Air conditioning unit energy consumption optimization regulation and control method, device and equipment based on artificial intelligence and medium

Abstract

The invention provides an air conditioning unit energy consumption optimization regulation and control method, device and equipment based on artificial intelligence and a medium, and belongs to the technical field of air conditioning unit energy consumption control. Judging whether similar environment parameters exist or not; judging whether a previous optimization record exists or not, and if yes, carrying out optimization; exporting earlier-stage optimization data; step-by-step optimization is carried out based on a swarm intelligence algorithm to obtain an optimal control parameter in a current external constraint environment; the air conditioning unit operates according to the optimal control parameters in the current external constraint environment, and operation data of the air conditioning unit are read in real time; judging whether the operation data of the air conditioning unit meet autonomous optimization ending conditions or not; and if yes, terminating the current autonomous optimization strategy, and storing the optimization record in the current environment. According to the invention, the operation efficiency of the equipment is effectively improved, and the energy consumption of the equipment is effectively reduced under the condition of satisfying the comfort level of a user.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy consumption control of air-conditioning units, and in particular relates to an artificial intelligence-based energy consumption optimization control method, device, equipment and medium for air-conditioning units. Background Art

[0002] In the field of air-conditioning systems, traditional control methods are often based on fixed set values ​​and simple logical judgments, which are difficult to adapt to complex and changing external environmental conditions and user needs.

[0003] Traditional air conditioning systems often have difficulty adapting to complex and changing external environmental conditions, resulting in low energy efficiency. Air conditioning systems often ignore the use of historical data and operating data. Failure to use historical data resources cannot provide reference and basis for the optimization process.

[0004] With the rapid development of artificial intelligence technology, intelligent control can be achieved. How to effectively manage and optimize the energy consumption of air-conditioning units by introducing artificial intelligence algorithms and intelligent optimization mechanisms is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present invention provides an artificial intelligence-based method for optimizing and controlling the energy consumption of an air-conditioning unit. By integrating real-time detection data from multiple sensors, the advantages of a swarm intelligence algorithm in multi-parameter optimization are fully utilized, and ultimately low-energy consumption operation of a central air-conditioning core unit is achieved.

[0006] Methods include: S101: using cosine similarity to evaluate the similarity between external environment parameters and current environment parameters; S102: Determine whether there are similar environmental parameters. If there are similar environmental parameters, jump to step S103; If there are no similar environmental parameters, jump to step S105; S103: Determine whether there is a previous optimization record. If there is a previous optimization record, jump to step S104; otherwise, it is determined that there is no previous optimization record, jump to step S105; S104: exporting the early optimization data, where the exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage; S105: Initialize the swarm intelligence algorithm and optimize the constraints; S106: Perform stepwise optimization based on a swarm intelligence algorithm to obtain optimal control parameters under the current external constraint environment; S107: The air conditioning unit operates according to the optimal control parameters under the current external constraint environment, and reads the air conditioning unit operation data in real time; S108: Determine whether the operating data of the air conditioning unit meets the conditions for ending the autonomous optimization search; If satisfied, the current autonomous optimization strategy is terminated and the optimization record in the current environment is saved.

[0007] It should be further explained that the method also includes: obtaining environmental data , air conditioning unit operation process data , power consumption data and air conditioning unit setting parameter range ; i Represents a data type. t A data type that represents a point in time.

[0008] It should be further explained that the energy consumption sample pairs are constructed based on the environmental data, the air-conditioning unit operation process data and the power consumption data, which are expressed as: .

[0009] It should be further explained that in the method, the heat released by a certain instantaneous liquid is calculated based on the following formula: The temperature difference between the current temperature of the liquid and the temperature of the contact environment ;

[0010]

[0011] in, is the specific heat capacity of water, Indicates the mass of the liquid; The heat exchanged by the air conditioner at a certain flow rate within the preset time period is obtained by integrating a certain instantaneous heat through the preset time period. , calculated as:

[0012] in, represents a calculation time point, Indicates the corresponding time interval.

[0013] It should be further explained that in step S106, the optimal control parameters under the current external constraint environment are obtained based on the following formula: ; (5) Among them, opt Indicates the current status of the air conditioning unit; It means that starting from time t, a certain set of air-conditioning control parameters is used for operation within a time period of T; A represents the parameter range of the air-conditioning unit's autonomous regulation; S represents the constraint relationship between the variables of the air-conditioning unit.

[0014] It should be further explained that swarm intelligence algorithms include: genetic algorithm, particle swarm algorithm, ant colony optimization algorithm, artificial fish swarm algorithm and artificial bee colony algorithm.

[0015] It should be further explained that the optimization constraint conditions in step S105 include: Configure the startup sequence of each host in the air conditioning unit; Configure the operating timing of each cooling tower of the air conditioning unit; Configure the inlet and return water temperature thresholds for the air conditioner host, and only adjust one of the inlet or return water temperatures.

[0016] The present application also provides an artificial intelligence-based air conditioning unit energy consumption optimization control device, the device comprising: A similarity evaluation module is used to evaluate the similarity between external environment parameters and current environment parameters using cosine similarity; A parameter judgment module is used to determine whether similar environmental parameters exist; The optimization record search module is used to determine whether there is a prior optimization record; The optimization data export module is used to export the early optimization data. The exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage. Algorithm processing module, used to initialize swarm intelligence algorithm and optimize constraint conditions; The optimization control module performs step-by-step optimization based on the swarm intelligence algorithm to obtain the optimal control parameters under the current external constraint environment; The equipment control module is used to make the air-conditioning unit operate according to the optimal control parameters under the current external constraint environment and read the air-conditioning unit operation data in real time; The optimization state judgment module is used to judge whether the operation data of the air-conditioning unit meets the conditions for ending the autonomous optimization; if so, the current autonomous optimization strategy is terminated and the optimization record under the current environment is saved.

[0017] According to another embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for optimizing energy consumption of an air-conditioning unit based on artificial intelligence are implemented.

[0018] According to another embodiment of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for optimizing energy consumption of an air-conditioning unit based on artificial intelligence are implemented.

[0019] It can be seen from the above technical solutions that the present invention has the following advantages: The air conditioning unit energy consumption optimization control method provided by the present invention uses a swarm intelligence algorithm to search for the optimal solution, and based on real-time monitoring data from multiple sensors, achieves the goal of minimizing the energy consumption of building air conditioning unit equipment while satisfying user comfort. The present invention uses a swarm intelligence algorithm to autonomously optimize within the normal operating parameters of various types of equipment, and searches for the optimal energy-saving solution for large buildings under various complex conditions.

[0020] The present invention determines whether the air conditioning unit has achieved the expected control effect, thereby determining whether the autonomous optimization process needs to be terminated, thereby ensuring that the air conditioning unit minimizes energy consumption while meeting comfort requirements, while avoiding unnecessary control operations and energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0022] Figure 1 A flow chart of the method for optimizing the energy consumption of air-conditioning units; Figure 2 This is the framework diagram of the method for optimizing the energy consumption of air-conditioning units; Figure 3 A flow chart of an embodiment of a method for optimizing the energy consumption of an air-conditioning unit; Figure 4 Schematic diagram of an energy consumption optimization and control device for air-conditioning units based on artificial intelligence. DETAILED DESCRIPTION

[0023] The artificial intelligence-based energy consumption optimization and control method for air-conditioning units provided in the present application integrates the real-time detection data of multiple sensors, analyzes the implicit and nonlinear relationship between different working environments such as indoor and outdoor temperature and humidity, light, and population density and the sensor data and energy consumption data of the air-conditioning units, and utilizes the advantages of swarm intelligence algorithms in multi-parameter optimization to ultimately achieve the lowest energy consumption operation strategy for the air-conditioning units in different working environments, thereby reducing the energy consumption of the air-conditioning unit equipment.

[0024] The following will describe in detail the steps of the method for optimizing the energy consumption of air conditioner units based on artificial intelligence. For the purpose of illustration rather than limitation, specific details such as specific system structures and technologies are proposed to facilitate a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application can also be implemented in other embodiments without these specific details.

[0025] When the method for optimizing energy consumption of air conditioner units of the present application is used in the specification of the present application, the term "comprising" indicates the existence of the described features, entities, steps, operations, elements and / or components, but does not exclude the existence or addition of one or more other features, entities, steps, operations, elements, components and / or their collections. The terms "comprising", "including", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0026] The phrases such as "one embodiment" or "some embodiments" described in the present application mean that the specific features, structures or characteristics described in the embodiment are included in one or more embodiments of the present application. Therefore, the phrases such as "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments" etc. that appear in different places in the present application do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways.

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] See also Figure 1 The figure is a flow chart of a method for optimizing energy consumption of an air conditioning unit in a specific embodiment, the method comprising: S101: Using cosine similarity to evaluate the similarity between external environment parameters and current environment parameters.

[0029] In some embodiments, based on the cosine similarity, the distance is measured by calculating the cosine of the angle between the external environment parameter vector and the current environment parameter vector to evaluate the similarity of the two environment parameters.

[0030] In the optimal control of energy consumption of the air-conditioning unit in this embodiment, temperature, humidity, and light can be regarded as external environmental parameters and current environmental parameters as two vectors, and the cosine similarity formula is used to calculate the similarity between them.

[0031] Specifically, the external environmental parameters and current environmental parameters that need to be evaluated are determined, and the parameters may include temperature, humidity, light intensity, wind speed, etc.

[0032] Since the value ranges and units of the external environment parameters and the current environment parameters may be different, the external environment parameters and the current environment parameters are standardized to ensure that they have the same weight when calculating the cosine similarity.

[0033] The external environment parameters and the current environment parameters are expressed in vector form respectively.

[0034] Exemplarily, based on the two parameters of temperature and humidity, the external environment parameter can be represented as a temperature and humidity vector, and the current environment parameter can be represented as a temperature and humidity vector. The calculation is performed based on the cosine similarity formula. That is, the external environment parameter vector and the current environment parameter vector are substituted into the cosine similarity formula to calculate the similarity value. The closer the similarity value is to 1, the more similar the two environment parameters are; the closer it is to -1, the less similar the two environment parameters are.

[0035] It can be seen that the cosine similarity evaluation of environmental parameters is intuitive and can effectively measure the similarity between two environmental parameters.

[0036] In this embodiment, the similarity between the external environment parameters and the current environment parameters can be determined based on the calculated cosine similarity value. If the similarity value exceeds a preset threshold, the two environment parameters can be considered similar. If it is determined to be a similar environment, the control strategy of the current environment can be formulated with reference to the historical control strategy to optimize the energy consumption of the air conditioning unit.

[0037] S102: Determine whether there are similar environmental parameters, if so, jump to step S103. If not, jump to step S105.

[0038] In some embodiments, similar environmental parameters are defined as external environmental parameters with a higher similarity to the current environmental parameters under the cosine similarity evaluation. The parameters include but are not limited to temperature, humidity, light intensity, etc., depending on the actual needs of the air conditioning unit energy consumption optimization control.

[0039] In this embodiment, it is determined whether the current environment is similar to the historical environment to determine whether the historical control strategy needs to be referred to. If there are similar environmental parameters, the historical control strategy can be used to optimize the current control strategy to improve control efficiency and accuracy.

[0040] S103: Determine whether there is a previous optimization record. If so, jump to step S104; otherwise, it is determined that there is no previous optimization record, and jump to step S105.

[0041] In some embodiments, the previous air conditioning unit energy consumption optimization record may include historical environmental parameters, historical control strategies, historical energy consumption data, etc. The data records the control strategies and energy consumption of the air conditioning unit under different environmental parameters, providing a reference for the formulation of subsequent control strategies.

[0042] It should be noted that this embodiment determines whether there are historical control records similar to the current environment, so as to determine whether the current control strategy can be optimized by drawing on historical experience. If there are prior optimization records, these records can be used to guide the formulation of the current control strategy to improve control efficiency and accuracy.

[0043] S104: Exporting the early optimization data, where the exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage.

[0044] In some embodiments, the exported preliminary optimization data may include the swarm intelligence algorithm used in the preliminary stage, the equipment configuration parameters such as the fan speed and compressor power searched in the preliminary stage, and the corresponding energy consumption data.

[0045] S105: Initialize the swarm intelligence algorithm and optimize the constraints.

[0046] In some embodiments, swarm intelligence algorithms play an important role in optimizing the energy consumption of air-conditioning units based on artificial intelligence. They can simulate the behavior of biological groups in nature and find the optimal solution or approximate optimal solution through iteration and search. In optimizing the energy consumption of air-conditioning units, swarm intelligence algorithms can be used to search for optimal equipment configuration parameters and control strategies to minimize energy consumption. Beneficial effects include improving control efficiency and accuracy, and reducing energy consumption and operating costs of air-conditioning units.

[0047] S106: Perform step-by-step optimization based on the swarm intelligence algorithm to obtain the optimal control parameters under the current external constraint environment.

[0048] In some embodiments, the process of performing step-by-step optimization based on a swarm intelligence algorithm includes the steps of initializing a population, evaluating population fitness, selecting excellent individuals, generating a new population, and iteratively updating.

[0049] The swarm intelligence algorithm of this embodiment generates a new population according to the current population situation and fitness function, and iterates and updates until the termination condition is met, such as reaching the maximum number of iterations or finding the optimal solution.

[0050] The optimal control parameters obtained under the current external constraint environment include the operating parameters of the air-conditioning unit such as fan speed, compressor power, refrigerant flow, etc. The optimal solution or approximate optimal solution is obtained by searching through the swarm intelligence algorithm under the current external constraint environment.

[0051] In this way, this embodiment uses the swarm intelligence algorithm to search for optimal control parameters under the current external constraint environment to minimize the energy consumption of the air-conditioning unit.

[0052] Optionally, the specific process of this embodiment may include: S1061: Initialize population: Generate a set of random air-conditioning unit control parameters as the initial population.

[0053] S1062: Evaluate population fitness: Calculate the fitness value of each individual based on the current external constraint environment and the energy consumption model of the air-conditioning unit.

[0054] S1063: Select excellent individuals: select a portion of excellent individuals as parents according to their fitness values.

[0055] S1064: Generate new population: Generate a new population through operations such as crossover and mutation.

[0056] Iterative update: Repeat steps S1062-S1064 until the maximum number of iterations is reached or the optimal solution is found.

[0057] S107: The air-conditioning unit operates according to the optimal control parameters under the current external constraint environment, and reads the air-conditioning unit operation data in real time.

[0058] In some embodiments, the air conditioning unit operates according to the optimal control parameters of the fan speed and compressor power searched in step S106, which are transmitted to the actuator of the air conditioning unit through the control system, thereby achieving precise control of the operation of the air conditioning unit.

[0059] The optimal control parameters under the current external constraints include fan speed, compressor power, refrigerant flow, etc. The optimal solution or approximate optimal solution obtained by searching through the swarm intelligence algorithm under the current external constraints can ensure that the air-conditioning unit can minimize energy consumption while meeting the comfort requirements.

[0060] This embodiment can make the air conditioning unit operate according to the optimal control parameters to minimize energy consumption and maximize operating efficiency. Beneficial effects include improving the energy efficiency ratio and operating stability of the air conditioning unit, reducing energy consumption and operating costs, and improving user comfort and satisfaction.

[0061] For this embodiment, reading the optimal control parameter is to obtain the optimal control parameter from step S106. The optimal control parameter is sent to the actuator of the air-conditioning unit through the control system. The actuator of the air-conditioning unit adjusts the operation according to the received control instruction. The operating status and energy consumption of the air-conditioning unit are monitored in real time through the sensor.

[0062] S108: Determine whether the air-conditioning unit operation data meets the conditions for ending the autonomous optimization. If so, terminate the current autonomous optimization strategy and save the optimization record under the current environment.

[0063] In some embodiments, determining whether the operating data of the air-conditioning unit meets the conditions for ending autonomous optimization may include multiple aspects, such as whether the energy consumption reaches a preset target, whether the operating stability meets the requirements, whether the user comfort is guaranteed, etc.

[0064] This embodiment may specifically include the following steps: S1081: Collect operation data.

[0065] Collect operating data of air conditioning units through sensors and control systems.

[0066] S1082: Analyze operation data.

[0067] The collected operating data is processed and analyzed to evaluate indicators such as the energy consumption, operating stability and user comfort of the air-conditioning unit.

[0068] S1083: Determine whether the conditions are met.

[0069] According to the preset conditions for ending autonomous optimization, determine whether the current operating data meets the requirements.

[0070] This embodiment determines whether the air conditioning unit has achieved the expected control effect, thereby determining whether to end the autonomous optimization process, thereby ensuring that the air conditioning unit minimizes energy consumption while meeting comfort requirements, and avoiding unnecessary control operations and energy waste.

[0071] Further, as a refinement and expansion of the specific implementation of the above embodiment, in order to fully explain the specific implementation process of this embodiment and realize the operation of the air-conditioning unit according to the minimum energy consumption strategy under different working environments, the following provides a more specific implementation process of the air-conditioning unit energy consumption optimization control method. Figure 2 shown.

[0072] In some embodiments, the environmental parameters collected, processed, and analyzed are respectively environmental data ( )、Air conditioning unit operation process data( )、Electricity consumption data( ) and air conditioning unit setting parameter range ( ),in i Indicates a data type under this category of data. t Indicates the data type at a certain point in time under this category of data.

[0073] Specifically, environmental data refers to the environmental parameters inside and outside the building during the operation of the air-conditioning unit, including but not limited to outdoor temperature and humidity sensor data, floor infrared radiation data, and camera-based number monitoring data.

[0074] The air-conditioning unit operation process data refers to the operation data generated by each device during the operation of the air-conditioning unit, including but not limited to ultrasonic flow meter sensor data, pressure transmitter sensor data, cooling water inlet and return water temperature sensor data, chilled water inlet and return water temperature sensor data, etc.

[0075] Electricity consumption data refers to the data of the main power-consuming equipment products during the operation of the air-conditioning unit, specifically the data generated by the three-phase electricity meters of each power-consuming equipment.

[0076] The setting parameters of the air-conditioning unit refer to the reasonable control and operation range of the adjustable parameters of each device of the central air-conditioning unit, including the air-conditioning host operation combination, cooling tower operation combination, parameter setting range of the chilled water supply and return water temperature, parameter setting range of the chilled pump frequency, parameter setting range of the cooling water supply and return water temperature, and parameter setting range of the cooling pump frequency.

[0077] A sample pair of energy consumption can be formed by using environmental data, air conditioning unit operation process data and power consumption data, which can be expressed as follows using formula (1): (1) The swarm intelligence algorithm of this embodiment may include three parts: a swarm intelligence algorithm library, a physical model constraint module, and a parameter autonomous optimization module.

[0078] Among them, the swarm intelligence algorithm library has a swarm intelligence algorithm.

[0079] Swarm intelligence algorithms are a type of computational model that imitates the behavior of biological groups in nature. They are used to solve complex problems, especially non-convex optimization problems. Swarm intelligence algorithms can simulate the intelligent behavior of biological groups and solve complex problems through simple interaction rules between individuals.

[0080] This embodiment achieves the lowest energy consumption on the basis of satisfying user comfort by intelligently adjusting various parameters of the air conditioning unit. However, considering that the intelligent adjustment of air conditioning involves comprehensive changes in the internal and external environment of the building, such optimization problems are difficult to express through clear logical relationships and are NP-hard problems.

[0081] This embodiment uses a swarm intelligence algorithm to find the optimal solution within an adjustable parameter range. The swarm intelligence algorithm used in this embodiment includes a genetic algorithm, a particle swarm algorithm, an ant colony optimization algorithm, an artificial fish swarm algorithm, and an artificial bee colony algorithm.

[0082] The swarm intelligence algorithm library is detailed in Table 1: Table 1 Swarm intelligence algorithm library

[0083] Furthermore, when performing parameter initialization, this embodiment may include the size of the population, the initial position, the learning rate, and some control parameters of the algorithm itself (such as the learning factor, pheromone concentration, etc.). Therefore, in order to eliminate the influence of the algorithm and parameter selection as much as possible and search for the lowest energy consumption of the central air-conditioning unit in the current environment, this embodiment uses the above-mentioned 5 types of swarm intelligence algorithms, and each swarm intelligence algorithm randomly initializes 2 groups of parameters to search for the optimal solution under the current parameter environment. And compare the 10 groups of search results, select the optimal combination of operating parameters, and through the above method, try to obtain the global optimal solution and avoid falling into the local optimal solution.

[0084] The air conditioning unit of this embodiment is a thermodynamic system based on liquid to achieve heat exchange, which complies with the thermodynamic laws in the field of physics, as shown in formula (2): (2) (3) in, Indicates the amount of heat released by a liquid at a certain instant. is the specific heat capacity of water, represents the mass of the liquid, Indicates the temperature difference between the current temperature of the liquid and the temperature of the contact environment.

[0085] By integrating a certain instantaneous heat over a period of time, the heat exchanged by the air-conditioning system under a certain flow rate in a certain period of time can be obtained, as shown in formula (4): (4) in, It indicates the heat exchanged by a certain flow rate of liquid in a certain calculation section. represents a calculation time point, Indicates the corresponding time interval.

[0086] In view of the above-mentioned laws of physics, this embodiment can obtain the restriction conditions in the global optimization of the swarm intelligence algorithm to prevent the occurrence of safety hazards and damage to equipment caused by violating the laws of physics. The relevant restriction conditions are shown in Table 2: Table 2 Constraints for optimization of swarm intelligence algorithm

[0087] This embodiment clarifies the swarm intelligence algorithm for performing optimization and the constraint variables in the optimization process. Subsequently, AI autonomous optimization is performed based on the current external environment and parameter settings, which can be expressed by formula (5): (5) in, Indicates the optimal control parameters obtained under the current external constraint environment; opt Represents the entire current real central air conditioning system; It means that starting from time t, a certain set of air conditioning control parameters is used for operation within a time period of T; A represents the parameter range that the central air-conditioning system can adjust autonomously; S represents the constraint relationship between the variables of the air-conditioning unit.

[0088] Combined with the above methods, the further process of the air conditioning unit energy consumption optimization control method is explained as follows: Figure 3 shown.

[0089] S301: Calculate the similarity between the current environment and the external environment.

[0090] This embodiment uses cosine similarity to evaluate the similarity between the calculated external environment parameter vector and the current environment parameter vector.

[0091] S302: Determine whether similar environmental parameters exist.

[0092] When the similarity is greater than 0.8, it is determined that similar environmental parameters exist, and the process jumps to step S303; otherwise, it is determined that similar environmental parameters do not exist, and the process jumps to step S305.

[0093] S303: Determine whether there is a previous optimization record.

[0094] If there is a previous optimization record, jump to step S304; otherwise, it is determined that "there is no previous optimization record", jump to step S305.

[0095] S304: Importing previous data.

[0096] This embodiment imports the optimization data from the early stage, and the imported data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage.

[0097] S305: Initialize parameters, including initializing the swarm intelligence algorithm and corresponding parameters.

[0098] S306: Optimization using swarm intelligence algorithm.

[0099] In this embodiment, each group of intelligent algorithms performs step-by-step optimization according to its search algorithm to calculate the next device configuration parameters.

[0100] S307: Strategy execution. The air-conditioning unit executes the strategy searched by the current swarm intelligence algorithm and evaluates whether the strategy is effectively executed by reading the data of the equipment and sensors. The effective execution time of the air-conditioning unit is not less than 1 hour.

[0101] S308: According to the preset end condition of autonomous optimization, determine whether the current operation data meets the requirements.

[0102] This embodiment realizes effective management and optimization of the energy consumption of the air conditioning unit. The cosine similarity is used to evaluate the similarity of environmental parameters, and the swarm intelligence algorithm is combined to perform step-by-step optimization, ensuring that the air conditioning unit operates with the optimal control parameters under the current external constraint environment.

[0103] The following is an embodiment of an energy consumption optimization control device for air-conditioning units based on artificial intelligence provided by the embodiments of the present disclosure. The device and the energy consumption optimization control methods for air-conditioning units based on artificial intelligence in the above-mentioned embodiments belong to the same inventive concept. For details not fully described in the embodiment of the energy consumption optimization control device for air-conditioning units based on artificial intelligence, reference can be made to the embodiment of the energy consumption optimization control method for air-conditioning units based on artificial intelligence.

[0104] The device comprises: a similarity evaluation module, which is used for evaluating the similarity between the external environment parameters and the current environment parameters by using cosine similarity.

[0105] The parameter judgment module is used to determine whether similar environmental parameters exist.

[0106] The optimization record search module is used to determine whether there is a prior optimization record.

[0107] The optimization data export module is used to export the early optimization data. The exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage.

[0108] The algorithm processing module is used to initialize the swarm intelligence algorithm and optimize the constraints.

[0109] The optimization control module performs step-by-step optimization based on the swarm intelligence algorithm to obtain the optimal control parameters under the current external constraint environment.

[0110] The equipment control module is used to make the air-conditioning unit operate according to the optimal control parameters under the current external constraint environment and read the air-conditioning unit operation data in real time.

[0111] The optimization state judgment module is used to judge whether the operation data of the air-conditioning unit meets the conditions for ending the autonomous optimization; if so, the current autonomous optimization strategy is terminated and the optimization record under the current environment is saved.

[0112] In one embodiment of the present invention, based on the device for optimizing the energy consumption of an air-conditioning unit, a possible embodiment will be given below to illustrate its specific implementation scheme in a non-limiting manner.

[0113] In an exemplary embodiment, by establishing an air-conditioning unit energy consumption optimization control device and introducing a reinforcement learning algorithm into the air-conditioning unit energy consumption optimization control device, the air-conditioning unit energy consumption optimization control device is used to perceive and analyze the external environment, and make reasonable decisions based on the group intelligent optimization results.

[0114] The energy consumption optimization control device based on the air-conditioning unit can realize a dynamic optimization process, that is, the process of selecting the best or most satisfactory solution from several alternative air-conditioning control schemes according to multiple indicator data of each scheme, or reusing the swarm intelligence algorithm for optimization.

[0115] The energy consumption optimization control device for air-conditioning units also includes a group intelligent model algorithm library, an external environment library, a control strategy library and a device mapping library.

[0116] Among them, the swarm intelligence model algorithm library includes swarm intelligence algorithms such as artificial bee colony algorithm and genetic algorithm, and the swarm intelligence algorithm library stores code data.

[0117] The external environment database includes the external temperature, humidity and light collected by sensors in different months, as well as data information collected by video cameras and infrared sensors on each floor of the office building.

[0118] The control strategy library includes the air conditioning control parameters under different environmental parameters currently searched by the swarm intelligence algorithm. The external environment library and the control strategy library store data through a relational database.

[0119] The intelligent control operation process based on the energy consumption optimization control device of the air-conditioning unit is as follows: Step 401: Acquire environmental information through internal and external sensors; Step 402: Read the external environment library to determine whether similar environment parameters exist at present; if so, jump to step 403; if not, jump to step 406 Step 403: Match the control strategy through the external environment library and determine whether the current control strategy is mature; if mature, jump to step 404; if immature, jump to step 405; Step 404: Pushing the control strategy to the air-conditioning unit and establishing a virtual point to implement the distribution of the equipment control strategy; Step 405: confirm whether the issued mature strategy is effective, and count the time according to the device running for 1 hour, and monitor the changes of the external environment at all times during the operation; Step 406: call the operation strategy with the highest similarity to the current environment, jump to step 404 for execution, and start step 407 at the same time; Step 407: Select the optimal control strategy matched under the current similar external environment. If no optimal control strategy exists, generate a control strategy randomly, and further optimize the current control strategy based on the swarm intelligence algorithm.

[0120] This embodiment uses a swarm intelligence algorithm to search for the optimal solution, and based on real-time monitoring data from multiple sensors, achieves the goal of minimizing the energy consumption of building air conditioning units while meeting user comfort. In addition, a swarm intelligence algorithm is used to autonomously search for optimal solutions within the normal operating parameters of various types of equipment, and to search for the optimal energy-saving solution for large buildings under various complex conditions (including temperature, light, personnel flow, etc.). This effectively improves the efficiency of equipment operation and effectively reduces the energy consumption of equipment while meeting user comfort.

[0121] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of an artificial intelligence-based method for optimizing the energy consumption of an air-conditioning unit are implemented.

[0122] In embodiments of the present invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or required herein.

[0123] This embodiment also provides a storage medium, in which a program product capable of implementing an artificial intelligence-based method for optimizing the energy consumption of air-conditioning units is stored. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps described in the above "Exemplary Method" section of this specification according to various exemplary implementations of the present disclosure.

[0124] The storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0125] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing energy consumption of air-conditioning units based on artificial intelligence, characterized in that: Methods include: S101: using cosine similarity to evaluate the similarity between external environment parameters and current environment parameters; S102: Determine whether there are similar environmental parameters. If there are similar environmental parameters, jump to step S103; If there are no similar environmental parameters, jump to step S105; S103: Determine whether there is a prior optimal search record. If there is a prior optimal search record, jump to step S104; Otherwise, it is determined that there is no previous optimization record, and the process jumps to step S105; S104: exporting the early optimization data, where the exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage; S105: Initialize the swarm intelligence algorithm and optimize the constraints; S106: Perform stepwise optimization based on a swarm intelligence algorithm to obtain optimal control parameters under the current external constraint environment; S107: The air conditioning unit operates according to the optimal control parameters under the current external constraint environment, and reads the air conditioning unit operation data in real time; S108: Determine whether the operating data of the air conditioning unit meets the conditions for ending the autonomous optimization search; If satisfied, the current autonomous optimization strategy is terminated and the optimization record in the current environment is saved.

2. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 1 is characterized in that: The method also includes: obtaining environmental data , air conditioning unit operation process data , power consumption data and air conditioning unit setting parameter range ; i Represents a data type. t A data type that represents a point in time.

3. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 2 is characterized in that: Energy consumption sample pairs are constructed based on environmental data, air conditioning unit operation process data and power consumption data, expressed as: 。 4. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 1 is characterized in that: In the method, the heat released by a certain instantaneous liquid is calculated based on the following formula: The temperature difference between the current temperature of the liquid and the temperature of the contact environment ; in, is the specific heat capacity of water, Indicates the mass of the liquid; The heat exchanged by the air conditioner at a certain flow rate within the preset time period is obtained by integrating a certain instantaneous heat through the preset time period. , calculated as: in, represents a calculation time point, Indicates the corresponding time interval.

5. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 1 is characterized in that: In step S106, the optimal control parameters under the current external constraint environment are obtained based on the following formula: ; (5) Among them, opt Indicates the current status of the air conditioning unit; It means that starting from time t, a certain set of air-conditioning control parameters is used for operation within a time period of T; A represents the parameter range of the air-conditioning unit's autonomous regulation; S represents the constraint relationship between the variables of the air-conditioning unit.

6. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 1 is characterized in that: Swarm intelligence algorithms include: genetic algorithm, particle swarm algorithm, ant colony optimization algorithm, artificial fish swarm algorithm and artificial bee colony algorithm.

7. The method for optimizing energy consumption of air conditioner units based on artificial intelligence according to claim 1 is characterized in that: The optimization constraints in step S105 include: Configure the startup sequence of each host in the air conditioning unit; Configure the operating timing of each cooling tower of the air conditioning unit; Configure the inlet and return water temperature thresholds for the air conditioner host, and only adjust one of the inlet or return water temperatures.

8. An air conditioning unit energy consumption optimization control device based on artificial intelligence, characterized in that: The device is used to implement the method for optimizing energy consumption of an air-conditioning unit based on artificial intelligence as described in any one of claims 1 to 7; the device comprises: A similarity evaluation module is used to evaluate the similarity between external environment parameters and current environment parameters using cosine similarity; A parameter judgment module is used to determine whether similar environmental parameters exist; The optimization record search module is used to determine whether there is a prior optimization record; The optimization data export module is used to export the early optimization data. The exported early optimization data includes the swarm intelligence algorithm used in the early stage and the device configuration parameters searched in the early stage. Algorithm processing module, used to initialize swarm intelligence algorithm and optimize constraint conditions; The optimization control module performs step-by-step optimization based on the swarm intelligence algorithm to obtain the optimal control parameters under the current external constraint environment; The equipment control module is used to make the air-conditioning unit operate according to the optimal control parameters under the current external constraint environment and read the air-conditioning unit operation data in real time; The optimization state judgment module is used to judge whether the operation data of the air-conditioning unit meets the conditions for ending the autonomous optimization; if so, the current autonomous optimization strategy is terminated and the optimization record under the current environment is saved.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method for optimizing energy consumption of an air-conditioning unit based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for optimizing energy consumption of an air-conditioning unit based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

Images