Thermoelectric decoupling dynamic scheduling system based on efficient heat storage tank

Abstract

The invention relates to the technical field of energy scheduling and energy storage, and discloses a thermoelectric decoupling dynamic scheduling system based on an efficient heat storage tank, which comprises an energy storage module, a regulation and control module, a monitoring module and a dynamic adjustment module. The energy storage module adopts supercritical water as a heat storage medium, and heat loss is reduced through a multi-layer heat insulation structure; the regulation and control module predicts the thermoelectric load by using a deep learning algorithm to generate an optimal scheduling scheme; the monitoring module collects data in real time and detects abnormity; and the dynamic adjustment module flexibly executes heat storage or heat release operation according to the priority. The method can improve the heat storage efficiency, optimize the prediction precision of the thermoelectric load, and enhance the flexibility of the system, thereby reducing the energy waste, improving the heat supply stability and the energy utilization efficiency, and achieving the efficient and economical operation of the cogeneration system.

Description

Technical Field

[0001] The present invention relates to the field of energy scheduling and energy storage technology, and in particular to a thermoelectric decoupling dynamic scheduling system based on a high-efficiency heat storage tank. Background Art

[0002] With the widespread adoption of cogeneration systems, the tight coupling between thermal and electrical loads presents challenges in responding to diverse demands. Traditional thermal decoupling technologies and scheduling methods present the following major challenges: Regarding thermal storage technology, existing equipment often uses conventional water or phase change materials as the thermal storage medium, resulting in low energy density, large installation size, extensive floor space, and high investment costs. Furthermore, the low efficiency of heat storage and release limits performance under rapidly fluctuating thermal load demands. Regarding load forecasting, traditional methods often rely on simple statistical models or manual experience, making it difficult to accurately capture the complex dynamics of thermal loads. This compromises the scientific nature of scheduling decisions, easily leading to imbalances in thermal power supply and demand, and reducing heating stability and energy efficiency. Currently, scheduling methods are mostly based on fixed operating modes and parameters, lacking the ability to dynamically adjust to real-time thermal load changes, thermal storage status, and energy prices. This limits the regulatory role of thermal storage devices, impacting system flexibility and economic efficiency. Summary of the Invention

[0003] The present invention aims to provide a thermoelectric decoupling dynamic scheduling system based on high-efficiency thermal storage tanks. This system aims to address existing issues in the cogeneration field, such as low thermal storage efficiency, inaccurate load forecasting, and static scheduling. These issues lead to imbalances in thermal power supply and demand, poor heat supply stability, low energy efficiency, and high operating costs.

[0004] The embodiment of the present invention is implemented as follows: on the one hand, a thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank comprises:

[0005] The energy storage module is the main body of the thermal storage tank, which is used to: receive and store heat, where the heat comes from the excess heat energy generated by the cogeneration unit during power off-peak periods;

[0006] A control module is used to generate a dispatch instruction based on real-time thermal power demand and energy price changes, wherein the dispatch instruction includes at least a heat storage operation instruction and a heat release operation instruction;

[0007] The monitoring module is used to detect in real time the actual changes in thermal load, the temperature and pressure parameters of the energy storage module, and the price fluctuations in the external energy market;

[0008] The dynamic adjustment module is used to: when it is detected that the thermal load is higher than the preset value and the power supply is tight, control the energy storage module to release heat and reduce the power generation load of the cogeneration unit; when it is detected that the thermal load is lower than the preset value and the electricity price is low, control the energy storage module to store heat.

[0009] As a further solution of the present invention, the energy storage module specifically includes:

[0010] The medium selection unit is used to select supercritical water as the heat storage medium. Supercritical water has high specific heat capacity and high energy density characteristics when the temperature is higher than 374°C and the pressure is higher than 22.1MPa.

[0011] The structural optimization unit is used to design a multi-layer insulation structure to reduce heat loss. The inner layer uses ceramic fiber insulation material, the middle layer uses aerogel insulation material, and the outer layer is covered with a polyurethane foam insulation layer. The positions of the water inlet and outlet are optimized to make the flow of supercritical water in the tank more uniform, thereby improving heat exchange efficiency.

[0012] As a further solution of the present invention, the control module further includes:

[0013] Data collection unit, used to obtain historical thermal power load data, meteorological data, production plan data and energy price data;

[0014] A model building unit is used to build a thermal power load prediction model using a deep learning algorithm. The model uses a long short-term memory network (LSTM) or a convolutional neural network (CNN) to learn the time series characteristics of the thermal power load.

[0015] A strategy formulation unit is used to generate an optimal heat storage and release plan by combining the prediction results, the current status of the energy storage module, and energy price information.

[0016] As a further solution of the present invention, the monitoring module further includes:

[0017] Real-time data collection unit, used to collect temperature and pressure parameters of thermal and electrical loads, energy storage modules, and energy market price data in real time through a sensor network;

[0018] The anomaly detection unit is used to: trigger the dynamic adjustment module to increase the heat release of the energy storage module when it detects that the actual thermal power load exceeds the predicted value; and re-evaluate the timing of heat storage and heat release when it detects that the energy price fluctuates greatly.

[0019] As a further solution of the present invention, the dynamic adjustment module further includes:

[0020] A priority setting unit, used to set the priority of heat storage and heat release according to the urgency of thermal power load and the change range of energy price;

[0021] The execution unit is used to: perform heat storage or heat release operations in sequence according to the priority order, and feed back the operation results to the monitoring module in real time.

[0022] As a further solution of the present invention, the monitoring module further includes:

[0023] A user interaction unit is used to send system operation status information to the user terminal, including the current heat storage status of the energy storage module, thermal power load forecast results, and energy price trends;

[0024] The feedback unit is used to receive instructions from the user terminal, where the instructions include manually adjusting the timing and intensity of the heat storage or heat release operation.

[0025] As a further solution of the present invention, the water inlet and outlet of the energy storage module are connected to the cogeneration unit and the heating network through pipes respectively. Electric valves are provided on the pipes, and the electric valves are controlled by the dynamic adjustment module to achieve precise input and output of heat.

[0026] As a further solution of the present invention, the control module further includes:

[0027] A scenario adaptation unit is used to adjust the parameters of the thermal power load forecasting model according to the characteristics of different application scenarios, such as the differences in thermal power demand among industrial, commercial, and residential areas;

[0028] The optimization unit is used to further optimize the heat storage and release schemes through genetic algorithms or particle swarm optimization algorithms to improve the economy and flexibility of the system.

[0029] As a further solution of the present invention, the dynamic adjustment module further includes:

[0030] Redundant verification unit, used to verify the system's operating status before each heat storage or heat release operation to ensure operational safety;

[0031] The recovery unit is used to quickly restore the system to its pre-interruption state based on the records of the monitoring module when the system is interrupted due to a fault or abnormality.

[0032] As a further solution of the present invention, in the multi-layer insulation structure of the energy storage module, the thickness of the ceramic fiber insulation material is 50 mm, the thickness of the aerogel insulation material is 30 mm, and the thickness of the polyurethane foam insulation layer is 20 mm. The layers are fixedly connected by a high-temperature resistant adhesive to ensure the stability and sealing of the structure.

[0033] The present invention provides a thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank.

[0034] Beneficial effects:

[0035] By adopting supercritical water as the heat storage medium, the present invention significantly improves the energy density of the heat storage device, thereby reducing the equipment volume and floor space. The design of the multi-layer insulation structure effectively reduces heat loss and improves the heat storage and heat release efficiency. The thermoelectric load prediction model based on deep learning can accurately capture the changing trend of the thermoelectric load and provide a scientific basis for scheduling decisions. The dynamic adjustment module flexibly adjusts the heat storage and heat release operations according to real-time data, giving full play to the regulatory role of the energy storage module and enhancing the flexibility and economy of the system. Through the above-mentioned technical means, the present invention realizes the efficient operation of the cogeneration system, reduces energy waste, and improves the heating stability and energy utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a block diagram of the overall structure of the system of the present invention;

[0037] Figure 2 Schematic diagram of the internal structure of the energy storage module of the present invention;

[0038] Figure 3 This is a functional module diagram of the control module of the present invention;

[0039] Figure 4 This is a functional module diagram of the monitoring module of the present invention;

[0040] Figure 5 This is a functional module diagram of the dynamic adjustment module of the present invention;

[0041] Figure 6 Schematic diagram of the interaction between the user interaction unit and the feedback unit of the present invention;

[0042] Figure 7 This is a functional diagram of the scene adaptation unit and the optimization unit of the present invention;

[0043] Figure 8 This is a workflow diagram of the redundancy check unit and the recovery unit of the present invention. DETAILED DESCRIPTION

[0044] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] The embodiment of the present invention provides a thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank, the overall structure of which is as follows: Figure 1As shown in the figure, it includes energy storage module, control module, monitoring module and dynamic adjustment module. These modules cooperate with each other through data communication and physical connection to achieve efficient operation of the system. Figure 1 -Attached Figure 8 The specific implementation of each module is described in detail.

[0046] The energy storage module is the main body of the heat storage tank, which is one of the core components of the system. Its structure is as follows Figure 2 As shown, the system primarily comprises a multi-layer insulation structure and water inlets and outlets. The multi-layer insulation structure consists of ceramic fiber insulation, aerogel insulation, and a polyurethane foam insulation layer. The ceramic fiber insulation is 50 mm thick, the aerogel insulation is 30 mm thick, and the polyurethane foam insulation is 20 mm thick. The layers are secured together with a high-temperature-resistant adhesive to ensure structural stability and a tight seal. The water inlets and outlets are optimally positioned at the top and bottom of the energy storage module to ensure uniform flow of supercritical water within the tank. These inlets and outlets are connected to the cogeneration unit and the heating network via pipes equipped with electric valves controlled by a dynamic adjustment module. The energy storage module uses supercritical water as the thermal storage medium. Supercritical water, when heated above 374°C and under pressures exceeding 22.1 MPa, exhibits high specific heat capacity and high energy density, significantly increasing the energy density of the thermal storage device while reducing its size.

[0047] The functional module diagram of the control module is as follows Figure 3 As shown, the system includes a data collection unit, a model building unit, and a strategy formulation unit. The data collection unit acquires historical thermal power load data, meteorological data, production plan data, and energy price data through wired or wireless communication and transmits this data to the model building unit. The model building unit uses a deep learning algorithm to construct a thermal power load forecasting model. The model can choose a long short-term memory network (LSTM) or a convolutional neural network (CNN). By learning the time series characteristics of the thermal power load, it generates a thermal power load forecast for a period of time. The strategy formulation unit generates the optimal heat storage and release plan based on the forecast results, the current state of the energy storage module, and energy price information. The control module also includes a scenario adaptation unit and an optimization unit. The scenario adaptation unit adjusts the parameters of the thermal power load forecasting model based on the characteristics of different application scenarios, such as the differences in thermal power demand in industrial, commercial, and residential areas. The optimization unit further optimizes the heat storage and release plans using a genetic algorithm or a particle swarm optimization algorithm to improve the economy and flexibility of the system.

[0048] The functional module diagram of the monitoring module is as follows Figure 4As shown, it includes a real-time acquisition unit and an anomaly detection unit. The real-time acquisition unit collects the temperature and pressure parameters of the thermal power load, the energy storage module, and the external energy market price data in real time through the sensor network. These sensors are distributed in various key locations of the system, such as the water inlet and outlet of the energy storage module, the output end of the cogeneration unit, and the entrance of the heating network. The anomaly detection unit analyzes the collected data. When it is detected that the actual thermal power load exceeds the predicted value, it triggers the dynamic adjustment module to increase the heat release of the energy storage module; when it is detected that the energy price fluctuates greatly, the heat storage and heat release timing is re-evaluated. The monitoring module also includes a user interaction unit and a feedback unit, such as Figure 6 As shown, the user interaction unit sends the system's operating status information to the user terminal through the communication interface, including the current heat storage status of the energy storage module, the thermal power load forecast results, and the energy price trend; the feedback unit receives instructions from the user terminal, including manual adjustment of the time point and intensity of the heat storage or heat release operation.

[0049] The functional module diagram of the dynamic adjustment module is as follows Figure 5 As shown, it includes a priority setting unit, an execution unit, a redundancy check unit, and a recovery unit. The priority setting unit sets the priority of heat storage and heat release according to the urgency of the thermal power load and the fluctuation range of energy prices. The execution unit performs heat storage or heat release operations in sequence according to the priority order and feeds back the operation results to the monitoring module in real time. The redundancy check unit verifies the operating status of the system before each heat storage or heat release operation to ensure the safety of the operation. After the system is interrupted due to a fault or abnormality, the recovery unit quickly restores it to the state before the interruption based on the records of the monitoring module. The dynamic adjustment module is connected to the electric valve of the energy storage module through the communication interface to achieve accurate input and output of heat.

[0050] The system operates as follows: During periods of low electricity demand, excess heat generated by the cogeneration unit is transported via pipelines to the energy storage module, where supercritical water, acting as a heat storage medium, absorbs and stores the heat. The data collection unit in the control module acquires real-time data on thermal load, meteorological data, production plans, and energy prices, and transmits this data to the model building unit. The model building unit uses a deep learning algorithm to construct a thermal load forecasting model, generating a forecast for the future. The strategy formulation unit combines the forecast results with the current state of the energy storage module and energy price information to generate optimal heat storage and release strategies. The real-time data collection unit in the monitoring module uses a sensor network to collect data on the thermal load, temperature and pressure parameters of the energy storage module, and energy market prices. When the thermal load is detected to be above a preset value and electricity supply is tight, the dynamic adjustment module controls the energy storage module to release heat while reducing the generation load of the cogeneration unit. When the thermal load is detected to be below a preset value and electricity prices are low, the dynamic adjustment module controls the energy storage module to store heat. The user interaction unit sends the system's operating status information to the user terminal, and the feedback unit receives instructions from the user terminal to achieve human-computer interaction.

[0051] This system is suitable for a variety of application scenarios, such as industrial parks, commercial centers, and residential areas. In industrial parks, the demand for thermal power is large and fluctuates violently. The system's scenario adaptation unit can adjust the parameters of the thermal power load prediction model according to the industrial production plan. The optimization unit further optimizes the heat storage and heat release schemes through genetic algorithms or particle swarm optimization algorithms to meet the needs of industrial parks. In commercial centers, the demand for thermal power is relatively stable but there are peak periods. The system's monitoring module can detect changes in thermal power load in real time, and the dynamic adjustment module can flexibly adjust heat storage and heat release operations based on the detection results to ensure heating stability. In residential areas, the demand for thermal power is greatly affected by weather and time. The system's control module can accurately predict the thermal power load through deep learning algorithms, and the dynamic adjustment module can perform heat storage or heat release operations in advance based on the prediction results to improve heating efficiency.

[0052] In order to better enable relevant personnel in this technical field to fully understand and implement the present invention, the specific implementation principle of the present invention is supplemented below with reference to a specific application scenario.

[0053] In the application scenario of the industrial park, the operation process of the system is as follows: First, the excess heat energy generated by the cogeneration unit during the power off-peak period is transported to the energy storage module through a pipeline. After the electric valve is opened, supercritical water, as a heat storage medium, absorbs heat and stores it in the energy storage module at a temperature above 374°C and a pressure above 22.1MPa. The multi-layer insulation structure of the energy storage module consists of ceramic fiber insulation material, aerogel insulation material and polyurethane foam insulation layer. The layers are fixedly connected by high-temperature resistant adhesives to ensure that heat loss is minimized. The positions of the water inlet and outlet have been optimized and are located at the top and bottom of the energy storage module respectively, so that the flow of supercritical water in the tank is more uniform, thereby improving the heat exchange efficiency.

[0054] The data collection unit in the control module obtains historical thermal power load data, meteorological data, production plan data and energy price data in real time, and transmits these data to the model construction unit. The model construction unit uses a deep learning algorithm to build a thermal power load prediction model. The model can choose a long short-term memory network (LSTM) or a convolutional neural network (CNN). By learning the time series characteristics of the thermal power load, it generates a thermal power load prediction result for a period of time in the future. The strategy formulation unit generates the best heat storage and release scheme based on the prediction results, the current status of the energy storage module and energy price information. The scenario adaptation unit adjusts the parameters of the thermal power load prediction model according to the production plan of the industrial park. The optimization unit further optimizes the heat storage and release schemes through genetic algorithms or particle swarm optimization algorithms to meet the needs of the industrial park.

[0055] The real-time data acquisition unit in the monitoring module collects data on the thermal load, the temperature and pressure parameters of the energy storage module, and external energy market prices in real time through a sensor network. The anomaly detection unit analyzes this data. If the actual thermal load exceeds the predicted value, it triggers the dynamic adjustment module to increase the heat release of the energy storage module. If significant energy price fluctuations are detected, the timing of heat storage and release is reassessed. The user interaction unit transmits system operating status information to the user terminal via a communication interface, including the current heat storage status of the energy storage module, thermal load forecast results, and energy price trends. The feedback unit receives instructions from the user terminal, including manual adjustments to the timing and intensity of heat storage or release operations.

[0056] The priority setting unit in the dynamic adjustment module sets the priority of heat storage and heat release based on the urgency of the thermal power load and the fluctuation of energy prices. The execution unit performs heat storage or heat release operations in order of priority and provides real-time feedback to the monitoring module. The redundancy check unit verifies the system's operating status before each heat storage or heat release operation to ensure operational safety. If the system is interrupted by a fault or abnormality, the recovery unit quickly restores it to its pre-interruption state based on the monitoring module's records.

[0057] In a commercial center application scenario, the system operates as follows: Excess heat generated by the cogeneration unit during periods of low electricity consumption is transported via pipelines to the energy storage module, where supercritical water, acting as a heat storage medium, absorbs the heat and stores it. The data collection unit in the control module acquires historical thermal power load data, meteorological data, production plan data, and energy price data in real time and transmits this data to the model building unit. The model building unit uses a deep learning algorithm to construct a thermal power load forecasting model, generating forecasts for the future. The strategy development unit combines these forecasts with the current status of the energy storage module and energy price information to generate optimal heat storage and release plans.

[0058] The real-time data acquisition unit in the monitoring module uses a sensor network to collect data on the thermal load, the temperature and pressure parameters of the energy storage module, and external energy market prices. The anomaly detection unit analyzes this data. If the actual thermal load exceeds the predicted value, it triggers the dynamic adjustment module to increase the heat release of the energy storage module. If significant energy price fluctuations are detected, the timing of heat storage and release is reassessed. The dynamic adjustment module flexibly adjusts heat storage and release based on these detection results to ensure stable heating.

[0059] In a residential community application scenario, the system operates as follows: Excess heat generated by the cogeneration unit during periods of low electricity consumption is transported via pipelines to the energy storage module, where supercritical water, acting as a heat storage medium, absorbs the heat and stores it. The data collection unit in the control module acquires historical thermal power load data, meteorological data, production plan data, and energy price data in real time and transmits this data to the model building unit. The model building unit uses a deep learning algorithm to construct a thermal power load forecasting model, generating forecasts for the future. The strategy development unit combines these forecasts with the current status of the energy storage module and energy price information to generate the optimal heat storage and release plan.

[0060] The real-time data acquisition unit in the monitoring module uses a sensor network to collect data on the thermal load, the temperature and pressure parameters of the energy storage module, and external energy market prices. The anomaly detection unit analyzes this data. If the actual thermal load exceeds the predicted value, it triggers the dynamic adjustment module to increase the heat release of the energy storage module. If significant energy price fluctuations are detected, the timing of heat storage and release is reassessed. The dynamic adjustment module preempts heat storage or release based on the predicted results, improving heating efficiency.

[0061] Through the above steps, the system has achieved efficient operation in different application scenarios, significantly improved the flexibility and economy of the cogeneration system, reduced energy waste, and improved heating stability and energy utilization efficiency.

[0062] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank, characterized in that: include: An energy storage module is used to receive and store heat, the heat being derived from excess heat energy generated by the cogeneration unit during periods of low electricity consumption; A control module, configured to generate a dispatch instruction based on real-time thermal power demand and energy price changes, wherein the dispatch instruction includes at least a heat storage operation instruction and a heat release operation instruction; A monitoring module is used to detect in real time the actual changes in thermal load, the temperature and pressure parameters of the energy storage module, and price fluctuations in the external energy market; The dynamic adjustment module is used to control the energy storage module to release heat and reduce the power generation load of the cogeneration unit when it detects that the thermal load is higher than the preset value and the power supply is tight; when it detects that the thermal load is lower than the preset value and the electricity price is low, it controls the energy storage module to store heat.

2. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The energy storage module comprises: a medium selection unit for selecting supercritical water as a heat storage medium, wherein the supercritical water has high specific heat capacity and high energy density characteristics when the temperature is higher than 374°C and the pressure is higher than 22.1 MPa; The structural optimization unit is used to design a multi-layer insulation structure to reduce heat loss. The multi-layer insulation structure includes an inner layer of ceramic fiber insulation material, a middle layer of aerogel insulation material, and an outer layer of polyurethane foam insulation layer. The thickness of the ceramic fiber insulation material is 50 mm, the thickness of the aerogel insulation material is 30 mm, and the thickness of the polyurethane foam insulation layer is 20 mm. The layers are fixedly connected by a high-temperature resistant adhesive. The positions of the water inlet and outlet are optimized to make the flow of supercritical water in the tank more uniform.

3. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The control module also includes: Data collection unit, used to obtain historical thermal power load data, meteorological data, production plan data and energy price data; A model building unit, configured to build a thermal power load prediction model using a deep learning algorithm, wherein the model uses a long short-term memory network or a convolutional neural network to learn the time series characteristics of the thermal power load; The strategy formulation unit is used to generate the optimal heat storage and release plan by combining the prediction results, the current status of the energy storage module and energy price information.

4. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The monitoring module also includes: Real-time data collection unit, used to collect temperature and pressure parameters of thermal and electric loads, energy storage modules, and energy market price data in real time through a sensor network; The anomaly detection unit is used to trigger the dynamic adjustment module to increase the heat release of the energy storage module when it detects that the actual thermal power load exceeds the predicted value; when it detects that the energy price fluctuates greatly, it re-evaluates the timing of heat storage and heat release.

5. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The dynamic adjustment module also includes: A priority setting unit for setting the priority of heat storage and heat release according to the urgency of thermal power load and the variation range of energy price; The execution unit is used to perform heat storage or heat release operations in sequence according to the priority order and to feed back the operation results to the monitoring module in real time.

6. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The monitoring module also includes: A user interaction unit is used to send system operating status information to the user terminal, including the current heat storage status of the energy storage module, thermal power load forecast results, and energy price trends; The feedback unit is used to receive instructions from the user terminal, wherein the instructions include manually adjusting the time point and intensity of the heat storage or heat release operation.

7. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 1 is characterized in that: The water inlet and outlet of the energy storage module are connected to the cogeneration unit and the heating network through pipelines respectively. The pipelines are provided with electric valves, which are controlled by the dynamic adjustment module to achieve accurate input and output of heat.

8. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 3 is characterized in that: The control module also includes: A scenario adaptation unit, used to adjust the parameters of the thermal power load prediction model according to the characteristics of different application scenarios; The optimization unit is used to further optimize the heat storage and release schemes through genetic algorithm or particle swarm optimization algorithm.

9. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 5 is characterized in that: The dynamic adjustment module also includes: Redundant verification unit, used to verify the system's operating status before each heat storage or heat release operation to ensure operational safety; The recovery unit is used to quickly restore the system to the state before the interruption based on the records of the monitoring module when the system is interrupted due to a fault or abnormality.

10. The thermoelectric decoupling dynamic scheduling system based on a high-efficiency thermal storage tank according to claim 2 is characterized in that: The thicknesses of the ceramic fiber insulation material, aerogel insulation material and polyurethane foam insulation layer in the multi-layer insulation structure are 50 mm, 30 mm and 20 mm respectively. The layers are fixedly connected by a high-temperature resistant adhesive to ensure the stability and sealing of the structure.

Images