Power distribution cabinet intelligent control method and system, power distribution cabinet, and storage medium

Abstract

The application provides a power distribution cabinet intelligent control method and system, a power distribution cabinet and a storage medium, and belongs to the technical field of power distribution. The method is applied to an energy storage system. The energy storage system comprises a power distribution cabinet and an energy storage element. The energy storage element is connected in parallel with a power grid through the power distribution cabinet. The method is executed by the power distribution cabinet. The method comprises the following steps: determining a load prediction value of the power grid in a future period based on historical load data of the power grid; determining a target charging and discharging power of the energy storage element based on the load prediction value of the power grid in the future period and a current residual power of the energy storage element; and controlling the energy storage element to charge or discharge the power grid according to the target charging and discharging power based on the target charging and discharging power. The power distribution cabinet intelligent control method and system, the power distribution cabinet and the storage medium provided by the application can improve the stability of power grid operation.

Description

Technical Field

[0001] This application belongs to the field of power distribution technology, and more specifically, relates to a method and system for intelligent control of power distribution cabinets, power distribution cabinets, and storage media. Background Technology

[0002] Energy storage systems can store electrical energy and release it when needed to regulate energy supply and demand, improve the stability and efficiency of the power system, and their role is widely covered in multiple fields such as power systems, renewable energy, and the user side. As a key power control device in energy storage systems, the switchboard is mainly used for the distribution, conversion, protection, and monitoring of electrical energy.

[0003] Existing control methods for distribution cabinets mostly employ fixed threshold control, stopping charging when the energy storage device reaches its upper limit and stopping discharging when it reaches its lower limit. Fixed thresholds cannot adapt to dynamic changes in the power grid, potentially leading to poor coordination between the energy storage system and the grid, and affecting the overall stability of the power grid operation. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for intelligent control of power distribution cabinets, power distribution cabinets, and storage media to improve the stability of power grid operation.

[0005] A first aspect of this application provides an intelligent control method for a distribution cabinet, applied to an energy storage system. The energy storage system includes a distribution cabinet and energy storage elements, the energy storage elements being connected in parallel with the power grid through the distribution cabinet. The method is executed by the distribution cabinet and includes:

[0006] The load forecast values ​​for the power grid in future periods are determined based on historical load data of the power grid; the load forecast values ​​for the power grid in future periods include N load forecast values ​​for the power grid in the next N periods;

[0007] The target charging and discharging power of the energy storage element is determined based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element.

[0008] Based on the target charging and discharging power, the energy storage element is controlled to charge or discharge the power grid according to the target charging and discharging power;

[0009] The step of determining the target charging and discharging power of the energy storage element based on the grid load forecast for a future period and the current remaining power of the energy storage element includes:

[0010] The load forecast of the power grid in the future period and the current remaining power of the energy storage element are input into the reinforcement learning network to obtain the target charging and discharging power of the energy storage element.

[0011] The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods.

[0012] A second aspect of this application provides an intelligent control system for a power distribution cabinet, which is disposed in a power distribution cabinet. The power distribution cabinet is included in an energy storage system, and the energy storage system further includes energy storage elements. The energy storage elements are connected in parallel with the power grid through the power distribution cabinet. The intelligent control system for the power distribution cabinet includes:

[0013] The power grid load forecasting module is used to determine the power grid load forecast for future periods based on historical power grid load data; the power grid load forecast for future periods includes N load forecasts for the power grid over N future periods;

[0014] The charging and discharging power determination module is used to determine the target charging and discharging power of the energy storage element based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element.

[0015] The control module is used to control the energy storage element to charge or discharge the power grid according to the target charging and discharging power based on the target charging and discharging power;

[0016] The charge / discharge power determination module is specifically used for:

[0017] The load forecast of the power grid in the future period and the current remaining power of the energy storage element are input into the reinforcement learning network to obtain the target charging and discharging power of the energy storage element.

[0018] The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods.

[0019] A third aspect of this application provides a power distribution cabinet, including a controller. The controller includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the above-described intelligent control method for the power distribution cabinet.

[0020] In a fourth aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described intelligent control method for power distribution cabinets.

[0021] The beneficial effects of the intelligent control method and system for power distribution cabinets, power distribution cabinets, and storage media provided in this application embodiment are as follows:

[0022] Based on the predicted changes in grid load and the current remaining power of the energy storage element, the embodiments of this application determine the target charging and discharging power (i.e., the optimal charging and discharging power) of the energy storage element in the current time period. Based on the target charging and discharging power, the energy storage element is controlled to charge or discharge the grid to adapt to changes in grid load. This can enhance the coordination between the energy storage system and the grid and ensure the stable operation of the grid. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A structural block diagram of an energy storage system provided in an embodiment of this application;

[0025] Figure 2 A flowchart illustrating an embodiment of the intelligent control method for a power distribution cabinet provided in this application;

[0026] Figure 3 This is a structural block diagram of an intelligent control system for a power distribution cabinet provided in one embodiment of this application;

[0027] Figure 4 This is a schematic block diagram of a controller provided in one embodiment of this application. Detailed Implementation

[0028] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0030] This application provides an intelligent control method for a power distribution cabinet, applied to an energy storage system 110, such as... Figure 1 As shown, the energy storage system 110 includes a distribution cabinet 112 and an energy storage element 111. The energy storage element 111 is connected in parallel with the power grid 120 through the distribution cabinet 112.

[0031] Furthermore, the intelligent control method for a power distribution cabinet provided in this application embodiment can be... Figure 1The distribution cabinet 112 shown is in operation; please refer to [the documentation / reference]. Figure 2 , Figure 2 This is a flowchart illustrating an embodiment of an intelligent control method for a power distribution cabinet provided in this application. The method may include:

[0032] S101: Determine the load forecast value of the power grid for future periods based on the historical load data of the power grid; the load forecast value of the power grid for future periods includes N load forecast values ​​of the power grid for the next N periods;

[0033] In this embodiment, historical load data of the power grid can reflect users' electricity consumption habits (such as the diurnal fluctuation of industrial load and the morning and evening peaks of residential load). Therefore, the power grid load for future periods can be predicted based on the historical load data of the power grid, thus obtaining the predicted load value of the power grid for future periods. The future period can be several hours to several days in the future. For example, the power grid load for the next 1 hour, 2 hours, 1 day, or 2 days can be predicted.

[0034] Specifically, since the power grid supplies power in regional areas, stable operation of the corresponding power grid can be achieved by setting up energy storage systems in one or more power supply areas. Therefore, in this embodiment, the historical load data of the power grid refers to the historical load data of the power grid in any power supply area (denoted as the target power supply area). The historical load data of the target power supply area power grid can be obtained from the power grid dispatch center responsible for that power supply area. For example, the historical load data of the power grid for the most recent month can be obtained from the power grid dispatch center of the target power supply area. The historical load data of the power grid is then input into a pre-trained extreme gradient boosting tree model (XGBoost) or a lightweight gradient boosting machine model (LightGBM) to obtain the load forecast value of the power grid for the future period (7 days).

[0035] S102: Determine the target charging and discharging power of the energy storage element based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element.

[0036] In this embodiment, the energy storage element can be a battery or a supercapacitor. Based on the load forecast of the power grid in the future period, if the load forecast of the power grid in the future period is greater than the current power grid load, the energy storage element can be controlled to discharge to provide power to the power grid and alleviate the power supply pressure of the power grid. If the load forecast of the power grid in the future period is less than the current power grid load, the energy storage element can be charged to absorb excess power and avoid power grid voltage / frequency fluctuations.

[0037] For example, if it is predicted that the grid load will increase within the next hour (such as during the evening peak), the energy storage components can be controlled to discharge in advance during the current period to alleviate the upcoming power supply pressure. Conversely, if it is predicted that a load slump will occur within the next two hours (such as late at night), the energy storage components can be controlled to charge during the current period to absorb excess energy.

[0038] Specifically, considering the limited remaining capacity of energy storage devices, to avoid overcharging or over-discharging, the target charging / discharging power of the energy storage devices in the current period can be determined by combining the grid load forecast for the future period with the current remaining capacity of the devices. This target charging / discharging power controls the charging or discharging of the energy storage devices, thus reducing damage to the devices while ensuring grid demand is met. The current remaining capacity of the energy storage devices can be obtained by reading data from the corresponding management system. For example, if the energy storage device is a battery, the current remaining capacity can be obtained from the battery management system; if the energy storage device is a supercapacitor, the current remaining capacity can be obtained from the supercapacitor management system.

[0039] S103: Based on the target charging and discharging power, control the energy storage element to charge or discharge the grid according to the target charging and discharging power.

[0040] In this embodiment, the distribution cabinet is typically equipped with a controller and a power storage converter (PCS). The power storage converter can realize the conversion of electrical energy between the AC power of the power grid and the DC power of the energy storage element. The controller adjusts the output of the power storage converter according to the target charging and discharging power, and can adjust the charging and discharging current / voltage of the energy storage element to achieve tracking control of the target charging and discharging power.

[0041] As can be seen from the above, this embodiment determines the target charging and discharging power (i.e., the optimal charging and discharging power) of the energy storage element in the current period based on the predicted changes in grid load and the current remaining power of the energy storage element. Based on the target charging and discharging power, the energy storage element is controlled to charge or discharge the grid to adapt to changes in grid load. This can enhance the coordination between the energy storage system and the grid and ensure the stable operation of the grid.

[0042] In one embodiment of this application, the target charging and discharging power of the energy storage element is determined based on the load forecast of the power grid in a future period and the current remaining power of the energy storage element. Specifically, this may include:

[0043] The load forecast of the power grid in the future period and the current remaining power of the energy storage device are input into the reinforcement learning network to obtain the target charging and discharging power of the energy storage device.

[0044] The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes the candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods.

[0045] Specifically, the calculation process of the reward function of a reinforcement learning network includes:

[0046] The load fluctuation value of the power grid is determined based on N load forecast values ​​for the power grid in the next N time periods;

[0047] Based on the candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods and the current remaining power of the energy storage element, determine the N predicted values ​​of the remaining power of the energy storage element in the next N time periods.

[0048] The state of charge (SOC) assessment value of the energy storage element is determined based on the N predicted remaining energy values ​​of the energy storage element in the next N time periods.

[0049] The reward function of the reinforcement learning network is calculated based on the grid load fluctuation value and the state of charge assessment value of the energy storage element.

[0050] In this embodiment, by predicting the load value of the power grid in the next N time periods, the charging and discharging strategy of the energy storage element can be determined in advance, the multi-time period objectives can be optimized globally, and short-sighted decision-making in a single time period can be avoided.

[0051] Specifically, reinforcement learning networks can be used to determine the target charging and discharging power of energy storage components. Reinforcement learning networks optimize decision-making strategies through dynamic interaction between the agent and the environment (the state space determined by the input data). By trying new actions and using the reward function to evaluate the value of the actions, the network gradually learns the optimal mapping from state to action.

[0052] Each action corresponds to a sequence of charging and discharging power over the next N time periods. , ,..., ..., Each power value in this sequence represents a candidate value for the charging and discharging power of the energy storage element in each of the next N time periods. For example, The candidate values ​​for charging and discharging power in the i-th time period are defined (positive numbers represent discharging, negative numbers represent charging), with the subscript t representing the current time period. The theoretical range of charging and discharging power determines the maximum and minimum allowable charging and discharging power of the energy storage element, and each power value in the charging and discharging power sequence should be selected within this theoretical range. By calculating the reward function corresponding to each action, a target action is selected from the action space, and the target charging and discharging power is determined based on the charging and discharging power sequence corresponding to the target action.

[0053] For example, the reward function corresponding to each action is determined based on the grid load fluctuation value and the state of charge assessment value of the energy storage element. The larger the grid load fluctuation value, the greater the degree of grid load fluctuation, and the smaller the value of the reward function. The state of charge assessment value of the energy storage element is used to characterize the safety level of the charging and discharging process of the energy storage element. The larger the state of charge assessment value of the energy storage element, the lower the safety level of the charging and discharging process of the energy storage element, and the smaller the value of the reward function.

[0054] Specifically, the grid load fluctuation value can be determined based on N load forecast values ​​for the grid in the next N time periods. Correspondingly, the N remaining power forecast values ​​of the energy storage element in the next N time periods can be determined based on the candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods and the current remaining power of the energy storage element. The formula for calculating the remaining power forecast value of the energy storage element in the i-th time period is as follows:

[0055] ;

[0056] in, This represents the predicted remaining power of the energy storage device in the i-th time period in the future. This represents the predicted remaining power of the energy storage device in the (i-1)th time period in the future. For the charging and discharging efficiency of energy storage components, This represents the candidate values ​​for charging and discharging power in the (i-1)th time period. Indicates the rated capacity of the energy storage element. This represents the time difference between the i-th time period and the (i-1)-th time period in the future.

[0057] Based on the predicted N remaining energy values ​​of the energy storage element in the next N time periods, the charge and discharge performance of the energy storage element can be evaluated to obtain the state of charge evaluation value of the energy storage element.

[0058] Furthermore, based on the obtained grid load fluctuation values ​​and energy storage element state-of-charge assessment values, the two can be weighted and summed, and the reward function of the reinforcement learning network can be determined based on the weighted summation result.

[0059] As can be seen from the above, this embodiment uses a reinforcement learning network to perform multi-period joint optimization based on N load forecasts of the power grid in the next N time periods, which is beneficial for determining the optimal target charging and discharging power.

[0060] In one embodiment of this application, determining the grid load fluctuation value based on N load forecast values ​​for the grid over N future time periods may specifically include:

[0061] Obtain the target load curves of the power grid for the next N time periods;

[0062] Based on the N load forecasts for the power grid over the next N time periods and the candidate charging and discharging power values ​​of the energy storage components in each of the next N time periods, the N net load forecasts for the power grid over the next N time periods are determined; where the net load forecast is the power grid's own load forecast.

[0063] The power grid load fluctuation value is obtained by comparing the N net load forecasts for the power grid in the next N periods with the target load curve for the power grid in the next N periods.

[0064] In this embodiment, those skilled in the art can pre-set the target load curve of the power grid for future periods based on historical load data, industry electricity consumption patterns, weather forecasts (such as the impact of temperature on air conditioning load), holidays, and other factors. During power grid operation, the power supply (such as generators) is usually adjusted in advance according to the target load curve of the power grid to avoid power outages or overcapacity. By extracting the curve for the corresponding period from the target load curve of the power grid, the target load curve of the power grid for the next N periods can be obtained.

[0065] The net load forecast of the power grid refers to the actual load value of the power grid after taking into account the impact of energy storage charging and discharging. That is, if the candidate value of the charging and discharging power of the energy storage element is greater than zero in the i-th time period in the future, it indicates that the energy storage element is discharging to the power grid in that time period. In this case, the net load forecast of the power grid is equal to the load forecast of the power grid minus the discharge power of the energy storage element. If the candidate value of the charging and discharging power of the energy storage element is less than zero in the i-th time period in the future, it indicates that the power grid is charging the energy storage element in that time period. In this case, the net load forecast of the power grid is equal to the load forecast of the power grid plus the discharge power of the energy storage element.

[0066] In this embodiment, comparing the N net load forecasts for the power grid over the next N time periods with the target load curve for the power grid over the next N time periods can be described in detail as follows:

[0067] The target load value for each of the next N time periods is determined based on the load value of the corresponding time period on the target load curve of the power grid for the next N time periods.

[0068] The power grid load fluctuation value is obtained by comparing the N net load forecasts for the next N time periods with the target load values ​​for the corresponding time periods. The specific calculation formula is as follows:

[0069] ;

[0070] in, Indicates the value of power grid load fluctuation. This represents the predicted power grid load for the i-th time period. This represents the candidate values ​​for the charging and discharging power of the energy storage element in the i-th time period in the future. This represents the predicted net load of the power grid for the i-th time period. This represents the target load value corresponding to the i-th time period in the future on the target load curve.

[0071] As can be seen from the above, this embodiment calculates the N net load forecast values ​​of the power grid in the next N time periods, and the target load value corresponding to each of the N time periods. It then compares the N net load forecast values ​​of the power grid in the next N time periods with the target load values ​​of the corresponding time periods to obtain the power grid load fluctuation value. Based on the power grid load fluctuation value, the reward function of the reinforcement learning network is determined. This helps guide the reinforcement learning network to determine the target charging and discharging power with the goal of "reducing the difference between the N net load forecast values ​​and the target load value of the corresponding time period". As a result, the actual net load curve of the power grid is closer to the target load curve, which is conducive to the stable operation of the power grid.

[0072] In one embodiment of this application, determining the state-of-charge (SOC) assessment value of an energy storage element based on N predicted remaining energy values ​​over N future time periods includes:

[0073] Obtain the charging and discharging safety thresholds of energy storage components;

[0074] The predicted remaining power of the energy storage element in the next N time periods is compared with the charging and discharging safety threshold to determine the charging and discharging risk assessment value of the energy storage element in the next N time periods.

[0075] Based on the N predicted remaining power values ​​of the energy storage element in the next N time periods, the rate of change of remaining power between two adjacent time periods is determined, resulting in N-1 remaining power change rates. Based on the N-1 remaining power change rates, the fluctuation value of the remaining power is determined.

[0076] The state of charge (SOC) assessment value of the energy storage element is obtained by weighting and summing the charge and discharge risk assessment values ​​and the fluctuation values ​​of the remaining power of the energy storage element over the next N time periods.

[0077] In this embodiment, taking a battery as an example, the charging and discharging safety threshold of an energy storage element may include an upper limit of the remaining power (e.g., 95%) and a lower limit of the remaining power (e.g., 5%). If the battery exceeds the charging and discharging safety threshold during the charging and discharging process, it may lead to a shortened lifespan (e.g., lithium plating, sulfation) or safety risks (e.g., thermal runaway).

[0078] Therefore, in this embodiment, the energy storage element's charge and discharge risk assessment value for the next N time periods is obtained by comparing the N predicted remaining energy values ​​of the energy storage element with the charge and discharge safety threshold, and the state of charge assessment value of the energy storage element is determined based on the charge and discharge risk assessment value.

[0079] Specifically, the charge / discharge risk assessment value can be calculated using the following formula:

[0080] ;

[0081] in, This represents the charge / discharge risk assessment value of the energy storage device over the next N time periods. This represents the charging and discharging risk assessment value for the i-th time period. This represents the predicted remaining electricity consumption for the i-th time period. This indicates the upper limit threshold for safe charging and discharging. This indicates the lower limit threshold for safe charging and discharging. and This indicates the preset scaling factor.

[0082] The above formula shows that for any future time period i, if its corresponding remaining power prediction value lie in and If the remaining power is between 0 and 1, then the charging / discharging risk assessment value for the i-th time period is equal to 0; if the remaining power prediction value is... Greater than Based on and The difference determines the charging and discharging risk assessment value for the i-th time period; if the remaining power prediction value... Less than Based on and The difference between the values ​​determines the charge / discharge risk assessment value for the i-th time period. Following the above method, the charge / discharge risk assessment values ​​for each time period can be obtained.

[0083] Based on the charging and discharging risk assessment values ​​obtained for each time period, the charging and discharging risk assessment values ​​for each time period can be accumulated to obtain the charging and discharging risk assessment values ​​of the energy storage element for the next N time periods.

[0084] Meanwhile, considering that a large change in the remaining charge rate between two adjacent time periods may lead to increased battery heating, increased internal resistance, and accelerated aging, this embodiment also determines the state of charge (SOC) assessment value of the energy storage element based on the rate of change in remaining charge.

[0085] Specifically, based on the rate of change of remaining electricity between two adjacent time periods over N future time periods, N-1 rates of change of remaining electricity can be obtained. The fluctuation value of the remaining electricity can then be determined based on these N-1 rates of change. For example, the fluctuation value of the remaining electricity can be calculated using the following formula:

[0086] ;

[0087] in, This indicates the fluctuation value of the remaining battery power. This represents the predicted remaining electricity value for the i-th time period in the future. This represents the predicted remaining power consumption for the (i+1)th time period in the future.

[0088] Based on the charging and discharging risk assessment value and the fluctuation value of the remaining power, the weighted sum of the charging and discharging risk assessment value and the fluctuation value of the remaining power can be used to obtain the state of charge assessment value of the energy storage element.

[0089] As can be seen from the above, this embodiment comprehensively considers the charging and discharging risk assessment value and the fluctuation value of the remaining power to determine the state of charge assessment value of the energy storage element. This can optimize the operating efficiency of the energy storage element while ensuring that it does not exceed the safety boundary.

[0090] In one embodiment of this application, the reward function of the reinforcement learning network is calculated based on the grid load fluctuation value and the state of charge assessment value of the energy storage element, including:

[0091] The first weight of the grid load fluctuation value is determined based on the proportion of renewable energy generation in the grid; wherein, the first weight corresponding to the proportion of renewable energy generation in the grid being greater than the first threshold is greater than the first weight corresponding to the proportion of renewable energy generation in the grid being less than or equal to the first threshold.

[0092] The second weight is used to determine the state-of-charge assessment value of the energy storage element based on the first weight;

[0093] The first summation result is obtained by weighting and summing the grid load fluctuation value and the state of charge assessment value of the energy storage element based on the first weight and the second weight.

[0094] The reciprocal of the first summation result is used as the reward function for the reinforcement learning network.

[0095] In this embodiment, considering that the larger the grid load fluctuation value and the state of charge (SCC) assessment value of the energy storage element, the smaller the corresponding reward function, the two values ​​can be weighted and summed. The reciprocal of the first summation result (to avoid the denominator being zero, the first summation result can be incremented by 1 before taking the reciprocal) is used as the reward function of the reinforcement learning network. The first weight of the grid load fluctuation value and the second weight of the SCC assessment value are complementary, and their sum is 1.

[0096] Furthermore, considering that when renewable energy (such as wind and solar power) accounts for a large proportion of the power grid's output, the strong intermittency of renewable energy output can exacerbate grid load fluctuations. In this case, the weight of grid load fluctuation values ​​can be increased to encourage the reinforcement learning network to prioritize smoothing out fluctuations and ensure grid stability. The proportion of renewable energy generation in the grid can be obtained based on real-time operational data from the grid dispatch center.

[0097] Specifically, a first threshold can be preset. When the proportion of renewable energy (such as wind power and photovoltaic) power generation in the grid is greater than the first threshold, it indicates that the proportion of renewable energy power generation in the grid is relatively large. At this time, the first weight of the grid load fluctuation value is set to a larger first value. When the proportion of renewable energy (such as wind power and photovoltaic) power generation in the grid is less than or equal to the first threshold, it indicates that the proportion of renewable energy power generation in the grid is relatively small. At this time, the first weight of the grid load fluctuation value is set to a smaller second value to increase the second weight of the state of charge assessment value, so as to encourage the reinforcement learning network to prioritize the healthy operation of energy storage components.

[0098] As can be seen from the above, this embodiment dynamically adjusts the first weight of the grid load fluctuation value based on the proportion of renewable energy power generation in the grid, which can enable the energy storage system to play the best regulation effect in different scenarios and improve the coordinated operation effect of the grid and the energy storage system.

[0099] In one embodiment of this application, the load forecast of the power grid for a future period and the current remaining power of the energy storage device are input into a reinforcement learning network to obtain the target charging and discharging power of the energy storage device, including:

[0100] The load forecast of the power grid in the future period and the current remaining power of the energy storage device are input into the reinforcement learning network to obtain the target action;

[0101] The target charging and discharging power candidate value of the target time period is determined from the N charging and discharging power candidate values ​​included in the target action. The target time period is the time period closest to the current time period among the N time periods.

[0102] In this embodiment, the load forecast of the power grid for future periods and the current remaining power of the energy storage devices are input into the reinforcement learning network. In the target action output by the reinforcement learning network, the candidate values ​​of charging and discharging power for each period are the optimal values ​​of charging and discharging power for each period. Based on this, the period closest to the current period (e.g., the current time is t, and the target period is t+1) is selected as the target period, and the candidate values ​​of charging and discharging power for the target period are used as the target charging and discharging power to control the charging and discharging of the energy storage devices for the current period. The power candidate values ​​for other periods (e.g., t+2 to t+N) can be dynamically adjusted based on newly acquired data and used as the target charging power for the next period.

[0103] As can be seen from the above, this embodiment calculates the reward function based on the prediction information of the next N time periods and determines the target charging and discharging power for the current time period. This can ensure the real-time performance of the charging and discharging control of the energy storage element while achieving the long-term optimization goal.

[0104] In one embodiment of this application, the method for determining the theoretical range of charging and discharging power includes:

[0105] Get the initial value range;

[0106] The first adjustment factor is determined based on the temperature of the energy storage element;

[0107] The second adjustment factor is determined based on the remaining lifetime of the energy storage element;

[0108] Based on the minimum adjustment coefficient between the first and second adjustment coefficients, the initial value range is adjusted to obtain the theoretical value range of the charging and discharging power.

[0109] In this embodiment, the initial value range determines the initial safety boundary of the charging and discharging power of the energy storage element, and the initial value range can be obtained based on the design parameters of the energy storage element.

[0110] Considering that the temperature of energy storage components affects their charging and discharging performance, taking batteries as an example, overcharging and discharging at high temperatures may lead to thermal runaway and accelerate battery aging, while high-current charging and discharging at low temperatures will reduce capacity utilization and increase internal resistance loss.

[0111] Meanwhile, considering that the remaining lifespan of energy storage components can reflect their state of health (SOH), batteries nearing the end of their lifespan experience increased internal resistance, capacity decay, and reduced ability to withstand high-current charging and discharging, making them prone to failure.

[0112] Therefore, in this embodiment, based on the initial value range, a first adjustment coefficient is determined based on the temperature of the energy storage element, a second adjustment coefficient is determined based on the remaining lifetime of the energy storage element, and then the initial value range is adjusted based on the minimum adjustment coefficient among the first and second adjustment coefficients to obtain the theoretical value range of the charging and discharging power.

[0113] For example, if the initial value range is [-50kW, 50kW] (negative values ​​are for charging and positive values ​​are for discharging), the first adjustment coefficient is determined to be 0.9 based on the temperature of the energy storage element, and the second adjustment coefficient is determined to be 0.7 based on the remaining lifespan of the energy storage element. Then, the initial value range is adjusted based on the second adjustment coefficient to obtain the theoretical value range of charging and discharging power as [-35kW, 35kW].

[0114] Specifically, the first adjustment coefficient can be determined using the following formula:

[0115] ;

[0116] in, This represents the first adjustment factor. This indicates the current temperature of the energy storage element. A reference value representing temperature. Indicates the lower limit of temperature. Indicates the upper limit of temperature. and All of these represent preset scaling factors.

[0117] Meanwhile, the second adjustment coefficient can be determined using the following second formula:

[0118] ;

[0119] in, This represents the second adjustment factor. Indicates the remaining lifespan of the energy storage element. A reference value indicating remaining lifespan. This indicates the preset scaling factor.

[0120] As can be seen from the above, this embodiment dynamically adjusts the theoretical range of charging and discharging power based on the actual performance of the energy storage element, further improving the coordinated operation effect of the power grid and the energy storage system.

[0121] Corresponding to the intelligent control method for the distribution cabinet in the above embodiment, Figure 3 This is a structural block diagram of an intelligent control system for a power distribution cabinet according to an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 3 The intelligent control system 20 for the distribution cabinet is installed in the distribution cabinet 112, which is contained in the energy storage system 110. The energy storage system 110 also includes energy storage elements 111, which are connected in parallel with the power grid 120 through the distribution cabinet 112. The intelligent control system 20 for the distribution cabinet includes: a power grid load prediction module 21, a charging and discharging power determination module 22, and a control module 23.

[0122] Among them, the power grid load forecasting module 21 is used to determine the power grid load forecast value for future periods based on the historical load data of the power grid; the power grid load forecast value for future periods includes N load forecast values ​​for the power grid in the next N periods;

[0123] The charging and discharging power determination module 22 is used to determine the target charging and discharging power of the energy storage element based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element.

[0124] Control module 23 is used to control the energy storage element to charge or discharge the grid according to the target charging and discharging power based on the target charging and discharging power.

[0125] In one embodiment of this application, the charge / discharge power determination module 22 is specifically used for:

[0126] The load forecast of the power grid in the future period and the current remaining power of the energy storage device are input into the reinforcement learning network to obtain the target charging and discharging power of the energy storage device.

[0127] The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes the candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods.

[0128] The calculation process of the reward function in a reinforcement learning network includes:

[0129] The load fluctuation value of the power grid is determined based on N load forecast values ​​for the power grid in the next N time periods;

[0130] Based on the candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods and the current remaining power of the energy storage element, determine the N predicted values ​​of the remaining power of the energy storage element in the next N time periods.

[0131] The state of charge (SOC) assessment value of the energy storage element is determined based on the N predicted remaining energy values ​​of the energy storage element in the next N time periods.

[0132] The reward function of the reinforcement learning network is calculated based on the grid load fluctuation value and the state of charge assessment value of the energy storage element.

[0133] In one embodiment of this application, the charge / discharge power determination module 22 is further configured to:

[0134] Obtain the target load curves of the power grid for the next N time periods;

[0135] Based on the N load forecasts for the power grid over the next N time periods and the candidate charging and discharging power values ​​of the energy storage components in each of the next N time periods, the N net load forecasts for the power grid over the next N time periods are determined; where the net load forecast is the power grid's own load forecast.

[0136] The power grid load fluctuation value is obtained by comparing the N net load forecasts for the power grid in the next N periods with the target load curve for the power grid in the next N periods.

[0137] In one embodiment of this application, the charge / discharge power determination module 22 is further configured to:

[0138] Obtain the charging and discharging safety thresholds of energy storage components;

[0139] The predicted remaining power of the energy storage element in the next N time periods is compared with the charging and discharging safety threshold to determine the charging and discharging risk assessment value of the energy storage element in the next N time periods.

[0140] Based on the N predicted remaining power values ​​of the energy storage element in the next N time periods, the rate of change of remaining power between two adjacent time periods is determined, resulting in N-1 remaining power change rates. Based on the N-1 remaining power change rates, the fluctuation value of the remaining power is determined.

[0141] The state of charge (SOC) assessment value of the energy storage element is obtained by weighting and summing the charge and discharge risk assessment values ​​and the fluctuation values ​​of the remaining power of the energy storage element over the next N time periods.

[0142] In one embodiment of this application, the charge / discharge power determination module 22 is further configured to:

[0143] The first weight of the grid load fluctuation value is determined based on the proportion of renewable energy generation in the grid; wherein, the first weight corresponding to the proportion of renewable energy generation in the grid being greater than the first threshold is greater than the first weight corresponding to the proportion of renewable energy generation in the grid being less than or equal to the first threshold.

[0144] The second weight is used to determine the state-of-charge assessment value of the energy storage element based on the first weight;

[0145] The first summation result is obtained by weighting and summing the grid load fluctuation value and the state of charge assessment value of the energy storage element based on the first weight and the second weight.

[0146] The reciprocal of the first summation result is used as the reward function for the reinforcement learning network.

[0147] In one embodiment of this application, the charge / discharge power determination module 22 is further configured to:

[0148] The load forecast of the power grid in the future period and the current remaining power of the energy storage device are input into the reinforcement learning network to obtain the target action;

[0149] The target charging and discharging power candidate value of the target time period is determined from the N charging and discharging power candidate values ​​included in the target action. The target time period is the time period closest to the current time period among the N time periods.

[0150] In one embodiment of this application, the charge / discharge power determination module 22 is further configured to:

[0151] Get the initial value range;

[0152] The first adjustment factor is determined based on the temperature of the energy storage element;

[0153] The second adjustment factor is determined based on the remaining lifetime of the energy storage element;

[0154] Based on the minimum adjustment coefficient between the first and second adjustment coefficients, the initial value range is adjusted to obtain the theoretical value range of the charging and discharging power.

[0155] In one embodiment of this application, the distribution cabinet 112 may include a controller 300, an energy storage converter, and a protection module, etc. See [link to relevant documentation]. Figure 4 , Figure 4 This is a schematic block diagram of a controller provided in one embodiment of this application. Figure 4 The controller 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of each module / unit in the above-described device embodiments, for example... Figure 3 The functions of the power grid load prediction module 21, the charging and discharging power determination module 22, and the control module 23 are shown.

[0156] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0157] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0158] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store preset data such as initial value ranges and target load curves.

[0159] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation method described in the intelligent control method for power distribution cabinets provided in the embodiments of this application, or they can execute the implementation method of power distribution cabinets described in the embodiments of this application, which will not be repeated here.

[0160] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0161] The computer-readable storage medium can be an internal storage unit of the distribution cabinet in any of the foregoing embodiments, such as a hard drive or memory within the distribution cabinet. The computer-readable storage medium can also be an external storage device of the distribution cabinet, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card mounted on the distribution cabinet. Furthermore, the computer-readable storage medium can include both internal storage units and external storage devices within the distribution cabinet. The computer-readable storage medium is used to store computer programs and other programs and data required by the distribution cabinet. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0162] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0163] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the power distribution cabinet and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0164] In the several embodiments provided in this application, it should be understood that the disclosed power distribution cabinet and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, modules may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0165] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0166] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0167] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for intelligent control of a distribution cabinet, applied to an energy storage system, the energy storage system comprising a distribution cabinet and energy storage elements, the energy storage elements being connected in parallel with the power grid through the distribution cabinet, characterized in that, The method is performed by the power distribution cabinet, and the method includes: The load forecast values ​​for the power grid in future periods are determined based on historical load data of the power grid; the load forecast values ​​for the power grid in future periods include N load forecast values ​​for the power grid in the next N periods; The target charging and discharging power of the energy storage element is determined based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element. Based on the target charging and discharging power, the energy storage element is controlled to charge or discharge the power grid according to the target charging and discharging power; The step of determining the target charging and discharging power of the energy storage element based on the grid load forecast for a future period and the current remaining power of the energy storage element includes: The load forecast of the power grid in the future time period and the current remaining power of the energy storage element are input into the reinforcement learning network to obtain the target action; The target charging and discharging power candidate value of the target time period among the N charging and discharging power candidate values ​​included in the target action is determined as the target charging and discharging power of the energy storage element, and the target time period is the time period closest to the current time period among the N time periods; The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods. The calculation process of the reward function of the reinforcement learning network includes: The load fluctuation value of the power grid is determined based on N load forecast values ​​for the power grid in the next N time periods; Based on the candidate values ​​of the charging and discharging power of the energy storage element in each of the next N time periods and the current remaining power of the energy storage element, N predicted values ​​of the remaining power of the energy storage element in the next N time periods are determined. The state of charge assessment value of the energy storage element is determined based on the N predicted remaining power values ​​of the energy storage element in the next N time periods. The reward function of the reinforcement learning network is calculated based on the power grid load fluctuation value and the state of charge assessment value of the energy storage element; The determination of power grid load fluctuation values ​​based on N load forecasts for the power grid over N future time periods includes: Obtain the target load curves of the power grid for the next N time periods; Based on N load forecasts for the power grid over N time periods and candidate charging and discharging power values ​​for energy storage devices in each of the N time periods, N net load forecasts for the power grid over the N time periods are determined; wherein, the net load forecasts are the power grid's own load forecasts. The power grid load fluctuation value is obtained by comparing the N net load forecast values ​​of the power grid in the next N time periods with the target load curve of the power grid in the next N time periods. Specifically, based on N load forecasts for the power grid over N time periods and candidate charging / discharging power values ​​for energy storage components in each of those N time periods, N net load forecasts for the power grid over the next N time periods are determined, including: If, in the i-th future time period, the candidate value of the charging and discharging power of the energy storage element is greater than zero, it indicates that the energy storage element is discharging to the grid during that time period. In this case, the net load forecast of the grid is equal to the grid load forecast minus the discharge power of the energy storage element. If, in the i-th future time period, the candidate value of the charging and discharging power of the energy storage element is less than zero, it indicates that the grid is charging the energy storage element during that time period. In this case, the net load forecast of the grid is equal to the grid load forecast plus the discharge power of the energy storage element. i is a natural number, and i = 1, ..., N. The method for determining the theoretical range of the charging and discharging power includes: Get the initial value range; A first adjustment coefficient is determined based on the temperature of the energy storage element; The second adjustment factor is determined based on the remaining lifetime of the energy storage element; Based on the minimum adjustment coefficient between the first adjustment coefficient and the second adjustment coefficient, the initial value range is adjusted to obtain the theoretical value range of the charging and discharging power.

2. The intelligent control method for power distribution cabinets as described in claim 1, characterized in that, The determination of the state of charge (SOC) assessment value of the energy storage element based on N predicted remaining energy values ​​of the energy storage element over N future time periods includes: Obtain the charging and discharging safety thresholds of energy storage components; The predicted remaining power of the energy storage element in the next N time periods is compared with the charging and discharging safety threshold to determine the charging and discharging risk assessment value of the energy storage element in the next N time periods. Based on the N predicted remaining power values ​​of the energy storage element in the next N time periods, the rate of change of remaining power between two adjacent time periods is determined, resulting in N-1 remaining power change rates. Based on the N-1 remaining power change rates, the fluctuation value of the remaining power is determined. The state of charge assessment value of the energy storage element is obtained by weighted summing of the charging and discharging risk assessment value of the energy storage element in the next N time periods and the fluctuation value of the remaining power.

3. The intelligent control method for power distribution cabinets as described in claim 1, characterized in that, The calculation of the reward function for the reinforcement learning network based on the grid load fluctuation value and the state of charge assessment value of the energy storage element includes: The first weight of the grid load fluctuation value is determined based on the proportion of renewable energy generation in the grid; wherein, the first weight corresponding to the proportion of renewable energy generation in the grid being greater than a first threshold is greater than the first weight corresponding to the proportion of renewable energy generation in the grid being less than or equal to a first threshold; The second weight is determined based on the first weight to determine the state of charge assessment value of the energy storage element; The power grid load fluctuation value and the state of charge assessment value of the energy storage element are weighted and summed based on the first weight and the second weight to obtain the first summation result; The reciprocal of the first summation result is determined as the reward function of the reinforcement learning network.

4. An intelligent control system for a power distribution cabinet, disposed in a power distribution cabinet, the power distribution cabinet comprising an energy storage system, the energy storage system further comprising energy storage elements, the energy storage elements being connected in parallel with the power grid through the power distribution cabinet, characterized in that, The intelligent control system for the power distribution cabinet includes: The power grid load forecasting module is used to determine the power grid load forecast for future periods based on historical power grid load data; the power grid load forecast for future periods includes N load forecasts for the power grid over N future periods; The charging and discharging power determination module is used to determine the target charging and discharging power of the energy storage element based on the load forecast of the power grid in the future period and the current remaining power of the energy storage element. The control module is used to control the energy storage element to charge or discharge the power grid according to the target charging and discharging power based on the target charging and discharging power; The charge / discharge power determination module is specifically used for: The load forecast of the power grid in the future time period and the current remaining power of the energy storage element are input into the reinforcement learning network to obtain the target action; The target charging and discharging power candidate value of the target time period among the N charging and discharging power candidate values ​​included in the target action is determined as the target charging and discharging power of the energy storage element, and the target time period is the time period closest to the current time period among the N time periods; The action space of the reinforcement learning network is constructed based on the theoretical range of charging and discharging power. Each action in the action space includes candidate values ​​of charging and discharging power of the energy storage element in each of the next N time periods. The calculation process of the reward function of the reinforcement learning network includes: The load fluctuation value of the power grid is determined based on N load forecast values ​​for the power grid in the next N time periods; Based on the candidate values ​​of the charging and discharging power of the energy storage element in each of the next N time periods and the current remaining power of the energy storage element, N predicted values ​​of the remaining power of the energy storage element in the next N time periods are determined. The state of charge assessment value of the energy storage element is determined based on the N predicted remaining power values ​​of the energy storage element in the next N time periods. The reward function of the reinforcement learning network is calculated based on the power grid load fluctuation value and the state of charge assessment value of the energy storage element; When determining the grid load fluctuation value based on N load forecast values ​​for the grid in the next N time periods, the charging and discharging power determination module is also specifically used for: Obtain the target load curves of the power grid for the next N time periods; Based on N load forecasts for the power grid over N time periods and candidate charging and discharging power values ​​for energy storage devices in each of the N time periods, N net load forecasts for the power grid over the N time periods are determined; wherein, the net load forecasts are the power grid's own load forecasts. The power grid load fluctuation value is obtained by comparing the N net load forecast values ​​of the power grid in the next N time periods with the target load curve of the power grid in the next N time periods. Specifically, based on N load forecasts for the power grid over N time periods and candidate charging / discharging power values ​​for energy storage components in each of those N time periods, N net load forecasts for the power grid over the next N time periods are determined, including: If, in the i-th future time period, the candidate value of the charging and discharging power of the energy storage element is greater than zero, it indicates that the energy storage element is discharging to the grid during that time period. In this case, the net load forecast of the grid is equal to the grid load forecast minus the discharge power of the energy storage element. If, in the i-th future time period, the candidate value of the charging and discharging power of the energy storage element is less than zero, it indicates that the grid is charging the energy storage element during that time period. In this case, the net load forecast of the grid is equal to the grid load forecast plus the discharge power of the energy storage element. i is a natural number, and i = 1, ..., N. The method for determining the theoretical range of the charging and discharging power includes: Get the initial value range; A first adjustment coefficient is determined based on the temperature of the energy storage element; The second adjustment factor is determined based on the remaining lifetime of the energy storage element; Based on the minimum adjustment coefficient between the first adjustment coefficient and the second adjustment coefficient, the initial value range is adjusted to obtain the theoretical value range of the charging and discharging power.

5. A power distribution cabinet, comprising a controller, the controller including a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 3.

Images