak-valley arbitrage is a storage system management strategy that achieves economic benefits by utilizing the peak-valley electricity price difference in the power market. Its core principle is to charge the energy storage system during the valley period when the electricity price is lower (such as at night or during non-peak hours), and release the stored electricity to the load during the peak period when the electricity price is higher (such as during the day or during peak hours), thereby reducing the electricity cost or obtaining arbitrage benefits through the price difference.

[0003] At present, the charging and discharging control of industrial and commercial energy storage peak-valley arbitrage mainly relies on expert experience control methods. When the energy management system (EMS), battery management system (BMS) and power conversion system (PCS) encounter an alarm, the method uses preset fixed parameters to control the charging and discharging power, which lacks the adaptability of the optimal strategy for various random scenarios. In addition, the control instructions issued by the cloud (such as the valley charging and peak discharging principle) also need to be manually set. In the long run, this decision-making method is not automated and intelligent enough, and it is difficult to meet the requirements of dynamically changing market demands and system operation optimization.

[0004] In view of the above, how to solve the current charging and discharging control of industrial and commercial energy storage peak-valley arbitrage, which is faced with the lack of adaptability of expert experience methods and the lack of automation and intelligence, is an urgent problem that needs to be solved by technicians in this field. Summary of the invention

[0005] The purpose of this application is to provide an electric energy control method, device, equipment and medium to solve the problems of insufficient adaptability of expert experience methods and lack of automation and intelligence in the current charging and discharging control of industrial and commercial energy storage peak-valley arbitrage.

[0006] In order to solve the above technical problems, the present application provides a power control method, comprising:

[0007] Obtain electricity price information, energy storage system status information and user production load information within the historical period;

[0008] Determine the power distribution plan and the corresponding decision time within the historical period according to the power price information, the energy storage system status information and the production load information; wherein the decision time represents the time when the power price changes within the historical period and / or the time when the energy storage system generates an alarm;

[0009] Determine the cumulative cost value in the historical period based on electricity price information, energy storage system status information, production load information, power allocation plan and corresponding decision time;

[0010] A target power allocation scheme is determined from among the candidate power allocation schemes in a preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in a future period.

[0011] On the one hand, obtain the user's production load information, including:

[0012] Obtaining the user's historical production load independent variables; wherein the historical production load independent variables at least include historical temperature, historical production plan and historical electricity price information;

[0013] Construct a production load forecasting model based on historical production load independent variables and linear regression algorithm;

[0014] Obtain the target production load independent variable of the user in the historical period;

[0015] The target production load independent variable is input into the production load forecasting model to determine the production load information of the user in the historical period.

[0016] On the other hand, based on the electricity price information, energy storage system status information, production load information, power distribution plan and corresponding decision time, the cumulative cost value in the historical period is determined, including:

[0017] Determine the cost coefficient; wherein the cost coefficient includes the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, and the shutdown cost coefficient of the energy storage system for operation and maintenance;

[0018] Divide the historical period into multiple historical decision cycles according to the decision moment;

[0019] Determine the electric energy allocation scheme corresponding to each historical decision cycle, and determine the electric energy allocation type of the electric energy allocation scheme; wherein the electric energy allocation type includes a charging process and a discharging process;

[0020] According to the cost coefficient and the type of electric energy allocation of each electric energy allocation scheme, the cost value in each historical decision cycle is determined respectively;

[0021] The cost values ​​in each historical decision cycle are summed up to obtain the cumulative cost value in the historical period.

[0022] On the other hand, according to the cost coefficient and the type of power distribution of each power distribution scheme, the cost value in each historical decision cycle is determined respectively, including:

[0023] When the electric energy allocation type of the electric energy allocation scheme is a discharge process, the corresponding historical decision cycle is determined as a discharge decision cycle;

[0024] Determine the discharge weight coefficient, and determine the energy storage system alarm level, electricity price information and production load information within the discharge decision cycle;

[0025] The cumulative cost of discharge within the discharge decision cycle is determined according to the discharge weight coefficient, the alarm level of the energy storage system within the discharge decision cycle, and the electricity price information.

[0026] On the other hand, according to the discharge weight coefficient, the alarm level of the energy storage system in the discharge decision cycle and the electricity price information, the cumulative discharge cost in the discharge decision cycle is determined, including:

[0027] Determine whether the alarm level of the energy storage system within the discharge decision cycle is greater than a first threshold;

[0028] If not, the cumulative discharge cost within the discharge decision cycle is determined based on the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the discharge decision cycle and the power allocation plan within the discharge decision cycle, the energy storage system alarm level, the electricity price information and the production load information;

[0029] If so, determine the first moment of the energy storage system alarm within the discharge decision cycle;

[0030] Dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment;

[0031] Determine the discharge cost in the first normal sub-period according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first normal sub-period and the power distribution plan in the first normal sub-period, the alarm level of the energy storage system, the electricity price information and the production load information;

[0032] Determine the discharge cost in the first alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan in the first alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0033] The discharge cost in the first normal sub-period is added to the discharge cost in the first alarm sub-period to determine the cumulative discharge cost in the discharge decision period.

[0034] On the other hand, before dividing the discharge decision cycle into the first normal sub-cycle and the first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the discharge decision cycle, it also includes:

[0035] Determine whether the energy storage system is to be shut down for operation and maintenance after the first moment in the discharge decision cycle;

[0036] If not, entering the step of dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment;

[0037] If so, determining the second time when the energy storage system is to be shut down for operation and maintenance within the discharge decision cycle;

[0038] According to the first moment and the second moment, the discharge decision cycle is divided into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance;

[0039] Determine the discharge cost in the second normal sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the second normal sub-cycle and the power distribution plan in the second normal sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0040] Determine the discharge cost in the second alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan in the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0041] The discharge cost in the second normal sub-period is added to the discharge cost in the second alarm sub-period to determine the cumulative discharge cost in the discharge decision period.

[0042] On the other hand, according to the cost coefficient and the type of power distribution of each power distribution scheme, the cost value in each historical decision cycle is determined respectively, including:

[0043] When the electric energy allocation type of the electric energy allocation scheme is a charging process, the corresponding historical decision cycle is determined as a charging decision cycle;

[0044] Determine the charging weight coefficient, and determine the energy storage system alarm level, electricity price information and production load information within the charging decision cycle;

[0045] The cumulative charging cost within the charging decision cycle is determined based on the charging weight coefficient, the energy storage system alarm level within the charging decision cycle, and the electricity price information.

[0046] On the other hand, the cumulative charging cost within the charging decision cycle is determined based on the charging weight coefficient, the energy storage system alarm level within the charging decision cycle, and the electricity price information, including:

[0047] Determining whether the alarm level of the energy storage system within the charging decision cycle is greater than a second threshold;

[0048] If not, the cumulative charging cost within the charging decision cycle is determined based on the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the charging decision cycle and the power allocation plan within the charging decision cycle, the energy storage system alarm level, the electricity price information and the production load information;

[0049] If so, determine the first moment of the energy storage system alarm within the charging decision cycle;

[0050] Dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment;

[0051] Determine the charging cost in the first normal sub-period according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first normal sub-period and the power distribution plan in the first normal sub-period, the alarm level of the energy storage system, the electricity price information and the production load information;

[0052] Determine the charging cost in the first alarm sub-period according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first alarm sub-period and the power distribution plan in the first alarm sub-period, the alarm level of the energy storage system, the electricity price information and the production load information;

[0053] The charging cost in the first normal sub-cycle is added to the charging cost in the first alarm sub-cycle to determine the cumulative charging cost in the charging decision cycle.

[0054] On the other hand, before dividing the charging decision cycle into the first normal sub-cycle and the first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the charging decision cycle, the method further includes:

[0055] Determine whether the energy storage system is shut down for operation and maintenance after the first moment in the charging decision cycle;

[0056] If not, entering the step of dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment;

[0057] If so, determining the second time when the energy storage system is to be shut down for operation and maintenance within the charging decision cycle;

[0058] According to the first moment and the second moment, the charging decision cycle is divided into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance;

[0059] Determine the charging cost in the second normal sub-period according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the second normal sub-period and the power distribution plan in the second normal sub-period, the alarm level of the energy storage system, the electricity price information and the production load information;

[0060] Determine the charging cost in the second alarm sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan in the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0061] The charging cost in the second normal sub-cycle is added to the charging cost in the second alarm sub-cycle to determine the cumulative charging cost in the charging decision cycle.

[0062] On the other hand, a target power allocation scheme is determined from among the candidate power allocation schemes in the preset strategy space according to the accumulated cost value, including:

[0063] Determine a reinforcement learning optimization goal; wherein the reinforcement learning optimization goal is to determine a target power allocation scheme among the candidate power allocation schemes in a preset strategy space so as to minimize the expected average cost per unit time of the system in an infinite time interval;

[0064] Construct a reinforcement learning model according to the reinforcement learning optimization goal, the accumulated cost value and each candidate power allocation scheme in the preset strategy space;

[0065] Solve the reinforcement learning model to obtain the target power distribution plan.

[0066] On the other hand, solving the reinforcement learning model includes:

[0067] Initialize the Q value table and average cost, and set the learning step attenuation factor, simulated annealing initial temperature, cooling coefficient and maximum number of iterations; the Q value table contains the Q values ​​of multiple state-action pairs under the average criterion; the state is a joint state composed of electricity price information, energy storage system state information and production load information, and the action is a candidate power allocation scheme;

[0068] Read the current state at the current decision moment;

[0069] Determine the current temperature according to the simulated annealing initial temperature, the cooling coefficient and the current iteration number, and determine the exploration probability according to the current temperature;

[0070] Generate a random number and determine whether the random number is less than the exploration probability;

[0071] If the random number is less than the exploration probability, an action is randomly selected from the Q value table;

[0072] If the random number is not less than the exploration probability, select the action with the minimum cost corresponding to the current state in the Q value table;

[0073] Perform actions and determine the cost of the actions;

[0074] Calculate the difference result based on the cost of the action, the average cost, the minimum Q value of the next state, and the Q value corresponding to the current state;

[0075] Update the Q value corresponding to the current state according to the Q value corresponding to the current state, the learning step attenuation factor and the difference result;

[0076] Update the average cost and learning step attenuation factor to determine whether the current number of iterations has reached the maximum number of iterations and whether the Q value table meets the convergence conditions;

[0077] If it is determined that the current number of iterations has not reached the maximum number of iterations, and / or the Q value table does not meet the convergence condition, the next decision moment is taken as the current decision moment, and the process returns to the step of reading the current state of the current decision moment;

[0078] If it is determined that the current number of iterations reaches the maximum number of iterations and the Q value table meets the convergence condition, then the Q value table is confirmed to converge;

[0079] Generate the target power distribution plan according to the converged Q value table.

[0080] On the other hand, a target power distribution plan is generated according to the converged Q value table, including:

[0081] Traverse all states in the converged Q value table;

[0082] Based on the converged Q-value table, select the minimum cost action in each state to obtain the action set;

[0083] The action set is determined as the target power allocation scheme.

[0084] In order to solve the above technical problems, the present application also provides an electric energy control device, comprising:

[0085] An acquisition module is used to obtain electricity price information, energy storage system status information and user production load information within a historical period;

[0086] A first determination module is used to determine the power distribution plan and the corresponding decision time within the historical period according to the power price information, the energy storage system status information and the production load information; wherein the decision time represents the time when the power price changes within the historical period and / or the time when the energy storage system generates an alarm;

[0087] The second determination module is used to determine the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the power distribution plan and the corresponding decision time;

[0088] The third determination module is used to determine the target power allocation scheme from among the candidate power allocation schemes in the preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in the future time period.

[0089] In order to solve the above technical problems, the present application also provides an electric energy control device, including:

[0090] Memory for storing computer programs;

[0091] The processor is used to implement the steps of the above-mentioned power control method when executing the computer program.

[0092] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above power control method are implemented.

[0093] The electric energy control method provided in the present application obtains electricity price information, energy storage system status information and user's production load information within a historical period; determines the electric energy distribution plan and the corresponding decision time within the historical period according to the electricity price information, energy storage system status information and production load information; wherein the decision time represents the time when the electricity price changes within the historical period and / or the time when the energy storage system generates an alarm; determines the cumulative cost value within the historical period according to the electricity price information, energy storage system status information, production load information, the electric energy distribution plan and the corresponding decision time; determines the target electric energy distribution plan from each candidate electric energy distribution plan in the preset strategy space according to the cumulative cost value, so as to execute the target electric energy distribution plan in the future period. It can be seen that this scheme takes into account the fluctuations and changes in the state of the energy storage system in the historical period, the electricity price in the peak and off-peak periods, and the user's production load, that is, it fully considers the changes in the parameters of the energy storage system under various random scenarios; based on the above three parameters combined with the power distribution plan and decision-making time of the historical period, the cumulative cost value in the historical period is determined, so that the historical cost value is used as the iterative learning basis for selecting the power distribution plan for the future period, and finally the target power distribution plan to be executed in the future period is determined from the candidate power distribution plans in the preset strategy space, avoiding the use of fixed parameters for charging and discharging power control; compared with the expert experience method, this scheme has stronger optimal strategy adaptability to various random scenarios and improves system performance.

[0094] In addition, the present application also provides an electric energy control device, equipment and medium, with the same effects as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0096] Figure 1 A schematic diagram of an industrial and commercial energy storage peak-valley arbitrage system provided in an embodiment of the present application;

[0097] Figure 2 A flow chart of a power control method provided in an embodiment of the present application;

[0098] Figure 3 A schematic diagram of the peak-valley arbitrage of industrial and commercial energy storage provided in the embodiment of the present application;

[0099] Figure 4 A schematic diagram of an electric energy control device provided in an embodiment of the present application;

[0100] Figure 5 A schematic diagram of an electric energy control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0101] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0102] The core of this application is to provide an electric energy control method, device, equipment and medium to solve the problems faced by the current charging and discharging control of industrial and commercial energy storage peak-valley arbitrage, such as insufficient adaptability of expert experience methods, and lack of automation and intelligence.

[0103] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0104] Figure 1 Schematic diagram of the industrial and commercial energy storage peak-valley arbitrage system provided in the embodiment of the present application. In the energy storage equipment power consumption scenario in the field of new energy storage, the cloud platform issues a charge and discharge allocation strategy, and the energy storage system allocates the charge and discharge weights to assist users in producing electricity demand for peak-valley arbitrage. Figure 1As shown, the industrial and commercial energy storage peak-valley arbitrage system consists of user-side power loads, energy storage systems, and cloud platforms. In order to solve the problems of insufficient adaptability of expert experience methods, lack of automation and intelligence in the current charging and discharging control of industrial and commercial energy storage peak-valley arbitrage, this application proposes an electric energy control method based on the existing hardware structure of the industrial and commercial energy storage peak-valley arbitrage system.

[0105] Figure 2 This is a flow chart of a power control method provided in an embodiment of the present application. Figure 2 As shown, the method includes:

[0106] S10: Obtain electricity price information, energy storage system status information and user production load information within a historical period.

[0107] First, obtain the electricity price information within the historical period , including the electricity price information during the peak and valley periods, and its state space is , k is the identifier of different electricity price information. Obtain energy storage system status information , including but not limited to the status information of EMS, BMS, PCS, communication modules, and smart meters, etc., and its state space is , j is the status information of different equipment. Get the user's production load information , and its state space is , n is the identifier of different production loads. At the same time, define is the joint state of the industrial and commercial energy storage peak-valley arbitrage system, and its state space is .

[0108] It should be noted that in this embodiment, there is no restriction on the size of the historical period, which depends on the specific implementation situation.

[0109] S11: Determine the power distribution plan and corresponding decision time within the historical period based on the electricity price information, energy storage system status information and production load information.

[0110] The decision time represents the time when the electricity price changes in the historical period and / or the time when the energy storage system generates an alarm.

[0111] Furthermore, the power distribution plan and the corresponding decision time within the historical period are determined. , Energy storage system status information And the user's production load information As the state variable of the peak-valley arbitrage strategy control of the reference energy storage system. In order to ensure that the energy storage system can perform its work tasks better and avoid downtime, when the system stops during operation, the state of the energy storage system is , the cloud platform decision center immediately stops the new round of decision-making until the device is running again. The downtime caused by the failure is In this embodiment, the charging and discharging allocation plan for the current period issued by the cloud platform is defined. In addition, the decision time represents the time when the electricity price changes in the historical period and / or the time when the energy storage system generates an alarm, which can be determined according to the time information in the electricity price information, the energy storage system status information and the production load information.

[0112] S12: Determine the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the electricity distribution plan and the corresponding decision time.

[0113] S13: determining a target power allocation scheme from among the candidate power allocation schemes in the preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in a future period.

[0114] Figure 3 The peak-valley arbitrage principle diagram of industrial and commercial energy storage provided in the embodiment of this application. Figure 3 As shown, after obtaining the electricity price information, energy storage system status information, production load information, and determining the electricity distribution plan and corresponding decision time in the historical period, the cumulative cost value in the historical period is determined according to the electricity price information, energy storage system status information, production load information, and the electricity distribution plan and decision time in the historical period, that is, a mathematical model of each state information is established. Finally, the mathematical model is solved by strategy, and the target electricity distribution plan is determined among the candidate electricity distribution plans in the preset strategy space. The obtained target electricity distribution plan is used to guide the actual working process of the industrial and commercial energy storage peak-valley arbitrage system in the future period, realizing the improvement of the peak-valley arbitrage efficiency of the energy storage system.

[0115] It should be noted that the preset strategy space contains a plurality of pre-generated candidate power allocation schemes, including charging schemes and discharging schemes. In this embodiment, the specific types of the candidate power allocation schemes in the preset strategy space are not restricted. In addition, in this embodiment, the determination process of the accumulated cost value in the historical period is not restricted, and the determination method of the target power allocation scheme is not restricted, which depends on the specific implementation situation.

[0116] In this embodiment, the state of the energy storage system in the historical period, the electricity price during the peak and off-peak periods, and the fluctuations and changes in the user's production load are taken into account, that is, the changes in the parameters of the energy storage system under various random scenarios are fully considered; based on the above three parameters combined with the power allocation plan and decision-making time of the historical period, the cumulative cost value in the historical period is determined, so that the historical cost value is used as the iterative learning basis for selecting the power allocation plan for the future period, and finally the target power allocation plan to be executed in the future period is determined from the various candidate power allocation plans in the preset strategy space, avoiding the use of fixed parameters for charging and discharging power control; compared with the expert experience method, this scheme has stronger optimal strategy adaptability to various random scenarios and improves system performance.

[0117] Based on the above embodiment, in some embodiments, obtaining the production load information of the user includes:

[0118] S101: Obtain the user's historical production load independent variable.

[0119] The historical production load independent variables include at least historical temperature, historical production plan and historical electricity price information.

[0120] S102: Construct a production load prediction model based on historical production load independent variables and a linear regression algorithm.

[0121] S103: Obtain the target production load independent variable of the user in the historical period.

[0122] S104: Input the target production load independent variable into the production load prediction model to determine the production load information of the user in the historical period.

[0123] In order to accurately obtain the user's production load information, linear regression is used in this embodiment to construct the user's production load prediction mathematical model. Specifically, the user's historical production load independent variable is obtained. It can be understood that the historical production load independent variable is the user's production load independent variable in the historical production process, including at least historical temperature, historical production plan and historical electricity price information, and may also contain other information, which is not limited in this embodiment. Subsequently, a production load prediction model is constructed based on the historical production load independent variable and the linear regression algorithm, as follows:

[0124] ;

[0125] in, is the dependent variable, i.e., production load information; are different historical production load independent variables; is the intercept; are regression coefficients, representing the influence of each variable on the dependent variable; is the error; Is a positive integer.

[0126] Furthermore, the target production load independent variables of the user in the historical period are obtained, including but not limited to the target temperature, target production plan and target electricity price information. Finally, the target production load independent variables are input into the production load forecasting model to determine the production load information of the user in the historical period. In this way, the analysis and forecasting of the production load information of the user is realized.

[0127] Based on the above embodiments, in some embodiments, the accumulated cost value in the historical period is determined according to the electricity price information, the energy storage system status information, the production load information, the power distribution plan and the corresponding decision time, including:

[0128] S111: Determine the cost coefficient;

[0129] Among them, the cost coefficients include the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, and the shutdown cost coefficient of the energy storage system for operation and maintenance.

[0130] S112: Divide the historical period into multiple historical decision cycles according to the decision moment.

[0131] S113: Determine the power distribution plan corresponding to each historical decision cycle, and determine the power distribution type of the power distribution plan.

[0132] Among them, the power distribution types include charging process and discharging process.

[0133] S114: Determine the cost value in each historical decision cycle according to the cost coefficient and the power distribution type of each power distribution plan.

[0134] S115: summing up the cost values ​​in each historical decision cycle to obtain a cumulative cost value in the historical period.

[0135] In order to determine the cumulative cost value in the historical period, this embodiment specifically defines the cost components of the system: charging cost, alarm cost, discharge reward and shutdown cost. At the same time, the cost coefficient corresponding to each cost is defined: the charging cost coefficient of the energy storage system per unit time , the alarm cost coefficient of the energy storage system per unit time , Discharge reward coefficient of energy storage system per unit time (usually a negative number, indicating the actual peak-valley arbitrage reward), energy storage system downtime cost coefficient for operation and maintenance .

[0136] Since there are peak and valley electricity price changes in historical time periods, the energy storage system status, user production load, and actual energy distribution plan are also different in different cycles, so it is necessary to divide the historical period into multiple historical decision cycles according to the decision time. For example, suppose a factory faces different production loads and electricity price fluctuations in a week. In order to optimize the use of the energy storage system, the historical period can be divided into multiple decision cycles according to the decision time. For example, from Monday to Wednesday, the production load is low, and the valley electricity price is significantly lower than the peak period. It is suitable to charge a lot during the valley period and discharge during the peak period to reduce costs; from Thursday to Friday, the production load increases, and the peak electricity price rises. The strategy needs to be adjusted to increase charging during the normal period to cope with higher electricity demand.

[0137] Further determine the electric energy allocation scheme corresponding to each historical decision cycle, and determine the electric energy allocation type of the electric energy allocation scheme. It can be understood that the electric energy allocation type includes a charging process and a discharging process, that is, in the electric energy allocation scheme corresponding to each historical decision cycle, there are charging schemes and discharging schemes. Finally, according to the cost coefficient and the electric energy allocation type of each electric energy allocation scheme, the cost value in each historical decision cycle is determined respectively, and the cost value in each historical decision cycle is added up, thereby realizing the determination of the cumulative cost value in the historical time period, so as to determine the target electric energy allocation scheme for the future time period using the cumulative cost value.

[0138] The following is an explanation of the process of determining the cost value in the historical decision cycle in conjunction with a specific embodiment:

[0139] 1. Discharge process;

[0140] Based on the above embodiments, in some embodiments, the cost value in each historical decision cycle is determined according to the cost coefficient and the power allocation type of each power allocation scheme, including:

[0141] S120: When the electric energy allocation type of the electric energy allocation scheme is a discharge process, determining the corresponding historical decision cycle as a discharge decision cycle;

[0142] S121: Determine the discharge weight coefficient, and determine the energy storage system alarm level, electricity price information and production load information within the discharge decision cycle;

[0143] S122: Determine the cumulative cost of discharge within the discharge decision cycle according to the discharge weight coefficient, the alarm level of the energy storage system within the discharge decision cycle, and the electricity price information.

[0144] Specifically, when the energy distribution type of the energy distribution plan is the discharge process, the corresponding historical decision cycle is determined as the discharge decision cycle, and the discharge process is executed during the discharge decision cycle. Then the discharge weight coefficient is determined, and the energy storage system alarm level, electricity price information and production load information within the discharge decision cycle are determined. Finally, based on the discharge weight coefficient, the energy storage system alarm level and electricity price information within the discharge decision cycle, the cumulative discharge cost within the discharge decision cycle is determined.

[0145] It is worth noting that the cumulative cost is expressed as , specifically representing the decision moment Status In Action Jump to next decision moment At the same time, under normal operation, the cumulative discharge cost within the discharge decision cycle needs to be calculated according to different situations, as follows:

[0146] (1) Energy storage system alarm;

[0147] Specifically, the cumulative discharge cost within the discharge decision cycle is determined according to the discharge weight coefficient, the alarm level of the energy storage system within the discharge decision cycle, and the electricity price information, including:

[0148] S123: Determine whether the alarm level of the energy storage system in the discharge decision cycle is greater than the first threshold; if not, proceed to step S124; if yes, proceed to step S125;

[0149] S124: Determine the cumulative discharge cost within the discharge decision cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the discharge decision cycle and the power allocation plan within the discharge decision cycle, the energy storage system alarm level, the electricity price information and the production load information;

[0150] S125: Determine the first moment when the energy storage system issues an alarm within the discharge decision cycle;

[0151] S126: dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment;

[0152] S127: Determine the discharge cost in the first normal sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first normal sub-cycle and the power distribution plan in the first normal sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0153] S128: Determine the discharge cost in the first alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan in the first alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information;

[0154] S129: Add the discharge cost in the first normal sub-cycle and the discharge cost in the first alarm sub-cycle to determine the cumulative discharge cost in the discharge decision cycle.

[0155] Specifically, first determine whether the alarm level of the energy storage system within the discharge decision cycle is greater than the first threshold. It should be noted that in this embodiment, there is no restriction on the classification of the alarm level of the energy storage system, and there is no restriction on the size of the first threshold; for example, the alarm can be divided into level 1 alarm, level 2 alarm and level 3 alarm according to the severity, and the first threshold is set to 2; then when the alarm level of the energy storage system is level 1 alarm or level 2 alarm, it is not greater than the first threshold, and when the alarm level of the energy storage system is level 3 alarm, it is greater than the first threshold.

[0156] If it is confirmed that the alarm level of the energy storage system within the discharge decision cycle is not greater than the first threshold, then it is confirmed that the energy storage system is discharging normally within the discharge decision cycle. Specifically, according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the discharge decision cycle and the power allocation plan within the discharge decision cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the cumulative discharge cost within the discharge decision cycle is determined. The formula is as follows:

[0157] ;

[0158] in, is the cumulative discharge cost within the discharge decision cycle, is the discharge weight coefficient, is the energy allocation scheme within the discharge decision cycle, is the discharge decision cycle, is the alarm level of the energy storage system during the discharge decision cycle, is the electricity price information during the discharge decision cycle, is the production load information within the discharge decision cycle, is the alarm cost coefficient of the energy storage system per unit time, It is the discharge reward coefficient of the energy storage system per unit time.

[0159] If it is confirmed that the alarm level of the energy storage system in the discharge decision cycle is greater than the first threshold, it is confirmed that there is an abnormal alarm in the energy storage system in the discharge decision cycle. It is also necessary to determine the first moment of the energy storage system alarm in the discharge decision cycle. Divided into the first normal sub-period and the first alarm sub-cycle . In the first normal sub-cycle, the energy storage system did not alarm, and in the first alarm sub-cycle, the energy storage system alarmed. Subsequently, according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first normal sub-cycle and the power distribution plan in the first normal sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the discharge cost in the first normal sub-cycle is determined, and the formula is as follows:

[0160]

[0161] in, is the discharge cost in the first normal sub-cycle, is the discharge weight coefficient, is the power distribution plan in the first normal sub-period, is the first normal sub-period, is the alarm level of the energy storage system in the first normal sub-cycle, is the electricity price information in the first normal sub-period, is the production load information in the first normal sub-period, is the alarm cost coefficient of the energy storage system per unit time, It is the discharge reward coefficient of the energy storage system per unit time.

[0162] At the same time, according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan in the first alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the discharge cost in the first alarm sub-cycle is determined. The formula is as follows:

[0163] ;

[0164] in, is the discharge cost in the first alarm sub-cycle, is the discharge weight coefficient, is the power distribution plan in the first alarm sub-cycle, is the first alarm sub-cycle, is the alarm level of the energy storage system in the first alarm sub-cycle, is the electricity price information in the first alarm sub-cycle, is the production load information in the first alarm sub-cycle, is the alarm cost coefficient of the energy storage system per unit time, It is the discharge reward coefficient of the energy storage system per unit time.

[0165] Finally, the discharge cost in the first normal sub-cycle is The discharge cost in the first alarm sub-cycle The sum is added to determine the cumulative discharge cost within the discharge decision cycle.

[0166] (2) The energy storage system is shut down for maintenance;

[0167] Specifically, before dividing the discharge decision cycle into the first normal sub-cycle and the first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the discharge decision cycle, it also includes:

[0168] S130: Determine whether the energy storage system is shut down for operation and maintenance after the first moment in the discharge decision cycle; if not, proceed to step S126; if yes, proceed to step S131.

[0169] S131: Determine the second time when the energy storage system is to be shut down for operation and maintenance within the discharge decision cycle.

[0170] S132: Divide the discharge decision cycle into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance according to the first moment and the second moment.

[0171] S133: Determine the discharge cost in the second normal sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the second normal sub-cycle and the power distribution plan in the second normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information.

[0172] S134: Determine the discharge cost within the second alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the maintenance shutdown cost coefficient of the energy storage system, the second alarm sub-cycle and the power distribution plan within the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information.

[0173] S135: Add the discharge cost in the second normal sub-period and the discharge cost in the second alarm sub-period to determine the cumulative discharge cost in the discharge decision period.

[0174] In this embodiment, after determining the first moment of the energy storage system alarm within the discharge decision cycle, it is necessary to further confirm whether the energy storage system has been shut down for maintenance after a period of time. It is understandable that the energy storage system will not output external power after the shutdown, and will not incur any cost, so the situation of the energy storage system being shut down for maintenance should be taken into account. If it is confirmed that the energy storage system has not been shut down for maintenance after the first moment within the discharge decision cycle, the step of dividing the discharge decision cycle into a first normal sub-period and a first alarm sub-period according to the first moment is entered.

[0175] If it is confirmed that the energy storage system has a maintenance shutdown after the first moment in the discharge decision cycle, the second moment of the energy storage system maintenance shutdown in the discharge decision cycle is determined. Divided into the second normal sub-period , Second alarm sub-cycle and downtime period for maintenance Since the energy storage system does not incur any cost during the maintenance downtime, it is only necessary to determine the second normal sub-period and the second alarm sub-cycle The discharge cost within is sufficient.

[0176] Specifically, the discharge cost in the second normal sub-cycle is determined according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the second normal sub-cycle and the power distribution plan in the second normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information. The formula is as follows:

[0177] ;

[0178] in, is the discharge cost in the second normal sub-cycle, is the discharge weight coefficient, is the power distribution plan in the second normal sub-period, is the second normal sub-period, is the alarm level of the energy storage system in the second normal sub-cycle, is the electricity price information in the second normal sub-period, is the production load information in the second normal sub-period, is the alarm cost coefficient of the energy storage system per unit time, It is the discharge reward coefficient of the energy storage system per unit time.

[0179] At the same time, according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan in the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the discharge cost in the second alarm sub-cycle is determined. The formula is as follows:

[0180] ;

[0181] in, is the discharge cost in the second alarm sub-cycle, is the discharge weight coefficient, is the power distribution plan in the second alarm sub-cycle, is the second alarm sub-cycle, is the alarm level of the energy storage system in the second alarm sub-cycle, is the electricity price information in the second alarm sub-period, is the production load information in the second alarm sub-cycle, is the alarm cost coefficient of the energy storage system per unit time, is the discharge reward coefficient of the energy storage system per unit time, is the cost coefficient of downtime for energy storage system waiting for operation and maintenance.

[0182] Finally, the discharge cost in the second normal sub-cycle is and the discharge cost in the second alarm sub-cycle The sum is added to determine the cumulative discharge cost within the discharge decision cycle.

[0183] (ii) Charging process;

[0184] Based on the above embodiments, in some embodiments, the cost value in each historical decision cycle is determined according to the cost coefficient and the power allocation type of each power allocation scheme, including:

[0185] S140: When the electric energy allocation type of the electric energy allocation scheme is a charging process, determining the corresponding historical decision cycle as a charging decision cycle;

[0186] S141: Determine the charging weight coefficient, and determine the energy storage system alarm level, electricity price information and production load information within the charging decision cycle;

[0187] S142: Determine the cumulative charging cost within the charging decision cycle according to the charging weight coefficient, the energy storage system alarm level within the charging decision cycle, and the electricity price information.

[0188] Specifically, when the energy distribution type of the energy distribution plan is the charging process, the corresponding historical decision cycle is determined as the charging decision cycle, and the charging process is performed during the charging decision cycle. Then the charging weight coefficient is determined, and the energy storage system alarm level, electricity price information and production load information within the charging decision cycle are determined. Finally, based on the charging weight coefficient, the energy storage system alarm level and electricity price information within the charging decision cycle, the cumulative charging cost within the charging decision cycle is determined.

[0189] It is worth noting that the cumulative cost is expressed as , specifically representing the decision moment Status In Action Jump to next decision moment Accumulated cost. Similar to the discharge process, under normal operation, the accumulated charging cost within the charging decision cycle also needs to be calculated according to different situations, as follows:

[0190] (1) Energy storage system alarm;

[0191] Specifically, the cumulative charging cost within the charging decision cycle is determined according to the charging weight coefficient, the alarm level of the energy storage system within the charging decision cycle, and the electricity price information, including:

[0192] S143: Determine whether the alarm level of the energy storage system within the charging decision cycle is greater than the second threshold; if not, proceed to step S144; if yes, proceed to step S145.

[0193] S144: Determine the cumulative charging cost within the charging decision cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the charging decision cycle and the power distribution plan within the charging decision cycle, the energy storage system alarm level, the electricity price information and the production load information.

[0194] S145: Determine the first moment when the energy storage system issues an alarm within the charging decision cycle.

[0195] S146: Divide the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment.

[0196] S147: Determine the charging cost within the first normal sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first normal sub-cycle and the power distribution plan within the first normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information.

[0197] S148: Determine the charging cost within the first alarm sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan within the first alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information.

[0198] S149: Add the charging cost in the first normal sub-cycle and the charging cost in the first alarm sub-cycle to determine the cumulative charging cost in the charging decision cycle.

[0199] Specifically, first determine whether the energy storage system alarm level within the charging decision cycle is greater than the second threshold. It should be noted that in this embodiment, there is no restriction on the classification of the energy storage system alarm level, and there is no restriction on the size of the second threshold; for example, the alarm can be divided into level 1 alarm, level 2 alarm and level 3 alarm according to the severity, and the second threshold is set to 2; then when the energy storage system alarm level is level 1 alarm or level 2 alarm, it is not greater than the second threshold, and when the energy storage system alarm level is level 3 alarm, it is greater than the second threshold.

[0200] If it is confirmed that the alarm level of the energy storage system within the charging decision cycle is not greater than the second threshold, it is confirmed that the energy storage system is charged normally within the charging decision cycle. Specifically, according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the charging decision cycle and the power distribution plan within the charging decision cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the cumulative charging cost within the charging decision cycle is determined. The formula is as follows:

[0201] ;

[0202] in, is the cumulative cost of charging within the charging decision cycle, is the charging weight coefficient, It is the energy allocation plan within the charging decision cycle. For the charging decision cycle, is the alarm level of the energy storage system during the charging decision cycle, is the electricity price information within the charging decision cycle, is the production load information within the charging decision cycle, is the charging cost coefficient of the energy storage system per unit time, is the alarm cost coefficient of the energy storage system per unit time.

[0203] If it is confirmed that the alarm level of the energy storage system in the charging decision cycle is greater than the second threshold, it is confirmed that there is an abnormal alarm in the energy storage system in the charging decision cycle. It is also necessary to determine the first moment of the energy storage system alarm in the charging decision cycle. Divided into the first normal sub-period and the first alarm sub-cycle . In the first normal sub-cycle, the energy storage system did not sound an alarm, and in the first alarm sub-cycle, the energy storage system sounded an alarm. Subsequently, according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first normal sub-cycle and the power distribution plan in the first normal sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the charging cost in the first normal sub-cycle is determined, and the formula is as follows:

[0204] ;

[0205] in, is the charging cost in the first normal sub-cycle, is the charging weight coefficient, is the power distribution plan in the first normal sub-period, is the first normal sub-period, is the alarm level of the energy storage system in the first normal sub-cycle, is the electricity price information in the first normal sub-period, is the production load information in the first normal sub-period, is the charging cost coefficient of the energy storage system per unit time, is the alarm cost coefficient of the energy storage system per unit time.

[0206] At the same time, according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan in the first alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the charging cost in the first alarm sub-cycle is determined, and the formula is as follows:

[0207] ;

[0208] in, is the charging cost in the first alarm sub-cycle, is the charging weight coefficient, is the power distribution plan in the first alarm sub-cycle, is the first alarm sub-cycle, is the alarm level of the energy storage system in the first alarm sub-cycle, is the electricity price information in the first alarm sub-cycle, is the production load information in the first alarm sub-cycle, is the charging cost coefficient of the energy storage system per unit time, is the alarm cost coefficient of the energy storage system per unit time.

[0209] Finally, the charging cost in the first normal sub-cycle is The charging cost in the first alarm sub-cycle The sum is added to determine the cumulative charging cost within the charging decision cycle.

[0210] (2) The energy storage system is shut down for maintenance;

[0211] Specifically, before dividing the charging decision cycle into the first normal sub-cycle and the first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the charging decision cycle, it also includes:

[0212] S150: Determine whether the energy storage system is shut down for operation and maintenance after the first moment in the charging decision cycle; if not, proceed to step S146; if yes, proceed to step S151.

[0213] S151: Determine the second time when the energy storage system is to be shut down for operation and maintenance within the charging decision cycle.

[0214] S152: Divide the charging decision cycle into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance according to the first moment and the second moment.

[0215] S153: Determine the charging cost in the second normal sub-period according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the second normal sub-period and the power distribution plan in the second normal sub-period, the alarm level of the energy storage system, the electricity price information and the production load information.

[0216] S154: Determine the charging cost within the second alarm sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan within the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information.

[0217] S155: Add the charging cost in the second normal sub-cycle and the charging cost in the second alarm sub-cycle to determine the cumulative charging cost in the charging decision cycle.

[0218] In this embodiment, after determining the first moment of the energy storage system alarm within the charging decision cycle, it is necessary to further confirm whether the energy storage system has been shut down for maintenance after a period of time. It is understandable that the energy storage system will not be charged after the shutdown, and will not incur any cost, so the situation of the energy storage system being shut down for maintenance should be taken into account. If it is confirmed that the energy storage system has not been shut down for maintenance after the first moment within the charging decision cycle, the step of dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment is entered.

[0219] If it is confirmed that the energy storage system has been shut down for maintenance after the first moment in the charging decision cycle, the second moment of the energy storage system being shut down for maintenance in the charging decision cycle is determined. Divided into the second normal sub-period , Second alarm sub-cycle and downtime period for maintenance Since the energy storage system does not incur any cost during the maintenance downtime, it is only necessary to determine the second normal sub-period and the second alarm sub-cycle The charging price within the range is sufficient.

[0220] Specifically, the charging cost in the second normal sub-cycle is determined according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the second normal sub-cycle and the power distribution plan in the second normal sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information. The formula is as follows:

[0221] ;

[0222] in, is the charging cost in the second normal sub-cycle, is the charging weight coefficient, is the power distribution plan in the second normal sub-period, is the second normal sub-period, is the alarm level of the energy storage system in the second normal sub-cycle, is the electricity price information in the second normal sub-period, is the production load information in the second normal sub-period, is the charging cost coefficient of the energy storage system per unit time, is the alarm cost coefficient of the energy storage system per unit time.

[0223] At the same time, according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan in the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information, the charging cost in the second alarm sub-cycle is determined, and the formula is as follows:

[0224] ;

[0225] in, is the charging cost in the second alarm sub-cycle, is the charging weight coefficient, is the power distribution plan in the second alarm sub-cycle, is the second alarm sub-cycle, is the alarm level of the energy storage system in the second alarm sub-cycle, is the electricity price information in the second alarm sub-period, is the production load information in the second alarm sub-cycle, is the charging cost coefficient of the energy storage system per unit time, is the alarm cost coefficient of the energy storage system per unit time, is the cost coefficient of downtime for energy storage system waiting for operation and maintenance.

[0226] Finally, the charging cost in the second normal sub-cycle is The charging cost in the second alarm sub-cycle The sum is added to determine the cumulative charging cost within the charging decision cycle.

[0227] In summary, the determination of the cumulative cost value within the historical period is achieved.

[0228] On the basis of the above embodiments, in some embodiments, determining the target power allocation scheme from among the candidate power allocation schemes in the preset strategy space according to the accumulated cost value includes:

[0229] S161: Determine the reinforcement learning optimization goal.

[0230] Among them, the optimization goal of reinforcement learning is to determine the target power allocation scheme among the candidate power allocation schemes in the preset strategy space, so as to minimize the expected average cost per unit time of the system in an infinite time interval.

[0231] S162: Construct a reinforcement learning model according to the reinforcement learning optimization objective, the accumulated cost value and each candidate power allocation scheme in the preset strategy space.

[0232] S163: Solve the reinforcement learning model to obtain a target power distribution plan.

[0233] In order to determine the target power allocation scheme among the candidate power allocation schemes, the present embodiment specifically determines the reinforcement learning optimization target, specifically, determining the target power allocation scheme among the candidate power allocation schemes in the preset strategy space, so that the expected average cost per unit time of the system in an infinite time interval is minimized. Further, according to the reinforcement learning optimization target, the accumulated cost value and the candidate power allocation schemes in the preset strategy space, a reinforcement learning model is constructed, and the formula is as follows:

[0234] ;

[0235] in, For the optimal power distribution solution, is the power distribution scheme to be selected, is the preset strategy space, D is the number of time steps, For the selected power distribution scheme The expectations below, is the time interval, For decision-making moments Status In Action Jump to next decision moment The accumulated cost.

[0236] Finally, the above reinforcement learning model is solved to obtain the target power distribution plan. In this embodiment, the target power distribution plan is obtained by constructing and solving the reinforcement learning model, and the charging and discharging strategy control of the energy storage peak-valley arbitrage system is better optimized from the perspective of overall system stable operation.

[0237] Based on the above embodiments, in some embodiments, solving the reinforcement learning model includes:

[0238] S170: Initialize the Q value table and the average cost, and set the learning step attenuation factor, the simulated annealing initial temperature, the cooling coefficient and the maximum number of iterations.

[0239] Among them, the Q value table contains Q values ​​of multiple state-action pairs under the average criterion; the state is a joint state composed of electricity price information, energy storage system state information and production load information, and the action is a candidate power allocation plan.

[0240] S171: Read the current state at the current decision moment.

[0241] S172: Determine the current temperature according to the simulated annealing initial temperature, the cooling coefficient and the current number of iterations, and determine the exploration probability according to the current temperature.

[0242] S173: Generate a random number and determine whether the random number is less than the exploration probability; if so, proceed to step S174; if not, proceed to step S175.

[0243] S174: Randomly select an action from the Q value table.

[0244] S175: Select the action with the minimum cost corresponding to the current state in the Q value table.

[0245] S176: Execute the action and determine the cost of the action.

[0246] S177: Calculate the difference result according to the cost of the action, the average cost, the minimum Q value of the next state and the Q value corresponding to the current state.

[0247] S178: Update the Q value corresponding to the current state according to the Q value corresponding to the current state, the learning step attenuation factor and the differential result.

[0248] S179: Update the average cost and learning step attenuation factor, determine whether the current number of iterations reaches the maximum number of iterations, and whether the Q value table meets the convergence conditions; if not, take the next decision moment as the current decision moment and return to step S171; if so, confirm that the Q value table converges and enter step S180.

[0249] S180: Generate a target power distribution plan according to the converged Q value table.

[0250] In this embodiment, a Q-learning algorithm based on simulated annealing is used to solve the strategy of the established reinforcement learning model to achieve peak-valley arbitrage control optimization of the energy storage system.

[0251] First, initialize the Q value table and average cost , and set the learning step size attenuation factor , simulated annealing initial temperature , Cooling coefficient and the maximum number of iterations It should be noted that the Q value table contains multiple Q values ​​of state-action pairs under the average criterion; the state is a joint state composed of electricity price information, energy storage system state information and production load information, and the action is a candidate power allocation scheme. In a specific implementation, the initial value of the Q value table can be set to 0.

[0252] Further reading on current decision moment Current status According to the simulated annealing initial temperature , Cooling coefficient and the current iteration number Determine the current temperature and determine the exploration probability based on the current temperature as follows:

[0253] ;

[0254] ;

[0255] in, is the current temperature, To explore the probability.

[0256] Then, a random number is generated in the range of 0 to 1 to determine whether the random number is less than the exploration probability. If it is confirmed that the random number is less than the exploration probability, an action is randomly selected from the Q value table. If the random number is confirmed to be not less than the exploration probability, the action with the minimum cost corresponding to the current state is selected in the Q value table. . Perform an action , and determine the action The cost .

[0257] Further, based on the cost of the action, the average cost, the minimum Q value of the next state, and the Q value corresponding to the current state, the difference result is calculated as follows:

[0258] ;

[0259] in, is the difference result, For Action The price, is the average cost, is the minimum Q value of the next state, is the Q value corresponding to the current state.

[0260] According to the Q value corresponding to the current state, the learning step attenuation factor and the difference result, the Q value corresponding to the current state is updated. The formula is as follows:

[0261] ;

[0262] Then adjust the parameters to update the average cost and the learning step attenuation factor. In this embodiment, there is no restriction on the specific update method of the average cost and the learning step attenuation factor, which depends on the specific implementation situation. Determine the current number of iterations Whether the maximum number of iterations has been reached , and the Q value table meets the convergence condition. If the current number of iterations is confirmed The maximum number of iterations was not reached , and / or the Q value table does not meet the convergence condition, the next decision moment is taken as the current decision moment, and the process returns to the step of reading the current state of the current decision moment. Reached the maximum number of iterations , and the Q value table meets the convergence conditions, the Q value table is confirmed to be converged, and the target power distribution plan is generated according to the converged Q value table.

[0263] It should be noted that, in this embodiment, there is no limitation on the specific method of generating the target power distribution scheme according to the converged Q value table, which depends on the specific implementation situation.

[0264] In this embodiment, the Q-learning algorithm based on simulated annealing is used to optimize and solve the reinforcement learning model. Compared with other algorithms, the Q-learning algorithm based on simulated annealing can evaluate the expected utility of available actions without the need for an environmental model, and can effectively solve the problems of random transfer and random rewards without any modification; at the same time, it avoids local optimality and has a fast convergence speed.

[0265] Based on the above embodiments, in some embodiments, generating a target power distribution scheme according to the converged Q value table includes:

[0266] S181: Traverse all states in the converged Q value table.

[0267] S182: Select the minimum cost action in each state based on the converged Q value table to obtain an action set.

[0268] S183: Determine the action set as the target power distribution plan.

[0269] In order to generate a target power distribution plan according to the converged Q value table, in this embodiment, all states in the converged Q value table are traversed, and the minimum cost action in each state is selected based on the converged Q value table. The formula is as follows:

[0270] ;

[0271] in, is the minimum cost action; correspondingly, the action set is , the action set The target power distribution plan is determined. During the operation of the energy storage system, the target power distribution plan is called according to the real-time status and the corresponding charging and discharging instructions are executed.

[0272] In the above embodiments, the power control method is described in detail, and the present application also provides corresponding embodiments of the power control device.

[0273] Figure 4 Schematic diagram of a power control device provided in an embodiment of the present application. Figure 4 As shown, the device comprises:

[0274] The acquisition module 10 is used to acquire electricity price information, energy storage system status information and user production load information within a historical period.

[0275] The first determination module 11 is used to determine the power distribution plan and the corresponding decision time within the historical period according to the electricity price information, the energy storage system status information and the production load information; wherein the decision time represents the time when the electricity price changes within the historical period and / or the time when the energy storage system generates an alarm.

[0276] The second determination module 12 is used to determine the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the power distribution plan and the corresponding decision time.

[0277] The third determination module 13 is used to determine a target power allocation scheme from among the candidate power allocation schemes in the preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in a future period.

[0278] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0279] Figure 5 A schematic diagram of an electric energy control device provided in an embodiment of the present application. Figure 5 As shown, the power control device includes:

[0280] A memory 20, used for storing computer programs;

[0281] The processor 21 is used to implement the steps of the power control method mentioned in the above embodiment when executing the computer program.

[0282] The power control device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0283] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0284] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the power control method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. Data 203 may include but is not limited to data related to the power control method.

[0285] In some embodiments, the power control device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0286] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the power control device, and may include more or fewer components than shown in the figure.

[0287] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0288] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0289] The above is a detailed introduction to an electric energy control method, device, equipment and medium provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can refer to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the present application.

[0290] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A method for controlling electric energy, characterized in that: include: Obtain electricity price information, energy storage system status information and user production load information within the historical period; Determine the power distribution plan and the corresponding decision time within the historical period according to the power price information, the energy storage system status information and the production load information; wherein the decision time represents the time when the power price changes within the historical period and / or the time when the energy storage system generates an alarm; Determine the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the electricity allocation plan and the corresponding decision time; A target power allocation scheme is determined from among the candidate power allocation schemes in a preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in a future period.

2. The electric energy control method according to claim 1, characterized in that: Acquiring the production load information of the user includes: Acquire the user's historical production load independent variable; wherein the historical production load independent variable at least includes historical temperature, historical production plan and historical electricity price information; Constructing a production load prediction model based on the historical production load independent variable and a linear regression algorithm; Obtaining a target production load independent variable of the user in a historical period; The target production load independent variable is input into the production load prediction model to determine the production load information of the user in a historical period.

3. The electric energy control method according to claim 1, characterized in that: Determining the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the electricity distribution plan and the corresponding decision time, including: Determine the cost coefficient; wherein the cost coefficient includes the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, and the shutdown cost coefficient of the energy storage system for operation and maintenance; Dividing the historical period into a plurality of historical decision cycles according to the decision moments; Determine the electric energy allocation scheme corresponding to each of the historical decision cycles, and determine the electric energy allocation type of the electric energy allocation scheme; wherein the electric energy allocation type includes a charging process and a discharging process; Determining the cost value in each of the historical decision cycles respectively according to the cost coefficient and the electric energy allocation type of each of the electric energy allocation schemes; The cost values ​​in each of the historical decision cycles are summed up to obtain the accumulated cost value in the historical period.

4. The electric energy control method according to claim 3, characterized in that: Determining the cost value in each of the historical decision cycles according to the cost coefficient and the electric energy allocation type of each of the electric energy allocation schemes respectively includes: When the electric energy allocation type of the electric energy allocation scheme is a discharging process, determining the corresponding historical decision cycle as a discharging decision cycle; Determine a discharge weight coefficient, and determine an energy storage system alarm level, electricity price information, and production load information within the discharge decision cycle; The cumulative cost of discharge within the discharge decision cycle is determined according to the discharge weight coefficient, the alarm level of the energy storage system within the discharge decision cycle, and the electricity price information.

5. The electric energy control method according to claim 4, characterized in that: Determining the cumulative cost of discharge within the discharge decision cycle according to the discharge weight coefficient, the alarm level of the energy storage system within the discharge decision cycle, and the electricity price information, including: Determining whether an alarm level of the energy storage system within the discharge decision cycle is greater than a first threshold; If not, the accumulated discharge cost within the discharge decision cycle is determined according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the discharge decision cycle and the electric energy allocation plan within the discharge decision cycle, the energy storage system alarm level, the electricity price information and the production load information; If so, determining the first moment of the energy storage system alarming within the discharge decision cycle; dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment; Determine the discharge cost within the first normal sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first normal sub-cycle and the power allocation plan within the first normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; Determine the discharge cost within the first alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan within the first alarm sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; The discharge cost in the first normal sub-cycle is added to the discharge cost in the first alarm sub-cycle to determine the cumulative discharge cost in the discharge decision cycle.

6. The electric energy control method according to claim 5, characterized in that: Before dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the discharge decision cycle, the method further includes: Determining whether the energy storage system is shut down for operation and maintenance after a first moment in the discharge decision cycle; If not, entering the step of dividing the discharge decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment; If yes, determining a second time point in the discharge decision cycle when the energy storage system is to be shut down for operation and maintenance; According to the first moment and the second moment, the discharge decision cycle is divided into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance; Determine the discharge cost within the second normal sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the second normal sub-cycle and the power allocation plan within the second normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; Determine the discharge cost within the second alarm sub-cycle according to the discharge weight coefficient, the alarm cost coefficient of the energy storage system per unit time, the discharge reward coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power distribution plan within the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information; The discharge cost in the second normal sub-cycle is added to the discharge cost in the second alarm sub-cycle to determine the cumulative discharge cost in the discharge decision cycle.

7. The electric energy control method according to claim 3, characterized in that: Determining the cost value in each of the historical decision cycles according to the cost coefficient and the electric energy allocation type of each of the electric energy allocation schemes respectively includes: When the electric energy allocation type of the electric energy allocation scheme is a charging process, determining the corresponding historical decision cycle as a charging decision cycle; Determine a charging weight coefficient, and determine an energy storage system alarm level, electricity price information, and production load information within the charging decision cycle; The cumulative cost of charging within the charging decision cycle is determined according to the charging weight coefficient, the alarm level of the energy storage system within the charging decision cycle, and the electricity price information.

8. The electric energy control method according to claim 7, characterized in that: Determining the cumulative charging cost within the charging decision cycle according to the charging weight coefficient, the energy storage system alarm level within the charging decision cycle, and the electricity price information, including: Determining whether the energy storage system alarm level within the charging decision cycle is greater than a second threshold; If not, the cumulative charging cost within the charging decision cycle is determined according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the charging decision cycle and the electric energy allocation plan within the charging decision cycle, the energy storage system alarm level, the electricity price information and the production load information; If yes, determining the first moment of the energy storage system alarm in the charging decision cycle; dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment; Determine the charging cost within the first normal sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first normal sub-cycle and the power distribution plan within the first normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; Determine the charging cost within the first alarm sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the first alarm sub-cycle and the power distribution plan within the first alarm sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; The charging cost in the first normal sub-cycle is added to the charging cost in the first warning sub-cycle to determine the cumulative charging cost in the charging decision cycle.

9. The electric energy control method according to claim 8, characterized in that: Before dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment, after determining the first moment of the energy storage system alarm in the charging decision cycle, the method further includes: Determining whether the energy storage system is shut down for operation and maintenance after a first moment in the charging decision cycle; If not, entering the step of dividing the charging decision cycle into a first normal sub-cycle and a first alarm sub-cycle according to the first moment; If yes, determining a second time point in the charging decision cycle when the energy storage system is to be shut down for operation and maintenance; According to the first moment and the second moment, the charging decision cycle is divided into a second normal sub-cycle, a second alarm sub-cycle and a shutdown cycle for operation and maintenance; Determine the charging cost within the second normal sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the second normal sub-cycle and the power distribution plan within the second normal sub-cycle, the energy storage system alarm level, the electricity price information and the production load information; Determine the charging cost within the second alarm sub-cycle according to the charging weight coefficient, the charging cost coefficient of the energy storage system per unit time, the alarm cost coefficient of the energy storage system per unit time, the cost coefficient of the energy storage system shutdown for operation and maintenance, the second alarm sub-cycle and the power allocation plan within the second alarm sub-cycle, the alarm level of the energy storage system, the electricity price information and the production load information; The charging cost in the second normal sub-cycle is added to the charging cost in the second alarm sub-cycle to determine the cumulative charging cost in the charging decision cycle.

10. The electric energy control method according to any one of claims 3 to 9, characterized in that: Determining a target power allocation scheme from among the candidate power allocation schemes in a preset strategy space according to the accumulated cost value includes: Determining a reinforcement learning optimization goal; wherein the reinforcement learning optimization goal is to determine the target power allocation scheme among the candidate power allocation schemes in the preset strategy space so as to minimize the expected average cost per unit time of the system in an infinite time interval; Constructing a reinforcement learning model according to the reinforcement learning optimization objective, the accumulated cost value and each candidate power allocation scheme in the preset strategy space; Solve the reinforcement learning model to obtain the target power distribution plan.

11. The electric energy control method according to claim 10, characterized in that: Solving the reinforcement learning model includes: Initialize the Q value table and average cost, and set the learning step attenuation factor, simulated annealing initial temperature, cooling coefficient and maximum number of iterations; wherein the Q value table contains multiple Q values ​​of state-action pairs under the average criterion; the state is a joint state composed of electricity price information, energy storage system state information and production load information, and the action is a candidate power allocation scheme; Read the current state at the current decision moment; Determining a current temperature according to the simulated annealing initial temperature, the cooling coefficient and the current number of iterations, and determining an exploration probability according to the current temperature; Generate a random number, and determine whether the random number is less than the exploration probability; If the random number is less than the exploration probability, randomly select an action from the Q value table; If the random number is not less than the exploration probability, selecting the action with the minimum cost corresponding to the current state in the Q value table; performing the action and determining the cost of the action; Calculating a difference result according to the cost of the action, the average cost, the minimum Q value of the next state, and the Q value corresponding to the current state; Update the Q value corresponding to the current state according to the Q value corresponding to the current state, the learning step attenuation factor and the difference result; Updating the average cost and the learning step attenuation factor, and determining whether the current number of iterations reaches the maximum number of iterations, and whether the Q value table meets the convergence condition; If it is determined that the current number of iterations does not reach the maximum number of iterations, and / or the Q value table does not meet the convergence condition, the next decision moment is taken as the current decision moment, and the process returns to the step of reading the current state of the current decision moment; If it is determined that the current number of iterations reaches the maximum number of iterations and the Q value table satisfies the convergence condition, confirming that the Q value table converges; A target power distribution plan is generated according to the converged Q value table.

12. The electric energy control method according to claim 11, characterized in that: Generating a target power distribution plan according to the converged Q value table includes: Traversing all states in the Q value table after convergence; Select the minimum cost action in each state based on the converged Q value table to obtain an action set; The action set is determined as the target power allocation scheme.

13. An electric energy control device, characterized in that: include: An acquisition module is used to obtain electricity price information, energy storage system status information and user production load information within a historical period; A first determination module is used to determine the power distribution plan and the corresponding decision time within the historical period according to the power price information, the energy storage system status information and the production load information; wherein the decision time represents the time when the power price changes within the historical period and / or the time when the energy storage system generates an alarm; A second determination module is used to determine the accumulated cost value in the historical period according to the electricity price information, the energy storage system status information, the production load information, the power allocation plan and the corresponding decision time; The third determination module is used to determine a target power allocation scheme from among the candidate power allocation schemes in a preset strategy space according to the accumulated cost value, so as to execute the target power allocation scheme in a future period.

14. An electric energy control device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the power control method according to any one of claims 1 to 12 when executing the computer program.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power control method according to any one of claims 1 to 12 are implemented.

Images