Target control method and device, electronic equipment, storage medium and program product

Abstract

The invention provides a target control method and device, electronic equipment, a storage medium and a program product, and the method comprises the steps: predicting the load condition of an energy storage unit through employing historical data in advance, and determining a target time period in which the future load is likely to be higher based on a prediction result; relevant characteristic data of the energy storage unit in the target time period can be obtained, data matching is carried out on one side of the temperature control assembly according to the characteristic data, the use condition of the temperature control assembly when the working condition is approximate is determined, and an advanced starting control strategy of the temperature control assembly for the target time period is formed on the basis of the use condition. In this way, the temperature control assembly can be started in advance before the high-load operation of the energy storage unit, the temperature attribute of the energy storage unit is controlled in advance, and the control strength can be gradually improved by gradually improving the power, so that the problems of load impact, too high energy consumption and the like are solved, the service life of the temperature control assembly is prolonged, and the service life of the energy storage unit is prolonged. And the overall use cost is reduced.

Description

Technical Field

[0001] This disclosure relates to the field of machine control technology, and in particular to a target control method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In energy storage systems in related fields, the control of cooling units mainly relies on real-time feedback. For example, in liquid cooling schemes, the operating status of the cooling unit is dynamically adjusted by detecting the inlet temperature of the coolant or the current operating condition of the energy storage unit (such as a battery pack).

[0003] It can be seen that this type of approach is a passive response method, relying on real-time data, resulting in a certain lag in the response. This delayed response places higher demands on the cooling unit, leading not only to excessive energy consumption but also to frequent load shocks, reducing equipment lifespan and increasing overall costs.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] In view of this, the present disclosure proposes a target control method, apparatus, electronic device, storage medium, and program product to solve or partially solve the above-mentioned problems.

[0006] Based on the above objectives, in a first aspect, this disclosure provides a target control method, which is applied to a system composed of a temperature control component and an energy storage unit, wherein the temperature control component is used to adjust the temperature properties of the energy storage unit, and the method includes: Based on the historical data of the energy storage unit, load forecasting is performed for future working periods to obtain target periods. The target periods are determined by dividing the future working periods according to the load forecast results. Based on the characteristic data of the target time period, data matching is performed in the database of the temperature control component to determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained by the load prediction. A control strategy is determined based on the matching result, and the control strategy is used to control the temperature control component to start in advance before the target time period.

[0007] Based on the same concept, in a second aspect, this disclosure also provides a target control device, which is applied to a system composed of a temperature control component and an energy storage unit, wherein the temperature control component is used to adjust the temperature properties of the energy storage unit, and the device includes: The first module is used to perform load forecasting for future working periods based on historical data of the energy storage unit to obtain a target period, wherein the target period is a time period determined by dividing the future working periods based on the load forecasting results. The second module is used to perform data matching in the database of the temperature control component based on the characteristic data of the target time period, and determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained by the load prediction. The third module is used to determine a control strategy based on the matching result. The control strategy is used to control the temperature control component to start in advance before the target time period.

[0008] Based on the same concept, in a third aspect, this disclosure also provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0009] Based on the same concept, in a fourth aspect, this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method described in the first aspect above.

[0010] Based on the same concept, in a fifth aspect, this disclosure also provides a computer program product, including computer program instructions that, when run on a computer, cause the computer to perform the method described in the first aspect above.

[0011] As described above, this disclosure provides a target control method, device, electronic device, storage medium, and program product. This disclosure predicts the load of the energy storage unit using historical data in advance, determines the target period where the future load may be high based on the prediction results, and then obtains relevant characteristic data of the energy storage unit during the target period. Based on this characteristic data, data matching is performed on the temperature control component to determine the usage of the temperature control component under similar operating conditions. Based on this usage, an early start control strategy for the temperature control component during the target period is formed. This method allows the temperature control component to start before the energy storage unit operates under high load, pre-controlling the temperature attributes of the energy storage unit. Furthermore, by gradually increasing power, the control intensity can be gradually increased, thereby reducing load impact and excessive energy consumption caused by direct high-power start-up. It also reduces the start-up frequency of the temperature control component to a certain extent, thus extending its service life and improving the performance of the energy storage unit. Ultimately, this reduces overall operating costs and improves overall performance. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A flowchart illustrating an exemplary method provided in an embodiment of this disclosure.

[0014] Figure 2 This is a schematic diagram illustrating the overall process of the exemplary method provided in this disclosure in a specific application scenario.

[0015] Figure 3 This is a schematic diagram illustrating the judgment process during the specific execution of the exemplary method provided in the embodiments of this disclosure.

[0016] Figure 4 A schematic diagram of the structure of an exemplary device provided in an embodiment of this disclosure.

[0017] Figure 5 This is a schematic diagram of the electronic device structure provided in an embodiment of this disclosure. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this specification clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this disclosure should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in the embodiments of this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element, object, or method step preceding the term covers the element, object, or method step listed after the term and its equivalents, but does not exclude other elements, objects, or method steps. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] As described in the background section, cooling units in related technologies typically determine their cooling strategy by acquiring real-time data on the temperature and other attributes of the energy storage system. This method, requiring measurement before strategy determination and only then activating the cooling unit, inevitably introduces a certain lag. Since the temperature and other attributes of the energy storage system are constantly changing, the temperature may continue to rise after reaching a threshold, and cooling also requires a certain process. Consequently, the cooling unit may need higher power to quickly stabilize the temperature and other attributes below the threshold. This results in higher energy consumption for the cooling unit during actual operation, and excessive power demand leads to significant load impacts, limiting equipment lifespan and reducing overall service life. It also negatively impacts the energy storage system.

[0021] In specific application scenarios, by utilizing the solutions described in the above embodiments, the power curve of the cooling unit is effectively smoothed, avoiding energy consumption peaks and reducing overall energy consumption. The frequency of equipment start-ups and shutdowns is significantly reduced, load impacts are decreased, and mechanical and thermal stress wear is correspondingly reduced, extending equipment lifespan. Based on adaptive and hybrid control mechanisms, the system possesses stronger adaptability and stability for multiple scenarios and long-term evolving conditions.

[0022] It should be noted that the energy storage system in the relevant technology can use liquid cooling or gas cooling methods to cool the energy storage device. For example, pure water, deionized water, water-based solutions, fluorinated liquids, mineral oil, etc., can be used for liquid cooling, and air, nitrogen, carbon dioxide, helium, etc., can be used for gas cooling. In this embodiment and subsequent application scenarios, only a water-cooled chiller unit with liquid water cooling will be used as an example for illustration. Similarly, the energy storage system can also include mechanical energy storage, chemical energy storage, electromagnetic energy storage, and other energy storage application scenarios. Here, only a battery pack energy storage system in chemical energy storage will be used as an example for illustration.

[0023] In light of the above-mentioned practical situation, this disclosure provides a target control method. This disclosure pre-predicts the load conditions of the energy storage unit using historical data, determines the target period when the future load is likely to be high based on the prediction results, and then obtains relevant characteristic data of the energy storage unit during the target period. Based on this characteristic data, data matching is performed on the temperature control component to determine the usage of the temperature control component under similar operating conditions. Based on this usage, an early start control strategy for the temperature control component during the target period is formed. This method allows the temperature control component to start before the energy storage unit operates under high load, pre-controlling the temperature attributes of the energy storage unit. Furthermore, by gradually increasing power, the control intensity can be gradually increased, thereby reducing load impact and excessive energy consumption caused by direct high-power start-up. It also reduces the start-up frequency of the temperature control component to a certain extent, thus extending its service life and improving the overall performance of the energy storage unit. Ultimately, this reduces overall operating costs and improves overall efficiency.

[0024] Figure 1 A flowchart illustrating an exemplary method provided by an embodiment of this disclosure is shown.

[0025] like Figure 1 As shown in the embodiments of this disclosure, an exemplary target control method is proposed. Applied to a temperature control system composed of a temperature control component and an energy storage unit, the temperature control component is used to adjust the temperature attributes of the energy storage unit. The energy storage unit can be a battery pack in the aforementioned energy storage system, and the temperature control component can be a water-cooled unit. The temperature attribute is the temperature reached by the energy storage unit, which can be a predicted result or an actual result. The temperature control component can determine its control strategy based on this temperature attribute to ensure that the energy storage unit can operate sustainably and stably under appropriate temperature conditions. Specifically, this method may include the following steps.

[0026] Step 102: Based on the historical data of the energy storage unit, perform load forecasting for the future working period to obtain the target period, wherein the target period is a time period determined by dividing the future working period according to the load forecasting results.

[0027] In this step, historical data can be data generated during the operation of the energy storage unit. In specific scenarios, various distributed sensors can be installed on the battery pack system and water-cooled unit to collect data such as ambient temperature, water-cooled unit power, and battery pack operating status (SOC, power, internal temperature) in real time at a set frequency (e.g., a sampling frequency of no less than once per minute), and these data can be timestamped. This data can be stored in a corresponding database to provide a data foundation for querying and training. Here, we first utilize historical data related to the energy storage unit. This historical data can record the usage data of the energy storage unit within a certain period of time (e.g., within a week), specifically load data. Then, using a pre-trained prediction model, we can predict the load of the energy storage unit within a certain period of time in the future (future operating time) based on this data, such as predicting the load of the energy storage unit within the next 24 hours.

[0028] Then, based on the load prediction result, the target time period that may require control by the temperature control component can be determined. For example, a certain threshold can be set, and then the future operating time period of the temperature control component can be divided according to the load prediction result. This divides the time period that requires targeted control by the temperature control component and the time period that does not require control or only requires low-power operation. The time period that requires targeted control can then be set as the target time period. In other words, the solution in this embodiment can operate all time, and only target the temperature control component when the target time period is reached or about to be reached; or it can only activate the solution of this embodiment to control the temperature control component when the target time period is reached or about to be reached.

[0029] In specific application scenarios, before performing load forecasting, historical data related to the energy storage unit can be acquired. This historical data can include at least one of the following: load data of the energy storage unit, ambient temperature of the energy storage unit, temperature data of the energy storage unit, and temperature change data of the energy storage unit, etc., which can reflect the specific operating conditions of the energy storage unit in historical scenarios. This data can be acquired by retrieving it from the aforementioned database of stored sensor data, or by retrieving it from a network, etc.

[0030] In some embodiments, a pre-trained deep learning model, such as a Long Short-Term Memory (LSTM) network model, can be used to predict the load of energy storage units. By analyzing the periodic patterns and trends of the input historical data, the load situation (i.e., the load state prediction result) for the future working period can be output. By analyzing the load state prediction result, the load time period that needs to be focused on can be obtained and then set as the target time period. The time period can be divided according to the needs of the specific scenario. For example, the time can be divided into half-hour or one-hour periods to generate time periods, and then the load state within each time period can be determined. Alternatively, the predicted load state within a period of time can be divided according to the set threshold, and the time period that meets the load state requirements can be selected. Then, the focus can be distinguished between the parts that need to be focused on and the parts that do not need to be focused on, or different load levels can be set. For example, the load can be divided into high, medium, and low load levels according to the set threshold. The time period corresponding to the high load level is the high priority time period, and the high priority time period can be used as the target time period. That is, in some embodiments, the step of predicting the load for future working periods based on the historical data of the energy storage unit to obtain the target period includes: analyzing the historical data of the energy storage unit through a deep learning prediction model to generate a load status prediction result of the energy storage unit in the future working period; classifying the future working period into load levels based on the load status prediction result, and determining the time period with the high priority load level in the future working period as the target period.

[0031] In other embodiments, taking high, medium and low load levels as an example, in addition to the high priority time period, the medium priority time period and the low priority time period can also be determined accordingly. Then, based on the usage of the temperature control component, it can be determined whether the medium priority time period and / or the low priority time period should also be determined as the target time period. Of course, their priorities are also retained accordingly. Then, it is determined which (part or all) of the target time periods to process are determined according to the priority order.

[0032] Subsequently, during the load state prediction process using the predictive model, for any given time period (candidate period), multiple prediction results may be output. These prediction results can be referred to as candidate load states, and each candidate load state may have a corresponding confidence level. In one embodiment, the candidate load state with the highest confidence level can be selected as the final output load state for that candidate period. In other embodiments, a confidence threshold can be set, and all schemes exceeding the threshold can be output as results. A final scheme can then be formed by merging intermediate values, or each scheme can be considered directly, taking into account different prediction scenarios when generating the control strategy. That is, in some embodiments, the step of analyzing the historical data of the energy storage unit using a deep learning prediction model to generate a load state prediction result of the energy storage unit in the future working time period includes: using the prediction model to output at least one candidate load state of the energy storage unit in a candidate time period, and labeling the confidence level of the at least one candidate load state, wherein the candidate time period is any time period within the future working time period; and determining the one with the highest confidence level among the at least one candidate load state as the load state of the energy storage unit in the candidate time period.

[0033] Furthermore, in some embodiments, to distinguish different load conditions, multiple load states can be set, such as the aforementioned high, medium, and low load states. These can be divided by setting different thresholds. Different load states generally correspond to different time periods. At this time, the processing priority of these time periods can be divided according to the different load state levels. Then, it can be determined whether to process the medium and low priority time periods based on the specific capabilities of the temperature control component. For example, in some scenarios, in order to control the start frequency of the temperature control component and protect its lifespan, the number of start times and intervals of the temperature control component can be limited. In this scenario, the high priority time periods can be prioritized as target time periods, and these time periods must be operated. Then, it is determined whether the low priority (medium and low load states) time periods need to be controlled. If the entire load can be handled, then all time periods are used as target time periods. If only a portion can be handled, then the selected time periods are used as target time periods according to priority.

[0034] Step 104: Perform data matching in the database of the temperature control component based on the characteristic data of the target time period, and determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained by the load prediction.

[0035] In this step, after determining a target time period, characteristic data related to the temperature control component and / or energy storage unit for that target time period is predicted based on historical data and prediction results. This characteristic data can be the operating condition data of the temperature control component and / or energy storage unit, specifically including the ambient temperature during the target time period, the specific load data of the energy storage unit, the temperature data of the energy storage unit and its temperature change data due to the load, the start-up time period of the temperature control component, the power data reached by the temperature control component, and the power change data, etc. That is, the operating condition data can include at least one of the following: the load data of the energy storage unit, the temperature data of the energy storage unit, the temperature change data of the energy storage unit, the start-up time period of the temperature control component, the power data of the temperature control component, the power change data of the temperature control component, and the ambient temperature of the energy storage unit. Then, using this characteristic data, data matching can be performed in the historical database of the temperature control component to select historical data with similar conditions. This historical data also records the processing methods and results at that time, which facilitates the generation of subsequent control strategies. Finally, these historical data with similar conditions obtained through matching can be considered the matching results.

[0036] In some embodiments, data matching can be performed using the principle of vector similarity, such as cosine similarity, Euclidean distance, and Manhattan distance. However, considering computational efficiency and convergence speed, a K-means clustering algorithm can be further selected to perform cluster analysis on the feature data in the temperature control component database to locate similar historical operating conditions. Specifically, one or a set number of historical time periods can be selected from the database whose feature data (historical data) is closest to the feature data of the target time period, and this or these historical time periods and their corresponding operating data are used as the output matching result. That is, in some embodiments, the step of performing data matching on the feature data of the target time period in the temperature control component database to determine the matching result includes: using a clustering algorithm to determine the matching result in the temperature control component database based on the feature data of the target time period, wherein the matching result is the historical time period whose feature data is closest to the feature data of the target time period and the corresponding operating data of that historical time period.

[0037] Step 106: Determine a control strategy based on the matching result. The control strategy is used to control the temperature control component to start in advance before the target time period.

[0038] In this step, the matching result can be the most similar data in the database as the unique matching result, or multiple data can be selected as a matching result set. Then, the various processing methods in the matching result set are comprehensively considered to obtain the final control strategy. For example, multiple matching results may involve multiple start times. These matching results can be comprehensively considered by taking the average or other methods to form a control strategy.

[0039] This example illustrates the process of obtaining a matching result. Once the matching result is obtained, the database typically records the corresponding execution details, allowing us to obtain historical execution data such as the start-up time, start-up power, execution deviation, and final adjustment of the temperature control component. In some embodiments, since the matching result closely resembles the predicted target time period, historical control strategies can be directly used to control the temperature control component. This involves starting the component at the same power and lead time, and using the same power curve to control it.

[0040] It should be noted that the control strategy in this solution can be used for pre-starting the temperature control component. Pre-starting can be either early start or synchronous start. For example, if the predicted target time period is 10:00 AM, the temperature control component will start at 9:30 AM (startup time) with a certain power (startup power). In other embodiments, if the load on the energy storage unit is not too high during the target time period, the control strategy can also control the temperature control component to start simultaneously when the target time period arrives, achieving synchronous feedback and preventing the aforementioned problems caused by delayed feedback. Here, we will only use the early start scenario as an example. In the early start scenario, since the energy storage unit has not yet reached the predicted high load time point at startup, the power of the temperature control component can be gradually increased through a relatively smooth control method. Finally, when the energy storage unit reaches high load, the temperature control component also reaches the specified power, thereby preventing load shock and excessive energy consumption caused by sudden high load startup of the temperature control component.

[0041] In some embodiments, to further optimize the generation process of the control strategy, this mainly focuses on the start-up time and start-up frequency of the temperature control component in the control strategy. As mentioned above, historical data can be used to determine the historical execution results of the temperature control component within a historical time period, and corresponding control data (such as the historical start-up time and start-up power of the temperature control component) can also be obtained. Therefore, the corresponding matching results can include the above execution results and control data. The historical execution results can then be analyzed. If the analysis results meet expectations, the corresponding control data can be directly used to form a control strategy. For example, using the same lead time and the same start-up power. If the results do not meet expectations, fine-tuning can be made based on the historical control data to form a control strategy. For example, based on historical execution data, if the temperature (set attribute) deviation of the battery pack (energy storage unit) after final execution is within a certain range (e.g., deviation less than 2°C), the historical control strategy can be directly applied. If the deviation exceeds this range, the historical control strategy can be fine-tuned, such as advancing the start-up time by a certain amount (set range), increasing the start-up power by a certain amount (set range), or increasing the power increase by a certain amount (set range) (curve slope), etc. The specific amount of increase can be determined based on the magnitude of the deviation. That is, in some embodiments, the matching result includes the control data and execution results of the temperature control component within a historical time period; determining the control strategy based on the matching result includes: generating the control strategy based on the control data corresponding to the matching result when the execution result meets the set expectations; and adjusting the control data corresponding to the matching result by a set range when the execution result does not meet the set expectations to generate the control strategy. The control strategy includes at least the start-up time and start-up power of the temperature control component. The execution result here is the aforementioned historical execution result. The set expectation can be understood as the deviation being within a certain range to meet the set expectation, and exceeding the aforementioned deviation being outside the certain range to fail to meet the set expectation.

[0042] In some embodiments, the matching results can be used to determine the start-up time and start-up power of the temperature control component when dealing with similar operating conditions in the past, and the start-up time and start-up power required for this execution can be determined according to the foregoing embodiments. Simultaneously, based on the aforementioned load prediction, the predicted load of the energy storage unit during the target period can be determined (i.e., the load value of the target load that the energy storage unit is expected to reach during the target period), which can be used to calculate and determine the target power required by the temperature control component. Furthermore, by combining the current start-up time, start-up power, target power of the temperature control component, and the start time of the target period (equivalent to the target time point for reaching the target power), a power control curve for controlling the temperature control component can be derived, and this forms the final control strategy. The start-up time and start-up power can be used as the starting point, and the target power and target time point as the ending point to form this power control curve. That is, in some embodiments, determining the control strategy based on the matching result includes: determining the target power of the temperature control component based on the target load of the energy storage unit, wherein the target load is the load value that the energy storage unit is expected to reach during the target time period as determined by the load prediction; determining the start-up time and start-up power of the temperature control component based on the matching result; and determining the power change curve of the temperature control component based on the target power, the start-up time, the start-up power, and the start time of the target time period, thereby generating the control strategy.

[0043] Furthermore, to make the power control curve relatively smooth and further protect the temperature control component, an S-curve interpolation calculation can be used to generate a power change trajectory from the start-up time to the target time, i.e., the corresponding power control curve. Of course, in specific scenarios, the water-cooled unit, as the temperature control component, is itself used to control the battery pack temperature. Therefore, the corresponding temperature change curve can be obtained first through S-curve interpolation calculation, and then directly converted into the power change curve of the water-cooled unit. Additionally, to control the rate of change of temperature or power, i.e., the slope of the control curve, a threshold can be set for the rate of change (slope), which can be set to not exceed this threshold. Alternatively, a rated value for the rate of change (slope) can be specified, and the actual rate of change (slope) must be within the threshold range of the rated value (e.g., not exceeding 5% of the rated value or not exceeding the rated value). That is, in some embodiments, determining the power change curve of the temperature control component includes: generating the power change curve through an interpolation algorithm and controlling the amplitude of the power change curve by setting a threshold.

[0044] In some embodiments, after the control strategy is determined, the temperature control component executes it accordingly. Since the control strategy is preset through prediction, it can be called a feedforward control strategy. Subsequently, to further achieve the control objective and prevent control accidents caused by control deviations, feedback (PID) control logic can be executed simultaneously during execution. Here, feedback (PID) control is a conventional passive response control logic that generates a corresponding control strategy for the temperature control component based on real-time measured temperature attributes. This generated control strategy can be called a feedback strategy. Although it has a lag problem, it can supplement or remedy the current scheme when encountering situations such as excessive deviations, ensuring the safety of the energy storage unit.

[0045] Specifically, in combination Figure 3 As shown, the temperature attributes of the energy storage unit can be monitored in real time. After the temperature control component reaches the start-up time point according to the control strategy, it can monitor the changes in the temperature attributes of the energy storage unit in real time, determine whether there is a deviation between the current actual temperature and the expected temperature at the current time point in the control strategy, and determine the magnitude of this deviation as the temperature deviation. For example, according to the control strategy, the current expected temperature should be 25℃, but the current actual temperature is 26℃, then the temperature deviation is... The expected temperature is 1℃. This is the temperature that the energy storage unit should reach at the current point in time, according to the control strategy.

[0046] Next, a threshold range (i.e., a set range) can be set. This range can be specifically set according to the specific scenario. For example, it can be set to... When temperature deviation If the deviation is less than this range, it means that the deviation is within a reasonable range and the temperature control component can be controlled completely according to the control strategy (i.e., the feedforward control strategy is executed).

[0047] And when temperature deviation If the value falls within this range, it indicates a certain degree of deviation, requiring adjustment of the current control strategy. In this case, the control strategy can be adjusted based on the aforementioned feedback strategy. Specifically, this can be achieved by mixing the specific control parameters of both strategies (i.e., executing a hybrid control strategy). For example, the current power determined by the control strategy and the current power obtained from the feedback strategy can be mixed to obtain the final power, which is then used to control the temperature control component. The specific mixing method can be based on a set ratio, either by creating a mixing ratio lookup table based on the degree of deviation and determining the mixing ratio by referring to the table, or by calculating the set ratio based on a linear or nonlinear S-curve.

[0048] Finally, if there is a temperature deviation It is directly greater than the set range, that is If the value exceeds the maximum value of the threshold range, it indicates a serious deviation problem requiring immediate correction. In this case, a feedback strategy can be used to directly replace the control strategy to control the temperature control component (i.e., execute the feedback control strategy), and the corresponding abnormal data is recorded to facilitate subsequent error correction and adaptive optimization. Specifically, in some embodiments, after determining the control strategy based on the matching result, the method further includes: determining the temperature difference between the actual temperature and the expected temperature of the energy storage unit; if the temperature difference falls within a set range, mixing the control strategy and the feedback strategy according to a set ratio, and using the mixed strategy to control the temperature control component; if the temperature difference exceeds the set range, using the feedback strategy to control the temperature control component; wherein, the feedback strategy is a strategy for controlling the temperature control component determined based on the temperature difference.

[0049] Then regarding attribute deviation In scenarios falling within a set range, more specifically, the mixing ratio can be determined through a set control function, and then the control strategy and relevant parameters in the feedback strategy (such as the current output power of the temperature control component) can be mixed according to the set ratio.

[0050] The specific control function can be...

[0051] in, This indicates a set ratio. You can then specify that a smaller set ratio indicates a stronger control strategy and a larger set ratio indicates a stronger feedback strategy; alternatively, you can specify that a larger set ratio indicates a stronger control strategy and a smaller set ratio indicates a stronger feedback strategy. Taking power as an example, you can... This is used to obtain the final power value after mixing. This indicates the set adjustment weight, and the specific values ​​can be: , When the mixing ratio approaches 0, the mixing ratio is closer to 0. The mixing ratio is close to linear. The mixing ratio approaches 1. This indicates the degree of deviation in the input temperature range. , Indicates temperature deviation. and These represent the minimum and maximum values ​​of a specified interval, respectively. For example, in the scenario described above, the specified interval would be... , That is, in some embodiments, the step of mixing the control strategy and the feedback strategy according to a set ratio when the temperature difference falls within a set range includes: mixing the current output power of the temperature control component in the control strategy and the feedback strategy according to the set ratio when the temperature difference falls within the set range; the set ratio includes: ;in, This indicates the set ratio. This indicates the set adjustment weight. This indicates the degree of deviation of the input temperature difference. , This indicates the temperature difference value. and These represent the minimum and maximum values ​​of the defined interval, respectively.

[0052] In some embodiments, an adaptive optimization strategy can be employed to optimize the system in real time, enabling immediate updates and adjustments to relevant parameters. For example, the parameters of the current system model can be fine-tuned based on the deviation between each prediction result and the actual control result (such as the model's learning rate, network weight decay coefficient, confidence interval range, power change curve slope, and the shape of the mixture curve function). Furthermore, if the deviation exceeds expectations (e.g., the severity of the deviation exceeds expectations, the frequency of deviation exceeds expectations, etc.), the current system can be retrained using data from a certain time period. That is, in some embodiments, after determining the control strategy based on the matching result, the method further includes: obtaining the actual control result corresponding to the control strategy; and correcting the generation process of the control strategy based on the actual control result.

[0053] Subsequently, in some specific application scenarios, since the cost of using temperature control components varies at different times (such as peak electricity price and off-peak electricity price), from an economic perspective, when carrying out specific control, it is possible to first determine whether the target time period is within the set time period (such as within the peak electricity price period). If it is, the maximum power of the temperature control component can be limited to optimize economic efficiency.

[0054] Subsequently, in some other embodiments, the execution entity of this solution can be set separately from the temperature control component and the energy storage unit. For example, the execution entity of this solution can be set in the cloud, while the temperature control component and the energy storage unit can be set locally. This achieves architecture optimization, leverages the computing advantages of the cloud to quickly determine the solution, and then uses the local edge controller to receive data and implement execution.

[0055] In more specific application scenarios, combined with Figure 2 and Figure 3The following provides an exemplary description of this solution embodiment in a specific scenario. The overall process is as follows: Figure 2 As shown, the specific judgment process during execution is as follows: Figure 3 As shown. First, in the system consisting of the battery energy storage system (energy storage unit) and the water-cooled chiller (temperature control component), a sensor network can be used to collect system temperature, power, and environmental parameters sequentially at a 1-minute sampling period and store them in a database, while also adding timestamps, thus collecting operational data. Next, for the data mining and strategy generation stage, the operational data of the past 24 hours can be analyzed daily. An LSTM network can be used to predict the battery load (load) range for the next 24 hours, performing load range prediction. For the predicted high load range, the K-Means clustering algorithm is applied to locate similar historical operating conditions and intelligently calculate the chiller's early start point, predicting the water-cooled chiller's start-up time. Then, for each load range, a temperature target curve can be generated based on an S-shaped function, limiting the heating and cooling rate (e.g., not exceeding 0.3°C / minute). The power change curve of the water-cooled chiller can then be generated based on the temperature target curve to control the real-time power of the water-cooled chiller, thereby generating a control strategy. Subsequently, during the execution phase, the aforementioned scheme (i.e., the feedforward control scheme based on the aforementioned control strategy) and the feedback scheme in related technologies can be executed in real-time parallel, i.e., multiple strategies can be executed in parallel. The specific execution method can be the same as or similar to the execution process of using a set interval for strategy selection in the aforementioned embodiments, and will not be elaborated here. Finally, after the execution is completed, model adaptive optimization can be performed: the prediction accuracy is evaluated periodically, and the parameters are automatically tuned when the deviation exceeds 5%; if the deviation exceeds the limit for two consecutive months, the system recalls the data of the most recent three months for retraining; effective configurations are synchronously added to the strategy library during hybrid control.

[0056] As can be seen from the above embodiments, this disclosure provides a target control method applied to a system composed of a temperature control component and an energy storage unit. The temperature control component is used to adjust the temperature attributes of the energy storage unit. The method includes: predicting the load of a future working period based on historical data of the energy storage unit to obtain a target period, wherein the target period is a time period determined by dividing the future working period based on the load prediction result; performing data matching in the database of the temperature control component based on the characteristic data of the target period to determine a matching result, wherein the characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target period obtained by the load prediction; and determining a control strategy based on the matching result, wherein the control strategy is used to control the temperature control component to start in advance before the target period. This disclosure predicts the load of the energy storage unit in advance using historical data, determines the target period where the future load may be high based on the prediction result, and then obtains the relevant characteristic data of the energy storage unit in the target period. Based on these characteristic data, data matching is performed on the temperature control component side to determine the usage of the temperature control component when the operating conditions are similar, and a control strategy for the early start of the temperature control component for the target period is formed based on the usage. This method allows the temperature control component to start in advance before the energy storage unit operates under high load, pre-controlling the temperature attributes of the energy storage unit. Furthermore, by gradually increasing the power, the control intensity can be gradually improved, thereby reducing load impact and excessive energy consumption caused by direct high-power startup. It can also reduce the startup frequency of the temperature control component to a certain extent, thus extending its service life and improving the performance of the energy storage unit. Ultimately, this reduces overall operating costs and improves overall performance.

[0057] It should be noted that the method of this disclosure embodiment can be executed by a single device, such as a computer or server. The method of this disclosure embodiment can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this disclosure embodiment, and the multiple devices will interact with each other to complete the method described.

[0058] It should be noted that the above description describes specific embodiments of this disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] Based on the same concept, corresponding to any of the above embodiments, this disclosure also provides a target control device, which is applied to a system composed of a temperature control component and an energy storage unit, wherein the temperature control component is used to adjust the temperature properties of the energy storage unit.

[0060] refer to Figure 4 The target control device includes: The first module 410 is used to perform load prediction for future working time periods based on the historical data of the energy storage unit to obtain a target time period, wherein the target time period is a time period determined by dividing the future working time period based on the load prediction results.

[0061] The second module 420 is used to perform data matching in the database of the temperature control component based on the characteristic data of the target time period, and determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained by the load prediction.

[0062] The third module 430 is used to determine a control strategy based on the matching result. The control strategy is used to control the temperature control component to start in advance before the target time period.

[0063] In some exemplary embodiments, the first module 410 is further configured to: The historical data of the energy storage unit is analyzed by a deep learning prediction model to generate a load state prediction result of the energy storage unit in the future working period. Based on the load status prediction results, the future working time period is divided into load levels, and the time period with the highest load level within the future working time period is determined as the target time period.

[0064] In some exemplary embodiments, the first module 410 is further configured to: The prediction model is used to output at least one candidate load state of the energy storage unit in the candidate time period, and the confidence level of the at least one candidate load state is marked. The candidate time period is any time period within the future working time period. The load state with the highest confidence among the at least one candidate load states is determined as the load state of the energy storage unit during the candidate time period.

[0065] In some exemplary embodiments, the second module 420 is further configured to: Based on the feature data of the target time period, a clustering algorithm is used to determine the matching result in the database of the temperature control component. The matching result is the historical time period whose feature data is closest to the feature data of the target time period and the corresponding operating data of the historical time period.

[0066] In some exemplary embodiments, the matching result includes the control data and execution results of the temperature control component within a historical time period; The third module 430 is also used for: If the execution result meets the set expectations, the control strategy is generated based on the control data corresponding to the matching result; If the execution result does not meet the set expectations, the control data corresponding to the matching result is adjusted by a set amount to generate the control strategy; The control strategy includes at least the start-up time and start-up power of the temperature control component.

[0067] In some exemplary embodiments, the third module 430 is further configured to: Based on the target load of the energy storage unit, the target power of the temperature control component is determined, wherein the target load is the load value that the energy storage unit is expected to reach during the target time period, as determined by the load prediction. The start-up time and start-up power of the temperature control component are determined based on the matching results. Based on the target power, the start-up time, the start-up power, and the start time of the target time period, the power change curve of the temperature control component is determined, thereby generating the control strategy.

[0068] In some exemplary embodiments, the third module 430 is further configured to: The power change curve is generated by an interpolation algorithm, and the change amplitude of the power change curve is controlled by setting a threshold.

[0069] In some exemplary embodiments, the third module 430 is further configured to: Determine the temperature difference between the actual temperature and the expected temperature of the energy storage unit; When the temperature difference falls within a set range, the control strategy and the feedback strategy are mixed according to a set ratio, and the mixed strategy is used to control the temperature control component. When the temperature difference is greater than the set range, the temperature control component is controlled using the feedback strategy; The feedback strategy is a strategy for controlling the temperature control component based on the temperature difference.

[0070] In some exemplary embodiments, the third module 430 is further configured to: When the temperature difference falls within the set range, the current output power of the temperature control component in the control strategy and the feedback strategy is mixed according to the set ratio. The set ratio includes:

[0071] in, This indicates the set ratio. This indicates the set adjustment weight. This indicates the degree of deviation of the input temperature difference. , This indicates the temperature difference value. and These represent the minimum and maximum values ​​of the defined interval, respectively.

[0072] In some exemplary embodiments, the third module 430 is further configured to: Obtain the actual control results corresponding to the control strategy; The generation process of the control strategy is modified based on the actual control results.

[0073] In some exemplary embodiments, the first module 410 is further configured to: Obtain the historical data corresponding to the energy storage unit, the historical data including at least one of the following: load data of the energy storage unit, ambient temperature of the energy storage unit, temperature data of the energy storage unit, and temperature change data of the energy storage unit.

[0074] In some exemplary embodiments, the operating data includes at least one of the following: load data of the energy storage unit, temperature data of the energy storage unit, temperature change data of the energy storage unit, start-up time period of the temperature control component, power data of the temperature control component, power change data of the temperature control component, and ambient temperature of the energy storage unit.

[0075] For ease of description, the above apparatus is described in terms of its functions, divided into various modules. Of course, in implementing the embodiments of this disclosure, the functions of each module can be implemented in one or more software and / or hardware.

[0076] The apparatus described above is used to implement the corresponding target control method in the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0077] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the target control method as described in any of the above embodiments.

[0078] Figure 5This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0079] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0080] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0081] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0082] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0083] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0084] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0085] The electronic devices described above are used to implement the corresponding target control methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0086] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a non-transitory computer-readable storage medium that stores computer instructions for causing the computer to execute the target control method as described in any of the above embodiments.

[0087] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, which can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0088] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the target control method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0089] Based on the same concept, corresponding to the methods of any of the above embodiments, this disclosure also provides a computer program product, which includes computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processors to perform the target control method. Corresponding to the execution entity for each step in each embodiment of the target control method, the processor executing the corresponding step may belong to the corresponding execution entity.

[0090] The computer program products of the above embodiments are used to cause the computer and / or the processor to execute the target control method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0091] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this disclosure, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this disclosure as described above, which are not provided in detail for the sake of brevity.

[0092] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this disclosure, the provided drawings may or may not show well-known power / ground connections to integrated circuit (IC) chips and other components. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this disclosure, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this disclosure will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this disclosure, it will be apparent to those skilled in the art that the embodiments of this disclosure can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0093] Although this disclosure has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0094] This disclosure is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A target control method, characterized in that, The method is applied to a system consisting of a temperature control component and an energy storage unit, wherein the temperature control component is used to adjust the temperature properties of the energy storage unit, and the method includes: Based on the historical data of the energy storage unit, load forecasting is performed for future working periods to obtain target periods. The target periods are determined by dividing the future working periods according to the load forecast results. The temperature control component's database is matched with the characteristic data of the target time period to determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained from the load prediction. A control strategy is determined based on the matching result, and the control strategy is used to control the temperature control component to start in advance before the target time period.

2. The method according to claim 1, characterized in that, The step of predicting the load for future operating periods based on historical data from the energy storage unit to obtain the target period includes: The historical data of the energy storage unit is analyzed by a deep learning prediction model to generate a load state prediction result of the energy storage unit in the future working period. Based on the load status prediction results, the future working time period is divided into load levels, and the time period with the highest load level within the future working time period is determined as the target time period.

3. The method according to claim 2, characterized in that, The process of analyzing historical data of the energy storage unit using a deep learning prediction model to generate a load state prediction result for the energy storage unit during the future operating period includes: The prediction model is used to output at least one candidate load state of the energy storage unit in the candidate time period, and the confidence level of the at least one candidate load state is marked. The candidate time period is any time period within the future working time period. The load state with the highest confidence among the at least one candidate load states is determined as the load state of the energy storage unit during the candidate time period.

4. The method according to claim 1, characterized in that, The step of matching data in the database of the temperature control component based on the characteristic data of the target time period to determine the matching result includes: Based on the feature data of the target time period, a clustering algorithm is used to determine the matching result in the database of the temperature control component. The matching result is the historical time period whose feature data is closest to the feature data of the target time period and the corresponding operating data of the historical time period.

5. The method according to claim 1, characterized in that, The matching results include the control data and execution results of the temperature control component within a historical time period; The step of determining the control strategy based on the matching result includes: If the execution result meets the set expectations, the control strategy is generated based on the control data corresponding to the matching result; If the execution result does not meet the set expectations, the control data corresponding to the matching result is adjusted by a set amount to generate the control strategy; The control strategy includes at least the start-up time and start-up power of the temperature control component.

6. The method according to claim 1, characterized in that, The step of determining the control strategy based on the matching result includes: Based on the target load of the energy storage unit, the target power of the temperature control component is determined, wherein the target load is the load value that the energy storage unit is expected to reach during the target time period, as determined by the load prediction. The start-up time and start-up power of the temperature control component are determined based on the matching results. Based on the target power, the start-up time, the start-up power, and the start time of the target time period, the power change curve of the temperature control component is determined, thereby generating the control strategy.

7. The method according to claim 6, characterized in that, Determining the power change curve of the temperature control component includes: The power change curve is generated by an interpolation algorithm, and the change amplitude of the power change curve is controlled by setting a threshold.

8. The method according to claim 1, characterized in that, After determining the control strategy based on the matching result, the method further includes: Determine the temperature difference between the actual temperature and the expected temperature of the energy storage unit; When the temperature difference falls within a set range, the control strategy and the feedback strategy are mixed according to a set ratio, and the mixed strategy is used to control the temperature control component. When the temperature difference is greater than the set range, the temperature control component is controlled using the feedback strategy; The feedback strategy is a strategy for controlling the temperature control component based on the temperature difference.

9. The method according to claim 8, characterized in that, When the temperature difference falls within a set range, the control strategy and feedback strategy are mixed according to a set ratio, including: When the temperature difference falls within the set range, the current output power of the temperature control component in the control strategy and the feedback strategy is mixed according to the set ratio. The set ratio includes: ； in, This indicates the set ratio. This indicates the set adjustment weight. This indicates the degree of deviation of the input temperature difference. , This indicates the temperature difference value. and These represent the minimum and maximum values ​​of the defined interval, respectively.

10. The method according to claim 1, characterized in that, After determining the control strategy based on the matching result, the method further includes: Obtain the actual control results corresponding to the control strategy; The generation process of the control strategy is modified based on the actual control results.

11. The method according to claim 1, characterized in that, Before performing load forecasting for future operating periods based on historical data from the energy storage unit, the method further includes: Obtain the historical data corresponding to the energy storage unit, the historical data including at least one of the following: load data of the energy storage unit, ambient temperature of the energy storage unit, temperature data of the energy storage unit, and temperature change data of the energy storage unit.

12. The method according to claim 1, characterized in that, The operating data includes at least one of the following: load data of the energy storage unit, temperature data of the energy storage unit, temperature change data of the energy storage unit, start-up time period of the temperature control component, power data of the temperature control component, power change data of the temperature control component, and ambient temperature of the energy storage unit.

13. A target control device, characterized in that, The device is applied in a system consisting of a temperature control component and an energy storage unit. The temperature control component is used to adjust the temperature properties of the energy storage unit. The device includes: The first module is used to perform load forecasting for future working periods based on historical data of the energy storage unit to obtain a target period, wherein the target period is a time period determined by dividing the future working periods based on the load forecasting results. The second module is used to perform data matching in the database of the temperature control component based on the characteristic data of the target time period, and determine the matching result. The characteristic data is the operating condition data of the temperature control component and / or the energy storage unit within the target time period obtained by the load prediction. The third module is used to determine a control strategy based on the matching result. The control strategy is used to control the temperature control component to start in advance before the target time period.

14. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing a computer to perform the method as described in any one of claims 1 to 12.

16. A computer program product, characterized in that, It includes computer program instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 12.

Images