Efficient energy-saving refrigeration and heat supply method for central air conditioner

Abstract

The invention relates to an efficient energy-saving refrigeration and heat supply method for a central air conditioner. The method comprises the steps that user expected information, air conditioning equipment information and environment parameter information are obtained; based on the user expected information, the air conditioning equipment information and the environment parameter information, effectiveness judgment is conducted on the first central air conditioner operation strategy; if the first central air conditioner operation strategy is judged to be invalid, user expected information and environment parameter information are input into an edge strategy generation model, and a second central air conditioner operation strategy is generated; and the first central air conditioner operation strategy is updated based on the second central air conditioner operation strategy, and refrigeration equipment information and / or heating equipment information of the central air conditioner are / is adjusted based on the updated first central air conditioner operation strategy. By adopting the method, the user experience can be improved, the operation efficiency is improved, the energy consumption is reduced, the system adaptability is enhanced and the management process is simplified.

Description

Technical Field

[0001] The present invention belongs to the field of central air conditioning systems, and in particular to a method for high-efficiency energy-saving refrigeration and heating of central air conditioning. Background Technology

[0002] With the development of modern architecture, central air conditioning systems are widely used in various places, such as commercial buildings, office buildings, large residential buildings, etc. However, traditional central air conditioning systems usually adopt a relatively fixed operation mode, which is difficult to flexibly and accurately adjust according to actual needs. As a result, in some cases, central air conditioning cannot be dynamically adjusted according to real-time load conditions and environmental changes, resulting in excessive energy consumption and low energy utilization efficiency.

[0003] In traditional technology, some existing central air conditioning energy-saving control systems can achieve energy-saving effects to a certain extent, but most systems rely only on environmental data. Energy-saving strategies formulated without fully considering user behavior characteristics often fail to achieve the best energy-saving effects and user experience. In addition, existing technologies usually adopt a single optimization goal in the process of formulating energy-saving strategies, failing to take into account both energy saving and user comfort. In addition, the existing central air conditioning cold and heat source centralized control system has a low degree of integration, and lacks effective coordination and integration between modules, resulting in difficulties in system maintenance and upgrades. SUMMARY OF THE INVENTION

[0004] Based on this, it is necessary to provide a central air-conditioning high-efficiency energy-saving cooling and heating method that can improve the comprehensive performance of the central air-conditioning system in terms of operating efficiency, energy utilization, user comfort, adaptability and management convenience in response to the above technical problems.

[0005] This application provides a method for high-efficiency energy-saving cooling and heating of a central air conditioner, comprising: Obtain user expectation information, air conditioning equipment information and environmental parameter information. Air conditioning equipment information includes refrigeration equipment information and heating equipment information; Based on the user expectation information, the air conditioning equipment information and the environmental parameter information, the effectiveness of the first central air conditioning operation strategy is judged, and the first central air conditioning operation strategy is used to characterize the real-time operation status of the air conditioning equipment of the central air conditioner; If the first central air-conditioning operation strategy is judged to be invalid, the user expectation information and environmental parameter information are input into the edge strategy generation model to generate a second central air-conditioning operation strategy, which is used to characterize the expected operation state of the central air-conditioning air conditioning equipment; The first central air conditioner operation strategy is updated based on the second central air conditioner operation strategy, and the refrigeration equipment information and / or heating equipment information of the central air conditioner is adjusted based on the updated first central air conditioner operation strategy.

[0006] The above-mentioned central air-conditioning efficient and energy-saving cooling and heating method can better understand the user's personalized needs by obtaining user expectation information, thereby providing a more accurate and comfortable indoor environment; through the edge strategy generation model, the system can generate a more optimized operation strategy based on user expectation information and environmental parameter information, thereby reducing unnecessary equipment startup and shutdown, avoiding frequent equipment switching, and improving the equipment's operating efficiency; through the edge strategy generation model, the system can generate a more optimized operation strategy to enable the equipment to operate in the most energy-saving mode; by automatically judging the effectiveness of the operation strategy and automatically generating a new operation strategy when the strategy fails, it can reduce manual intervention and make the management of the central air-conditioning system more automated and intelligent. Brief Description of the Figures

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of the application environment of a method for high-efficiency energy-saving cooling and heating of a central air conditioner provided by an embodiment of the present application; Figure 2 A flow chart of a method for high-efficiency energy-saving cooling and heating of a central air conditioner provided in one embodiment of the present application; Figure 3 A schematic diagram of a control system for efficient energy-saving cooling and heating of a central air conditioner provided in one embodiment of the present application; Figure 4 A flow chart of another method for high-efficiency energy-saving cooling and heating of a central air conditioner provided in one embodiment of the present application; Figure 5 A schematic diagram of a control strategy prediction and control model optimization process provided by an embodiment of the present application; Figure 6 A schematic diagram of a flow chart of regulating air conditioning equipment based on a control strategy provided in one embodiment of the present application; Figure 7 A flow chart of another method for high-efficiency energy-saving cooling and heating of a central air conditioner provided in one embodiment of the present application; Figure 8 This is a schematic diagram of the structure of a central air-conditioning high-efficiency energy-saving cooling and heating system provided by one embodiment of the present application. Specific implementation method

[0009] In order to make the purpose, technical solutions and advantages of this application more clear, the following is a further detailed description of this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0010] The central air-conditioning high-efficiency energy-saving cooling and heating method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the edge computing device 101 communicates with the working device 103 and the sensor device 102 through a communication channel. The data storage system can store the data that the edge computing device 101 needs to process. The data storage system can be integrated on the edge computing device 101, or it can be placed on the cloud or other network servers. The edge computing device 101 can generate control information based on the sensor data obtained by the sensor device 102, and the edge computing device 101 can control the operating state of the working device 103 based on the generated control information. Among them, the edge computing device 101 can be, but not limited to, various single-chip microcomputers, personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The sensor device 102 can include, but is not limited to, temperature sensors, humidity sensors, infrared sensors, radio frequency sensors, Bluetooth sensors, air quality sensors, flow sensors, and light sensors. The working equipment 103 may include, but is not limited to, a compressor, a condenser, an evaporator, a throttle, a fan coil, a cooling tower, a refrigeration pump, a fresh air unit, a boiler, a heat pump, a solar collector, an electric heater, and a heat recovery device.

[0011] In an exemplary embodiment, as Figure 2 shows a method for high-efficiency energy-saving cooling and heating of a central air conditioner, which is applied to Figure 1 The edge computing device 101 in is used as an example to illustrate, including the following steps S201 to S204. Among them: Step S201, obtaining user expectation information, air conditioning equipment information and environmental parameter information.

[0012] Specifically, the edge computing device 101 may obtain user expectation information, air conditioning equipment information, and environmental parameter information. The air conditioning equipment information may include refrigeration equipment information and heating equipment information.

[0013] Optionally, the user's expected information may include but is not limited to expected temperature setting, expected humidity control range, expected switch setting, expected scene mode and expected partition control.

[0014] Optionally, the air conditioning equipment information may include but is not limited to equipment type information, operation mode information, energy efficiency ratio information, operation load ratio information and fault information.

[0015] Optionally, the environmental parameter information may include but is not limited to indoor and outdoor environmental difference information, expected environmental information, and real-time environmental information of work zones. The indoor and outdoor environmental difference information may include but is not limited to air pollution index difference information, temperature difference information, humidity difference information, solar radiation information, wind field information, and season information.

[0016] Step S202, judging the effectiveness of the first central air-conditioning operation strategy based on user expectation information, air conditioning equipment information and environmental parameter information.

[0017] Specifically, the edge computing device 101 can judge the effectiveness of the first central air-conditioning operation strategy that has been deployed and is being implemented based on the acquired user expectation information, air conditioning equipment information and environmental parameter information. The first central air-conditioning operation strategy can be used to characterize the real-time operation status of the air conditioning equipment of the central air-conditioning.

[0018] Illustratively, the edge computing device 101 can evaluate the effectiveness of the first central air-conditioning operation strategy from three dimensions: user demand satisfaction, equipment operation efficiency, and environmental adaptability, based on the acquired user expectation information, air conditioning equipment information, and environmental parameter information. Among them, the user demand satisfaction dimension may include but is not limited to determining whether the set user expectation information is achieved after a preset response cycle; the equipment operation efficiency dimension may include but is not limited to determining the degree of deviation between the equipment operation status and the design performance and whether the load distribution of each device in the multi-unit system is reasonable; environmental adaptability may include but is not limited to determining whether the environmental parameters exceed the equipment design conditions and determining whether the air conditioning equipment information matches the user expectation information under the environmental conditions corresponding to the environmental parameter information.

[0019] Optionally, the expression of the first central air-conditioning operation strategy effectiveness evaluation model can be: ; Where, is the effectiveness evaluation model of the first central air-conditioning operation strategy, and They are user expectation coefficient and equipment status coefficient respectively, 、 and They are user expectation item, environment adaptation item and device status item, is the user's expected fuzzy function, For The actual value of the environmental parameters at the moment, For The user's expected environmental parameter value at is the total number of environmental parameters, For the first The weight coefficient of the environmental parameter, For the first Environmental adaptation fuzzy function of environmental parameters, 、 and Respectively Outdoor value, indoor value and reference value of environmental parameters, is the total number of air conditioning equipment, 、 、 and Respectively The weight coefficient, actual energy consumption, set energy consumption and performance coefficient of each air conditioning equipment, is the total number of physical properties of the air regulated by the central air conditioner, and They are respectively the first The weight parameters and allowable error parameters of the physical properties of the air, and They are The moment of Measurements and setpoints of various physical properties of air.

[0020] Step S203: If the first central air-conditioning operation strategy is judged to be invalid, the user expectation information and environmental parameter information are input into the edge strategy generation model to generate a second central air-conditioning operation strategy.

[0021] For details, please refer to Figure 3 , if the first central air-conditioning operation strategy is judged to be invalid, the edge computing device 101 can input the user expectation information and environmental parameter information into the edge strategy generation model mounted on the edge computing device 101 to generate a second central air-conditioning operation strategy, which can be used to characterize the expected operation state of the central air-conditioning air conditioning equipment.

[0022] Optionally, the expected operating state of the air conditioning equipment may include but is not limited to specific parameters such as the start-up time, operating power and adjustment mode of the refrigeration equipment and / or heating equipment.

[0023] Optionally, the edge strategy generation model can be, but is not limited to, a BP neural network model, a fuzzy logic model, and a deep learning model and a reinforcement learning model optimized based on the TinyML algorithm. Among them, the deep learning model optimized based on the TinyML algorithm can be, but is not limited to, a convolutional neural network model and a recurrent neural network (RNN) and its variants (LSTM, GRU), and the reinforcement learning model optimized based on the TinyML algorithm can be, but is not limited to, a deep Q network model.

[0024] Step S204: updating the first central air conditioner operation strategy based on the second central air conditioner operation strategy, and adjusting the refrigeration equipment information and / or heating equipment information of the central air conditioner based on the updated first central air conditioner operation strategy.

[0025] Specifically, the edge computing device 101 can update the current first central air-conditioning operation strategy based on the second central air-conditioning operation strategy generated by the edge strategy generation model mounted on the edge computing device 101, and adjust the refrigeration equipment information and / or heating equipment information of the central air-conditioning based on the updated first central air-conditioning operation strategy.

[0026] Illustratively, when in a specific scenario where both cooling and heating are required, the edge computing device 101 can adjust the cooling equipment information and heating equipment information of the central air conditioner based on the updated first central air conditioner operation strategy; when only cooling is required, the edge computing device 101 can adjust the cooling equipment information of the central air conditioner based on the updated first central air conditioner operation strategy; when only heating is required, the edge computing device 101 can adjust the heating equipment information of the central air conditioner based on the updated first central air conditioner operation strategy.

[0027] In the above-mentioned central air-conditioning efficient and energy-saving cooling and heating method, by real-time collection of user expectations, equipment status and environmental parameters, combined with edge computing to generate the optimal operation strategy, it is possible to avoid energy waste caused by traditional fixed modes; by immediately generating a new strategy when it is detected that the current strategy cannot meet the energy efficiency target, it is possible to prevent inefficient operation from continuing to consume energy; by deploying the strategy generation model on the edge, bypassing the cloud data transmission delay, it is possible to quickly respond to environmental changes, ensure that equipment parameters are quickly and accurately adjusted, and when the network is interrupted, the edge can still maintain operation, which can avoid system paralysis.

[0028] In one of the optional embodiments, please refer to Figure 3 and Figure 4 , input the user expectation information and environmental parameter information into the edge strategy generation model to generate the second central air conditioning operation strategy, and then also include: Step S304: Input the user expectation information and environmental parameter information into the central strategy generation model to generate the third central air conditioning operation strategy.

[0029] Specifically, the edge computing device can transmit the user expectation information and environmental parameter information to the central computing device through the communication channel, and can input the user expectation information and environmental parameter information into the central strategy generation model carried by the central computing device to generate the third central air-conditioning operation strategy. The central computing device can be an Internet of Things central device.

[0030] Step S305: Update the second central air conditioning operation strategy based on the third central air conditioning operation strategy.

[0031] Step S307, optimizing the edge strategy generation model based on the third central air conditioning operation strategy.

[0032] Specifically, the edge computing device can optimize the edge strategy generation model that can be carried by the edge computing device based on the third central air conditioning operation strategy, and the edge computing device can be a networked edge device.

[0033] In the above-mentioned method for efficient and energy-saving cooling and heating of central air conditioners, by simultaneously inputting user expectation information and environmental parameter information into the edge strategy generation model and the central strategy generation model, the second and third central air conditioner operation strategies are generated, which can realize a multi-layer optimization mechanism, can better cope with complex and changing environments and user needs, and improve the overall optimization effect; through the collaborative work of the edge strategy generation model and the central strategy generation model, real-time feedback and adjustment can be realized to ensure the accuracy and effectiveness of the strategy; by optimizing the edge strategy generation model based on the third central air conditioner operation strategy, the performance of the edge strategy generation model can be continuously improved, and then the edge strategy generation model can be continuously learned and improved in actual applications, improving the quality and accuracy of its generated strategy; through the collaborative work of the edge strategy generation model and the central strategy generation model, automatic operation strategy optimization can be realized, reducing the need for manual intervention, which can not only reduce management complexity, but also improve the reliability and stability of the system.

[0034] In one of the optional embodiments, please refer to Figure 3 , the central policy generation model carried by the central computing device can be a deep learning neural network model, and the central policy generation model can include an improved convolution module and an improved converter module.

[0035] The edge strategy generation model carried by the edge computing device can be an improved BP neural network, and the improved BP neural network is obtained by distilling the central strategy generation model into the initial BP neural network.

[0036] ​Among them, the loss function of the central strategy generation model is a multi-objective comprehensive loss function, and the expression of the multi-objective comprehensive loss function is: ; Where, is a multi-objective comprehensive loss function, 、 、 and They are energy efficiency loss, adjustment target loss, strategy stability loss and strategy classification loss, 、 、 and They are energy efficiency loss parameter, adjustment target loss parameter, strategy stability loss parameter and strategy classification loss parameter, is the total number of air conditioning equipment, 、 and Respectively The actual energy consumption, set energy consumption and performance coefficient of each air conditioning equipment, is the number of environmental data samples, is the total number of physical properties of the air regulated by the central air conditioner, and They are respectively the first The weight parameters and allowable error parameters of the physical properties of the air, and Respectively The second sampling time Measurement and setting values ​​of various physical properties of air, is the total number of adjustment parameters of the third central air conditioning operation strategy and the first central air conditioning operation strategy, and are the third central air conditioning operation strategy th adjustment parameter and The output corresponding to the adjustment parameters, and are the first central air conditioning operation strategy th adjustment parameter and The output corresponding to the adjustment parameters, and Respectively The maximum and minimum output values ​​corresponding to the adjustment parameters, is the adjustment parameter coefficient, is the output coefficient of the adjustment parameter, is the number of samples, is the number of categories of the third central air-conditioning operation strategy, is the balance factor, ​is the focus parameter, Generate a model for the central strategy for the first The sample belongs to The predicted probability of the class.

[0037] Symbolically, when the air conditioning equipment is a refrigeration equipment, the performance coefficient of the air conditioning equipment can be: ; Where, is the refrigeration performance coefficient of the refrigeration equipment, is the cooling rate, is the actual input power.

[0038] Indicatively, when the air conditioning equipment is a heating equipment, the performance coefficient of the air conditioning equipment can be: ; Where, is the heating performance coefficient of the heating equipment, is the heating rate, is the actual input power.

[0039] In the above-mentioned central air-conditioning efficient energy-saving cooling and heating method, by combining deep learning and improved BP neural network, a multi-objective comprehensive loss function is adopted, which can comprehensively consider energy efficiency, adjustment objectives, strategy stability and strategy classification, etc., to generate efficient, accurate and stable operation strategies, thereby significantly improving the operation efficiency and management effect of the central air-conditioning system.

[0040] In one of the optional embodiments, please refer to Figure 5 , a method for high-efficiency energy-saving cooling and heating of central air conditioner, further comprising: Step S501, obtaining information on the proportion of time during which the first central air-conditioning operation strategy is judged to be invalid within a preset sampling period.

[0041] Specifically, the expression of duration ratio information is: ; Where, is the duration ratio information, is the sampling period, is the number of times the first central air-conditioning operation strategy is judged to be invalid within the sampling period, For the first The sampling history coefficient attenuation term when the first central air-conditioning operation strategy is judged to be ineffective, For the first The sampling history time when the first central air-conditioning operation strategy was judged to be invalid, For the first ​The strategy adjustment fuzzy coefficient term when the first central air-conditioning operation strategy is judged to be ineffective, For the first The adjustment parameters when the first central air-conditioning operation strategy is judged to be ineffective, For the first The adjustment parameters of the second central air conditioning operation strategy corresponding to the first central air conditioning operation strategy after it is judged to be invalid, For the first The duration when the first central air-conditioning operation strategy is judged to be ineffective.

[0042] Optional, first The sampling history coefficient attenuation term when the first central air conditioning operation strategy is judged to be ineffective The expression of can be: ; Where, and are the proportional coefficient and exponential decay coefficient of the sampling history, is the upper limit coefficient of sampling history impact.

[0043] Step S502: If the duration ratio information exceeds the preset normal threshold of the working environment, the future change trend of the central air-conditioning operation demand is predicted based on the edge strategy prediction model, and the fourth central air-conditioning operation strategy and the first activation timing information of the fourth central air-conditioning operation strategy are generated.

[0044] For details, please refer to Figure 3 , if the duration ratio information exceeds the preset normal threshold of the working environment, the edge computing device can predict the future change trend of the central air-conditioning operation demand based on the edge strategy prediction model installed on the edge computing device, generate the fourth central air-conditioning operation strategy and the first activation timing information corresponding to the fourth central air-conditioning operation strategy, and the fourth central air-conditioning operation strategy is used to update the first central air-conditioning operation strategy at the time corresponding to the first activation timing information.

[0045] In the above-mentioned central air-conditioning efficient energy-saving cooling and heating method, by obtaining the time proportion information of the first central air-conditioning operation strategy being judged as invalid within the preset sampling period, the system can monitor the effectiveness of the operation strategy in real time; by updating the first central air-conditioning operation strategy at the predicted future time, the central air-conditioning can better adapt to changes in the environment and user needs, and improve the accuracy and effectiveness of the operation strategy.

[0046] In one of the optional embodiments, please refer to Figure 5 ​, if the duration ratio information exceeds the preset normal environment threshold, the future central air-conditioning operation demand change trend is predicted based on the edge strategy prediction model, and the fourth central air-conditioning operation strategy and the activation timing information of the fourth central air-conditioning operation strategy are generated. After that, it also includes: Step S503, inputting the user expectation information and the environmental parameter information into the central strategy prediction model, generating the fifth central air conditioning operation strategy and the second activation timing information of the fifth central air conditioning operation strategy.

[0047] Step S504, updating the fourth central air conditioner operation strategy based on the fifth central air conditioner operation strategy, and updating the first activation timing information based on the second activation timing information.

[0048] Step S505, optimizing the edge strategy generation model, the edge strategy prediction model and the central strategy generation model based on the fifth central air conditioning operation strategy.

[0049] For details, please refer to Figure 3 , the edge strategy generation model and edge strategy prediction model mounted on the edge computing device and the central strategy generation model mounted on the central computing device can be optimized based on the fifth central air conditioning operation strategy mounted on the central computing device.

[0050] In the above-mentioned method of efficient and energy-saving cooling and heating of central air conditioners, by combining the edge strategy prediction model and the central strategy prediction model prediction, it is possible to predict the changing trend of the future central air conditioner operation demand in advance, generate and update reasonable operation strategies and activation timing information, thereby improving the operation efficiency, response speed and stability of the central air conditioner, as well as improving user satisfaction and the overall performance of the central air conditioner.

[0051] In one optional embodiment, the edge strategy prediction model may be a regression prediction model.

[0052] The central policy prediction model can be constructed based on an improved converter model and an improved long short-term memory network, and the improved converter model can include a residual convolution module.

[0053] In one of the optional embodiments, such as Figure 6 As shown, obtain user expectation information, air conditioning equipment information and environmental parameter information, including: Step S601, obtaining indoor environment information, outdoor environment information, user tag information and user control instructions.

[0054] Specifically, the edge computing center can obtain indoor environment information, outdoor environment information, user tag information and user control instructions based on sensor devices. Among them, user control instructions can include mode control instructions, target control instructions and wind speed control instructions.

[0055] Optionally, the target control instruction may include a partitioned temperature control instruction, a partitioned humidity control instruction, and a partitioned air quality control instruction.

[0056] Step S602, generating environmental parameter information based on indoor environmental information and outdoor environmental information.

[0057] Step S603, generating user expectation information based on user tag information, user control instructions and environmental parameter information.

[0058] Optionally, the edge computing device can obtain user tag information that covers the user's basic attributes, living habits, and usage scenarios based on user registration information, questionnaires, and historical usage records; the edge computing device can obtain user control instructions and environmental parameter information based on sensors. Among them, the environmental parameter information may include but is not limited to outdoor temperature information, outdoor humidity information, outdoor light intensity information, outdoor air quality information, indoor temperature information, indoor humidity information, indoor light intensity information, indoor air quality information, season information, weather information, and indoor occupancy information.

[0059] Step S604, setting the air conditioning equipment information to refrigeration equipment information and / or heating equipment information based on the environmental parameter information and the user's expected information.

[0060] In principle, the edge computing device can identify the working scenario of the central air conditioner based on the environmental parameter information and the user's expected information - if both cooling and heating are required, the air conditioning equipment information is set to the cooling equipment information and the heating equipment information; if only cooling is required, the air conditioning equipment information is set to the cooling equipment information; if only heating is required, the air conditioning equipment information is set to the heating equipment information.

[0061] In the above-mentioned central air-conditioning high-efficiency energy-saving cooling and heating method, by comprehensively collecting user expectation information, air conditioning equipment information and environmental parameter information, and conducting comprehensive analysis and optimization, it is possible to improve system reliability, optimize operation strategies, improve energy utilization efficiency, enhance system adaptability, reduce management complexity, improve user comfort and extend equipment life.

[0062] In one of the optional embodiments, the user tag information includes first user tag information and second user tag information, and generating user expected information based on the user tag information, user control instructions and environmental parameter information includes: Specifically, the edge computing center can input the first user label information and the second user label information into the conditional variational generative adversarial network to generate comprehensive user label information, and the comprehensive user label information is used to represent the label information that can simultaneously conform to the first user label information and the second user label information to the greatest extent.

[0063] Schematically, the conditional variational generative adversarial network (CVAE-GAN) is a deep learning model that combines the variational autoencoder (VAE) and the generative adversarial network (GAN). The conditional variational generative adversarial network can generate comprehensive user label information that can simultaneously meet all user label information to the greatest extent based on multiple user label information. By introducing conditional information, the controllability of the comprehensive user label information can be enhanced.

[0064] Specifically, the edge computing center can generate user expectation information based on comprehensive user tag information, user control instructions and environmental parameter information.

[0065] In one of the optional embodiments, please refer to Figure 7 , the refrigeration equipment information and the heating equipment information include global load index information and load distribution ratio information, and the refrigeration equipment information and / or heating equipment information of the central air conditioner are adjusted based on the updated first central air conditioner operation strategy, including: Step S706: Generate global load index information of the central air conditioner's refrigeration equipment information and / or heating equipment information based on the updated first central air conditioner operation strategy.

[0066] Optionally, the global load index information may include but is not limited to total cooling capacity, total heating capacity, total air supply capacity, total dehumidification capacity and total energy consumption target.

[0067] Step S707, using a genetic algorithm to perform multi-objective optimization based on the global load index information to generate load distribution ratio information of the central air-conditioning refrigeration equipment information and / or heating equipment information.

[0068] Optionally, the multi-objective optimization using genetic algorithms can include the actual energy consumption of air conditioning equipment and performance coefficient and , and user expectations .

[0069] Step S708, adjusting the refrigeration equipment information and / or heating equipment information of the central air conditioner based on the load distribution ratio information.

[0070] In the above-mentioned central air-conditioning high-efficiency energy-saving cooling and heating method, through sampling genetic algorithm optimization, multiple goals can be considered at the same time to maximize the comprehensive benefits; by optimizing load distribution, unnecessary energy consumption can be reduced, the goal of energy conservation and emission reduction can be achieved, and operating costs can be reduced.

[0071] In an exemplary embodiment, as Figure 3 As shown, a method for efficient and energy-saving cooling and heating of a central air conditioner is provided, comprising the following steps S301 to S307. Among them: Step S301, obtain user expected information, air conditioning equipment information, and environmental parameter information.

[0072] Step S302, determine the effectiveness of the first central air conditioning operation strategy based on the user expected information, air conditioning equipment information, and environmental parameter information.

[0073] Step S303, if the first central air conditioning operation strategy is determined to be ineffective, input the user expected information and environmental parameter information into the edge strategy generation model to generate a second central air conditioning operation strategy.

[0074] Step S304, input the user expected information and environmental parameter information into the central strategy generation model to generate a third central air conditioning operation strategy.

[0075] Step S305, update the second central air conditioning operation strategy based on the third central air conditioning operation strategy.

[0076] Step S306, update the first central air conditioning operation strategy based on the second central air conditioning operation strategy, and adjust the refrigeration equipment information and / or heating equipment information of the central air conditioning based on the updated first central air conditioning operation strategy.

[0077] Step S307, optimize the edge strategy generation model based on the third central air conditioning operation strategy.

[0078] In the above method for efficient energy-saving refrigeration and heating of central air conditioners, by establishing a multi-layer optimization mechanism, the operation strategy can be dynamically adjusted, the equipment utilization efficiency can be improved, and unnecessary energy waste can be reduced; by responding to user needs and environmental changes in real time, the adaptability and flexibility of the central air conditioning control strategy can be improved.

[0079] In an exemplary embodiment, as Figure 7 shown, a method for efficient energy-saving refrigeration and heating of central air conditioners is provided. Taking the method applied to Figure 1 the edge computing device 101 in as an example, it includes the following steps S701 to S709. Among them:

[0080] Step S701, obtain user expected information, air conditioning equipment information, and environmental parameter information.

[0081] Step S702, determine the effectiveness of the first central air conditioning operation strategy based on the user expected information, air conditioning equipment information, and environmental parameter information.

[0082] Step S704: Input the user expectation information and environmental parameter information into the central strategy generation model to generate the third central air conditioning operation strategy.

[0083] Step S705: Update the second central air conditioning operation strategy based on the third central air conditioning operation strategy.

[0084] Step S706: Generate global load index information of the central air conditioner's refrigeration equipment information and / or heating equipment information based on the updated first central air conditioner operation strategy.

[0085] Step S707, using a genetic algorithm to perform multi-objective optimization based on the global load index information to generate load distribution ratio information of the central air-conditioning refrigeration equipment information and / or heating equipment information.

[0086] Step S708, adjusting the refrigeration equipment information and / or heating equipment information of the central air conditioner based on the load distribution ratio information.

[0087] Step S709, optimizing the edge strategy generation model based on the third central air conditioning operation strategy.

[0088] In the above-mentioned central air-conditioning efficient and energy-saving cooling and heating method, by obtaining comprehensive multi-modal information, judging the effectiveness of existing strategies, as well as multi-model collaboration, strategy update, global load evaluation, multi-objective optimization and precise adjustment, the operating efficiency, response speed and stability of the central air-conditioning system can be improved. This will achieve continuous improvement and performance enhancement of the central air-conditioning.

[0089] It should be understood that, although the steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed in turn or alternation with other steps or at least a part of the steps or stages in other steps.

[0090] ​Based on the same inventive concept, the embodiment of the present application also provides a central air-conditioning high-efficiency energy-saving cooling and heating system for realizing the central air-conditioning high-efficiency energy-saving cooling and heating method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more central air-conditioning high-efficiency energy-saving cooling and heating system embodiments provided below can refer to the limitations of the central air-conditioning high-efficiency energy-saving cooling and heating method above, and will not be repeated here.

[0091] In an exemplary embodiment, as Figure 8 As shown, a central air-conditioning high-efficiency energy-saving cooling and heating system 800 is provided, including: The control parameter acquisition module 801 can be used to obtain user expectation information, air conditioning equipment information and environmental parameter information. The air conditioning equipment information includes refrigeration equipment information and heating equipment information.

[0092] The control strategy determination module 802 can be used to determine the effectiveness of the first central air-conditioning operation strategy based on user expectation information, air-conditioning equipment information and environmental parameter information. The first central air-conditioning operation strategy is used to characterize the real-time operation status of the air-conditioning equipment of the central air-conditioning.

[0093] The control strategy generation module 803 can be used to input user expectation information and environmental parameter information into the edge strategy generation model to generate a second central air conditioning operation strategy if the first central air conditioning operation strategy is judged to be invalid. The second central air conditioning operation strategy is used to characterize the expected operation state of the central air conditioning air conditioning equipment.

[0094] The control strategy update module 804 can be used to update the first central air conditioner operation strategy based on the second central air conditioner operation strategy, and adjust the refrigeration equipment information and / or heating equipment information of the central air conditioner based on the updated first central air conditioner operation strategy.

[0095] In an optional embodiment, the control strategy generation module 803 can also be used to input user expectation information and environmental parameter information into the central strategy generation model to generate a third central air-conditioning operation strategy, and the central strategy generation model is installed in the IoT central device; the control strategy update module 804 can also be used to update the second central air-conditioning operation strategy based on the third central air-conditioning operation strategy; optimize the edge strategy generation model based on the third central air-conditioning operation strategy, and the edge strategy generation model is installed in the IoT edge device.

[0096] In an optional embodiment, the control strategy determination module 802 can also be used to obtain the time proportion information of the first central air-conditioning operation strategy being judged as invalid within the preset sampling period; the control strategy generation module 803 can also be used to predict the future change trend of the central air-conditioning operation demand based on the edge strategy prediction model if the time proportion information exceeds the preset normal threshold of the working environment, generate the fourth central air-conditioning operation strategy and the first activation timing information of the fourth central air-conditioning operation strategy, and the fourth central air-conditioning operation strategy is used to update the first central air-conditioning operation strategy at the time corresponding to the first activation timing information.

[0097] In an optional embodiment, the control strategy generation module 803 can also be used to input user expectation information and environmental parameter information into the central strategy prediction model to generate the fifth central air-conditioning operation strategy and the second activation timing information of the fifth central air-conditioning operation strategy; the control strategy update module 804 can also be used to update the fourth central air-conditioning operation strategy based on the fifth central air-conditioning operation strategy, and update the first activation timing information based on the second activation timing information; optimize the edge strategy generation model, the edge strategy prediction model and the central strategy generation model based on the fifth central air-conditioning operation strategy.

[0098] In an optional embodiment, the control parameter acquisition module 801 can also be used to obtain indoor environment information, outdoor environment information, user tag information and user control instructions, the user control instructions include mode control instructions, target control instructions and wind speed control instructions; generate environmental parameter information based on indoor environment information and outdoor environment information; generate user expected information based on user tag information, user control instructions and environmental parameter information; set air conditioning equipment information as cooling equipment information and / or heating equipment information based on environmental parameter information and user expected information.

[0099] In an optional embodiment, the control parameter acquisition module 801 can also be used to input the first user tag information and the second user tag information into the conditional variational generative adversarial network to generate comprehensive user tag information, which is used to represent the tag information that can simultaneously meet the first user tag information and the second user tag information to the greatest extent; and generate user expected information based on the comprehensive user tag information, user control instructions and environmental parameter information.

[0100] The control strategy update module 804 can also be used to generate global load index information of the central air-conditioning refrigeration equipment information and / or heating equipment information based on the updated first central air-conditioning operation strategy; use genetic algorithms to perform multi-objective optimization based on the global load index information to generate load distribution ratio information of the central air-conditioning refrigeration equipment information and / or heating equipment information; and adjust the central air-conditioning refrigeration equipment information and / or heating equipment information based on the load distribution ratio information.

[0101] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for efficient and energy-saving cooling and heating of a central air conditioner as described above are implemented.

[0102] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0103] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. Ordinary technicians in this field can understand and implement it without creative work.

[0104] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A method for high-efficiency and energy-saving cooling and heating of a central air conditioner, characterized in that: The method comprises: Acquiring user expectation information, air conditioning equipment information and environmental parameter information, wherein the air conditioning equipment information includes refrigeration equipment information and heating equipment information; Based on the user expectation information, the air conditioning equipment information and the environmental parameter information, the effectiveness of a first central air conditioning operation strategy is judged, wherein the first central air conditioning operation strategy is used to characterize the real-time operation status of the air conditioning equipment of the central air conditioner; If the first central air-conditioning operation strategy is judged to be invalid, the user expectation information and the environmental parameter information are input into the edge strategy generation model to generate a second central air-conditioning operation strategy, wherein the second central air-conditioning operation strategy is used to characterize the expected operation state of the air conditioning equipment of the central air-conditioning; The first central air conditioner operation strategy is updated based on the second central air conditioner operation strategy, and the refrigeration equipment information and / or the heating equipment information of the central air conditioner is adjusted based on the updated first central air conditioner operation strategy.

2. The method according to claim 1, characterized in that: The step of inputting the user expectation information and the environmental parameter information into the edge strategy generation model to generate a second central air-conditioning operation strategy further includes: Inputting the user expectation information and the environmental parameter information into a central strategy generation model to generate a third central air-conditioning operation strategy, wherein the central strategy generation model is mounted in an Internet of Things central device; Updating the second central air conditioning operation strategy based on the third central air conditioning operation strategy; The edge strategy generation model is optimized based on the third central air-conditioning operation strategy, and the edge strategy generation model is installed in the Internet of Things edge device.

3. The method according to claim 2, characterized in that: The central strategy generation model is a deep learning neural network model, and the central strategy generation model includes an improved convolution module and an improved converter module; The edge strategy generation model is an improved BP neural network, and the improved BP neural network is obtained by distilling the central strategy generation model into the initial BP neural network; Among them, the loss function of the central strategy generation model is a multi-objective comprehensive loss function, and the expression of the multi-objective comprehensive loss function is: ； In the formula, is the multi-objective comprehensive loss function, , , and They are energy efficiency loss, adjustment target loss, strategy stability loss and strategy classification loss. , , and They are energy efficiency loss parameter, adjustment target loss parameter, strategy stability loss parameter and strategy classification loss parameter. is the total number of the air conditioning equipment, , and Respectively The actual energy consumption, set energy consumption and performance coefficient of each air conditioning equipment, is the number of environmental data samples, is the total number of physical properties of the air regulated by the central air conditioner, and They are respectively the first The weight parameters and allowable error parameters of the physical properties of the air, and Respectively The second sampling time The measured and set values ​​of the physical properties of the air, is the total number of adjustment parameters of the third central air-conditioning operation strategy and the first central air-conditioning operation strategy, and are respectively the first The adjustment parameters and The output corresponding to the adjustment parameters is and are respectively the first central air-conditioning operation strategy The adjustment parameters and The output corresponding to the adjustment parameters is and Respectively The maximum and minimum output values ​​corresponding to the adjustment parameters, is the adjustment parameter coefficient, To adjust the parameter output coefficient, is the number of samples, is the number of categories of the third central air-conditioning operation strategy, is the balance factor, is the focusing parameter, The central strategy generation model is for the The samples belong to The predicted probability of the class.

4. The method according to claim 1, characterized in that: The method further comprises: Obtaining information on the proportion of time during which the first central air-conditioning operation strategy is judged to be invalid within a preset sampling period; If the duration ratio information exceeds a preset normal threshold of the working environment, the future change trend of the central air-conditioning operation demand is predicted based on the edge strategy prediction model, and a fourth central air-conditioning operation strategy and the first activation timing information of the fourth central air-conditioning operation strategy are generated, and the fourth central air-conditioning operation strategy is used to update the first central air-conditioning operation strategy at the time corresponding to the first activation timing information; The expression of the duration ratio information is: ； In the formula, is the duration ratio information, is the sampling period, is the number of times the first central air-conditioning operation strategy is judged to be invalid within the sampling period, For the The sampling history coefficient attenuation term when the first central air-conditioning operation strategy is judged to be ineffective, For the The sampling history time when the first central air-conditioning operation strategy is judged to be invalid, For the The strategy adjustment fuzzy coefficient term when the first central air-conditioning operation strategy is judged to be ineffective, For the The adjustment parameters when the first central air-conditioning operation strategy is judged to be ineffective, For the The adjustment parameters of the second central air-conditioning operation strategy corresponding to the first central air-conditioning operation strategy are determined to be invalid. For the The duration when the first central air-conditioning operation strategy is judged to be ineffective.

5. The method according to claim 4, characterized in that If the duration ratio information exceeds the preset normal environment threshold, the future central air-conditioning operation demand change trend is predicted based on the edge strategy prediction model, and a fourth central air-conditioning operation strategy and activation timing information of the fourth central air-conditioning operation strategy are generated, and then, the method further includes: Inputting the user expectation information and the environmental parameter information into a central strategy prediction model to generate a fifth central air-conditioning operation strategy and second activation timing information of the fifth central air-conditioning operation strategy; updating the fourth central air-conditioning operation strategy based on the fifth central air-conditioning operation strategy, and updating the first activation timing information based on the second activation timing information; The edge strategy generation model, the edge strategy prediction model and the central strategy generation model are optimized based on the fifth central air conditioning operation strategy.

6. The method according to claim 5, characterized in that: The edge strategy prediction model is a regression prediction model; The center strategy prediction model is constructed based on an improved converter model and an improved long short-term memory network, and the improved converter model includes a residual convolution module.

7. The method according to claim 1, characterized in that The obtaining of user expectation information, air conditioning equipment information and environmental parameter information includes: Acquire indoor environment information, outdoor environment information, user tag information and user control instructions, wherein the user control instructions include mode control instructions, target control instructions and wind speed control instructions; generating the environmental parameter information based on the indoor environmental information and the outdoor environmental information; Generate the user expectation information based on the user tag information, the user control instruction and the environmental parameter information; The air conditioning equipment information is set as the refrigeration equipment information and / or heating equipment information based on the environmental parameter information and the user expectation information.

8. The method according to claim 7, characterized in that The user tag information includes first user tag information and second user tag information, and the generating the user expected information based on the user tag information, the user control instruction and the environmental parameter information includes: Inputting the first user label information and the second user label information into a conditional variational generative adversarial network to generate comprehensive user label information, where the comprehensive user label information is used to represent label information that can simultaneously conform to the first user label information and the second user label information to the greatest extent; The user expectation information is generated based on the comprehensive user tag information, the user control instruction and the environmental parameter information.

9. The method according to any one of claims 1 to 8, characterized in that: The refrigeration equipment information and the heating equipment information include global load index information and load distribution ratio information. The refrigeration equipment information and / or the heating equipment information of the central air conditioner are adjusted based on the updated first central air conditioner operation strategy, including: Generate global load index information of the refrigeration equipment information and / or the heating equipment information of the central air conditioner based on the updated first central air conditioner operation strategy; Based on the global load index information, a genetic algorithm is used to perform multi-objective optimization to generate the load distribution ratio information of the refrigeration equipment information and / or the heating equipment information of the central air conditioner; The refrigeration equipment information and / or the heating equipment information of the central air conditioner are adjusted based on the load distribution ratio information.

10. The method according to claim 9, characterized in that: The refrigeration equipment information includes cold source equipment information and cold recovery equipment information, and the heating equipment information includes heat source equipment information and heat recovery equipment information.

Images