Air conditioning energy-saving control method, device and computer-readable storage medium

Abstract

The present disclosure provides an air-conditioning energy-saving control method, device and computer-readable storage medium, which relate to the field of air-conditioning control technology. The method comprises: obtaining input parameters, the input parameters including operating parameters and environmental parameters of at least one air conditioner; inputting the input parameters into an air-conditioning energy-saving control model to obtain an air-conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, the air-conditioning energy-saving control model including a rule model and a classification model, the rule model is used with a first probability, and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; controlling at least one air conditioner according to the air-conditioning energy-saving control strategy; wherein the classification model is trained with a sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as output and with the sample input parameters as input, wherein the sample input parameters include the operating parameters and environmental parameters of at least one sample air conditioner.

Description

Technical Field

[0001] The present disclosure relates to the field of air conditioning control, and in particular to an air conditioning energy-saving control method, device, and computer-readable storage medium. Background Art

[0002] Data center cooling equipment consumes a significant amount of energy, so reducing its energy consumption and ensuring precise cooling are crucial. In related technologies, air conditioning energy-saving control models can be used for air conditioning control. Summary of the Invention

[0003] The inventors noted that the air conditioning control accuracy in related art is low. After analysis, the inventors found that the accuracy of the models in related art is closely related to the training dataset. Because training datasets rarely contain all possible data, some unlearned situations in actual working environments still exist, resulting in low air conditioning control accuracy. In addition, the training data requires manual experimentation and annotation before use, which consumes a lot of human resources.

[0004] In order to solve the above problems, the embodiments of the present disclosure propose the following solutions.

[0005] According to one aspect of an embodiment of the present disclosure, there is provided an air-conditioning energy-saving control method, comprising: obtaining input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; inputting the input parameters into an air-conditioning energy-saving control model to obtain an air-conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, wherein the air-conditioning energy-saving control model includes a rule model and a classification model, wherein the rule model is used with a first probability, and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; controlling the at least one air conditioner according to the air-conditioning energy-saving control strategy; wherein the classification model is trained using a sample air-conditioning energy-saving control strategy output by the rule model based on sample input parameters as output and the sample input parameters as input, wherein the sample input parameters include the operating parameters and the environmental parameters of at least one sample air conditioner.

[0006] In some embodiments, it further includes: when the air-conditioning energy-saving control strategy is output by the rule model, the classification model is trained with the air-conditioning energy-saving control strategy as output and the input parameters as input.

[0007] According to another aspect of an embodiment of the present disclosure, there is provided an air conditioner energy-saving control method, comprising: obtaining input parameters, the input parameters including operating parameters and environmental parameters of at least one air conditioner; inputting the input parameters into an air conditioner energy-saving control model to obtain an air conditioner energy-saving control strategy that meets temperature requirements and energy consumption requirements, the air conditioner energy-saving control model including a rule model and a classification model, the rule model being used with a first probability, the classification model being used with a second probability, and the sum of the first probability and the second probability being 1; controlling the at least one air conditioner according to the air conditioner energy-saving control strategy; and training the classification model with the air conditioner energy-saving control strategy as output and the input parameters as input, when the air conditioner energy-saving control strategy is output by the rule model.

[0008] In some embodiments, the operating parameter includes a fan speed.

[0009] In some embodiments, the operating parameters further include at least one of active power, switch status, set temperature, and wind speed range.

[0010] In some embodiments, the operating parameters include multiple ones of active power, switch status, set temperature and wind speed range.

[0011] In some embodiments, the environmental parameter includes cabinet temperature.

[0012] In some embodiments, the environmental parameters further include at least one of outdoor temperature, outdoor humidity, indoor humidity, and return air temperature.

[0013] In some embodiments, the environmental parameters include multiple ones of outdoor temperature, outdoor humidity, indoor humidity, and return air temperature.

[0014] In some embodiments, the energy consumption requirement is to minimize energy consumption.

[0015] In some embodiments, it also includes: after controlling the at least one air conditioner, if it is determined that the temperature requirement and the energy consumption requirement are met, increasing the second probability; if it is determined that at least one of the temperature requirement and the energy consumption requirement is not met, reducing the second probability.

[0016] In some embodiments, the rule model includes a policy network and a value network.

[0017] According to another aspect of an embodiment of the present disclosure, an air-conditioning energy-saving control device is provided, comprising: an acquisition module configured to input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; an input module configured to input the input parameters into an air-conditioning energy-saving control model to obtain an air-conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, wherein the air-conditioning energy-saving control model includes a rule model and a classification model, wherein the rule model is used with a first probability and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; a control module configured to control the at least one air-conditioner according to the air-conditioning energy-saving control strategy; wherein the classification model is trained by using a sample air-conditioning energy-saving control strategy output by the rule model based on sample input parameters as output and using the sample input parameters as input, wherein the sample input parameters include the operating parameters and the environmental parameters of at least one sample air conditioner.

[0018] According to another aspect of an embodiment of the present disclosure, an air-conditioning energy-saving control device is provided, comprising: an acquisition module configured to acquire input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; an input module configured to input the input parameters into an air-conditioning energy-saving control model to obtain an air-conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, wherein the air-conditioning energy-saving control model includes a rule model and a classification model, wherein the rule model is used with a first probability and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; a control module configured to control the at least one air conditioner according to the air-conditioning energy-saving control strategy; and a training module configured to train the classification model with the air-conditioning energy-saving control strategy as output and the input parameters as input, when the air-conditioning energy-saving control strategy is output by the rule model.

[0019] According to another aspect of an embodiment of the present disclosure, an air conditioner energy-saving control device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the method described in any one of the above embodiments based on instructions stored in the memory.

[0020] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, comprising computer program instructions, wherein when the computer program instructions are executed by a processor, the method described in any one of the above embodiments is implemented.

[0021] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method described in any one of the above embodiments is implemented.

[0022] In the embodiment of the present disclosure, on the one hand, by obtaining input parameters and inputting the input parameters into the air-conditioning energy-saving control model, an air-conditioning energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained, and the air-conditioning energy-saving control model includes a rule model and a classification model. Among them, the rule model has high control accuracy, but the convergence speed is slow, while the classification model has a fast convergence speed, but there are still some events in the actual working environment that have not been learned by the classification model, which affects the accuracy of control. By comprehensively using the rule model and the classification model, the situation of control errors caused by the occurrence of unlearned events is avoided, and the accuracy of air-conditioning energy-saving control is improved. On the other hand, by using the sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as the output and the sample input parameters as the input for training to obtain the classification model, the problem of manual labeling consuming a lot of resources is avoided, and the efficiency of air-conditioning energy-saving control is improved.

[0023] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0025] Figure 1 is a flowchart of an air-conditioning energy-saving control method according to some embodiments of the present disclosure;

[0026] Figure 2 is a flowchart of an air-conditioning energy-saving control method according to other embodiments of the present disclosure;

[0027] Figure 3 is a structural diagram of an air-conditioning energy-saving control device according to some embodiments of the present disclosure;

[0028] Figure 4 is a structural schematic diagram of an air-conditioning energy-saving control device according to other embodiments of the present disclosure;

[0029] Figure 5 It is a structural schematic diagram of an air-conditioning energy-saving control device according to some other embodiments of the present disclosure. DETAILED DESCRIPTION

[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0031] Unless specifically stated otherwise, the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure.

[0032] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0033] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0034] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0035] It should be noted that like reference numerals and letters refer to like items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0036] The air conditioning energy-saving control method provided in the embodiments of the present disclosure can be used for, but not limited to, air conditioning control in a computer room of a data center.

[0037] Figure 1 It is a flowchart of an air conditioning energy-saving control method according to some embodiments of the present disclosure.

[0038] In step 102, input parameters are acquired, where the input parameters include operating parameters and environmental parameters of at least one air conditioner.

[0039] At step 104, the input parameters are fed into the air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets the temperature and energy consumption requirements. The air conditioning energy-saving control model includes a rule model and a classification model. The rule model is used with a first probability, and the classification model is used with a second probability. The sum of the first and second probabilities is 1. In other words, each time an input parameter is fed into the air conditioning energy-saving control model, the probability of the air conditioning energy-saving control strategy output by the rule model is the first probability, and the probability of the air conditioning energy-saving control strategy output by the classification model is the second probability.

[0040] The classification model is trained with the sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as output and the sample input parameters as input, wherein the sample input parameters include the operating parameters and environmental parameters of at least one sample air-conditioner.

[0041] In some embodiments, the energy consumption requirement is to minimize energy consumption. For example, the air conditioner energy saving control strategy is to keep the temperature below a preset temperature and minimize energy consumption.

[0042] In some embodiments, the rule model is a reinforcement learning model, including a policy network and a value network. In some embodiments, the classification model is a neural network model.

[0043] In step 106, at least one air conditioner is controlled according to the air conditioner energy-saving control strategy.

[0044] In some implementations, the air conditioner energy-saving control strategy includes the on / off state, set temperature, and wind speed range of the air conditioner. In this case, for each air conditioner, whether the air conditioner is turned on or off can be controlled according to the air conditioner energy-saving control strategy, and when turned on, the air conditioner is controlled to operate within the set temperature and wind speed range in the air conditioner energy-saving control strategy.

[0045] In the above embodiment, on the one hand, by obtaining input parameters and inputting the input parameters into the air conditioning energy-saving control model, an air conditioning energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained. The air conditioning energy-saving control model includes a rule model and a classification model. Among them, the rule model has high control accuracy but slow speed, while the classification model is fast. However, there are still some events in the actual working environment that have not been learned by the classification model, which affects the accuracy of control. By comprehensively using the rule model and the classification model, the situation of control errors caused by the occurrence of unlearned events is avoided, and the accuracy of air conditioning energy-saving control is improved. On the other hand, by using the sample air conditioning energy-saving control strategy output by the rule model based on the sample input parameters as the output and the sample input parameters as the input for training to obtain the classification model, the problem of manual labeling consuming large resources is avoided, and the efficiency of air conditioning energy-saving control is improved.

[0046] Figure 2 It is a flowchart of an air conditioning energy-saving control method according to other embodiments of the present disclosure.

[0047] In step 202, input parameters are acquired, where the input parameters include operating parameters and environmental parameters of at least one air conditioner.

[0048] In step 204, the input parameters are input into the air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets the temperature requirements and energy consumption requirements. The air conditioning energy-saving control model includes a rule model and a classification model. The rule model is used with a first probability and the classification model is used with a second probability. The sum of the first probability and the second probability is 1.

[0049] In step 206, at least one air conditioner is controlled according to the air conditioner energy-saving control strategy.

[0050] In step 208 , when the air-conditioning energy-saving control strategy is output by the rule model, the classification model is trained with the air-conditioning energy-saving control strategy as output and the input parameters as input.

[0051] In the above embodiment, on the one hand, by obtaining input parameters and inputting them into the air conditioning energy-saving control model, an air conditioning energy-saving control strategy that meets temperature and energy consumption requirements is obtained. The air conditioning energy-saving control model includes a rule model and a classification model. The rule model has high control accuracy but is slow, while the classification model is fast. However, in actual working environments, there are still some events that have not been learned by the classification model, which affects the accuracy of control. By combining the rule model and the classification model, control errors caused by the occurrence of unlearned events are avoided, thereby improving the accuracy of air conditioning energy-saving control. On the other hand, when the air conditioning energy-saving control strategy is output by the rule model, by training with the air conditioning energy-saving control strategy as the output and the input parameters as the input, there is no need to train the classification model before using the air conditioning energy-saving control model. This avoids the problem of manual labeling that consumes a lot of resources, saves training time, and improves the efficiency of air conditioning energy-saving control training.

[0052] The inventors have noticed that when the operating parameters and environmental parameters include certain specific parameters, the accuracy of the air conditioner energy-saving control can be further improved. This will be described below with reference to different embodiments.

[0053] In some embodiments, the operating parameter includes at least one of fan speed, active power, switch status, set temperature, and wind speed range. In other embodiments, the environmental parameter includes at least one of cabinet temperature, outdoor temperature, outdoor humidity, indoor humidity, and return air temperature. This can further improve the accuracy of air conditioning energy-saving control.

[0054] As some implementations, the cabinet temperature includes a temperature of a data cabinet in a data center.

[0055] In yet other embodiments, the operating parameter includes at least one of fan speed, active power, switch status, set temperature, and wind speed range, and the environmental parameter includes at least one of cabinet temperature, outdoor temperature, outdoor humidity, indoor humidity, and return air temperature. This can further improve the accuracy of air conditioning energy-saving control.

[0056] The inventors have also noted that when the operating parameters include a specific parameter among fan speed, active power, switch status, set temperature, and wind speed range, the accuracy of air conditioner energy-saving control can be further improved. Furthermore, when the environmental parameters include a specific parameter among cabinet temperature, outdoor temperature, outdoor humidity, indoor humidity, and return air temperature, the accuracy of air conditioner energy-saving control can be further improved. This will be described below with reference to various embodiments.

[0057] In some embodiments, the operating parameter includes fan speed. In other embodiments, the environmental parameter includes cabinet temperature. This can further improve the accuracy of air conditioning energy saving control.

[0058] In some other embodiments, the operating parameter includes the fan speed, and the environmental parameter includes the cabinet temperature. In this way, the accuracy of the air conditioner energy-saving control can be further improved.

[0059] In some embodiments, the operating parameters include active power, switch status, at least one of a set temperature and a wind speed range, and a fan speed.

[0060] For example, the operating parameters include active power and fan speed. For another example, the operating parameters include active power and fan speed. For another example, the operating parameters include wind speed range and fan speed.

[0061] In the above embodiment, by inputting the active power, switch status, at least one of the set temperature and wind speed range of at least one air conditioner, the fan speed and environmental parameters into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained, which fully considers the impact of the air conditioner operating parameters on the air conditioner energy-saving control, and further improves the accuracy of the air conditioner energy-saving control.

[0062] In other embodiments, the operating parameters include active power, switch status, set temperature, wind speed range, and fan speed.

[0063] For example, operating parameters include active power, wind speed range, and fan speed. Another example includes switch status, wind speed range, and fan speed. Another example includes active power, switch status, set temperature, and fan speed.

[0064] In the above embodiment, by inputting the active power, switch status, set temperature and multiple wind speed ranges of at least one air conditioner, fan speed and environmental parameters into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets temperature requirements and energy consumption requirements is obtained, which more fully considers the impact of the air conditioner operating parameters on the air conditioner energy-saving control, and further improves the accuracy of the air conditioner energy-saving control.

[0065] In some embodiments, the operating parameters include active power, switch status, set temperature, wind speed range, and fan speed.

[0066] In the above embodiment, by inputting the active power, switch status, set temperature, wind speed range and fan speed of at least one air conditioner and environmental parameters into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained, which more fully considers the impact of the air conditioner operating parameters on the air conditioner energy-saving control, and further improves the accuracy of the air conditioner energy-saving control.

[0067] In some embodiments, the environmental parameter includes at least one of outdoor temperature, outdoor humidity, indoor humidity, and return air temperature, as well as the cabinet temperature.

[0068] Examples of environmental parameters are cabinet temperature and return air temperature.

[0069] In the above embodiment, by inputting at least one of the outdoor humidity, indoor humidity and return air temperature of at least one air conditioner, the cabinet temperature and operating parameters into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained, which fully considers the impact of environmental parameters on the air conditioner energy-saving control and further improves the accuracy of the air conditioner energy-saving control.

[0070] In other embodiments, the environmental parameters include multiple ones of outdoor temperature, outdoor humidity, indoor humidity, and return air temperature, as well as the cabinet temperature.

[0071] For example, the environmental parameters include cabinet temperature, return air temperature, and cabinet temperature. Another example is that the environmental parameters include outdoor humidity, indoor humidity, return air temperature, and cabinet temperature. Another example is that the environmental parameters include outdoor temperature, outdoor humidity, indoor humidity, and cabinet temperature.

[0072] In the above embodiment, by inputting multiple outdoor humidity, indoor humidity and return air temperature of at least one air conditioner, cabinet temperature and operating parameters into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets temperature requirements and energy consumption requirements is obtained, which more fully considers the impact of environmental parameters on air conditioner energy-saving control and further improves the accuracy of air conditioner energy-saving control.

[0073] In other embodiments, the environmental parameters include outdoor temperature, outdoor humidity, indoor humidity, return air temperature, and cabinet temperature.

[0074] In the above embodiment, by inputting the operating parameters of at least one air conditioner and the outdoor temperature, outdoor humidity, indoor humidity, return air temperature, and cabinet temperature into the air conditioner energy-saving control model, an air conditioner energy-saving control strategy that meets the temperature requirements and energy consumption requirements is obtained. This more fully considers the impact of environmental parameters on the air conditioner energy-saving control, and further improves the accuracy of the air conditioner energy-saving control.

[0075] In some embodiments, when the air-conditioning energy-saving control strategy is output by a rule model, the classification model is trained with the air-conditioning energy-saving control strategy as output and the input parameters as input.

[0076] In the above embodiment, when the air conditioner energy-saving control strategy is output by the rule model, the classification model is trained using the air conditioner energy-saving control strategy as output and the input parameters as input. This means that the classification model is continuously updated and improved while the air conditioner energy-saving control model is used, further improving the accuracy of the air conditioner energy-saving control training. Furthermore, training the classification model while performing air conditioner energy-saving control further improves the efficiency of the air conditioner energy-saving control training.

[0077] In some embodiments, after controlling at least one air conditioner, if it is determined that the temperature requirement and the energy consumption requirement are met, the second probability is increased; if it is determined that at least one of the temperature requirement and the energy consumption requirement is not met, the second probability is decreased.

[0078] As some implementation methods, the initial value of the second probability is 0.2. After the air conditioning energy-saving control model runs for a period of time, if the temperature requirements and energy consumption requirements are met during this period, the second probability is increased; if it is determined that at least one of the temperature requirements and energy consumption requirements is not met, the second probability is reduced.

[0079] In the above embodiment, by adjusting the second probability of using the classification model based on whether the temperature and energy consumption requirements are met, the accuracy of air conditioner energy-saving control training is further improved. Furthermore, because the classification model converges quickly, increasing the second probability of using the classification model when the classification model output meets the temperature and energy consumption requirements can improve the efficiency of air conditioner energy-saving control.

[0080] Each embodiment in this specification is described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the device embodiments, since they are essentially identical to the method embodiments, their descriptions are relatively simple. For relevant parts, reference can be made to the descriptions of the method embodiments.

[0081] Figure 3 It is a structural diagram of an air-conditioning energy-saving control device according to some embodiments of the present disclosure.

[0082] like Figure 3 As shown, the air conditioner energy-saving control device includes an acquisition module 301 , an input module 302 and a control module 303 .

[0083] The acquisition module 301 is configured to input parameters, which include operating parameters and environmental parameters of at least one air conditioner.

[0084] The input module 302 is configured to input the input parameters into the air-conditioning energy-saving control model to obtain an air-conditioning energy-saving control strategy that meets the temperature requirements and energy consumption requirements. The air-conditioning energy-saving control model includes a rule model and a classification model. The rule model is used with a first probability, and the classification model is used with a second probability. The sum of the first probability and the second probability is 1. The classification model is trained with the sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as output and the sample input parameters as input. The sample input parameters include the operating parameters and environmental parameters of at least one sample air conditioner.

[0085] The control module 303 is configured to control at least one air conditioner according to the air conditioner energy-saving control strategy.

[0086] Figure 4 It is a structural schematic diagram of an air-conditioning energy-saving control device according to other embodiments of the present disclosure.

[0087] like Figure 4 As shown, the air conditioner energy-saving control device includes an acquisition module 401 , an input module 402 , a control module 403 and a training module 404 .

[0088] The acquisition module 401 is configured to input parameters, which include operating parameters and environmental parameters of at least one air conditioner.

[0089] The input module 402 is configured to input input parameters into the air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements. The air conditioning energy-saving control model includes a rule model and a classification model. The rule model is used with a first probability, and the classification model is used with a second probability. The sum of the first probability and the second probability is 1.

[0090] The control module 403 is configured to control at least one air conditioner according to the air conditioner energy-saving control strategy.

[0091] The training module 404 is configured to train the classification model using the air conditioning energy-saving control strategy as output and the input parameters as input when the air conditioning energy-saving control strategy is output by the rule model.

[0092] Figure 5 It is a structural schematic diagram of an air-conditioning energy-saving control device according to some other embodiments of the present disclosure.

[0093] like Figure 5 As shown, the air conditioner energy-saving control device 500 includes a memory 501 and a processor 502 coupled to the memory 501 . The processor 502 is configured to execute the method of any one of the aforementioned embodiments based on instructions stored in the memory 501 .

[0094] The memory 501 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0095] The air conditioner energy-saving control device 500 may also include an input / output interface 503, a network interface 504, a storage interface 505, and the like. These interfaces 503, 504, and 505, as well as the memory 501 and the processor 502, may be connected, for example, via a bus 506. The input / output interface 503 provides a connection interface for input / output devices such as a display, mouse, keyboard, and touch screen. The network interface 504 provides a connection interface for various networked devices. The storage interface 505 provides a connection interface for external storage devices such as SD cards and USB flash drives.

[0096] An embodiment of the present disclosure further provides a computer-readable storage medium, comprising computer program instructions, which implement the method of any one of the above embodiments when executed by a processor.

[0097] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the method of any one of the above embodiments when executed by a processor.

[0098] Thus far, various embodiments of the present disclosure have been described in detail. To avoid obscuring the concept of the present disclosure, some details known in the art have not been described. Based on the above description, those skilled in the art can fully understand how to implement the technical solutions disclosed herein.

[0099] Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable non-transient storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present disclosure. It should be understood that the functions specified in one or more processes in the flowchart and / or one or more boxes in the 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 the functions for implementing the functions specified in the flowchart. 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.

[0101] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0103] Although some specific embodiments of the present disclosure have been described in detail through examples, those skilled in the art will understand that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that the above embodiments may be modified or some technical features may be replaced with equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. An air conditioning energy-saving control method, comprising: Acquiring input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; Inputting the input parameters into an air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, the air conditioning energy-saving control model including a rule model and a classification model, the rule model being used with a first probability, the classification model being used with a second probability, and the sum of the first probability and the second probability being 1; controlling the at least one air conditioner according to the air conditioner energy-saving control strategy; The classification model is trained with the sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as output and the sample input parameters as input, wherein the sample input parameters include the operating parameters and the environmental parameters of at least one sample air-conditioner.

2. The method according to claim 1, further comprising: In a case where the air-conditioning energy-saving control strategy is output by the rule model, the classification model is trained with the air-conditioning energy-saving control strategy as output and the input parameters as input.

3. An air conditioning energy-saving control method, comprising: Acquiring input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; Inputting the input parameters into an air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, the air conditioning energy-saving control model including a rule model and a classification model, the rule model being used with a first probability, the classification model being used with a second probability, and the sum of the first probability and the second probability being 1; controlling the at least one air conditioner according to the air conditioner energy-saving control strategy; In a case where the air-conditioning energy-saving control strategy is output by the rule model, the classification model is trained with the air-conditioning energy-saving control strategy as output and the input parameters as input.

4. The method according to any one of claims 1 to 3, wherein: The operating parameters include fan speed.

5. The method according to claim 4, wherein The operating parameters also include at least one of active power, switch status, set temperature and wind speed range.

6. The method according to claim 5, wherein: The operating parameters include multiple ones of active power, switch status, set temperature and wind speed range.

7. The method according to any one of claims 1 to 3, wherein: The environmental parameters include cabinet temperature.

8. The method according to claim 7, wherein: The environmental parameters further include at least one of outdoor temperature, outdoor humidity, indoor humidity and return air temperature.

9. The method according to claim 8, wherein The environmental parameters include multiple ones of outdoor temperature, outdoor humidity, indoor humidity and return air temperature.

10. The method according to any one of claims 1 to 3, wherein: The energy consumption requirement is the lowest energy consumption.

11. The method according to any one of claims 1 to 3, further comprising: After controlling the at least one air conditioner, if it is determined that the temperature requirement and the energy consumption requirement are met, increasing the second probability; If it is determined that at least one of the temperature requirement and the energy consumption requirement is not met, the second probability is reduced.

12. The method according to any one of claims 1 to 3, wherein: The rule model includes a policy network and a value network.

13. An air conditioning energy-saving control device, comprising: an acquisition module configured to input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; an input module configured to input the input parameters into an air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, wherein the air conditioning energy-saving control model includes a rule model and a classification model, wherein the rule model is used with a first probability and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; a control module configured to control the at least one air conditioner according to the air conditioner energy-saving control strategy; The classification model is trained with the sample air-conditioning energy-saving control strategy output by the rule model based on the sample input parameters as output and the sample input parameters as input, wherein the sample input parameters include the operating parameters and the environmental parameters of at least one sample air-conditioner.

14. An air conditioning energy-saving control device, comprising: an acquisition module configured to acquire input parameters, wherein the input parameters include operating parameters and environmental parameters of at least one air conditioner; an input module configured to input the input parameters into an air conditioning energy-saving control model to obtain an air conditioning energy-saving control strategy that meets temperature requirements and energy consumption requirements, wherein the air conditioning energy-saving control model includes a rule model and a classification model, wherein the rule model is used with a first probability and the classification model is used with a second probability, and the sum of the first probability and the second probability is 1; a control module configured to control the at least one air conditioner according to the air conditioner energy-saving control strategy; The training module is configured to train the classification model using the air conditioning energy-saving control strategy as output and the input parameters as input when the air conditioning energy-saving control strategy is output by the rule model.

15. An air conditioning energy-saving control device, comprising: Memory; as well as A processor coupled to the memory is configured to execute the method according to any one of claims 1 to 12 based on instructions stored in the memory.

16. A computer-readable storage medium comprising computer program instructions, wherein: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

17. A computer program product comprising a computer program, wherein When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images