Method and system for intelligently adjusting chilled water storage strategy, and storage medium
By embedding control modules and deep learning algorithms in the water storage and cooling system, the operation strategy is adjusted according to the power grid carbon emission responsibility factor, and the problems of carbon emission complexity and dynamic response in the existing technology are solved, achieving efficient low-carbon operation and cost savings.
Patent Information
- Application Number
- CN202411193606.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-12
AI Technical Summary
The existing technology is difficult to effectively reduce carbon emissions in the water storage and cooling system while maintaining the economicality of peak cutting and valley filling, especially when the carbon emission responsibility factor level is the same as electricity price, dynamic response and optimization control are complex.
By embedding control modules in the water storage and cooling system, dynamically adjusting the operating strategy based on the carbon emission responsibility factor and building load status provided by the power grid, using deep learning algorithms to build target networks and action decision networks, and combining with deep Q network reinforcement learning algorithms, optimizing water storage and cooling The operating mode of the system in response to the grid's dynamic carbon emission responsibility factor.
It realizes intelligent scheduling of the water storage and cooling system under different electricity prices and carbon emission responsibility factors, improves the operating efficiency of buildings, reduces carbon emissions, and saves operating costs.
Smart Images

Figure CN118935564A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of deep learning and relates to a method for adjusting a cooling strategy for a building. Background Art
[0002] Considering the consistency of the time step between the building load and the grid load, the water storage technology can realize the transfer of the building load in the time span. This peak-shaving and valley-filling method is conducive to the peak-shaving of the building load and the grid load, and improves the overall operation economy of the system by concentrating cold storage only in the valley period of electricity price. The economy is mainly reflected in the difference in electricity charges caused by different electricity prices. Under the guidance of the dual carbon goals, the future electricity consumption behavior planning on the electricity side should not only focus on electricity consumption and electricity cost economy, but should comprehensively consider the carbon emission responsibility factor of electricity consumption. With the steady increase in the installed capacity of sustainable energy power generation such as wind power, solar power, and biomass power generation, the carbon emissions per unit of power generation in the power grid system have decreased, but the uncertainty of the carbon emission responsibility factor in time has also increased. When the level of the carbon emission responsibility factor is equal to the electricity price (such as the carbon trading price reaches more than 1,000 yuan per ton), the evaluation of the peak-shaving and valley-filling effect of water storage becomes more complicated. Therefore, by embedding a control module in the water storage system to respond to different regulation needs of the power grid is an effective way to reduce the carbon emissions of the system operation while maintaining the economy of peak-shaving and valley-filling. Integrating the response of the water storage cooling system to the dynamic carbon emission responsibility factor of the power grid in the response module to achieve low-carbon operation of the system is a shortcoming in the existing technology. The intelligentization of the power grid system and the digitization of parameters provide a path for obtaining carbon emission responsibility factors and related data, and also provide original data accumulation for big data analysis. For complex dynamic response and optimization control problems, it is necessary to optimize the water storage cooling system strategy and integrate it into a response module. Summary of the invention
[0003] Therefore, it is necessary to provide a method for adjusting the execution strategy of water storage cooling so that the water storage cooling system can operate better.
[0004] In this regard, the inventor provides a method for intelligently adjusting the water storage cooling strategy, which is applied to the water storage cooling system in the building, including the following steps: dynamically adjusting the operation strategy of the water storage cooling system according to the carbon emission responsibility factor provided by the power grid and the building load state parameters.
[0005] In one embodiment of the present application, the operation strategy includes:
[0006] Operation mode 1: The water storage system is the main cooling system, and the unit is the auxiliary cooling system. During the daytime flat and peak electricity price periods, the water storage system operates at its designed cooling capacity, and the part exceeding its designed cooling capacity is supplemented by the chiller; Operation mode 2 is mainly cooling by the chiller, and the excess is provided by the water storage system; Operation mode 3 gives priority to the cooling of the water storage system. After the cooling is released, the cooling load for the remaining time is entirely borne by the chiller; Operation mode 4 is that the chiller and the water storage system maintain a certain ratio for cooling; Operation mode 5 is the cooling storage mode of the water storage system. The chiller operates during the valley price period and stores the cold energy in the water tank of the water storage system to prepare for the cooling demand during the flat and peak periods.
[0007] In one embodiment of the present application, when the electricity price is a peak price, a judgment is made whether the cooling load of the building is a high level or a low level. When the cooling load of the building is judged to be a high level, operation mode one is implemented, and when the cooling load of the building is a low level, operation mode three is implemented; when the electricity price is a parity price, a judgment is made whether the current carbon emission responsibility factor is a high level or a low level. When the carbon emission responsibility factor is a high level, operation mode four is changed according to the high level of the cooling load of the building, and operation mode three is changed according to the low level of the cooling load of the building; when the carbon emission responsibility factor is a low level, the execution strategy is operation mode two; when the electricity price is a valley price, operation strategy five is implemented.
[0008] In one embodiment of the present application, the steps are also included, for determining the high level and low level of the carbon emission responsibility factor by a preset threshold, and for determining the high level and low level of the cooling load of the building by a preset another threshold.
[0009] In one embodiment of the present application, the strategy of the water storage cooling system is adjusted by a deep learning algorithm, specifically including the steps of recording s at different times i ,s (i+1) , a and R are stored in the experience pool as data sets for model training, where s i is the current state, s (i+1) is the state of the next step, a is the control action for the water storage system, R is the reward value, and R is positively correlated with electricity costs, carbon emissions, and building cooling load.
[0010] In one embodiment of the present application, the steps are also included, constructing a target network and an action decision network, performing reverse gradient training on the action decision network using a loss function, and updating the action decision network using the target function after a time step of a preset length.
[0011] In one embodiment of the present application, the steps are also included: in the pre-training stage, power grid-related big data is collected, the environmental neural network is constructed, the environmental model is trained, and the power grid-user environmental model is generated; in the training stage, the environmental model is called, the DON model is constructed, the DON model is trained, and the DON target and action decision network is saved; in the application stage, the trained DON model network is called, real-time power grid and user-side data are obtained, and the operation strategy of the water storage cooling system is controlled according to the power grid and user-side data.
[0012] A storage medium for intelligently adjusting a water cooling storage strategy stores a computer program, and when the computer program is executed, the method for intelligently adjusting a water cooling storage strategy as described above is performed.
[0013] A building with intelligent adjustment of water storage cooling strategy, comprising: a water storage cooling system, including a chiller, a cooling tower, a terminal device, and a data collector, wherein the data collector is used to obtain carbon emission responsibility factor information provided by a power grid, and is also used to monitor or collect cooling load information of the building;
[0014] A data processor, the data processor is used to dynamically adjust the operation strategy of the water storage cooling system according to the carbon emission responsibility factor and the building load state parameter provided by the power grid,
[0015] A system controller is used to apply the operation strategy of the water storage cooling system to each terminal.
[0016] In one embodiment of the present application, the data processor is used to execute the aforementioned method.
[0017] Different from the existing technology, the above scheme can formulate a water storage cooling working strategy through the carbon emission factor and the building load, which helps to improve the operating efficiency of the building, reduce carbon emissions and save operating costs. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:
[0019] Figure 1 It is a flow chart of a method for intelligently adjusting a water cooling storage strategy according to a specific implementation method;
[0020] Figure 2 It is a schematic diagram of adjusting the operation mode described in the specific implementation mode;
[0021] Figure 3 It is a schematic diagram of a water storage cooling strategy adjustment scheme described in a specific implementation method;
[0022] Figure 4A schematic diagram of a deep Q network reinforcement learning algorithm described in a specific implementation method;
[0023] Figure 5 A flowchart of the training and application of the algorithm described in the specific implementation method;
[0024] Figure 6 A schematic diagram of the building unit structure for the specific implementation of the Hong Kong style;
[0025] Figure 7 It is a flow chart of low-carbon intelligent control described in a specific implementation method. DETAILED DESCRIPTION
[0026] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.
[0027] The following detailed description is an exemplary description, which is intended to provide further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as those generally understood by those skilled in the art to which the present invention belongs. The terms used in the present invention are only for describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present invention.
[0028] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.
[0029] In the present application, terms such as “first” and “second” are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship of quantity, priority or sequence between these entities or operations.
[0030] Without further limitations, in this application, the words "include", "comprises", "has" or other similar expressions used in the sentences are intended to cover non-exclusive inclusion. These expressions do not exclude the presence of additional elements in the process, method or product including the elements, so that the process, method or product including a series of elements may include not only those limited elements, but also other elements not explicitly listed, or also include elements inherent to such process, method or product.
[0031] Similar to the understanding in the Examination Guidelines, in this application, expressions such as "greater than", "less than", "exceed" and the like are understood to exclude the number itself; expressions such as "above", "below", "within" and the like are understood to include the number itself. In addition, in the description of the embodiments of this application, "multiple" means more than two (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups", "multiple times", etc., unless otherwise clearly and specifically limited.
[0032] In the description of the embodiments of the present application, space-related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "vertical", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicate the orientation or position relationship based on the orientation or position relationship shown in the specific embodiments or drawings, and are only for the convenience of describing the specific embodiments of the present application or facilitating the reader's understanding, and do not indicate or imply that the referred device or component must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore cannot be understood as a limitation on the embodiments of the present application.
[0033] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.
[0034] The building in the present application may be a new type of building with built-in water medium for temperature control, which is connected to water storage equipment such as a cooling tower through pipelines. The water storage equipment may be set in the building or outside the building.
[0035] The water storage system in this application refers to a water-based storage system that can meet the cooling load of a building, which may include a refrigeration unit, a water pipe, a terminal cooling device, a water storage tower, etc. Simple liquid-cooled internal and external units at the household air conditioner level are not included in the discussion.
[0036] Please refer here Figure 1, is a method for intelligently adjusting the water storage cooling strategy, which is applied to the water storage cooling system in the building, and includes the following steps: S1 dynamically adjusts the operation strategy of the water storage cooling system according to the carbon emission responsibility factor provided by the power grid and the building load state parameter. Among them, the building load state parameter may include power load and cooling load. The power load can be obtained through monitoring devices such as electric meters, and the cooling load can be calculated by the difference between the preset temperature in the building and the ambient temperature. The preset temperature includes a set of preset control temperatures of each room. The carbon emission responsibility factor can be the trading price of carbon emissions. When it is found that the carbon emission factor is high, the water storage cooling system is more involved in cooling and the electric cooling is reduced. When the carbon emission factor is low, the water storage cooling system is less involved in cooling. On the other hand, when the overall power load of the building is large, the water storage cooling system is increased. When the overall power load of the building is small, the water storage cooling system is reduced to cool, and electricity is used for water storage. By designing the above-mentioned strategy adjustment, it is possible to better adjust and formulate a comprehensive water storage cooling work strategy, which helps to improve the operation efficiency of the building, reduce carbon emissions, and save operating costs.
[0037] In one embodiment of the present application, please see Figure 2 As shown in the figure, the operation strategies include: Operation mode 1: The water storage system is mainly used to release cold, and the unit is used to provide cooling. During the daytime flat and peak electricity price periods, the water storage system operates at its designed cooling capacity, and the part exceeding its designed cooling capacity is supplemented by the chiller; this method can ensure the stable operation of the water storage system, but the chiller may be frequently started and stopped and operate under partial load conditions. Operation mode 2 is mainly based on the chiller for cooling, and the excess is provided by the water storage system; in this method, the chiller can operate at its rated cooling capacity (full load state) and maintain high energy efficiency. In operation mode 3, the water storage system is given priority to release cold. After the cold capacity is released, the remaining cold load is completely borne by the chiller; operation mode 4 is to maintain a certain ratio between the chiller and the water storage system for cooling; operation mode 5 is the cold storage mode of the water storage system. The chiller operates during the valley price period and stores the cold capacity in the water tank of the water storage system to prepare for the cooling demand during the flat and peak periods. In addition, a certain amount of cooling output is maintained to handle the building cooling load during the valley price period. The above five cooling modes cover feasible system operation strategies under different power grids and building conditions. Based on the above strategy adjustment, this method achieves intelligent scheduling of system operation modes under different power grid carbon emission factors and user-side parameters.
[0038] Another Figure 3In the illustrated embodiment, it is demonstrated how to apply a specific water storage cooling strategy. When the electricity price is the peak price, a judgment is made whether the cooling load of the building is high or low. When the cooling load of the building is judged to be high, operation mode one is executed, and operation mode three is executed when the cooling load of the building is low. When the electricity price is the parity price, a judgment is made whether the current carbon emission responsibility factor is high or low. When the carbon emission responsibility factor is high, the operation mode is changed to operation mode four according to the high level of the cooling load of the building, and the operation mode is changed to operation mode three according to the low level of the cooling load of the building. When the carbon emission responsibility factor is low, the execution strategy is operation mode two; when the electricity price is the valley price, the operation strategy five is executed. The above process of formulating the operation mode according to the working conditions simply reflects the system operation concept and the response that the system should have by comprehensively considering the electricity price, carbon factor and building cooling load. In the actual application process, different operation modes can be adopted for one working condition. Users can judge and predict the low carbon nature under different operation modes according to the actual application scenarios. The realization of intelligent regulation is the core content of the present invention.
[0039] In some specific embodiments of the present application, the steps are also included, and the high and low levels of the carbon emission responsibility factor are determined by a preset threshold value, and the high and low levels of the building's cooling load are determined by another preset threshold value. By setting the carbon emission responsibility factor threshold, a level higher than the carbon emission responsibility factor threshold is a high level, and a level lower than or equal to the carbon emission responsibility factor threshold is a low level. Then, the cooling load threshold of the building is set, and a level higher than the cooling load threshold of the building is a high level, and a level lower than or equal to the cooling load threshold of the building is a low level. The above settings can realize intelligent adjustment of the operation strategy of the water storage cooling system.
[0040] In one embodiment of the present application, the strategy of the water storage cooling system is adjusted by a deep learning algorithm, specifically including the steps of recording s at different times i ,s (i+1) , a and R are stored in the experience pool as data sets for model training, where s i is the current state, s (i+1) is the state of the next step, a is the control action for the water storage system, R is the reward value, and R is positively correlated with electricity costs, carbon emissions, and building cooling load. The control action that maximizes the R value by taking the R value as the objective function can be used as the optimal strategy. In some further embodiments, the calculation method of the R value can be obtained by the following formula:
[0041]
[0042] Among them, δ1, δ2 and δ3 represent the weights of different factors, U(τ) represents the system electricity cost, C e (τ) represents the system carbon emissions, Q s (τ) represents the cooling capacity of the system, Q b(τ) represents the cooling load of the building. What is trained here is the neural network that maps the state variables to the value function value Q. The neural network can be better adjusted to achieve the technical effect of adjusting the strategy of the water storage cooling system.
[0043] In order to avoid overfitting of the neural network, the steps include constructing the target network and the action decision network, using the loss function to perform reverse gradient training on the action decision network, and updating the action decision network with the target function after a preset length of time step. Figure 4 In the illustrated embodiment, the deep Q network reinforcement learning algorithm written in the carbon factor response module of the present invention is demonstrated. The dotted line represents the training process when the environment interacts with the agent, and the solid line represents the control process of the agent. The environment in the figure represents the changes in the power grid system and the building load. During the control process, the agent gives a control action by observing the current state variables in the environment. Here, the current state variable si is the acquired real-time electricity price and carbon factor of the power grid and the cooling load of the building. The control action a is the selected water storage system operation mode. The neural network is divided into a target network and an action decision network. The action decision network is reverse gradient trained using the loss function, and the action decision network is updated with the objective function after a certain time step. The loss function is calculated by the following formula:
[0044] L
[0045] =E[(r+γ
[0046] Q target (s (i+1) , argmax(Q main (s (i+1) , a (i+1) )))-Q main (s i , a i )) 2 ]
[0047] Where L is the number calculated by the loss function, E is the expectation, r is the reward obtained at the current time step, γ is the discount factor for future rewards, and Q target is the Q value output by the target network, Q main Q value is the output of the action decision network. After judging the training termination condition, the trained neural network model is saved for practical application. By setting the objective function to the action decision network and the loss function between the two, overfitting can be avoided, and the deep learning method can be used to more accurately schedule the water storage cooling system strategy.
[0048] exist Figure 5In the illustrated embodiment, the method of the present invention further includes the steps of: collecting grid-related big data, constructing an environmental neural network, training an environmental model, and generating a grid-user environmental model in a pre-training stage; in the training stage, calling the environmental model, constructing a DON model, training the DON model, and saving the DON target and action decision network; in the application stage, calling the trained DON model network, acquiring real-time grid and user-side data, and controlling the operation strategy of the water storage cooling system according to the grid and user-side data.
[0049] A storage medium for intelligently adjusting a water cooling storage strategy stores a computer program, and when the computer program is executed, the method for intelligently adjusting a water cooling storage strategy as described above is performed.
[0050] Figure 6 The internal architecture diagram of the carbon factor response module in the present invention is shown. The module is mainly composed of four parts, including a data collector, a data storage device, an algorithm processor (data processor) and a system controller. The data collector is responsible for communication and data collection with the power grid system and the building side. The collected data is stored in the data storage device while being transmitted to the algorithm processor. The stored data will transmit the data set to the algorithm processor during the algorithm training phase. During the algorithm application phase, the algorithm processor only reads real-time data. The algorithm processing includes a deep Q network deep learning algorithm model and callable trained model parameters. After inputting real-time data, a control signal is output to the system controller. After receiving the control signal, the system controller controls the operating mode of the water storage cooling system. The operating status of the water storage cooling system is finally fed back to the power grid system and the building side to update the real-time parameters.
[0051] In a specific embodiment, this solution also provides a building that intelligently adjusts the water storage strategy. Figure 6 It includes: a water storage cooling system, including a chiller, a cooling tower, and terminal equipment; a data collector, which is used to obtain carbon emission responsibility factor information provided by the power grid and is also used to monitor or collect cooling load information of the building; a data processor, which is used to dynamically adjust the operation strategy of the water storage cooling system according to the carbon emission responsibility factor provided by the power grid and the building load state parameters; and a system controller, which is used to apply the operation strategy of the water storage cooling system to each terminal. Figure 7The schematic diagram also shows the process of the carbon factor response module performing low-carbon intelligent control on the water storage system. The module can be installed nearby to the chiller controller of the water storage system, or it can be integrated into the building energy management system as a controller. The grid side sends a carbon signal to the response module, and the module receives the monitored internal load of the building. The internal algorithm of the response module calculates the Q value based on the collected data, evaluates the low-carbon nature of different system operation modes, and obtains the optimal system operation mode, thereby outputting the control strategy for the water storage system.
[0052] In some preferred embodiments, the data processor can be used to call the aforementioned storage medium, and can also be used to execute the executable program in the storage medium to perform the method for adjusting water cooling.
[0053] It is known from common technical knowledge that the present invention can be implemented by other embodiments that do not deviate from its spirit or essential features. Therefore, the above disclosed embodiments are only illustrative in all respects and are not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are included in the present invention.
[0054] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0055] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0056] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
Claims
1. A method for intelligently adjusting a water cooling strategy, characterized in that: The water storage chilled system used in buildings includes the following steps: The operation strategy of the water storage cooling system is dynamically adjusted according to the carbon emission responsibility factor provided by the power grid and the building load status parameters.
2. The method for intelligently adjusting the water storage cooling strategy according to claim 1, characterized in that: The operation strategy includes: Operation mode 1: The water storage system is the main cooling system, and the unit is the auxiliary cooling system. During the daytime flat and peak electricity price periods, the water storage system operates at its designed cooling capacity, and the part exceeding its designed cooling capacity is supplemented by the chiller; Operation mode 2 is mainly cooling by the chiller, and the excess is provided by the water storage system; Operation mode 3 gives priority to the cooling of the water storage system. After the cooling is released, the cooling load for the remaining time is entirely borne by the chiller; Operation mode 4 is that the chiller and the water storage system maintain a certain ratio for cooling; Operation mode 5 is the cooling storage mode of the water storage system. The chiller operates during the valley price period and stores the cold energy in the water tank of the water storage system to prepare for the cooling demand during the flat and peak periods.
3. The method for intelligently adjusting the water storage cooling strategy according to claim 2, characterized in that: When the electricity price is at the peak price, it is judged whether the cooling load of the building is high or low. When the cooling load of the building is judged to be high, operation mode 1 is implemented, and when the cooling load of the building is low, operation mode 3 is implemented; When the electricity price is parity, it is determined whether the current carbon emission responsibility factor is high or low. When the carbon emission responsibility factor is high, the operation mode is changed to operation mode 4 according to the high level of the building cooling load, and the operation mode is changed to operation mode 3 according to the low level of the building cooling load; when the carbon emission responsibility factor is low, the execution strategy is operation mode 2; When the electricity price is at the valley price, operation strategy five is executed.
4. The method for intelligently adjusting the water storage cooling strategy according to claim 3 is characterized in that: The method also includes steps of determining a high level or a low level of a carbon emission responsibility factor by preset threshold values, and determining a high level or a low level of a cooling load of a building by preset another threshold value.
5. The method for intelligently adjusting the water storage cooling strategy according to one of claims 2 or 3, characterized in that: The strategy of the water storage cooling system is adjusted through the deep learning algorithm, including the steps of recording the s at different times i ,s (i+1) , a and R are stored in the experience pool as data sets for model training, where s i is the current state, s (i+1) is the state of the next step, a is the control action for the water storage system, R is the reward value, and R is positively correlated with electricity costs, carbon emissions, and building cooling load.
6. The method for intelligently adjusting the water storage cooling strategy according to claim 5, characterized in that: The method also includes steps of constructing a target network and an action decision network, performing reverse gradient training on the action decision network using a loss function, and updating the action decision network using the target function after a time step of a preset length.
7. The method for intelligently adjusting the water storage cooling strategy according to claim 6, characterized in that: It also includes the steps of: collecting power grid-related big data, building an environmental neural network, training an environmental model, and generating a power grid-user environmental model in a pre-training phase; During the training phase: calling the environment model, building the DON model, learning and training the DON model, and saving the DON target and action decision network; In the application stage: call the trained DON model network, obtain real-time power grid and user-side data, and control the operation strategy of the water storage cooling system according to the power grid and user-side data.
8. A storage medium for intelligently adjusting water storage cooling strategy, characterized in that: A computer program is stored, and when the computer program is executed, the method for intelligently adjusting the water storage cooling strategy as described in any one of claims 1 to 7 is performed.
9. A building with intelligent adjustment of water storage strategy, characterized in that: include: Water storage cooling system, including chillers, cooling towers, and terminal equipment. A data collector, the data collector is used to obtain carbon emission responsibility factor information provided by the power grid, and is also used to monitor or collect cooling load information of the building; A data processor, the data processor is used to dynamically adjust the operation strategy of the water storage cooling system according to the carbon emission responsibility factor and the building load state parameter provided by the power grid, A system controller is used to apply the operation strategy of the water storage cooling system to each terminal.
10. The building with intelligent adjustment of water storage strategy according to claim 9, characterized in that: The data processor is configured to execute the method according to any one of claims 2 to 8.
Citation Information
Cited By
Multi-target control strategy optimization method for intelligent cold release scheduling of chilled water storage system
CN120450492A
Multi-objective control strategy optimization method for intelligent cooling scheduling of chilled water storage system
CN120450492B
Energy-saving and carbon-reducing refrigeration control method and system for building
CN120627324A
A method and system for energy-saving and carbon-reducing refrigeration control in buildings
CN120627324B
