Thermoelectric coupling energy-saving control method of energy storage system for commercial building

Abstract

The invention provides a thermoelectric coupling energy-saving control method of an energy storage system for a commercial building, and relates to the technical field of power distribution control. Determining a thermoelectric coupling energy efficiency reference of the energy storage system during thermoelectric coupling energy-saving control through the comprehensive energy efficiency index and response feedback under different thermoelectric coupling working conditions; predicting a thermoelectric distribution control strategy of the current energy storage system according to regulation and control correlation characteristics between the energy consumption mode of the historical operation cycle and the current thermoelectric regulation and control instruction and a thermoelectric conversion stability curve of the energy storage system in the historical operation cycle; and if the comprehensive energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency standard, the thermoelectric coupling energy efficiency standard restrains thermoelectric coupling energy-saving control of the energy storage system. According to the application, associated energy-saving regulation and control of comprehensive energy efficiency under the thermoelectric coupling working condition can be realized, so that the robustness of thermoelectric coupling energy-saving control of the energy storage system is improved.

Description

Technical Field

[0001] This application relates to the field of power distribution control technology, and more specifically, to a thermoelectric coupling energy-saving control method for an energy storage system for commercial buildings. Background Technology

[0002] In building energy systems, power distribution control is not only related to the stable operation of the power system, but also directly affects the overall energy efficiency of the building. Especially in commercial buildings, due to large fluctuations in energy load and diverse demands for heating, cooling and electricity, traditional single-energy control modes are difficult to adapt to the refined management requirements under multi-source coordination. Therefore, building an integrated and responsive power distribution control system and promoting the optimization of heat and power coordination has become an important direction for improving building energy efficiency and reducing operating costs.

[0003] However, existing thermoelectric coupling energy-saving control technologies generally suffer from poor adaptability to operating conditions. This is mainly reflected in the difficulty of dynamically adjusting control strategies based on real-time energy consumption. In traditional control methods, the allocation of heat and electrical loads is mostly based on static parameters or empirical rules, lacking in-depth modeling and feedback mechanisms of the system's operating history. This makes it difficult for control strategies to achieve optimal energy efficiency under complex operating conditions. Furthermore, the nonlinear response and stability changes during thermoelectric conversion are not effectively considered, easily leading to energy distribution imbalances and significant fluctuations in system operating efficiency, severely limiting the energy-saving potential of energy storage systems under dynamic operating conditions. Therefore, how to achieve correlated energy-saving regulation of comprehensive energy efficiency under thermoelectric coupling conditions, thereby improving the robustness of thermoelectric coupling energy-saving control in energy storage systems, has become a challenge for the industry. Summary of the Invention

[0004] This application provides a thermoelectric coupling energy-saving control method for energy storage systems in commercial buildings, which can realize the correlation energy-saving regulation of comprehensive energy efficiency under thermoelectric coupling conditions, thereby improving the robustness of thermoelectric coupling energy-saving control of energy storage systems.

[0005] In a first aspect, this application provides a thermoelectric coupling energy-saving control method for an energy storage system in commercial buildings, comprising the following steps: Collect thermal load data and electrical load data of the energy storage system during its historical operating cycle, and extract the response feedback of the energy storage system under different thermoelectric coupling conditions from the thermal load data and the electrical load data. When the energy management unit in a commercial building receives a thermoelectric control command, it obtains the overall environmental parameters and overall energy demand of the current commercial building, determines the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and overall energy demand, and then determines the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy-saving control through the comprehensive energy efficiency index and the response feedback under different thermoelectric coupling operating conditions. Analyze the regulation correlation characteristics between energy consumption patterns in historical operating cycles and current thermoelectric regulation commands, and predict the current thermoelectric distribution control strategy of the energy storage system based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system in historical operating cycles. If the overall energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark, then the thermoelectric coupling energy-saving control of the energy storage system is dynamically constrained based on the thermoelectric coupling energy efficiency benchmark.

[0006] In this embodiment, extracting the response feedback of the energy storage system under different thermoelectric coupling conditions from the heat load data and the electrical load data specifically includes: Different thermoelectric coupling conditions within the historical operating cycle are classified according to the preset thermoelectric coupling strength threshold. Time-domain features were extracted from the heat load data and electrical load data under each operating condition to obtain thermal response feature parameters and electrical response feature parameters. A mapping relationship is established between the thermal response characteristic parameters and the electrical response characteristic parameters to obtain response feedback under different thermoelectric coupling conditions.

[0007] In this embodiment, obtaining the overall environmental parameters and overall energy demand of the current commercial building specifically includes: Real-time data on indoor and outdoor temperature, humidity, and light intensity are collected using building environment monitoring equipment and used as the overall environmental parameters. The power demand time series data of each energy-consuming unit is retrieved from the energy management unit, and the total load curve of the commercial building is obtained by aggregating the power demand time series data. The overall energy demand of the current commercial building is determined based on the total load curve and the preset energy priority rules.

[0008] In this embodiment, determining the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and the overall energy demand specifically includes: Determine the environmental impact weighting coefficient under the current operating conditions based on the overall environmental parameters. Determine the demand fluctuation index for the current operating condition based on the load distribution characteristics in the overall energy demand. The comprehensive energy efficiency index for the current operating condition is determined by the influence weighting coefficient and the demand fluctuation index.

[0009] In this embodiment, determining the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy-saving control through the comprehensive energy efficiency index and response feedback under different thermoelectric coupling conditions specifically includes: The response feedback set is determined by the response feedback under different thermoelectric coupling conditions; Match the target operating condition category corresponding to the response feedback set according to the comprehensive energy efficiency index; Extract historical thermal and electrical response characteristic parameters under the target operating condition category; Based on historical thermal response and electrical response characteristic parameters, offset corrections are made using the comprehensive energy efficiency index to obtain the thermoelectric coupling energy efficiency benchmark for the energy storage system under thermoelectric coupling energy-saving control.

[0010] In this embodiment, the analysis of the regulation correlation characteristics between energy consumption patterns in historical operating cycles and current thermoelectric regulation commands specifically includes: Cluster analysis was performed on energy consumption data from historical operating cycles to identify typical energy consumption patterns; Extract the control parameters of the current thermoelectric control command, including the control target, time window and constraints; Establish a correlation mapping between typical energy consumption patterns and control parameters, determine the matching degree characteristics between control targets and historical energy consumption patterns, and use the matching degree characteristics as the control correlation characteristics.

[0011] In this embodiment, predicting the current thermoelectric distribution control strategy of the energy storage system based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system during its historical operating cycle specifically includes: The energy consumption behavior category of the energy storage system under the current control conditions is determined by the aforementioned control correlation features; Extract the thermoelectric conversion stability curves corresponding to the energy consumption behavior categories within the historical operating cycle; Based on a multivariate regression prediction model, the thermoelectric distribution control strategy of the current energy storage system is predicted by combining the regulation correlation characteristics and the thermoelectric conversion stability curve.

[0012] In this embodiment, the dynamic constraint on the thermoelectric coupling energy-saving control of the energy storage system based on the thermoelectric coupling energy efficiency benchmark specifically includes: A dynamic constraint mechanism for triggering thermoelectric coupling energy-saving control; Based on the dynamic constraint mechanism, the thermoelectric coupling coefficient is adjusted by a preset step size until the actual energy efficiency value is greater than or equal to the thermoelectric coupling energy efficiency benchmark, and the adjustment result is fed back to the energy management unit.

[0013] In this embodiment, the heat load data is collected using a heat flow sensor.

[0014] In this embodiment, the electrical load data is collected using a smart energy meter.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: First, heat load and electrical load data of the energy storage system during its historical operating cycle are collected. The response feedback of the energy storage system under different thermoelectric coupling conditions is extracted from these data. When the energy management unit in the commercial building receives a thermoelectric control command, it acquires the overall environmental parameters and overall energy demand of the building. Based on these parameters, the comprehensive energy efficiency index for the current operating condition is determined. Then, the thermoelectric coupling energy efficiency benchmark for the energy storage system under thermoelectric coupling energy-saving control is determined using the comprehensive energy efficiency index and the response feedback under different thermoelectric coupling conditions. The control correlation characteristics between the energy consumption patterns in the historical operating cycle and the current thermoelectric control command are analyzed. Based on these correlation characteristics and the thermoelectric conversion stability curve of the energy storage system during the historical operating cycle, the thermoelectric distribution control strategy of the current energy storage system is predicted. If the comprehensive energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark, dynamic constraints are applied to the thermoelectric coupling energy-saving control of the energy storage system based on the benchmark.

[0016] Therefore, this application dynamically constrains the thermoelectric coupling energy-saving control of the energy storage system based on the aforementioned thermoelectric coupling energy efficiency benchmark. First, by collecting historical heat load data and electrical load data and extracting response feedback under different thermoelectric coupling operating conditions, a response model of the energy storage system to changes in multiple operating conditions is effectively established, providing data support and dynamic adjustment basis for subsequent energy-saving control strategies. Second, upon receiving thermoelectric control commands, the current overall environmental parameters and energy demand are introduced, and the historical response model is further integrated to construct a comprehensive energy efficiency index and determine the thermoelectric coupling energy efficiency benchmark accordingly. This enables the control system to have sensitive perception and energy efficiency assessment capabilities for changes in operating conditions during real-time operation, strengthening the pertinence and effectiveness of energy-saving control. Then, by mining historical data... By analyzing the correlation between historical energy consumption patterns and current control commands, and combining this with thermoelectric conversion stability curves to predict thermoelectric distribution strategies, this approach addresses the lack of in-depth historical modeling and dynamic trend analysis in traditional schemes, achieving a high degree of matching between control strategies and system states. Finally, a dynamic constraint mechanism based on thermoelectric coupling energy efficiency benchmarks is established. When the overall energy efficiency of the predicted strategy falls below the benchmark, the system behavior is promptly adjusted to ensure that the energy storage system always operates in a highly efficient and safe state. The final solution not only overcomes the technical shortcomings of static rules, model lag, and response imbalance in existing thermoelectric coupling energy-saving control, but also constructs a closed-loop adaptive control system, enhancing the system's robustness and energy efficiency stability under complex operating conditions from a mechanism perspective.

[0017] In summary, the proposed solution can achieve correlated energy-saving regulation of comprehensive energy efficiency under thermoelectric coupling conditions, thereby improving the robustness of thermoelectric coupling energy-saving control of energy storage systems. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, 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 for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a thermoelectric coupling energy-saving control method for a commercial building energy storage system provided in this application; Figure 2 This is an exemplary flowchart for determining the comprehensive energy efficiency index provided in this application; Figure 3 This is an exemplary flowchart for determining regulatory correlation characteristics provided in this application; Figure 4 This is a modular structure diagram of the thermoelectric coupling energy-saving control system for a commercial building energy storage system provided in this application. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] This application provides a thermoelectric coupling energy-saving control method for energy storage systems in commercial buildings. The core of this method is to determine the comprehensive energy efficiency index (TEI) for the current operating conditions based on the overall environmental parameters and overall energy demand of the commercial building. Then, by using the TAI and E, a TAI and E performance benchmark for the energy storage system under different TAI and E operating conditions is determined. Based on the correlation characteristics between the energy consumption patterns of historical operating cycles and the current TAI and E control commands, and the thermoelectric conversion stability curve of the energy storage system during historical operating cycles, a TAI and E distribution control strategy for the current energy storage system is predicted. If the comprehensive energy efficiency of the TAI and E distribution control strategy is lower than the TAI and E performance benchmark, the TAI and E performance benchmark constrains the TAI and E performance energy-saving control of the energy storage system. This application can achieve correlated energy-saving regulation of comprehensive energy efficiency under TAI and E operating conditions, thereby improving the robustness of the TAI and E performance energy-saving control of the energy storage system.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1As shown in the figure, this is an exemplary flowchart of a thermoelectric coupling energy-saving control method for a commercial building energy storage system according to this embodiment of the present application. The thermoelectric coupling energy-saving control method for the commercial building energy storage system includes the following steps: In step S1, thermal load data and electrical load data of the energy storage system during historical operating cycles are collected, and the response feedback of the energy storage system under different thermoelectric coupling conditions is extracted from the thermal load data and the electrical load data.

[0023] It should be noted that the historical operating cycle in this application refers to the time period during which the energy storage system continuously operates and completes a full load response process within a specific time range in the past; it should also be noted that the heat load data in this application refers to the heat information absorbed or released by the energy storage system per unit time, which is collected by a heat flow sensor; the electrical load data in this application refers to the electrical energy input or output data of the energy storage system per unit time, which is collected by a smart energy meter.

[0024] In this embodiment, the extraction of the energy storage system's response feedback under different thermoelectric coupling conditions from the thermal load data and the electrical load data can be achieved through the following steps: Different thermoelectric coupling conditions within the historical operating cycle are classified according to the preset thermoelectric coupling strength threshold. Time-domain features were extracted from the heat load data and electrical load data under each operating condition to obtain thermal response feature parameters and electrical response feature parameters. A mapping relationship is established between the thermal response characteristic parameters and the electrical response characteristic parameters to obtain response feedback under different thermoelectric coupling conditions.

[0025] It should be noted that the response feedback in this application is a characteristic that measures the ability of an energy storage system to regulate load changes under specific thermoelectric coupling conditions.

[0026] In specific implementation, firstly, the time-series data of heat load and electrical load recorded in the energy storage system operation log can be used to set the ratio of heat power to electrical power as the thermoelectric coupling strength index. Based on multiple preset threshold intervals, historical operating cycles are classified to obtain multiple discrete thermoelectric coupling condition types. It should be noted that the thermoelectric coupling condition types in this application can be high-heat-low-electric coupling, equal-heat-equal-electric coupling, high-electric-low-heat coupling, etc. Secondly, for each thermoelectric coupling condition, a sliding time window is used to divide the heat load data and electrical load data corresponding to each thermoelectric coupling condition into short-cycle segments. The rate of change is extracted using first-order difference, the stability index is calculated using moving average, and the upper and lower limits of the response are obtained through extreme value extraction, thereby constructing a time-domain feature parameter set for the thermal response and electrical response. Then, a numerical mapping relationship between the thermal response parameters and the electrical response parameters is established using a multiple linear regression method, and the numerical feature set representing the mapping relationship is used as the response feedback in this embodiment. It should be further noted that the response feedback in this application is specifically represented as a set.

[0027] In step S2, when the energy management unit in the commercial building receives a thermoelectric control command, it obtains the overall environmental parameters and overall energy demand of the current commercial building, determines the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and the overall energy demand, and then determines the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy-saving control through the comprehensive energy efficiency index and the response feedback under different thermoelectric coupling operating conditions.

[0028] It should be noted that the thermoelectric control command in this application refers to the control command used to adjust the ratio of thermal energy to electrical energy output in the energy storage system.

[0029] In this embodiment, obtaining the overall environmental parameters and overall energy demand of the current commercial building can be achieved through the following steps: Real-time data on indoor and outdoor temperature, humidity, and light intensity are collected using building environment monitoring equipment and used as the overall environmental parameters. The power demand time series data of each energy-consuming unit is retrieved from the energy management unit, and the total load curve of the commercial building is obtained by aggregating the power demand time series data. The overall energy demand of the current commercial building is determined based on the total load curve and the preset energy priority rules.

[0030] It should be noted that the total load curve in this application refers to the cumulative change curve of the power demand of each energy-consuming unit of a commercial building within a certain time range; the overall energy demand in this application is an indicator that measures the intensity of the total energy consumption demand of a commercial building within a specific period.

[0031] In practical implementation, firstly, various environmental monitoring sensors deployed within the building, such as temperature sensors, humidity sensors, and light sensors, can collect indoor and outdoor environmental parameters in real time. This data can be uniformly aggregated through a building environmental monitoring and management system. Secondly, the power demand time series of each energy-consuming unit (such as air conditioning, lighting, and elevators) can be obtained from the energy management unit. The overall total load curve of the building can be obtained through time series data aggregation calculation. This process often uses sliding window statistics and peak-valley analysis methods to identify energy consumption patterns. Then, combined with pre-set energy priority rules (e.g., prioritizing critical loads and delaying non-critical loads), a rule-based decision algorithm is used to schedule and optimize the total load, and the output is used as the overall energy demand of the commercial building in the current time period. It should be noted that the rule-based decision-making algorithm in this application performs segmented analysis and load classification on the total load curve through preset energy consumption priorities and operational constraints. It can group the energy-consuming units in the building according to their importance and flexibility, such as critical equipment, adjustable loads, and delayable loads. The time slicing method is applied to the total load curve to restructure the load for load fluctuations in different time periods. According to the rules, the power demand of critical equipment is prioritized. At the same time, peak-valley switching strategies are set for adjustable and delayable loads to dynamically adjust their operating time and power. Furthermore, combined with the building's operating period and user comfort requirements, a heuristic scheduling process is used to determine the specific power allocation of each load in the current time period. Finally, the scheduling results are summarized to form the overall energy demand for the current time period.

[0032] In this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart for determining the comprehensive energy efficiency index in an embodiment of this application. In this embodiment, the determination of the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and the overall energy demand can be achieved by the following steps: In step S21, the influence weighting coefficient of the environment under the current working condition is determined based on the overall environmental parameters; In step S22, the demand fluctuation index for the current operating condition is determined based on the load distribution characteristics in the overall energy demand. In step S23, the comprehensive energy efficiency index for the current operating condition is determined by the influence weighting coefficient and the demand fluctuation index.

[0033] It should be noted that the impact weighting coefficient in this application is an indicator that measures the degree of influence of environmental parameters on the energy consumption of the energy storage system; the demand fluctuation index in this application is an indicator that measures the stability and fluctuation intensity of the energy load of commercial buildings within a certain time range; and the comprehensive energy efficiency index in this application is an indicator that measures the comprehensive level of energy utilization efficiency and environmental adaptability of commercial buildings under current operating conditions.

[0034] In practice, firstly, the collected environmental parameters undergo data preprocessing, including outlier removal and normalization, to ensure the comparability of parameters with different dimensions. Then, based on building energy consumption models or historical operating data, principal component analysis is used to extract key influencing factors from the environmental parameters, quantifying the contribution of each factor to energy consumption. The extracted contributions are then used as weights, and combined with expert experience or measured feedback, corresponding influence weight coefficients are assigned to each environmental parameter. Finally, a comprehensive weight coefficient reflecting the intensity of the current operating environment's influence is calculated through weighted aggregation. Secondly, the total load curve can be segmented into a time series, and sliding window technology can be used to extract power statistical characteristics within each time period, including mean, peak value, and standard deviation. The load's coefficient of variation or volatility index is then calculated to quantify the impact. The relative fluctuation range of the load reflects the stability and intensity of the load fluctuation. Combined with the load peak-to-valley ratio and the load gradient change trend, a multi-dimensional feature vector is constructed. A weighted synthesis method is used to fuse various statistical indicators to obtain a demand fluctuation index that reflects the energy demand fluctuation characteristics under the current operating conditions. Then, the influence weight coefficient and the demand fluctuation index are normalized to ensure that they are in the same dimension range. A weighted average method is then used to combine the environmental influence weight coefficient and the demand fluctuation index according to a preset ratio to obtain a single comprehensive index. This comprehensive index is used as the comprehensive energy efficiency index for the current operating conditions. This comprehensive energy efficiency index can reflect the combined impact of environmental conditions and energy demand fluctuations under the current operating conditions, and is used to evaluate the overall energy efficiency performance of the system to support subsequent energy-saving control decisions.

[0035] In this embodiment, the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy-saving control can be determined by the following steps, based on the comprehensive energy efficiency index and response feedback under different thermoelectric coupling conditions: The response feedback set is determined by the response feedback under different thermoelectric coupling conditions; Match the target operating condition category corresponding to the response feedback set according to the comprehensive energy efficiency index; Extract historical thermal and electrical response characteristic parameters under the target operating condition category; Based on historical thermal response and electrical response characteristic parameters, offset corrections are made using the comprehensive energy efficiency index to obtain the thermoelectric coupling energy efficiency benchmark for the energy storage system under thermoelectric coupling energy-saving control.

[0036] It should be noted that the thermoelectric coupling efficiency benchmark in this application is a reference indicator for measuring the efficiency of the combined output of thermal and electrical energy of an energy storage system under specific operating conditions.

[0037] In specific implementation, firstly, based on the previously defined thermoelectric coupling operating conditions, the thermal response feature parameters and electrical response feature parameters extracted within the corresponding time period for each type of operating condition are archived separately. Statistical processing is then performed on the parameter samples within each group of operating conditions, using indicators such as mean, standard deviation, and extreme values ​​to construct a stability description, resulting in an operating condition-level feature representation. Next, the parameter representations for all operating conditions are uniformly encoded to generate a structured response feedback matrix, using the operating condition type as the index and various response parameters as fields to form a complete response feedback set. Secondly, the comprehensive energy efficiency index calculated under the current operating condition is standardized to maintain dimensional consistency when compared with historical data. Historical comprehensive energy efficiency indices corresponding to each thermoelectric coupling operating condition are extracted from the response feedback set to form a multi-operating condition energy efficiency index vector. Then, a distance metric algorithm, such as Euclidean distance, is used to calculate the similarity between the current comprehensive energy efficiency index and the historical average energy efficiency of each operating condition. By setting a minimum distance matching principle, the target operating condition category with the smallest distance is selected, and the target operating condition category is then... The target operating condition is identified as the thermoelectric coupling operating state most similar to the current operating condition. Then, the thermal and electrical response characteristic parameters for the corresponding historical operating cycles are obtained. Finally, based on the extracted thermal and electrical response characteristic parameters for the target operating condition, feature vectors representing the typical response capability of the system under this operating condition are constructed for the thermal load side and the electrical load side, respectively. The difference between the comprehensive energy efficiency index corresponding to the current operating condition and the historical average energy efficiency of the target operating condition is calculated to obtain the energy efficiency offset. Based on this energy efficiency offset, key indicators (such as the rate of change of thermal power and the rate of change of electrical power) in the feature vectors of the thermal load side and the electrical load side are linearly corrected. The correction factor can be set with variable weights according to the offset direction and magnitude. To avoid introducing nonlinear disturbances during the correction process, upper and lower thresholds can be set to ensure that the adjustment range is within the stable operating range of the system. Finally, the corrected thermal and electrical response parameters are jointly characterized to obtain a dynamically adaptable thermoelectric coupling energy efficiency benchmark under the current operating condition.

[0038] It should be noted that, compared with existing thermoelectric coupling control methods based on static energy consumption data or single load characteristics, the proposed solution solves the problem of not being able to dynamically adjust the energy efficiency reference standard according to the current operating conditions. Its technical feature lies in introducing a comprehensive energy efficiency index as a comprehensive evaluation index of the energy consumption and environmental adaptability under the current operating conditions. By matching the index with historical operating conditions in the response feedback set, the closest operating state is determined, thereby avoiding the strategy deviation caused by misjudgment of operating conditions in traditional methods. By extracting historical thermal and electrical response characteristic parameters and combining them with the current energy efficiency deviation for correction, a thermoelectric coupling energy efficiency benchmark with real-time adaptability is established, solving the technical problem that static benchmarks cannot reflect changes in operating conditions. In terms of technical effect, this method can realize the dynamic evaluation and optimization judgment of the thermoelectric synergy efficiency of energy storage systems, improve the accuracy of energy efficiency evaluation and the responsiveness of control strategies, thereby improving the overall energy-saving control effect.

[0039] In step S3, the regulation correlation characteristics between the energy consumption patterns in the historical operating cycle and the current thermoelectric regulation command are analyzed. Based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system in the historical operating cycle, the thermoelectric distribution control strategy of the current energy storage system is predicted.

[0040] In this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart for determining the control correlation characteristics in an embodiment of this application. In this embodiment, the analysis of the control correlation characteristics between energy consumption patterns in historical operating cycles and current thermoelectric control commands can be achieved by the following steps: In step S31, cluster analysis is performed on the energy consumption data of historical operating cycles to identify typical energy consumption patterns; In step S32, the control parameters of the current thermoelectric control command are extracted, including the control target, time window and constraints. In step S33, a correlation mapping between typical energy consumption patterns and control parameters is established, the matching degree characteristics between the control target and historical energy consumption patterns are determined, and the matching degree characteristics are used as the control correlation characteristics.

[0041] It should be noted that the typical energy consumption pattern in this application refers to a representative energy consumption behavior characteristic pattern extracted from historical energy consumption data; the control target in this application refers to the specific performance indicators that the energy storage system's thermoelectric energy-saving control needs to achieve; the time window in this application refers to the specific time range for executing the control target; the constraint conditions in this application refer to the operational restrictions that must be met during the control process; and the control correlation characteristics in this application are characteristic indicators that measure the degree of matching between the current thermoelectric control command and the typical energy consumption pattern.

[0042] In practice, firstly, the energy consumption data collected during the historical operating cycle can be preprocessed, including outlier removal and normalization, to ensure data quality and consistency of dimensions. Then, an unsupervised clustering algorithm (K-means clustering is used in this application) is employed to analyze the preprocessed energy consumption data. Based on characteristics such as power fluctuation amplitude, load peak-valley characteristics, and energy consumption time period distribution, the historical operating cycle is divided into several typical energy consumption patterns. Each energy consumption pattern can be represented by a feature vector formed by calculating its center point or representative samples, reflecting its energy consumption behavior characteristics. Finally, the feature vectors and control parameter vectors of the typical energy consumption patterns are formatted in a unified manner. The process involves processing parameters to ensure matching of dimensions and data types, followed by the use of similarity measurement methods, such as cosine similarity or weighted Euclidean distance, to calculate the matching score between each set of control parameters and the characteristics of each typical energy consumption mode. To reflect the impact of different control objectives and constraints on the matching results, weighting coefficients are set to adjust the dimensions in the matching score calculation, and normalization is performed to ensure that the matching score is within a unified dimension, facilitating subsequent comparison and ranking. Furthermore, the most relevant typical energy consumption mode is selected based on the matching score ranking results, and its corresponding matching score is the matching score feature in this application. The matching score feature is then used as the control association feature.

[0043] In this embodiment, predicting the current thermoelectric distribution control strategy of the energy storage system based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system during its historical operating cycle can be achieved through the following steps: The energy consumption behavior category of the energy storage system under the current control conditions is determined by the aforementioned control correlation features; Extract the thermoelectric conversion stability curves corresponding to the energy consumption behavior categories within the historical operating cycle; Based on a multivariate regression prediction model, the thermoelectric distribution control strategy of the current energy storage system is predicted by combining the regulation correlation characteristics and the thermoelectric conversion stability curve.

[0044] It should be noted that the energy consumption behavior category in this application refers to the typical energy consumption mode characteristics exhibited by the energy storage system during the thermoelectric conversion process under specific control conditions, reflecting its dynamic distribution law in response to heat load and electrical load; the thermoelectric conversion stability curve in this application refers to the stability performance of the thermoelectric conversion efficiency of the energy storage system under different operating conditions over time; and the thermoelectric distribution control strategy in this application refers to the control scheme used to determine the ratio of heat energy and electrical energy output of the energy storage system.

[0045] In practical implementation, firstly, by adjusting the matching degree information in the correlation features, the current thermoelectric control command is mapped to an existing energy consumption behavior label. The K-nearest neighbor algorithm can be used to classify this label, and the corresponding energy consumption behavior category can be determined by the output result. Secondly, operating cycles consistent with the energy consumption behavior category are selected from historical data, and the stability curve formed by the change of the ratio of heat energy to electrical energy output during the thermoelectric conversion process over time is extracted. The mean and standard deviation of the fluctuation in the stability curve are often extracted as thermoelectric conversion stability indicators using the sliding window method. Then, when constructing a multivariate regression prediction model, the input variable is set as a combined feature vector composed of the control correlation features and the thermoelectric conversion stability indicators, and the response variable is set as the heat power to electrical power distribution ratio corresponding to the system reaching the optimal energy efficiency in the historical cycle. The least squares method is used to train the regression model, fit the relationship between the input features and the optimal distribution ratio, and obtain the thermoelectric distribution control strategy of the current energy storage system.

[0046] In step S4, if the overall energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark, then the thermoelectric coupling energy-saving control of the energy storage system is dynamically constrained based on the thermoelectric coupling energy efficiency benchmark.

[0047] In this embodiment, the dynamic constraint of the thermoelectric coupling energy-saving control of the energy storage system based on the thermoelectric coupling energy efficiency benchmark can be achieved by the following steps: A dynamic constraint mechanism for triggering thermoelectric coupling energy-saving control; Based on the dynamic constraint mechanism, the thermoelectric coupling coefficient is adjusted by a preset step size until the actual energy efficiency value is greater than or equal to the thermoelectric coupling energy efficiency benchmark, and the adjustment result is fed back to the energy management unit.

[0048] It should be noted that the thermoelectric coupling coefficient in this application is a proportional parameter that measures the strength of the coupling between thermal energy and electrical energy in an energy storage system.

[0049] In specific implementation, firstly, when the overall energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark, the dynamic constraint mechanism of thermoelectric coupling energy-saving control is triggered. It should be noted that the dynamic constraint mechanism in this application refers to a control method that automatically adjusts control parameters according to real-time energy efficiency status to maintain system operating efficiency. Then, the initial value of the thermoelectric coupling coefficient and the adjustment step size parameter are preset as the basic unit of system adjustment. The system collects the operating data of the energy storage system in real time and obtains the current actual energy efficiency value through the energy efficiency calculation model. If the actual energy efficiency value is lower than the preset thermoelectric coupling energy efficiency benchmark, the control unit increases the thermoelectric coupling coefficient by the preset step size (i.e., changes the heat and electricity distribution ratio). By adjusting the thermoelectric coupling parameters, the thermoelectric conversion process is optimized to improve the overall energy efficiency of the system. After each adjustment, the actual energy efficiency value is updated in real time, and the adjustment result is fed back to the energy management unit for overall control and subsequent strategy optimization. This process is continuously executed under the closed-loop control framework to ensure that the energy efficiency of the energy storage system is maintained at or above the benchmark level, realizing energy-saving control that dynamically adapts to the operating environment.

[0050] Therefore, this application dynamically constrains the thermoelectric coupling energy-saving control of the energy storage system based on the aforementioned thermoelectric coupling energy efficiency benchmark. First, by collecting historical heat load data and electrical load data and extracting response feedback under different thermoelectric coupling operating conditions, a response model of the energy storage system to changes in multiple operating conditions is effectively established, providing data support and dynamic adjustment basis for subsequent energy-saving control strategies. Second, upon receiving thermoelectric control commands, the current overall environmental parameters and energy demand are introduced, and the historical response model is further integrated to construct a comprehensive energy efficiency index and determine the thermoelectric coupling energy efficiency benchmark accordingly. This enables the control system to have sensitive perception and energy efficiency assessment capabilities for changes in operating conditions during real-time operation, strengthening the pertinence and effectiveness of energy-saving control. Then, by mining historical data... By analyzing the correlation between historical energy consumption patterns and current control commands, and combining this with thermoelectric conversion stability curves to predict thermoelectric distribution strategies, this approach addresses the lack of in-depth historical modeling and dynamic trend analysis in traditional schemes, achieving a high degree of matching between control strategies and system states. Finally, a dynamic constraint mechanism based on thermoelectric coupling energy efficiency benchmarks is established. When the overall energy efficiency of the predicted strategy falls below the benchmark, the system behavior is promptly adjusted to ensure that the energy storage system always operates in a highly efficient and safe state. The final solution not only overcomes the technical shortcomings of static rules, model lag, and response imbalance in existing thermoelectric coupling energy-saving control, but also constructs a closed-loop adaptive control system, enhancing the system's robustness and energy efficiency stability under complex operating conditions from a mechanism perspective.

[0051] In summary, the proposed solution can achieve correlated energy-saving regulation of comprehensive energy efficiency under thermoelectric coupling conditions, thereby improving the robustness of thermoelectric coupling energy-saving control of energy storage systems.

[0052] Example 2: This application provides a thermoelectric coupling energy-saving control system for an energy storage system in commercial buildings, referencing... Figure 4 As shown in the figure, this is a schematic diagram of the thermoelectric coupling energy-saving control system of the commercial building energy storage system according to this embodiment of the present application. The thermoelectric coupling energy-saving control system of the commercial building energy storage system includes: The acquisition module 100 is used to acquire heat load data and electrical load data of the energy storage system during historical operating cycles, and extract the response feedback of the energy storage system under different thermoelectric coupling conditions from the heat load data and the electrical load data. The feature processing module 200 is used to obtain the overall environmental parameters and overall energy demand of the current commercial building when the energy management unit in the commercial building receives the thermoelectric control command, determine the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and the overall energy demand, and then determine the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy saving control through the comprehensive energy efficiency index and the response feedback under different thermoelectric coupling operating conditions. The feature processing module 200 is also used to analyze the regulation correlation characteristics between the energy consumption pattern in the historical operating cycle and the current thermoelectric regulation command, and predict the thermoelectric distribution control strategy of the current energy storage system based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system in the historical operating cycle. The control module 300 is used to dynamically constrain the thermoelectric coupling energy-saving control of the energy storage system based on the thermoelectric coupling energy efficiency benchmark if the overall energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark.

[0053] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0055] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A thermoelectric coupling energy-saving control method for an energy storage system in commercial buildings, characterized in that, Includes the following steps: Collect thermal load data and electrical load data of the energy storage system during its historical operating cycle, and extract the response feedback of the energy storage system under different thermoelectric coupling conditions from the thermal load data and the electrical load data. When the energy management unit in the commercial building receives a thermoelectric control command, it obtains the overall environmental parameters and overall energy demand of the current commercial building, determines the comprehensive energy efficiency index of the current operating condition based on the overall environmental parameters and overall energy demand, and then determines the thermoelectric coupling energy efficiency benchmark of the energy storage system under thermoelectric coupling energy-saving control through the comprehensive energy efficiency index and the response feedback under different thermoelectric coupling operating conditions. Analyze the regulation correlation characteristics between energy consumption patterns in historical operating cycles and current thermoelectric regulation commands, and predict the current thermoelectric distribution control strategy of the energy storage system based on the regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system in historical operating cycles. If the overall energy efficiency of the thermoelectric distribution control strategy is lower than the thermoelectric coupling energy efficiency benchmark, then the thermoelectric coupling energy-saving control of the energy storage system is dynamically constrained based on the thermoelectric coupling energy efficiency benchmark.

2. The method as described in claim 1, characterized in that, Extracting the response feedback of the energy storage system under different thermoelectric coupling conditions from the heat load data and the electrical load data specifically includes: Different thermoelectric coupling conditions within the historical operating cycle are classified according to the preset thermoelectric coupling strength threshold. Time-domain features were extracted from the heat load data and electrical load data under each operating condition to obtain thermal response feature parameters and electrical response feature parameters. A mapping relationship is established between the thermal response characteristic parameters and the electrical response characteristic parameters to obtain response feedback under different thermoelectric coupling conditions.

3. The method as described in claim 1, characterized in that, Obtaining the overall environmental parameters and overall energy demand of the current commercial building specifically includes: Real-time data on indoor and outdoor temperature, humidity, and light intensity are collected using building environment monitoring equipment and used as the overall environmental parameters. The power demand time series data of each energy-consuming unit is retrieved from the energy management unit, and the total load curve of the commercial building is obtained by aggregating the power demand time series data. The overall energy demand of the current commercial building is determined based on the total load curve and the preset energy priority rules.

4. The method as described in claim 1, characterized in that, Determining the comprehensive energy efficiency index for the current operating condition based on the overall environmental parameters and the overall energy demand specifically includes: Determine the environmental impact weighting coefficient under the current operating conditions based on the overall environmental parameters. Determine the demand fluctuation index for the current operating condition based on the load distribution characteristics in the overall energy demand. The comprehensive energy efficiency index for the current operating condition is determined by the influence weighting coefficient and the demand fluctuation index.

5. The method as described in claim 1, characterized in that, The thermoelectric coupling energy efficiency benchmark for energy storage systems under thermoelectric coupling energy-saving control is determined by the comprehensive energy efficiency index and response feedback under different thermoelectric coupling conditions, specifically including: The response feedback set is determined by the response feedback under different thermoelectric coupling conditions; Match the target operating condition category corresponding to the response feedback set according to the comprehensive energy efficiency index; Extract historical thermal and electrical response characteristic parameters under the target operating condition category; Based on historical thermal response and electrical response characteristic parameters, offset corrections are made using the comprehensive energy efficiency index to obtain the thermoelectric coupling energy efficiency benchmark for the energy storage system under thermoelectric coupling energy-saving control.

6. The method as described in claim 1, characterized in that, The analysis of the correlation between energy consumption patterns in historical operating cycles and current thermoelectric control commands specifically includes: Cluster analysis was performed on energy consumption data from historical operating cycles to identify typical energy consumption patterns; Extract the control parameters of the current thermoelectric control command, including the control target, time window and constraints; Establish a correlation mapping between typical energy consumption patterns and control parameters, determine the matching degree characteristics between control targets and historical energy consumption patterns, and use the matching degree characteristics as the control correlation characteristics.

7. The method as described in claim 1, characterized in that, Based on the aforementioned regulation correlation characteristics and the thermoelectric conversion stability curve of the energy storage system during its historical operating cycle, the predicted thermoelectric distribution control strategy for the current energy storage system specifically includes: The energy consumption behavior category of the energy storage system under the current control conditions is determined by the aforementioned control correlation features; Extract the thermoelectric conversion stability curves corresponding to the energy consumption behavior categories within the historical operating cycle; Based on a multivariate regression prediction model, the thermoelectric distribution control strategy of the current energy storage system is predicted by combining the regulation correlation characteristics and the thermoelectric conversion stability curve.

8. The method as described in claim 1, characterized in that, The dynamic constraint on the thermoelectric coupling energy-saving control of the energy storage system based on the aforementioned thermoelectric coupling energy efficiency benchmark specifically includes: A dynamic constraint mechanism for triggering thermoelectric coupling energy-saving control; Based on the dynamic constraint mechanism, the thermoelectric coupling coefficient is adjusted by a preset step size until the actual energy efficiency value is greater than or equal to the thermoelectric coupling energy efficiency benchmark, and the adjustment result is fed back to the energy management unit.

9. The method as described in claim 1, characterized in that, The heat load data is collected using a heat flow sensor.

10. The method as described in claim 1, characterized in that, The electrical load data is collected using a smart energy meter.

Images