Non-inductive automatic decision-making method and system for central air conditioner

Abstract

The invention discloses a non-inductive automatic decision-making method and system for a central air conditioner, and relates to the technical field of participation of the central air conditioner in power demand response, and the method comprises the steps: collecting indoor and outdoor environment data and user behavior data in real time through a temperature and humidity sensor, an air quality monitor and human body inductor equipment; establishing a power operation model when the central air conditioner participates in demand response; a central air conditioner automatic decision-making model based on PMV indexes is established; and the intelligent terminal adjusts the operation mode of the central air conditioner through an execution unit of the central air conditioner system according to the central air conditioner regulation and control instruction output by the automatic decision-making model. According to the non-inductive automatic decision-making system for the central air conditioner, automatic adjustment of the central air conditioner is achieved by intelligently monitoring and analyzing user behaviors and indoor and outdoor environment data. By means of automatic regulation and control, energy use is optimized, energy efficiency and energy saving performance are improved, the air conditioner load can be dynamically adjusted to respond to the power grid requirement, and the response capacity of the system is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of central air conditioning participating in power demand response, and in particular to a central air conditioning non-sensing automatic decision-making method and system. Background Art

[0002] Central air conditioning has become an indispensable resource in electricity demand response due to its huge load. However, traditional central air conditioning control methods rely too much on preset time scheduling or manual setting of parameters such as temperature and humidity. This not only wastes human resources, but also lacks the ability to perceive and respond to real-time environmental changes, and cannot meet the personalized needs of electricity users.

[0003] In recent years, with the development of data processing technology and artificial intelligence, neural network methods have been widely used in the power industry. The advancement of various intelligent control technologies has enabled central air conditioners to monitor indoor and outdoor environmental data, user behavior data, etc. in real time, and automatically analyze and process these data to meet users' needs in terms of energy saving and comfort.

[0004] While satisfying the user's comfort, it is also necessary to reduce the frequency of users' manual adjustment of the central air-conditioning to truly achieve seamless operation. This is not only conducive to the regulation of the central air-conditioning by smart terminals, but also can increase the enthusiasm of central air-conditioning users to participate in demand response. Therefore, it is of great significance to study the seamless automatic decision-making method of central air-conditioning. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: how to achieve seamless automatic control of the central air-conditioning system through intelligent and automated technologies to optimize energy efficiency, improve user comfort, and effectively respond to changes in electricity demand, thereby reducing manual intervention and improving the overall operating efficiency of the system.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a central air-conditioning non-sensing automatic decision-making method, which comprises the following steps:

[0008] Through temperature and humidity sensors, air quality monitors, and human body sensors, indoor and outdoor environmental data and user behavior data are collected in real time; a power operation model for central air conditioning participating in demand response is established; an automatic decision-making model for central air conditioning based on the PMV indicator is established; and the intelligent terminal adjusts the operation mode of the central air conditioning through the execution unit of the central air conditioning system according to the central air conditioning control instructions output by the automatic decision-making model.

[0009] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the indoor and outdoor environmental data include indoor and outdoor temperature, indoor and outdoor humidity, indoor and outdoor air flow rate, indoor and outdoor air pressure, and the user behavior data include user clothing data and user activity data.

[0010] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the power operation model of the central air-conditioning when participating in demand response is:

[0011]

[0012]

[0013]

[0014] Among them, T t in and T t out are the indoor and outdoor temperatures of the user in period t, R in and C in are the thermal resistance and thermal capacity in the user's room, P t ac is the central air conditioning power during period t, η ac For the working efficiency of central air conditioning, T in and are the minimum and maximum indoor temperatures acceptable to users, is an action variable, with a value of 1 or 0, indicating whether the air conditioner is on or off during the period. A value of 1 indicates that the air conditioner is on, and a value of 0 indicates that the air conditioner is off. Rated power of the air conditioner.

[0015] The central air conditioning efficiency multiplied by the central air conditioning power is the cooling capacity or heating capacity of the central air conditioning, expressed as,

[0016] Q ac =η ac P ac .

[0017] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the PMV index is calculated from six parameters: individual activity, clothing thermal resistance, indoor temperature, relative humidity of the environment, indoor average radiation temperature and indoor air flow rate:

[0018]

[0019] in,

[0020]

[0021]

[0022] t cl =35.7-0.028×(MW)-I cl ×3.96×10 -8 ×f cl ×{[(t cl +273) 4 -(t r +273) 4 ]+h c ×f cl ×(t cl -t a )}

[0023]

[0024] Among them, e is a natural constant, M represents the energy metabolism rate generated by human activities, W is the power of mechanical work done by the human body, P a is the ambient saturated vapor pressure, is the relative humidity of the environment, t a is the ambient air temperature, f cl is the clothing influence coefficient, I cl is the thermal resistance of the clothing, t cl is the outer surface temperature of the garment, t r is the average radiation temperature of the environment, h c is the clothing surface heat transfer coefficient, v a is the ambient air velocity.

[0025] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the central air-conditioning automatic decision-making model adopts a deep deterministic policy gradient algorithm to analyze indoor and outdoor environmental data and user behavior data, predict the trend of indoor and outdoor environmental changes and user needs, and formulate a central air-conditioning non-sensing automatic control strategy. Based on the definition of non-sensing, the intelligent terminal formulates a central air-conditioning non-sensing automatic decision-making strategy to participate in demand response, and sets the reward function as follows:

[0026]

[0027]

[0028]

[0029] in, is the reward function of air conditioning comfort, Penalty for central air conditioning load fluctuation, is the total reward function, ω 1 ,ω2 is the weight coefficient.

[0030] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the central air-conditioning automatic decision-making model also includes the use of Actor neural network and Critic neural network, which are respectively used to learn the behavior of the central air-conditioning and evaluate the value of the behavior.

[0031] As a preferred solution of the central air-conditioning non-sensing automatic decision-making method described in the present invention, the Actor neural network defines the i-th state action as a by inputting the i-th state behavior data of the central air-conditioning. i , expressed as,

[0032] a i =μ θ (s i )

[0033] Among them, s i is the state, μ is the target state function of the action;

[0034] Based on the Bellman equation, the Critic network calculates the value y of the target action according to the current action and state of the central air conditioner. i :

[0035] y i =r i +γQ'(s i+1 ,μ' i+1 |θ Q' )

[0036] Among them, Q' is the value function of the current action, s i+1 is the i+1th state, μ' i+1 is the target state function of the current action in the i+1th state, γ is the discount factor, r i is the reward function, which can be directly substituted into the reward function in the central air-conditioning non-sensing automatic decision-making strategy

[0037] Update the Critic network by minimizing the loss:

[0038]

[0039] Among them, Q is the value function of the target action, θ is the random weight, and N is the random process.

[0040] Update the parameters in the Actor network by maximizing the cumulative expected reward:

[0041]

[0042] Update the action behavior decision network by exponential moving average method:

[0043] θ Q' ←τθ Q +(1-τ)θ Q'

[0044] θ μ' ←τθ μ +(1-τ)θ μ'

[0045] Among them, τ is the parameter that controls the model update speed, θ (*) Represents the random weights of the * function.

[0046] Another object of the present invention is to provide a central air-conditioning automatic decision-making system, which can automatically adjust the operation strategy of the central air-conditioning by real-time monitoring and analysis of indoor and outdoor environmental data and user behavior, thereby solving the problem that the existing system relies on preset timing scheduling and manual settings and lacks dynamic adjustment capabilities.

[0047] In order to solve the above technical problems, the present invention provides the following technical solutions: a central air-conditioning sensorless automatic decision-making system, including a data acquisition module, an automatic decision-making model module and an intelligent terminal module.

[0048] The data collection module is used to collect indoor and outdoor environmental data and user behavior data.

[0049] The automatic decision model module automatically determines the operating status of the central air conditioner.

[0050] The execution unit module adjusts the operation mode of the central air conditioner according to the control instructions received by the smart terminal.

[0051] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the central air-conditioning non-sensing automatic decision-making method as described above are implemented.

[0052] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the central air-conditioning non-sensing automatic decision-making method as described above.

[0053] Beneficial effects of the present invention: The central air-conditioning non-sensing automatic decision-making system provided by the present invention realizes automatic adjustment of the central air-conditioning by intelligently monitoring and analyzing user behavior and indoor and outdoor environmental data. This automated regulation not only optimizes energy use, improves energy efficiency and energy saving, but also dynamically adjusts the air-conditioning load to respond to grid demand and enhances the responsiveness of the system. In addition, the system reduces manual intervention and reduces operating and maintenance costs, while ensuring user comfort and providing users with a more personalized and precise indoor environment. In short, the present invention effectively combines the needs of user comfort and energy management, and provides an efficient and intelligent solution for the management of modern central air-conditioning systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0055] Figure 1 An overall flow chart of a central air-conditioning non-sensing automatic decision-making method provided for the first embodiment of the present invention.

[0056] Figure 2 An overall framework diagram of a central air-conditioning sensorless automatic decision-making system provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0058] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a central air-conditioning non-sensing automatic decision-making method, which is characterized by:

[0059] S1: Collect indoor and outdoor environmental data and user behavior data in real time through temperature and humidity sensors, air quality monitors, and human body sensor devices.

[0060] Indoor and outdoor environmental data include indoor and outdoor temperature, indoor and outdoor humidity, indoor and outdoor air flow rate, and indoor and outdoor air pressure. User behavior data includes user clothing data and user activity data.

[0061] S2: Establish the power operation model when central air conditioning participates in demand response.

[0062] The power operation model of central air conditioning when participating in demand response is:

[0063]

[0064]

[0065]

[0066] Among them, T t in and T t out are the indoor and outdoor temperatures of the user in period t, R in and C in are the thermal resistance and thermal capacity in the user's room, P t ac is the central air conditioning power during period t, η ac For the working efficiency of central air conditioning, T in and are the minimum and maximum indoor temperatures acceptable to users, is an action variable, with a value of 1 or 0, indicating whether the air conditioner is on or off during the period. A value of 1 indicates that the air conditioner is on, and a value of 0 indicates that the air conditioner is off. Rated power of the air conditioner.

[0067] The central air conditioning efficiency multiplied by the central air conditioning power is the cooling capacity or heating capacity of the central air conditioning, expressed as,

[0068] Q ac =η ac P ac .

[0069] S3: Establish a central air conditioning automatic decision-making model based on PMV indicators.

[0070] When using central air conditioning, people mostly use human thermal comfort as an indicator to measure the operation effect of central air conditioning. Human thermal comfort is closely related to the surrounding environment, human physiology and psychology and other factors. At present, experts have conducted in-depth research on human thermal comfort indicators. The most commonly used predicted mean vote (PMV) indicator can best reflect the level of thermal comfort. The PMV indicator is calculated through six parameters: individual activity, clothing thermal resistance, indoor temperature, relative humidity of the environment, indoor average radiation temperature and indoor air velocity:

[0071]

[0072] in,

[0073]

[0074]

[0075] t cl =35.7-0.028×(MW)-I cl ×3.96×10 -8 ×f cl ×{[(t cl +273) 4 -(t r +273) 4 ]+h c ×f cl ×(t cl -t a )}

[0076] h c =max(2.38×(t cl -t a ) 0.25 ,12.1×v a 0.5 )

[0077] Among them, e is a natural constant, M represents the energy metabolism rate generated by human activities, W is the power of mechanical work done by the human body, P a is the ambient saturated vapor pressure, is the relative humidity of the environment, t a is the ambient air temperature, f cl is the clothing influence coefficient, I cl is the thermal resistance of the clothing, t cl is the outer surface temperature of the garment, t r is the average radiation temperature of the environment, h c is the clothing surface heat transfer coefficient, v a is the ambient air velocity.

[0078] The PMV index measures the thermal comfort of the human body by dividing it into seven levels. Each level corresponds to a different thermal sensation. The 7 levels of the PMV index are: -3, -2, -1, 0, 1, 2, 3. The corresponding thermal sensation distribution is: cold, slightly cold, slightly cool, moderate, slightly warm, slightly hot, and hot. The PWM index affects the minimum and maximum values ​​of the indoor temperature that the user can accept. According to different application scenarios, the indoor temperature is adjusted and the thermal sensation given by the user is recorded to obtain the thermal comfort of each scenario. T in and

[0079] S4: The intelligent terminal adjusts the operation mode of the central air-conditioning through the execution unit of the central air-conditioning system according to the central air-conditioning control instructions output by the automatic decision-making model.

[0080] The "no sense" feature is reflected in two aspects. The first is that the smart terminal directly controls the central air-conditioning, and the user does not need to manually adjust the air-conditioning temperature. The second is that when the smart terminal adjusts the central air-conditioning, the indoor temperature is always kept within the user's thermal comfort range, and the user will not have a significant perception of the indoor temperature changes.

[0081] Through real-time monitoring and intelligent analysis of data, the smart terminal can continuously adjust the indoor temperature to ensure that it remains within the optimal range of the user's thermal comfort, greatly improving the user's comfort experience.

[0082] The central air-conditioning automatic decision-making model uses a deep deterministic policy gradient algorithm to analyze indoor and outdoor environmental data and user behavior data, predict the trend of indoor and outdoor environmental changes and user needs, and formulate a central air-conditioning non-sensing automatic control strategy. Based on the definition of non-sensing, the intelligent terminal formulates a central air-conditioning non-sensing automatic decision-making strategy to participate in demand response, and sets the reward function as follows:

[0083]

[0084]

[0085]

[0086] in, is the reward function of air conditioning comfort, Penalty for central air conditioning load fluctuation, is the total reward function, ω 1 ,ω 2 is the weight coefficient.

[0087] The central air-conditioning automatic decision-making model also includes the use of Actor neural network and Critic neural network, which are used to learn the behavior of the central air-conditioning and evaluate the value of the behavior respectively.

[0088] The Actor neural network inputs the i-th state behavior data of the central air conditioner and defines the i-th state action as a i , expressed as,

[0089] a i =μ θ (s i )

[0090] Among them, s i is the state, and μ is the target state function of the action.

[0091] Based on the Bellman equation, the Critic network calculates the value y of the target action according to the current action and state of the central air conditioner. i :

[0092] y i =r i +γQ'(s i+1 ,μ' i+1 |θ Q' )

[0093] Among them, Q' is the value function of the current action, s i+1 is the i+1th state, μ' i+1 is the target state function of the current action in the i+1th state, γ is the discount factor, r i is the reward function, which can be directly substituted into the reward function in the central air-conditioning non-sensing automatic decision-making strategy

[0094] Update the Critic network by minimizing the loss:

[0095]

[0096] Among them, Q is the value function of the target action, θ is the random weight, and N is the random process.

[0097] Update the parameters in the Actor network by maximizing the cumulative expected reward:

[0098]

[0099] Update the action behavior decision network by exponential moving average method:

[0100] θ Q' ←τθ Q +(1-τ)θ Q'

[0101] θ μ' ←τθ μ +(1-τ)θ μ'

[0102] Among them, τ is the parameter that controls the model update speed, θ (*) Represents the random weights of the * function.

[0103] Through precise control strategies, the trained central air-conditioning automatic decision-making model can help the central air-conditioning system reduce energy waste and reduce the situation of overcooling or overheating in the environment where the central air-conditioning is located. It not only improves energy efficiency but also reduces energy costs. The introduction of the DDPG algorithm increases the intelligence level of the system, enabling the central air-conditioning system to self-learn and adapt to the ever-changing environment and user behavior patterns without frequent manual adjustments, thus achieving seamless demand response.

[0104] Furthermore, the intelligent terminal accurately adjusts the operation mode of the central air-conditioning through the execution units of the central air-conditioning system (such as fans, cooling / heating modules, etc.) according to the central air-conditioning control instructions output by the automatic decision-making model, so as to meet the user's needs for non-perceptible control, ensure the user's thermal comfort, and achieve the goal of energy saving.

[0105] Example 2, reference Figure 2 , which is an embodiment of the present invention, provides a system for a central air-conditioning non-sensing automatic decision-making method, characterized in that it includes a data acquisition module, an automatic decision-making model module and an intelligent terminal module.

[0106] The data acquisition module is used to collect indoor and outdoor environmental data and user behavior data.

[0107] The automatic decision model module automatically determines the operating status of the central air conditioner.

[0108] The execution unit module adjusts the operation mode of the central air conditioner according to the control instructions received by the smart terminal.

[0109] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0110] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0111] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0112] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0113] Embodiment 3: In this embodiment, in order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments. This embodiment experiments the existing traditional method and the method of this embodiment respectively.

[0114] In the management and control of central air conditioning systems, traditional methods usually rely on preset timed scheduling or manual settings of parameters such as temperature and humidity. Although this method can meet basic temperature control needs to a certain extent, it often leads to energy waste and poor user comfort due to the lack of dynamic response capabilities to real-time environmental changes and user behavior. Specifically, after setting the temperature, the traditional method will not automatically adjust even if the external environment or indoor demand changes, resulting in inefficient air conditioning operation.

[0115] In order to overcome these limitations, the present invention proposes a central air-conditioning non-sensing automatic decision-making method and system. The present invention uses real-time data monitoring and intelligent algorithms to automatically adjust the air-conditioning settings to improve energy efficiency and user comfort. By comparing the performance of the present invention with traditional methods in different aspects, we can scientifically demonstrate the advantages of the present invention, as shown in Table 1.

[0116] Experimental design and data tables

[0117] Experimental design:

[0118] Control group: A traditional central air conditioning control strategy was used, based on a fixed schedule and manually set temperature.

[0119] Experimental group: The central air-conditioning non-sensing automatic decision-making system proposed by the present invention is adopted to adjust the strategy in real time.

[0120] Table 1 Experimental effect comparison chart

[0121] Experimental indicators Traditional methods Method of the present invention Energy consumption 1000 850 System response time 300 60 Economic costs 500 400

[0122] In summary, the present invention can intelligently adjust the air conditioning power according to real-time data to avoid unnecessary energy consumption. The above progress has reduced the energy consumption of our invention by 15%. Using advanced artificial intelligence technologies such as the Deep Deterministic Policy Gradient Algorithm (DDPG), the system can automatically analyze the collected data and intelligently adjust the operation mode of the central air conditioner according to the environment and user behavior. This automated decision-making significantly improves operational efficiency and reduces the need for human intervention, thereby greatly reducing response time in practical applications.

[0123] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A central air conditioning non-sensing automatic decision-making method, characterized in that: include: Through temperature and humidity sensors, air quality monitors, and human body sensors, indoor and outdoor environmental data and user behavior data are collected in real time; Establish a power operation model when central air conditioning participates in demand response; Establish a central air conditioning automatic decision-making model based on PMV indicators; The intelligent terminal adjusts the operation mode of the central air-conditioning through the execution unit of the central air-conditioning system according to the central air-conditioning control instructions output by the automatic decision-making model.

2. A central air conditioning non-sensing automatic decision-making method as claimed in claim 1, characterized in that: The indoor and outdoor environment data include indoor and outdoor temperature, indoor and outdoor humidity, indoor and outdoor air flow rate, and indoor and outdoor air pressure. The user behavior data includes user clothing data and user activity data.

3. A central air conditioning non-sensing automatic decision-making method as claimed in claim 2, characterized in that: The power operation model of the central air conditioner when participating in demand response is: Among them, T t in and T t out are the indoor and outdoor temperatures of the user in period t, R in and C in are the thermal resistance and thermal capacity in the user's room, P t ac is the central air conditioning power during period t, η ac For the working efficiency of central air conditioning, T in and are the minimum and maximum indoor temperatures acceptable to users, is an action variable, with a value of 1 or 0, indicating whether the air conditioner is on or off during the period. A value of 1 indicates that the air conditioner is on, and a value of 0 indicates that the air conditioner is off. is the rated power of the air conditioner; The central air conditioning efficiency multiplied by the central air conditioning power is the cooling capacity or heating capacity of the central air conditioning, expressed as, Q ac =η ac P ac 。 4. A central air conditioning non-sensing automatic decision-making method as claimed in claim 3, characterized in that: The PMV index is calculated from six parameters: individual activity, clothing thermal resistance, indoor temperature, relative humidity, indoor average radiation temperature and indoor air velocity: in, Among them, e is a natural constant, M represents the energy metabolism rate generated by human activities, W is the power of mechanical work done by the human body, P a is the ambient saturated vapor pressure, is the relative humidity of the environment, t a is the ambient air temperature, f cl is the clothing influence coefficient, I cl is the thermal resistance of the clothing, t cl is the outer surface temperature of the garment, t r is the average radiation temperature of the environment, h c is the clothing surface heat transfer coefficient, v a is the ambient air velocity.

5. A central air conditioning non-sensing automatic decision-making method as claimed in claim 4, characterized in that: The central air-conditioning automatic decision-making model adopts a deep deterministic policy gradient algorithm to analyze indoor and outdoor environmental data and user behavior data, predict the trend of indoor and outdoor environmental changes and user needs, and formulate a central air-conditioning non-sensing automatic control strategy. Based on the definition of non-sensing, the intelligent terminal formulates a central air-conditioning non-sensing automatic decision-making strategy to participate in demand response, and sets the reward function as follows: in, is the reward function of air conditioning comfort, Penalty for central air conditioning load fluctuation, is the total reward function, ω1 and ω2 are weight coefficients.

6. A central air conditioning non-sensing automatic decision-making method as claimed in claim 5, characterized in that: The central air-conditioning automatic decision-making model also includes adopting an Actor neural network and a Critic neural network, which are respectively used to learn the behavior actions of the central air-conditioning and evaluate the value of the behavior actions.

7. A central air conditioning non-sensing automatic decision-making method as claimed in claim 6, characterized in that: The Actor neural network defines the i-th state action as a by inputting the i-th state behavior data of the central air conditioner. i , expressed as, a i =μ θ (s i ) Among them, s i is the state, μ is the target state function of the action; Based on the Bellman equation, the Critic network calculates the value y of the target action according to the current action and state of the central air conditioner. i : y i =r i +γQ'(s i+1 ,m' i+1 |θ Q' ) Among them, Q' is the value function of the current action, s i+1 is the i+1th state, μ' i+1 is the target state function of the current action in the i+1th state, γ is the discount factor, r i is the reward function, which can be directly substituted into the reward function in the central air-conditioning non-sensing automatic decision-making strategy Update the Critic network by minimizing the loss: Among them, Q is the value function of the target action, θ is the random weight, and N is the random process; Update the parameters in the Actor network by maximizing the cumulative expected reward: Update the action behavior decision network by exponential moving average method: i Q’ ←tth Q’ +(1-τ)θ Q’ i μ’ ←tth μ’ +(1-τ)θ μ’ Among them, τ is the parameter that controls the model update speed, θ (*) Represents the random weights of the * function.

8. A system using a central air-conditioning non-sensing automatic decision-making method as claimed in any one of claims 1 to 7, characterized in that: It includes data acquisition module, automatic decision model module and intelligent terminal module; The data collection module is used to collect indoor and outdoor environmental data and user behavior data; The automatic decision model module automatically determines the operating state of the central air conditioner; The execution unit module adjusts the operation mode of the central air conditioner according to the control instructions received by the smart terminal.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a central air-conditioning non-sensing automatic decision-making method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a central air-conditioning sensorless automatic decision-making method as described in any one of claims 1 to 7 are implemented.

Images