Air conditioning energy-saving control method, system, medium and product based on multi-objective optimization

Abstract

The present invention discloses an air conditioning energy-saving control method, system, medium and product based on multi-objective optimization, and relates to the field of data processing. The method comprises: determining the optimization target and corresponding constraint conditions for energy-saving control of the air conditioner, the optimization target comprising target air conditioning energy consumption and target comfort; obtaining the current environmental data of the air conditioner; combining the equipment operation parameters of the air conditioner as particles in the multi-objective particle swarm algorithm; determining the optimal solution through the multi-objective particle swarm algorithm; controlling the air conditioner according to the parameter combination corresponding to the optimal solution; obtaining the actual air conditioning energy consumption and the actual comfort; adjusting the equipment operation parameters of the air conditioner through the PID control algorithm based on the target air conditioning energy consumption and the target comfort, as well as the actual air conditioning energy consumption and the actual comfort, to obtain the final equipment operation parameters; and controlling the air conditioner to work according to the final equipment operation parameters. The present invention achieves a balance between the energy-saving effect and comfort of the air conditioner through the above method.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an air-conditioning energy-saving control method, system, medium and product based on multi-objective optimization. Background Art

[0002] Air conditioners are widely used electrical equipment. Studies have shown that air conditioners account for 20% of total energy consumption. During the peak summer season, air conditioners even account for more than 40%. Therefore, air conditioner energy-saving technology is currently a hot topic.

[0003] Air conditioning energy-saving technology can reduce energy consumption, ease the pressure on electricity supply, reduce environmental pollution caused by power generation, and promote sustainable development.

[0004] Among the related technologies, traditional air-conditioning energy-saving control technology mainly revolves around hardware optimization such as frequency conversion technology, high-efficiency compressors and heat exchangers. Although it reduces energy consumption to a certain extent, its control strategy is usually fixed or single, and it is difficult to dynamically adjust operating parameters according to real-time environmental changes or user needs, resulting in energy-saving effects and comfort often cannot be balanced. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide an air-conditioning energy-saving control method, system, medium and product based on multi-objective optimization, which can achieve a balance between air-conditioning energy-saving effect and comfort.

[0006] To achieve the above-mentioned purpose, in a first aspect, the present invention provides an air conditioning energy-saving control method based on multi-objective optimization, which is applied to an air conditioning control system, and the method includes: determining an optimization target and corresponding constraints for energy-saving control of the air conditioner, the optimization target including target air conditioning energy consumption and target comfort; obtaining current environmental data of the air conditioner; using a combination of equipment operating parameters of the air conditioner as particles in a multi-objective particle swarm algorithm; determining an optimal solution of the particles based on the current environmental data, the optimization target and the constraints through the multi-objective particle swarm algorithm; controlling the air conditioner according to the target equipment operating parameter combination corresponding to the optimal solution; obtaining actual air conditioning energy consumption and actual comfort when the air conditioner works according to the target equipment operating parameter combination; adjusting the equipment operating parameters of the air conditioner through a PID control algorithm based on the target air conditioning energy consumption and target comfort, as well as the actual air conditioning energy consumption and actual comfort, to obtain final equipment operating parameters; and controlling the air conditioner to work according to the final equipment operating parameters.

[0007] The present invention achieves a balance between air conditioning energy saving effect and comfort by combining a multi-objective particle swarm optimization algorithm and a PID control algorithm. By setting optimization goals and constraints, current environmental data is obtained, and the multi-objective particle swarm algorithm is used to determine the optimal combination of equipment operating parameters. By using the combination of air conditioning equipment operating parameters as particles, the algorithm accurately determines the optimal solution based on environmental data, optimization goals and constraints. The air conditioner is controlled according to the optimal solution to ensure that it meets the comfort requirements while saving energy. In actual operation, the actual energy consumption and comfort data are obtained, and the equipment operating parameters are dynamically adjusted through the PID control algorithm to obtain the final operating parameters. This method realizes the precise control of the air conditioning system, reduces energy consumption, and maintains the comfort of the indoor environment. It effectively solves the problem that energy saving and comfort are difficult to balance in traditional air conditioning control methods, and has good energy-saving effects and good user experience.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the optimal solution of particles is determined based on current environmental data, optimization objectives and constraints through a multi-objective particle swarm algorithm, including: initializing parameters of the multi-objective particle swarm algorithm, the parameters including particle swarm size, maximum number of iterations, inertia weight and acceleration constant; setting the initial position and speed of the particles according to the current environmental data of the air conditioner; determining the initial fitness of the particles according to the optimization objectives and constraints, the fitness being used to measure the pros and cons of the combination of equipment operating parameters represented by the particles in achieving energy saving and comfort; determining an initial individual optimal solution for each particle based on the initial fitness. The optimal solution is obtained, and the global optimal solution set is screened out from the initial states of all particles as the current optimal solution set of the entire particle swarm; the speed of each particle is updated, and the new position of each particle is determined according to the updated speed; the new fitness of the particle is determined based on the new position; if the new fitness is greater than the previous individual optimal fitness of the particle, the individual optimal solution of the particle is updated according to the new fitness; the global optimal solution set is non-dominated sorted and the crowding distance is calculated to determine a better solution, and the global optimal solution set is updated based on the better solution; when the multi-objective particle swarm algorithm reaches the maximum number of iterations, the optimal solution is determined from the updated global optimal solution set based on the optimization goal.

[0009] The technical solution of the above embodiment is adopted, by initializing the parameters of the multi-objective particle swarm algorithm, setting the initial position and speed of the particles according to the current environmental data of the air conditioner, and determining the initial fitness to measure the advantages and disadvantages of the equipment operation parameter combination. By iteratively updating the speed and position of the particles, the individual and global optimal solutions are continuously optimized, and finally the optimal solution is determined. This method can effectively balance the energy saving and comfort of the air conditioner, realize intelligent optimization control, and significantly improve the operating efficiency and user experience of the air conditioning system.

[0010] In combination with some embodiments of the first aspect, in some embodiments, updating the speed of each particle includes: updating the speed of each particle using a preset particle speed update formula, where the particle speed update formula includes:

[0011]

[0012] in, represents the speed of particle i at time t+1, that is, the updated speed of particle i; represents the velocity of particle i at time t; w t represents the dynamic inertia weight, which changes with time t; c1, c2, c3, c4 all represent adaptive acceleration constants, which change with time t; r1, r2, r3, r4 represent random numbers; represents the individual optimal position of particle i at time t; represents the global optimal position of the particle swarm at time t; represents the position of particle i at time t; represents the target conflict adjustment item; Represents the domain exploration factor, with a value range of [0, 1].

[0013] The technical solution of the above embodiment is adopted, and the particle velocity update formula is innovatively improved by introducing dynamic inertia weight and adaptive acceleration constant, as well as target conflict adjustment term and domain exploration factor. This improvement enables particles to adjust speed and direction more flexibly during the search process. The dynamic inertia weight changes over time, which helps to balance the global search and local search capabilities; the adaptive acceleration constant is automatically adjusted according to the current search state to enhance the adaptability of the algorithm. The target conflict adjustment term and domain exploration factor further improve the exploration ability of particles in complex optimization problems, especially in multi-objective optimization, which can effectively deal with conflicts between targets and guide particles to move closer to a better solution, thereby improving the convergence speed of the algorithm and the quality of the solution.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the function of the target conflict adjustment term is:

[0015]

[0016] Where M represents the number of objective functions of the optimization goal, represents the value of particle i on the jth objective function, Global optimal solution The value of the j-th objective function, represents the historical maximum value of the j-th objective function, Represents the historical minimum value of the j-th objective function.

[0017] The technical solution of the above embodiment is adopted to define the specific function form of the target conflict adjustment term, and the movement direction of the particle is adjusted by calculating the relative difference of the particle on each target function. This mechanism can effectively deal with the conflict between targets in multi-objective optimization problems, ensuring that the particle not only pursues the optimality of a single target during the optimization process, but also finds a balance between multiple targets. By introducing the historical maximum and minimum values, the function can dynamically adjust the weight of the target conflict, so that the algorithm can maintain good optimization performance in different search stages, further improving the applicability and effectiveness of the algorithm in complex multi-objective problems.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, the function of the field exploration factor is,

[0019]

[0020] Where N(i) is the neighborhood set of particle i, including particles adjacent to particle i; N is the size of the domain set; Represents the distance between particle i and its neighbor particle k.

[0021] The technical solution of the above embodiment is adopted, and a domain exploration factor is introduced. By calculating the average distance between a particle and other particles in its neighborhood, the exploration behavior of the particle is dynamically adjusted. This mechanism enables the particle to not only focus on the global optimum and the individual optimum during the search process, but also fully consider the information in the local neighborhood, thereby enhancing the local search capability of the algorithm. The introduction of the domain exploration factor helps the particles to be more evenly distributed in the search space, avoids the algorithm from converging to the local optimal solution too early, and improves the diversity and distribution uniformity of the solution. In this way, the algorithm can achieve a better balance between global search and local search, and improve the stability and reliability of the optimization process.

[0022] In combination with some embodiments of the first aspect, in some embodiments, after controlling the air conditioner according to the equipment operating parameter combination corresponding to the optimal solution, it also includes: structuring the equipment operating parameter combination corresponding to the optimal solution to obtain multiple air conditioning operation structured parameters; storing the multiple air conditioning operation structured parameters in an air conditioning parameter database.

[0023] By adopting the technical solution of the above embodiment, structured processing converts complex parameter combinations into clear and standardized data formats, which is convenient for subsequent air conditioning control and data analysis; storage in the database supports historical record management, query and update of parameters, providing strong data support for subsequent data analysis, fault diagnosis, maintenance plan formulation and system upgrade. Through structured storage, users can more conveniently query and adjust the operating parameters of air conditioning equipment, ensure that the system can maintain the optimal operating state under different working conditions, and improve the operating efficiency of the system and user satisfaction.

[0024] In combination with some embodiments of the first aspect, in some embodiments, determining the optimization target and corresponding constraints for energy-saving control of an air conditioner includes: obtaining the user's operation record of the air conditioner; determining the user's personalized preference data based on the operation record; and determining the optimization target and the constraint according to the personalized preference data.

[0025] By adopting the technical solution of the above embodiment, the air conditioning control system can automatically adjust the operation strategy according to the user's actual usage habits and preferences to achieve personalized energy-saving control. In this way, the system can not only meet the user's comfort needs, but also achieve energy-saving goals without the user's knowledge, thereby improving the user's experience and the overall performance of the system. This optimization strategy based on user behavior improves the user experience of air conditioning equipment while ensuring the achievement of energy-saving goals, and is particularly suitable for scenarios that need to take into account both user comfort and energy efficiency.

[0026] In a second aspect, an embodiment of the present invention provides an air-conditioning control system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the air-conditioning control system to execute the method described in the first aspect or the second aspect, and any possible implementation method in the first aspect or the second aspect.

[0027] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on the air-conditioning control system, causes the air-conditioning control system to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0028] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when the computer program product is run on the air-conditioning control system, enables the air-conditioning control system to execute the method described in the first aspect or the second aspect, and any possible implementation method of the first aspect or the second aspect.

[0029] It is understandable that the air conditioning control system provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0030] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0031] 1. Through the multi-objective particle swarm optimization algorithm, a dynamic balance between energy saving and comfort of air-conditioning equipment is achieved. Traditional methods can only pursue energy saving or comfort alone. The present invention takes into account the target air-conditioning energy consumption and target comfort at the same time, and dynamically adjusts the optimization objectives and constraints according to real-time environmental data and user preferences, ensuring the best energy saving effect and comfortable indoor environment under different working conditions. For example, in a scenario where the user is sensitive to temperature, the system will automatically adjust the weight to prioritize comfort while minimizing energy consumption. This dynamic adjustment mechanism significantly improves the adaptability of the system and user satisfaction.

[0032] 2. The particle velocity update formula introduces dynamic inertia weights, adaptive acceleration constants, target conflict adjustment items, and domain exploration factors. These improvements enable particles to adjust speed and direction more flexibly during the search process, improving the global search capability and local search accuracy of the algorithm. In particular, in multi-objective optimization problems, the target conflict adjustment items and domain exploration factors can effectively handle conflicts between objectives, guide particles to move closer to a better solution, avoid the algorithm from converging to a local optimal solution too early, and improve the diversity and distribution uniformity of the solution. In this way, the present invention can find a better solution in complex optimization problems, significantly improving the operating efficiency and energy-saving effect of air-conditioning equipment.

[0033] 3. By obtaining the user's operation records of the air conditioner, the user's personalized preference data is analyzed, and the optimization objectives and constraints are adjusted accordingly. This method enables the air conditioning control system to automatically adjust the operation strategy according to the user's actual usage habits and preferences to achieve personalized energy-saving control. In addition, the equipment operation parameter combination corresponding to the optimal solution is structured and stored in the air conditioning parameter database, which not only facilitates the management and application of the optimization results, but also provides strong data support for subsequent data analysis, fault diagnosis, maintenance plan formulation and system upgrades. Through structured storage, users can more easily query and adjust the operating parameters of the air conditioning equipment, ensure that the system can maintain the optimal operating state under different working conditions, and improve the system's operating efficiency and user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0035] Figure 1 is a flow chart of an air conditioning energy-saving control method based on multi-objective optimization according to an embodiment of the present invention;

[0036] Figure 2 is a flow chart of a multi-objective particle swarm algorithm according to an embodiment of the present invention;

[0037] Figure 3 It is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0039] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0040] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0041] The embodiment of the present invention provides an air-conditioning energy-saving control method based on multi-objective optimization. By comprehensively considering the two core optimization goals of energy consumption and comfort, and combining the constraints in actual operation, a multi-objective particle swarm algorithm (MOPSO) is used for dynamic optimization, and PID control technology is combined to achieve the optimal balance between energy saving and comfort of the air conditioner.

[0042] The embodiment of the present invention achieves a balance between air conditioning energy saving effect and comfort by combining a multi-objective particle swarm optimization algorithm and a PID control algorithm. By setting optimization goals and constraints, current environmental data is obtained, and the multi-objective particle swarm algorithm is used to determine the optimal combination of equipment operating parameters. By using the combination of air conditioning equipment operating parameters as particles, the algorithm accurately determines the optimal solution based on environmental data, optimization goals and constraints. The air conditioner is controlled according to the optimal solution to ensure that it meets the comfort requirements while saving energy. In actual operation, the actual energy consumption and comfort data are obtained, and the equipment operating parameters are dynamically adjusted through the PID control algorithm to obtain the final operating parameters. This method realizes the precise control of the air conditioning system, reduces energy consumption, and maintains the comfort of the indoor environment. It effectively solves the problem that energy saving and comfort are difficult to balance in traditional air conditioning control methods, and has good energy saving effects and good user experience.

[0043] The method of this embodiment provides an efficient and reliable optimization means for intelligent control of air conditioners, and is applicable to energy-saving management in various building environments.

[0044] Combine the following Figure 1 The air conditioning energy saving control method based on multi-objective optimization of this embodiment is specifically described, which can be executed by an air conditioning control system (hereinafter referred to as the system). The method includes the following steps:

[0045] Step 101, determining the optimization target and corresponding constraint conditions for energy-saving control of the air conditioner.

[0046] Among them, the optimization goal includes target air conditioning energy consumption and target comfort. Comfort refers to the comfort of the indoor environment to people, which is evaluated through quantitative indicators such as indoor temperature, humidity, air quality, air conditioning wind speed, air conditioning noise and other parameters. Constraints refer to a series of restrictions that need to be met during the air conditioning energy-saving control process to ensure the safe and stable operation of the air conditioning equipment and to ensure that the indoor environmental parameters are within the comfortable range, such as the upper and lower limits of equipment operating parameters such as compressor speed, fan wind speed, and fresh air volume. It can also include the specific range of environmental parameters such as indoor temperature, humidity, and CO2 concentration.

[0047] In the optimization goal, the target air conditioning energy consumption refers to the minimum energy consumption level expected to be achieved by the air conditioning equipment during operation, and the air conditioning energy consumption is minimized to achieve the goal of energy conservation and emission reduction. The target comfort level refers to the comprehensive level of various indicators that the indoor environment should achieve under air conditioning control to make people feel comfortable and satisfied, such as suitable temperature, humidity and air quality, in order to maximize the comfort of indoor personnel.

[0048] Specifically, when the air conditioner is running, the system first collects the current indoor and outdoor environmental data, such as temperature, humidity, CO2 concentration, etc., through environmental sensors, and combines the preset comfort standards and equipment safety operation specifications to determine the optimization goals of minimizing air conditioning energy consumption and maximizing comfort. At the same time, according to the performance parameters of the air conditioning equipment and the manufacturer's recommendations, set the constraints of the operating parameters, such as the reasonable range of compressor speed and fan speed, and the comfortable range of indoor environmental parameters, to ensure that in the pursuit of energy saving and comfort, the equipment operates safely and stably and the indoor environment is always kept in a suitable state.

[0049] On the other hand, the system can quantify this optimization goal through energy consumption model and comfort model respectively. For example, the energy consumption model can be calculated based on the product of air conditioning power and operating time, while the comfort model can be evaluated using thermal comfort indicators (such as PMV-PPD model).

[0050] Then, constraints are set to ensure that the optimization results are feasible and safe in actual operation, including the physical limitations of equipment operating parameters and environmental requirements. By clarifying the optimization objectives and constraints, the best balance between energy saving and comfort can be achieved while ensuring the normal operation of the air-conditioning equipment, providing a clear optimization framework and boundary conditions for the subsequent multi-objective optimization algorithm.

[0051] Step 102, obtaining current environmental data of the air conditioner.

[0052] Specifically, it can be achieved by arranging various sensors in the space where the air conditioner is located. These sensors include temperature sensors, humidity sensors, carbon dioxide sensors, light sensors, etc., which can monitor indoor environmental parameters such as temperature, humidity, carbon dioxide concentration, light intensity, etc. in real time. For example, the temperature sensor is usually installed in the center of the room to avoid direct influence from sunlight or air conditioner outlet to ensure the accuracy of measurement. The sensor transmits the collected data to the air conditioning control system via wired or wireless means, and the control system analyzes and processes the received data in real time, thereby providing accurate environmental data basis for subsequent air conditioning energy-saving control, ensuring that the air conditioner can operate stably and efficiently under different environmental conditions, meet the user's comfort requirements and achieve energy-saving goals.

[0053] Step 103: Combining the equipment operating parameters of the air conditioner as particles in a multi-objective particle swarm algorithm.

[0054] Among them, in the multi-objective particle swarm optimization (MOPSO) algorithm, the equipment operating parameter combination of the air conditioner is represented as a particle, which means that each particle represents a specific equipment operating state. For example, a particle (equipment operating parameter combination) can include parameters such as the speed of the compressor, the wind speed of the fan, and the fresh air volume. These parameter combinations are abstracted as the positions of particles in the MOPSO algorithm and are used to search in the multi-dimensional solution space to find the optimal solution that meets the optimization objectives and constraints.

[0055] Step 104, determining the optimal solution of the particle based on the current environment data, the optimization goal and the constraint condition through the multi-objective particle swarm algorithm.

[0056] Specifically, through the multi-objective particle swarm algorithm, each particle in the particle swarm is iteratively optimized based on the currently collected environmental data (such as indoor temperature, humidity, CO2 concentration, etc.), the preset optimization goals (such as minimizing air conditioning energy consumption and maximizing indoor comfort), and the constraints (such as the operating range of equipment parameters, the comfortable range of indoor environmental parameters, etc.). The MOPSO algorithm simulates the movement of particles in the solution space and continuously adjusts the speed and position of particles to search for a better solution. In each iteration, the performance of the particles is evaluated according to the fitness function, and the individual optimal solution and the global optimal solution are updated through the cooperation and competition mechanism between particles, and finally the optimal solution that meets all conditions is determined, that is, the most suitable combination of equipment operating parameters.

[0057] Step 105: Control the air conditioner according to the target device operating parameter combination corresponding to the optimal solution.

[0058] Specifically, the system converts the target device operating parameter combination into a specific control instruction and sends it to each execution component of the air conditioning system. For example, if the parameters in the target device operating parameter combination include compressor speed, fan speed and fresh air volume, then these parameter values ​​are transmitted to the compressor, fan and fresh air adjustment device through the air conditioning control system, so that they can operate according to the predetermined parameters. The compressor controller will adjust its operating speed according to the target speed, the fan controller will adjust its air supply volume according to the target speed, and the fresh air adjustment device will control the opening of the fresh air valve according to the target fresh air volume.

[0059] The entire process requires ensuring the coordinated work between various components, as well as real-time monitoring and feedback of indoor environmental parameters, so as to continuously optimize the equipment operating status during operation and ensure that the air-conditioning system operates in the optimal state to meet energy-saving and comfort requirements.

[0060] Step 106, when the air conditioner operates according to the target device operating parameter combination, the actual air conditioning energy consumption and the actual comfort level are obtained.

[0061] Specifically, the energy metering equipment installed in the air conditioning system records the energy consumption of the air conditioner during operation in real time, and calculates the actual air conditioning energy consumption in kilowatt-hours (kWh). In addition, environmental sensors (such as temperature, humidity, CO2 concentration, etc.) are used to monitor indoor environmental parameters, collect data in real time and calculate the actual comfort score. The comfort score can be evaluated and determined by the PMV-PPD model mentioned above to ensure that it is within the comfort range set by the user. By comparing the actual energy consumption data with the target energy consumption, and comparing the actual comfort with the target comfort, the system can evaluate the effectiveness of the current operating status and provide a basis for subsequent adjustments.

[0062] Step 107, based on the target air conditioning energy consumption and the target comfort level, as well as the actual air conditioning energy consumption and the actual comfort level, the equipment operating parameters of the air conditioner are adjusted by a PID control algorithm to obtain final equipment operating parameters.

[0063] Among them, the PID control algorithm is the proportional-integral-differential control algorithm, which adjusts the control amount by calculating the error signal of the control object, that is, the difference between the target value and the actual value, so as to achieve precise control of the system. The core of the PID control algorithm lies in its three key components: proportional (P), integral (I) and differential (D). The proportional term adjusts the control amount proportionally according to the size of the current error, responds quickly to the error change, but may not completely eliminate the steady-state error; the integral term accumulates the error, which can eliminate the long-standing steady-state error and improve the control accuracy; the differential term adjusts the control amount according to the rate of change of the error, predicts the future trend of the error, responds in advance, and enhances the stability and response speed of the system. By reasonably adjusting the proportional gain, integral time and differential time parameters of the PID controller, the PID control algorithm can effectively balance the response speed, stability and control accuracy of the system.

[0064] Specifically, in this embodiment, the system compares and analyzes the actual air-conditioning energy consumption and actual comfort level with the preset target air-conditioning energy consumption and target comfort level, and calculates the energy consumption error and comfort error. The energy consumption error refers to the difference between the actual energy consumption and the target energy consumption, and the comfort error refers to the difference between the actual comfort level and the target comfort level.

[0065] Subsequently, these error values ​​are input into the PID control algorithm. The PID controller calculates the control quantities of the proportional term, integral term, and differential term according to the size and changing trend of the error. The proportional term is proportional to the current error and is used to quickly respond to error changes. The integral term accumulates the error to eliminate long-standing steady-state errors. The differential term is adjusted according to the rate of change of the error to predict the future trend of the error and respond in advance.

[0066] Finally, these three control quantities are added together to obtain the total control output, and the operating parameters of the air-conditioning equipment are adjusted according to this control output. For example, if the energy consumption error is large, the compressor speed may need to be reduced to reduce energy consumption; if the comfort error is large, the fan speed or fresh air volume may need to be adjusted to improve indoor comfort. By continuously cycling this process, the PID control algorithm can adjust the operating parameters of the air-conditioning equipment in real time so that it can achieve the best operating state while meeting the energy-saving and comfort requirements, thereby realizing precise control and optimized management of the air-conditioning system.

[0067] In this embodiment, the process of adjusting the equipment operating parameters by using the PID control algorithm is as follows:

[0068] (1) Error calculation:

[0069] Energy consumption error: Calculate the difference between the target air conditioning energy consumption and the actual air conditioning energy consumption, denoted as e energy .

[0070] Comfort error: Calculate the difference between the target comfort and the actual comfort, denoted as e comfort .

[0071] (2) PID control calculation:

[0072] Proportional term: According to the size of the error, the control amount is adjusted proportionally, and the proportional coefficient is K p , the calculation formula is P=K p ⋅(e energy +e comfort ).

[0073] Integral term: Integrate the error over time to eliminate the cumulative error. The integral coefficient is K. i , the calculation formula is I=K i ⋅∫(e energy +e comfort )dt.

[0074] Differential term: adjust the rate of change of the error to predict future trends, the differential coefficient is K d , the calculation formula is D=K d ⋅d(e energy +e comfort ) / dt.

[0075] (3) Output control quantity:

[0076] Add the proportional term, integral term and differential term to get the total control quantity Control=P+I+D.

[0077] (4) Parameter adjustment:

[0078] According to the control amount Control, the equipment operating parameters of the air conditioner are adjusted. For example, if the control amount is positive, it means that the equipment operating parameters need to be increased to improve comfort or reduce energy consumption; if the control amount is negative, it means that the equipment operating parameters need to be reduced.

[0079] (5) Get the final equipment operating parameters:

[0080] The adjusted equipment operating parameters are used as the final equipment operating parameters to control the air conditioning system. These parameters include compressor speed, fan speed, fresh air volume, etc., to ensure that the air conditioning system operates in the optimal state to meet energy saving and comfort requirements.

[0081] Through the above steps, the PID control algorithm can dynamically adjust the operating parameters of the air-conditioning equipment according to the target and actual energy consumption and comfort data, and realize precise control of the air-conditioning system.

[0082] Step 108, controlling the air conditioner to operate according to the final equipment operating parameters.

[0083] Specifically, these parameters are mainly converted into specific control instructions through the control system of the air conditioner, and sent to the various execution components of the air conditioner. Specifically, the final equipment operating parameters (such as compressor speed, fan speed, fresh air volume, etc.) are first input into the controller of the air conditioner, and the controller generates corresponding control signals based on these parameters. For example, if the final equipment operating parameters require the compressor to run at a specific speed, the controller will generate a corresponding control signal and send it to the compressor driver. After receiving the signal, the driver adjusts the operating state of the compressor to achieve the required speed. Similarly, for other components such as fans and fresh air adjustment devices, the controller will also generate corresponding control signals based on the final equipment operating parameters to ensure that they operate according to the predetermined parameters.

[0084] The entire process requires ensuring the coordinated work between various components, as well as real-time monitoring and feedback of indoor environmental parameters, so as to continuously optimize the equipment operating status during operation and ensure that the air-conditioning system operates in the optimal state to meet energy-saving and comfort requirements.

[0085] In this embodiment, the air conditioning energy-saving control method based on multi-objective optimization is adopted to effectively achieve a balance between energy saving and comfort. First, by clarifying the optimization goals, including target air conditioning energy consumption and target comfort, the system can set a clear direction in the design stage, making the subsequent control strategy more targeted. The step of obtaining current environmental data ensures that the system can reflect indoor and outdoor changes in real time, thereby providing accurate basic information for the optimization process.

[0086] After the air conditioner equipment operating parameter combination is used as a particle in the multi-objective particle swarm algorithm, the system uses the algorithm's powerful search capability to dynamically determine the optimal solution for each particle based on real-time environmental data and the set optimization goal. This process not only improves the adaptability of the algorithm, but also ensures that the air conditioning system can respond quickly and adjust operating parameters under complex environmental conditions to achieve the best energy-saving effect.

[0087] By controlling the air conditioner to work according to the target equipment operating parameter combination corresponding to the optimal solution, the system can monitor energy consumption and comfort in real time during actual operation, ensuring that the equipment meets the user's comfort needs while saving energy. Combined with the PID control algorithm, the system can dynamically adjust the equipment operating parameters according to the difference between the target and actual energy consumption and comfort, ensuring the optimization of the final equipment operating parameters. This closed-loop control mechanism enables the air conditioning system to maintain efficient operation under different working conditions, effectively reducing energy consumption while improving the comfort of the indoor environment.

[0088] The method of this embodiment improves the intelligence level of the air-conditioning system through multi-objective optimization and PID control algorithm, ensuring an effective balance between energy saving and comfort.

[0089] In some embodiments, Figure 2 As shown, step 104 specifically includes the following:

[0090] Step 201, initializing the parameters of the multi-objective particle swarm algorithm.

[0091] Among them, the parameters of the multi-objective particle swarm algorithm in this embodiment include particle swarm size, maximum number of iterations, inertia weight and acceleration constant. The particles in the algorithm represent the combination of equipment operating parameters of the air conditioner, including compressor speed, fan speed, fresh air volume, temperature setting value, etc. These equipment operating parameters jointly determine the operating state and performance of the air conditioner.

[0092] Specifically, when initializing the parameters of the multi-objective particle swarm algorithm, the particle swarm size, that is, the number of particles, is first determined, which is usually selected according to the complexity of the problem and the size of the search space and can be set between 20 and 100. Then the maximum number of iterations is set, which depends on the desired algorithm accuracy and the limitation of computing resources, and can be between 100 and 1000 iterations.

[0093] Particle velocity represents the direction and speed of a particle moving in the search space, and is used to guide the particle to move from the current position to a new position to find a better solution.

[0094] Then select the inertia weight. The inertia weight is used to control the influence of the particle's previous velocity on the current velocity. The value range can be between [0.4, 0.9] and can be fixed or dynamically adjusted with the number of iterations.

[0095] Finally, the acceleration constant is set to control the weight of the influence of individual optimum and global optimum on particle velocity, and to adjust the speed at which particles move to the individual optimum and global optimum positions, thereby affecting the convergence speed and accuracy of the algorithm. In this embodiment, the acceleration constant is specifically an adaptive acceleration constant, which can change dynamically according to time.

[0096] By properly initializing these parameters, the multi-objective particle swarm algorithm can be provided with efficient search capabilities to ensure that a high-quality Pareto optimal solution is found in the air conditioning energy-saving control problem. The Pareto optimal solution refers to a solution in a multi-objective optimization problem that, when improving any objective function value, will at least make another objective function value worse. It is a solution that cannot improve one objective without compromising at least one other objective, and represents the best trade-off between different objectives.

[0097] Step 202: setting the initial position and speed of the particle according to the current environmental data of the air conditioner.

[0098] Among them, the velocity of the particle is used to represent the moving direction and speed of the particle in the search space, thereby providing a starting point for the iterative optimization process of the particle swarm algorithm.

[0099] Specifically, when setting the initial position and speed of the particles according to the current environmental data of the air conditioner, first collect environmental parameters such as indoor temperature, humidity, CO2 concentration, and operating status data of the air conditioning equipment, such as the current speed of the compressor and the wind speed of the fan.

[0100] Then, based on these operating status data, an initial position is randomly generated for each particle, that is, the initial equipment operating parameter combination, ensuring that these equipment operating parameter combinations are within a reasonable operating range, such as the compressor speed is 1000-3000RPM and the fan speed is 1-5 m / s.

[0101] At the same time, the velocity of the particle is initialized, represented by a velocity vector. The initial value of the velocity vector can be set to zero or randomly generated within a certain range.

[0102] Step 203: Determine the initial fitness of each particle according to the optimization goal and the constraint condition.

[0103] Among them, fitness is used to measure the pros and cons of the equipment operating parameter combination represented by the particle in achieving energy saving and comfort.

[0104] Specifically, we first need to construct a fitness function that comprehensively considers both energy saving and comfort indicators. The fitness function can include the weighted sum of air conditioning energy consumption and indoor environmental comfort, where the energy consumption part is quantified by measuring the power consumption of air conditioning equipment under a specific parameter combination, and the comfort part is quantified by evaluating the deviation of indoor temperature, humidity, CO2 concentration and other parameters from the preset comfort range.

[0105] Then, for each particle (i.e., equipment operation parameter combination), its corresponding parameters are substituted into the fitness function to calculate the comprehensive score of the combination in achieving energy saving and comfort. The higher the fitness value, the better the performance of the parameter combination in terms of energy saving and comfort, thus providing a basis for the subsequent optimization process.

[0106] In some embodiments, the fitness function can be expressed as Fitness(), which is used to evaluate the performance of the particle under the current device parameter combination, comprehensively consider multiple goals such as energy saving and comfort, and return a scalar value. The smaller the value, the better the performance of the particle. In this embodiment, the specific mathematical form of the fitness function is:

[0107]

[0108] Among them, Xi is the equipment operating parameter combination represented by the i-th particle.

[0109] Energy(Xi) is the energy of the equipment operating parameter combination X i The energy consumption of the air conditioner is standardized. By converting the actual energy consumption data into a dimensionless standardized form, the energy consumption index can be comprehensively evaluated with other indicators such as comfort in the optimization algorithm.

[0110] Comfort(Xi) is when the device is running X i The comfort score of the indoor environment can range from [0, 1], where 1 means completely comfortable and 0 means completely uncomfortable.

[0111] α and β are weight coefficients used to balance the importance of energy consumption and comfort, usually α+β=1.

[0112] Furthermore, the comfort score can be evaluated based on multiple environmental parameters. The comfort score function Comfort(X i ) can be:

[0113]

[0114] Here, n is the number of environmental parameters considered, such as temperature, humidity, CO2 concentration, etc.

[0115] is the actual value of the jth environmental parameter under the parameter combination Xi.

[0116] is the ideal value or the midpoint of the comfort range of the jth environmental parameter.

[0117] is the width of the comfort range of the jth environmental parameter.

[0118] Step 204, based on the initial fitness, determine the initial individual optimal solution for each particle, and select the global optimal solution set from the initial states of all particles as the current optimal solution set of the entire particle swarm.

[0119] Specifically, after the initial position and fitness value of each particle are calculated, its current position is taken as its individual optimal solution (i.e., p besti ), because the particle has not moved yet, the current position is the current optimal one.

[0120] Then, by comparing the fitness values ​​of all particles, the non-dominated solutions with the best performance on multiple optimization objectives are selected to form the initial global optimal solution set (i.e., G best ), these solutions are superior to other solutions in terms of energy saving and comfort, and there is no dominance relationship between them. Finally, the screened global optimal solution set is used as the current optimal solution set of the entire particle swarm, providing a reference for subsequent particle speed and position updates. This process ensures that the algorithm can identify high-quality potential solutions in the initial stage, laying the foundation for subsequent optimization searches.

[0121] For example, first, the initial fitness value of each particle is compared, and the initial position and corresponding fitness value of each particle are stored as its individual optimal solution;

[0122] That is, for each particle i, p i =x i (0), and p fitness,i =Fitness(x i (0)), where x i (0) is the initial position of particle i, Fitness(x i (0)) is its initial fitness.

[0123] Next, the global optimal solution set is selected from the initial individual optimal solutions of all particles, and the non-dominated sorting method is used to find solutions that are not dominated by other solutions in both energy consumption and comfort optimization objectives to form the Pareto optimal solution set.

[0124] These solutions constitute the current global optimal solution set G of the entire particle swarm. best (0), providing a benchmark for subsequent iterative optimization.

[0125] Step 205, updating the velocity of each particle, and determining the new position of each particle according to the updated velocity.

[0126] Specifically, firstly, according to the preset particle velocity update formula in the multi-objective particle swarm algorithm, the velocity of the particle at the next moment is calculated by combining the current velocity, the individual optimal solution and the global optimal solution; the velocity update formula usually includes inertia weight, acceleration constant and random factor to balance the global search and local development capabilities.

[0127] Next, the updated velocity is added to the current position to obtain the new position of the particle. If the new position exceeds the boundary of the search space (such as the value range of the device operating parameters), it is adjusted to a reasonable range through truncation or reflection.

[0128] In this way, particles can continuously move in the search space, gradually approaching a better solution area, while ensuring the feasibility and diversity of the solution.

[0129] In some embodiments, the particle velocity update formula includes:

[0130]

[0131] in, represents the speed of particle i at time t+1, that is, the updated speed of particle i; represents the velocity of particle i at time t.

[0132] w t Represents the dynamic inertia weight, which changes with time t; specifically, the dynamic inertia weight decreases with time, with a larger initial value to enhance the global search capability, and a smaller value in the later stage to enhance the local development capability, ensuring that the algorithm efficiently balances exploration and development at different stages. The dynamic inertia weight is obtained by gradually decreasing the pre-set decreasing function as the number of iterations of the particle swarm optimization algorithm increases. Common decreasing methods include linear decreasing and nonlinear decreasing. The purpose is to give particles a larger search freedom in the early stage of the algorithm to enhance the global exploration capability, and gradually reduce the weight value as the iteration proceeds, so that the search behavior of the particles is more focused on the local area, thereby enhancing the local search accuracy of the algorithm, and finally achieving an effective balance between global and local searches, and improving the algorithm's optimization capability and convergence speed.

[0133] c1, c2, c3, and c4 all represent adaptive acceleration constants, which change with time t. Specifically, the adaptive acceleration constants include the individual optimal acceleration constant c1, the global optimal acceleration constant c2, the target conflict adjustment acceleration constant c3, and the domain exploration acceleration constant c4.

[0134] The individual optimal acceleration constant c1 controls the step size of the particle moving towards the individual optimal solution; the larger c1 is, the more the particle tends to move towards its own historical optimal position, enhancing the local search ability; c1 decreases with time, relying more on the individual optimal solution in the early stage and gradually weakening in the later stage.

[0135] The global optimal acceleration constant c2 controls the step size of the particle moving towards the global optimal solution; the larger c2 is, the more the particle tends to move towards the global optimal position, enhancing the global search capability; c2 generally increases over time, and later on it becomes more dependent on the global optimal solution.

[0136] c1 and c2 can be adjusted according to the ratio of the particle's current fitness to the global optimal fitness. If the particle's fitness is poor, c1 is increased to strengthen individual learning and encourage the particle to rely more on its own experience to explore new areas. On the contrary, if the particle is close to the global optimum, c2 is increased to strengthen social learning and push the particle to the optimal solution.

[0137] The target conflict adjustment acceleration constant c3 controls the step size of the particle moving toward the equilibrium solution in multi-target optimization, and is used to adjust the target conflict; the larger c3 is, the more the particle tends to balance multiple targets (such as energy consumption and comfort), avoiding a single target dominating the search process and accelerating over time, and gradually optimizing the particle search behavior. c3 usually accelerates over time, and the later stage emphasizes target conflict adjustment.

[0138] The domain exploration acceleration constant c4 controls the particle's tendency to explore the surrounding local area at the current position; the larger c4 is, the more the particle tends to explore the neighborhood, enhance the local search ability, and avoid premature convergence; c4 usually decreases over time, with more emphasis on domain exploration in the early stage and gradually weakening in the later stage.

[0139] c3 and c4 can be adjusted according to the degree of target conflict or neighborhood diversity. When the target conflict is significant, the weight of c3 is increased to alleviate the conflict and guide the particles to seek a multi-target balance. The domain exploration acceleration constant c4 changes with the uniformity of particle distribution in the neighborhood. The more dispersed the neighborhood, the larger c4 is, which encourages particles to explore areas that have not been fully searched. This adaptive adjustment mechanism enables the acceleration constant to change flexibly according to the actual situation in the optimization process, enhancing the algorithm's adaptability and efficiency in solving complex optimization problems.

[0140] r1, r2, r3, and r4 represent random numbers, which are used to introduce randomness, enhance the algorithm's exploration ability, and avoid falling into local optimality. These random numbers are usually distributed in the interval [0, 1] and are independently generated for each particle in each iteration through a random number generator (such as the linear congruential method, the Mersenne twister algorithm, etc.). After the generated random numbers are multiplied by the corresponding acceleration constants, the influence of individual optimality, global optimality, target conflict adjustment items, and domain exploration factors in the particle velocity update are adjusted to make the movement of particles in the search space more flexible and diverse. The introduction of this randomness helps particles to explore extensively in the global search phase and to search carefully in the local search phase, thereby improving the global convergence ability of the algorithm and the quality of the solution.

[0141] Represents the position of particle i at time t. During initialization, the initial position of each particle is randomly generated In each iteration, the new position is calculated based on the updated velocity, i.e. .

[0142] represents the individual optimal position of particle i at time t. When the algorithm is initialized, the initial position of each particle is its initial individual optimal position, that is, In each iteration, the fitness of each particle is calculated. If the current fitness is better than the previous individual optimal fitness, the individual optimal position is updated, that is, .

[0143] Represents the global optimal position of the particle swarm at time t. When the algorithm is initialized, one of the initial individual optimal positions of all particles is selected as the initial global optimal position. , usually select the optimal position g of the individual with the best fitness 0 , which is expressed as g 0 =arg min i Fitness( ). In each iteration, the position with the best fitness is selected from the individual optimal positions of all particles as the new global optimal position, denoted as g t =arg min i Fitness( ).

[0144] Represents the target conflict adjustment item, which is used to dynamically adjust the particle speed in multi-objective optimization to balance the conflicts between different objectives (such as energy consumption and comfort) and ensure that the algorithm can find the Pareto optimal solution.

[0145] Represents the domain exploration factor, with a value range of [0, 1]. It is used to indicate the tendency of a particle to explore the surrounding local area at the current position. By measuring the distribution of neighboring particles, the search behavior of particles is dynamically adjusted to enhance the local search capability.

[0146] The particle velocity update formula of this embodiment significantly improves the algorithm's search capability and optimization effect by introducing dynamic inertia weights, adaptive acceleration constants, target conflict adjustment items, and domain exploration factors. The dynamic inertia weights enhance global search capabilities in the early stages and local development capabilities in the later stages, ensuring that the algorithm efficiently explores the solution space; the adaptive acceleration constant is dynamically adjusted according to the number of iterations to balance the impact of individual optimal solutions and global optimal solutions; the target conflict adjustment item guides particles to approach the Pareto optimal solution by quantifying the conflicts between multiple objectives; the domain exploration factor enhances local search capabilities and avoids premature convergence by measuring the distribution of neighborhood particles. These mechanisms work together to enable the algorithm to find high-quality equilibrium solutions in complex multi-objective optimization problems while taking into account energy conservation and comfort goals, and have high practicality and robustness. Further, in this embodiment, the function of the target conflict adjustment item is,

[0147]

[0148] Wherein, M represents the number of objective functions of the optimization target. In this embodiment, the optimization targets include energy consumption and comfort, and M can take a value of 2.

[0149] Represents the value of particle i on the jth objective function. The specific way to obtain is: first define each objective function f j For air conditioning energy-saving control problems, the objective function may include energy consumption and comfort. For example, the energy consumption function can calculate the current power consumption based on parameters such as compressor speed and fan speed; the comfort function may involve environmental parameters such as indoor temperature, humidity, and CO2 concentration. In each iteration, according to the current position of particle i Calculate the value of each objective function. These values ​​can be obtained through sensor data, model calculations or experimental measurements, and are standardized as needed to ensure the comparability of different objective function values.

[0150] Global optimal solution The value of the j-th objective function. The specific method of obtaining is as follows: first determine the global optimal position , which is the optimal solution selected from the individual optimal positions of all particles by non-dominated sorting and other methods. Then, use The same objective function f jcalculate The value on the objective function. This value reflects the performance of the current global optimal solution on a specific goal. It also needs to be calculated according to the definition of the objective function and standardized so that it can be compared and adjusted during the optimization process.

[0151] represents the historical maximum value of the j-th objective function, Represents the historical minimum value of the j-th objective function. and Used for standardization of objective function values ​​to ensure comparability of different objective function values. and Initialize to the maximum and minimum values ​​of the initial values ​​of all particles on the objective function. As the algorithm iterates, these values ​​are continuously updated to reflect the range of changes in the objective function value. Specifically, after each calculation of the objective function value, compare the current value with and , if the current value is greater or less, update or In this way, the standardized range of the objective function value can be adjusted dynamically, ensuring that the algorithm can effectively handle the conflicts and balances between different objectives throughout the optimization process.

[0152] In this embodiment, the target conflict adjustment function dynamically adjusts the particle speed by quantifying the conflict between multiple objectives (such as energy consumption and comfort), so that the particles can better balance multiple optimization objectives during the search process. Specifically, the target conflict adjustment function calculates the difference between the particle and the global optimal solution in each objective function, and normalizes it as an adjustment factor to guide the particle to the Pareto optimal solution. This mechanism avoids a single goal dominating the search process, ensures that the algorithm can find a set of solutions that achieve a good balance between multiple objectives, and enhances the robustness and convergence of the algorithm, making it perform well in multi-objective optimization problems.

[0153] In some embodiments, the function of the domain exploration factor is,

[0154]

[0155] Among them, N(i) is the neighborhood set of particle i, which means the set of particles adjacent to particle i in the particle swarm optimization algorithm. These neighboring particles are close to particle i in the search space and are used to calculate the domain exploration factor to help particle i perform more detailed search in the local area.

[0156] N is the size of the domain set, which indicates the number of particles in the neighborhood set N(i), that is, the total number of particles adjacent to particle i, and is used to average the distance when calculating the domain exploration factor;

[0157] represents the position of particle i at time t, represents the position of particle k at time t.

[0158] Represents the distance between particle i and its neighbor particle k.

[0159] The domain exploration factor function of this embodiment dynamically adjusts the search behavior of particles and enhances local search capabilities by measuring the distribution of particle neighborhoods. Specifically, the domain exploration factor function calculates the distance between particles and neighboring particles, and adjusts the exploration tendency of particles according to the degree of dispersion of the neighborhood: when the neighborhood is dispersed, particles tend to strengthen local search; when the neighborhood is concentrated, particles tend to maintain the current search direction. This mechanism effectively avoids the algorithm from converging to a local optimal solution too early, while improving the diversity of the search and the quality of the solution, enabling the algorithm to more comprehensively explore the solution space in complex multi-objective optimization problems and find a better equilibrium solution.

[0160] Step 206: Determine a new fitness of the particle based on the new position.

[0161] Specifically, after calculating the new position of each particle, determining the new fitness of the particle based on the new position is achieved by evaluating the performance of the equipment operating parameter combination corresponding to the new position in terms of energy saving and comfort.

[0162] First, according to the parameter combination of the new location (such as temperature setting, wind speed, etc.), the energy consumption value of the air conditioner (such as the product of power and running time) is calculated and normalized to a reasonable range; secondly, the comfort index of the indoor environment is calculated based on the thermal comfort model (such as the PMV-PPD model), and normalized in the same way. Then, these two target values ​​are weighted or combined through a multi-objective optimization method to form a comprehensive fitness value, which is used to measure the pros and cons of the new location in terms of energy saving and comfort. At the same time, check whether the new location meets the constraints (such as temperature, wind speed, humidity, etc.). If not, its fitness is penalized to ensure that the optimization results are feasible in actual operation.

[0163] In this way, a new fitness value reflecting its performance can be generated for each particle's new position, providing a basis for the subsequent optimization process.

[0164] Among them, the thermal comfort model (PMV-PPD model) is a mathematical model used to quantify human thermal comfort, in which PMV (Predicted Mean Vote) represents the average feeling of most people for the thermal environment, and the value range is usually -3 (cold) to +3 (hot), and 0 represents the thermal neutral state; PPD (Predicted Percentage of Dissatisfied) represents the proportion of people who are dissatisfied with the thermal environment, which is usually related to the PMV value. Even if PMV is 0, PPD may be 5%. This model comprehensively considers environmental factors (such as ambient temperature, humidity, air flow rate) and human factors (such as metabolic rate, clothing thermal resistance), and can accurately evaluate the comfort of the indoor environment and provide a scientific basis for the optimization control of air-conditioning equipment.

[0165] Next, determine whether the new fitness is greater than the previous individual optimal fitness of the particle.

[0166] If yes, proceed to step 207.

[0167] If not, the individual optimal solution and individual optimal fitness of the particle are kept unchanged and not updated. This means that the particle has not found a better solution in the current iteration, so it continues to use its historical optimal position and fitness value as a reference for subsequent searches. In this way, it can ensure that each particle always records its historical optimal state, avoiding the impact of local inferior solutions on the global search process, while providing guarantees for the convergence of the algorithm and the quality of the solution.

[0168] Step 207: Update the individual optimal solution of the particle according to the new fitness.

[0169] Specifically, the new fitness is first compared with the particle's current individual optimal fitness. If the new fitness is better (i.e., better in terms of energy saving and comfort), the particle's individual optimal solution is updated to the current new position, and the individual optimal fitness is updated to the new fitness value; if the new fitness is not better than the current individual optimal fitness, the original individual optimal solution and fitness value are retained. This process ensures that each particle always records its historical optimal position, providing a reliable basis for subsequent speed updates and global optimal solution screening, while driving the algorithm to gradually approach a better solution area.

[0170] Step 208: Perform non-dominated sorting and crowding distance calculation on the global optimal solution set to determine a better solution, and update the global optimal solution set based on the better solution.

[0171] Among them, non-dominated sorting is a method to divide the solution set into multiple Pareto frontier layers, which is used to identify non-dominated solutions in the solution set. The Pareto frontier refers to the boundary of all Pareto optimal solutions in the objective space in multi-objective optimization problems. These solutions improve one objective without deteriorating other objectives, representing the best trade-off and balance between different objectives.

[0172] First, all solutions that are not dominated by other solutions are selected from the global optimal solution set to form the first layer of Pareto frontier; then, non-dominated solutions are selected from the remaining solutions again to form the second layer of Pareto frontier, and so on, until all solutions are assigned to a certain layer. Non-dominated sorting ensures that the Pareto optimal solution can be retained first, and at the same time provides a stratification basis for the subsequent crowding distance calculation.

[0173] The crowding distance is used to measure the distribution density of solutions in the target space to ensure that the solution set is diverse. For each layer of the Pareto frontier solution, each objective function is first sorted, and then the difference in the objective function value between each solution and its adjacent solution is calculated, and these differences are normalized and accumulated to obtain the crowding distance of the solution. The larger the crowding distance, the sparser the distribution around the solution, and the more important the solution. Through the crowding distance calculation, evenly distributed solutions can be retained first to avoid excessive concentration of the solution set, thereby improving the diversity and representativeness of the solution set.

[0174] In this embodiment, the process of performing non-dominated sorting and crowding distance calculation on the global optimal solution set to determine a better solution and updating the global optimal solution set is as follows:

[0175] Firstly, the solutions in the global optimal solution set are divided into multiple Pareto front layers through non-dominated sorting, where the first Pareto front contains all non-dominated solutions, the second contains solutions dominated by the first layer, and so on; then, the crowding distance is calculated for the solutions in each Pareto front layer, and the larger the crowding distance, the sparser the distribution of the solution in the target space, and the higher the importance of the solution; then, the better solutions are screened out in the order of Pareto front layer and crowding distance from large to small, ensuring that the solution set is evenly distributed and diverse in the target space; finally, the screened solutions are used as the new global optimal solution set to guide the subsequent search process of the particle swarm.

[0176] This process ensures the high quality and diversity of the global optimal solution set, providing reliable support for multi-objective optimization.

[0177] Step 209: When the multi-objective particle swarm algorithm reaches the maximum number of iterations, an optimal solution is determined from the updated global optimal solution set based on the optimization objective.

[0178] Specifically, first, extract the first layer of Pareto frontier from the final global optimal solution set. These solutions are not dominated by other solutions in multiple objectives (such as energy consumption and comfort), and represent Pareto optimal solutions; then, according to specific application requirements (such as more emphasis on energy saving or more emphasis on comfort), select a solution that best meets the requirements from the Pareto frontier as the final optimal solution; if there are multiple candidate solutions, they can be further screened in combination with crowding distance or other decision methods (such as weighted summation method) to ensure that the selected solution is reasonably distributed in the target space and meets actual needs. The optimal solution finally determined is the optimal equipment operating parameter combination of the air conditioner recommended by the algorithm, which is used to actually control the air conditioning equipment.

[0179] The method of this embodiment achieves a balance between air conditioning energy saving effect and comfort through a multi-objective particle swarm optimization algorithm. First, air conditioning energy consumption and indoor comfort are taken as optimization targets, and constraints are introduced to ensure that the optimization results are feasible in actual operation; secondly, the multi-objective particle swarm algorithm is used to search for the optimal solution set in the solution space, and these solutions achieve a good balance between energy consumption and comfort; then, the optimal solution set with uniform distribution and diversity is screened out through non-dominated sorting and crowding distance calculation; finally, the most suitable solution is selected from the optimal solution set according to specific needs, and its corresponding operating parameter combination is applied to the air conditioning control system. Through real-time optimization algorithms and multi-objective particle swarm optimization, the equipment operating parameters of the air conditioner are dynamically adjusted according to environmental changes and user needs. This embodiment can reduce air conditioning energy consumption while ensuring the comfort of indoor personnel, and achieve the best trade-off between energy saving and comfort.

[0180] In some embodiments, after step 105, the present embodiment further includes: structuring the equipment operation parameter combination corresponding to the optimal solution to obtain a plurality of air conditioning operation structured parameters; and storing the plurality of air conditioning operation structured parameters in an air conditioning parameter database.

[0181] Specifically, for the convenience of storage and application, the system structures these parameters according to functional categories, such as classifying compressor speed as "cooling / heating parameter", fan speed as "air supply parameter", and fresh air volume as "air quality parameter", and assigns a unique identifier, value range and unit to each parameter. Through structured processing, complex parameter combinations can be converted into clear and standardized data formats, providing standardized input for subsequent air conditioning control.

[0182] The structured equipment operating parameters are then stored in the air conditioning parameter database, usually in a table format, with each record containing parameter name, value, unit, timestamp, etc. The design of the air conditioning parameter database should support efficient query, update, and historical data management, so that the optimal parameter combination can be quickly called in actual operation, and support the analysis and optimization of parameter usage.

[0183] By storing them in the air-conditioning parameter database, systematic management of parameters can be achieved, which not only provides a data basis for the intelligent control and energy efficiency optimization of air-conditioning equipment, but also provides strong data support for subsequent data analysis, fault diagnosis, maintenance plan formulation and system upgrades, thereby improving the operating efficiency of air-conditioning equipment and extending the service life of equipment, while ensuring the comfort and energy-saving effects of the indoor environment.

[0184] In some embodiments, step 101 specifically includes: obtaining the user's operation record of the air conditioner; determining the user's personalized preference data based on the operation record; and determining the optimization target and the constraint condition according to the personalized preference data.

[0185] Specifically, in order to obtain the user's operation records of the air conditioner, the user interface in the smart air conditioner device (such as mobile phone applications, remote controls or smart panels) can be used to collect the user's adjustments to the air conditioner settings at different times and in different scenarios, including temperature setting, wind speed selection, mode switching (cooling, heating, dehumidification, etc.), timed power on and off, etc. These operation records can be transmitted to the cloud server or local database in real time through the Internet of Things technology for subsequent data analysis and processing, so as to gain a deeper understanding of the user's usage habits and preferences.

[0186] Based on the collected user operation records, data analysis techniques (such as data mining and machine learning algorithms) are used to perform pattern recognition and preference analysis on user operation behaviors. For example, analyze the user's preference settings for temperature and wind speed in different time periods (such as weekdays, weekends, daytime, and nighttime), identify the user's sensitivity to specific environmental parameters (such as humidity and air quality), and the user's frequency of use of energy-saving modes, etc. Through these analyses, a personalized preference model of the user can be constructed, including the user's preferred temperature range, wind speed gear, operating mode, etc., to provide data support for subsequent personalized control strategies.

[0187] According to the user's personalized preference data, the optimization objectives and constraints of air conditioning energy-saving control are determined. The optimization objectives include not only the traditional minimization of energy consumption and maximization of comfort, but also the user's personalized preferences, such as the user's preference for a specific temperature range, sensitivity to wind speed, etc. For example, if the user prefers to set the temperature in a lower range at night, the optimization objective can be adjusted to give priority to satisfying the user's temperature preference at night while minimizing energy consumption. Constraints should also take into account the user's personalized needs. For example, the user may have special requirements for certain parameters (such as humidity). These requirements should be included in the control strategy as constraints to ensure that the energy-saving goals are achieved while satisfying the user's comfort. In this way, air conditioning equipment can provide users with a more personalized, comfortable and energy-saving operating environment.

[0188] In some embodiments, determining the optimization target and the constraint condition according to the personalized preference includes: adjusting the weights of the target air-conditioning energy consumption and the target personnel comfort in the optimization target according to the personalized preference data.

[0189] Specifically, according to the user's personalized preference data, the weight distribution of the target air conditioning energy consumption and the target personnel comfort in the overall optimization goal can be dynamically adjusted. For example, if the user's operation record shows that he frequently adjusts the temperature in pursuit of extreme comfort, and does not compromise even under high energy consumption, then the weight of the target personnel comfort can be increased accordingly, and the weight of the target air conditioning energy consumption can be reduced; on the contrary, if the user often enables the energy-saving mode and has a high tolerance for temperature fluctuations, then the weight of the target air conditioning energy consumption can be increased, and the emphasis on comfort can be reduced.

[0190] In this way, the optimization target can flexibly reflect the preferences of different users, achieve a balance between personalized energy saving and comfort, and make the operation of air-conditioning equipment more in line with the actual needs of users. It can achieve energy saving goals while ensuring personalized comfort, thus providing an air-conditioning operation plan that better meets user expectations.

[0191] The air conditioning control system of this embodiment includes an electronic device. The following describes this electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0192] It should be noted that Figure 3 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0193] like Figure 3 As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0194] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0195] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0196] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CDROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0197] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0198] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0199] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0200] As described above, 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 aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0201] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0202] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An air conditioning energy-saving control method based on multi-objective optimization, characterized in that: Applied to an air conditioning control system, the method comprises: Determining an optimization target for energy-saving control of the air conditioner and corresponding constraints, wherein the optimization target includes target air conditioner energy consumption and target comfort; Acquiring current environmental data of the air conditioner; The equipment operation parameter combination of the air conditioner is used as a particle in a multi-objective particle swarm algorithm; By means of the multi-objective particle swarm algorithm, based on the current environmental data, the optimization target and the constraint conditions, the optimal solution of the particle is determined, specifically including: initializing the parameters of the multi-objective particle swarm algorithm, the parameters including the particle swarm size, the maximum number of iterations, the inertia weight and the acceleration constant; setting the initial position and speed of the particle according to the current environmental data of the air conditioner; determining the initial fitness of the particle according to the optimization target and the constraint conditions, the fitness being used to measure the pros and cons of the combination of equipment operating parameters represented by the particle in achieving energy saving and comfort; determining the initial individual optimal solution for each particle based on the initial fitness, and selecting the global optimal solution set from the initial states of all the particles as the current optimal solution set of the entire particle swarm; The speed of each particle is updated, and the new position of each particle is determined according to the updated speed; the new fitness of the particle is determined based on the new position; if the new fitness is greater than the previous individual optimal fitness of the particle, the individual optimal solution of the particle is updated according to the new fitness; the global optimal solution set is non-dominated sorted and the crowding distance is calculated to determine a better solution, and the global optimal solution set is updated based on the better solution; when the multi-objective particle swarm algorithm reaches the maximum number of iterations, the optimal solution is determined from the updated global optimal solution set based on the optimization target; wherein, the speed of each particle is updated, including: the speed of each particle is updated by a preset particle speed update formula, and the particle speed update formula includes: in, represents the speed of particle i at time t+1, that is, the updated speed of particle i; represents the velocity of particle i at time t; w t represents the dynamic inertia weight, which changes with time t; c1, c2, c3, c4 all represent adaptive acceleration constants, which change with time t; r1, r2, r3, r4 represent random numbers; represents the individual optimal position of particle i at time t; g t represents the global optimal position of the particle swarm at time t; represents the position of particle i at time t; represents the target conflict adjustment item; Represents the domain exploration factor, with a value range of [0,1]; controlling the air conditioner according to the target device operating parameter combination corresponding to the optimal solution; When the air conditioner operates according to the target device operating parameter combination, obtaining actual air conditioning energy consumption and actual comfort; Based on the target air conditioning energy consumption and the target comfort level, as well as the actual air conditioning energy consumption and the actual comfort level, the equipment operating parameters of the air conditioner are adjusted by a PID control algorithm to obtain final equipment operating parameters; The air conditioner is controlled to operate according to the final equipment operating parameters.

2. The method according to claim 1, characterized in that: The function of the target conflict adjustment term is, Where M represents the number of objective functions of the optimization objective, represents the value of particle i on the jth objective function, f j (g t ) The global optimal solution g t The value of the j-th objective function, represents the historical maximum value of the j-th objective function, Represents the historical minimum value of the j-th objective function.

3. The method according to claim 1 or 2, characterized in that: The function of the domain exploration factor is, Where N(i) is the neighborhood set of particle i, including particles adjacent to particle i; N is the size of the domain set; Represents the distance between particle i and its neighbor particle k.

4. The method according to claim 1, characterized in that: After the air conditioner is controlled according to the equipment operation parameter combination corresponding to the optimal solution, the method further includes: Structuring the equipment operation parameter combination corresponding to the optimal solution to obtain a plurality of air conditioning operation structured parameters; The plurality of air-conditioning operation structured parameters are stored in an air-conditioning parameter database.

5. The method according to claim 1, characterized in that The determination of the optimization target and corresponding constraint conditions for energy-saving control of the air conditioner includes: Obtaining a user's operation record of the air conditioner; Determining personalized preference data of the user based on the operation record; The optimization target and the constraint condition are determined according to the personalized preference data.

6. An air conditioning control system, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the air-conditioning control system to execute the method as described in any one of claims 1-5.

7. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an air-conditioning control system, the air-conditioning control system is caused to execute the method as claimed in any one of claims 1 to 5.

8. A computer program product, characterized in that When the computer program product runs on an air-conditioning control system, the air-conditioning control system is enabled to execute the method according to any one of claims 1 to 5.

Images