Air conditioner energy-saving control method, device and system and storage medium

Abstract

The invention relates to the technical field of intelligent control, and discloses an air conditioner energy-saving control method, device and system and a storage medium, and the method is applied to edge equipment and comprises the steps that real-time environment state data are obtained, and the real-time environment state data and alternative regulation and control parameters are input into a preset parameter decision model; the preset decision parameter model comprises a temperature prediction sub-model and an energy consumption prediction sub-model; performing temperature prediction through the temperature prediction sub-model, and determining candidate regulation and control parameters based on a temperature prediction result; performing energy consumption prediction through the energy consumption prediction sub-model, and determining a target regulation and control parameter based on an energy consumption prediction result; and the target regulation and control parameters are sent to a power and environment monitoring unit, so that the power and environment monitoring unit executes air conditioner control operation. According to the method, parameter decision is carried out by introducing the edge device, dependence on the cloud can be reduced, quick response and low delay are realized, and meanwhile, the reliability of the target regulation and control parameter is guaranteed through the temperature prediction sub-model and the energy consumption prediction sub-model.

Description

Technical Field

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

[0002] With the global emphasis on energy conservation and emission reduction, energy efficiency management of air conditioning systems has become an important task in the operation of buildings and data centers. Traditional air conditioning control methods often rely on cloud servers for centralized management, which leads to delayed response and untimely information transmission. Therefore, when the environment changes or the load fluctuates, the cloud server cannot control the air conditioning equipment in time to make corresponding adjustments, resulting in energy waste and excessive use of air conditioning equipment. Summary of the invention

[0003] The main purpose of this application is to provide an air conditioning energy-saving control method, device, system and storage medium, aiming to solve the technical problem that the existing air conditioning control system relies on centralized management and cannot promptly control the air conditioning equipment to make corresponding adjustments when the environment changes or the load fluctuates, resulting in energy waste and excessive use of equipment.

[0004] To achieve the above purpose, the present application proposes an air conditioning energy-saving control method, the air conditioning energy-saving control method comprising:

[0005] Acquire real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model;

[0006] Performing temperature prediction according to the real-time environmental status data in combination with candidate control parameters through the temperature prediction sub-model, and determining the candidate control parameters based on the temperature prediction result;

[0007] Performing energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction result;

[0008] The target control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs an air conditioning control operation according to the target control parameter.

[0009] In one embodiment, before the step of acquiring real-time environmental status data, the method further includes:

[0010] Acquire historical environmental status data, and determine whether the historical environmental status data meets a preset data volume condition, the historical environmental status data including: historical air-conditioning operation data and corresponding historical temperature data and historical electric meter energy consumption data;

[0011] If yes, the historical environmental status data is packaged to obtain a training data set;

[0012] The initial temperature prediction sub-model and the initial energy consumption prediction sub-model are trained respectively according to the training data set to obtain a temperature prediction sub-model and an energy consumption prediction sub-model.

[0013] In one embodiment, before the step of inputting the real-time environmental status data and the candidate control parameters into the preset parameter decision model, the step includes:

[0014] Initialize parameter population based on preset genetic algorithm and determine target optimization conditions;

[0015] The parameter population is iteratively optimized until the iterative result meets the target optimization condition, and then the candidate control parameters are determined according to the iterated parameter population.

[0016] In one embodiment, the step of performing temperature prediction according to the real-time environmental status data in combination with candidate control parameters by the temperature prediction sub-model, and determining the candidate control parameters based on the temperature prediction result includes:

[0017] Inputting the real-time environmental status data and the alternative control parameters into the temperature prediction sub-model to obtain a temperature prediction result;

[0018] Determining whether the temperature prediction result meets the preset temperature safety condition;

[0019] If so, the alternative control parameter is determined as the candidate control parameter.

[0020] In one embodiment, the step of performing energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters by the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction result includes:

[0021] Inputting the real-time environmental status data and the candidate control parameters into the energy consumption prediction sub-model to obtain an energy consumption prediction result;

[0022] Determining whether the energy consumption prediction result meets the preset minimum energy consumption condition;

[0023] If so, the candidate control parameter is determined as the target control parameter.

[0024] In one embodiment, the step of sending the target control parameter to the dynamic environment monitoring unit so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter includes:

[0025] Analyze the target control parameters, and determine whether the target control parameters meet the preset safety parameter range according to the analysis results;

[0026] When the target control parameter meets the preset safety parameter range, the target control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

[0027] In one embodiment, after the step of obtaining real-time environmental status data, the method further includes:

[0028] When the real-time environmental status data meets the preset danger warning conditions, obtaining the corresponding safety strategy;

[0029] A mandatory control parameter is determined according to the security policy, and the mandatory control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs an air conditioning control operation according to the mandatory control parameter.

[0030] In addition, to achieve the above purpose, the present application also proposes an air conditioning energy-saving control device, the device comprising:

[0031] A data acquisition module is used to acquire real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model;

[0032] A model prediction module, configured to perform temperature prediction according to the real-time environmental status data in combination with the candidate control parameters through the temperature prediction submodel, and determine the candidate control parameters based on the temperature prediction results; perform energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction submodel, and determine the target control parameters based on the energy consumption prediction results;

[0033] The instruction issuing module is used to send the target control parameter to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes an air conditioning energy-saving control system, the system comprising: a number of air conditioning devices, a dynamic environment monitoring unit and an edge device;

[0035] The dynamic environment monitoring unit is used to collect real-time environmental status data and send the real-time environmental status data to the edge device;

[0036] The edge device is used to receive real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model;

[0037] The edge device is further used to perform temperature prediction according to the real-time environmental status data in combination with the candidate control parameters through the temperature prediction sub-model, and determine the candidate control parameters based on the temperature prediction result;

[0038] The edge device is further used to perform energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction sub-model, and determine the target control parameters based on the energy consumption prediction result;

[0039] The edge device is further used to send the target control parameter to the dynamic environment monitoring unit;

[0040] The dynamic environment monitoring unit is also used to receive the target control parameters and perform corresponding air-conditioning control operations on each of the air-conditioning devices according to the target control parameters.

[0041] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which an air-conditioning energy-saving control program is stored, and when the air-conditioning energy-saving control program is executed by a processor, the steps of the air-conditioning energy-saving control method described above are implemented.

[0042] The present application discloses an air conditioning energy-saving control method, which is applied to edge devices, including: obtaining real-time environmental status data, and inputting the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model; performing temperature prediction according to the real-time environmental status data combined with the alternative control parameters through the temperature prediction sub-model, and determining the candidate control parameters based on the temperature prediction results; performing energy consumption prediction according to the real-time environmental status data combined with the candidate control parameters through the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction results; sending the target control parameters to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs air conditioning control operations according to the target control parameters. Since the edge device responds to the real-time environmental status data to make parameter decisions in the present application, it can reduce dependence on the cloud, achieve fast response and low latency; and specifically optimize the control parameters through the temperature prediction sub-model and the energy consumption prediction sub-model, so as to achieve energy consumption optimization of the air conditioning system under the premise of ensuring the temperature safety of the computer room, and effectively improve the utilization efficiency of air conditioning resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0045] Figure 1 This is a flow chart of the first embodiment of the air conditioning energy-saving control method of the present application;

[0046] Figure 2 A schematic diagram of the system architecture of the air conditioning energy-saving control method of this application;

[0047] Figure 3 This is a flow chart of the second embodiment of the air conditioning energy-saving control method of the present application;

[0048] Figure 4 A schematic diagram of the training process of the preset parameter decision model in the air conditioning energy-saving control method of this application;

[0049] Figure 5 This is a flow chart of the third embodiment of the air conditioning energy-saving control method of the present application;

[0050] Figure 6 This is a schematic diagram of the entire process of the air conditioning energy-saving control method of this application;

[0051] Figure 7 This is a structural block diagram of the first embodiment of the air conditioning energy-saving control device of the present application.

[0052] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The present application provides an air conditioning energy saving control method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the air conditioning energy saving control method of the present application. In this embodiment, the method includes: Steps S10 to S40:

[0056] Step S10: acquiring real-time environmental status data, and inputting the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model.

[0057] It should be noted that the method of this embodiment can be applied to the scenario of energy consumption management of the air-conditioning system in the computer room. The executor of the method of this embodiment can be the edge computer device (edge ​​device) of the computer room. The Oasis software module can be deployed in the edge device for interacting with the Field Supervision Unit (FSU) to obtain real-time environmental status data collected by the FSU.

[0058] It is understandable that the FSU can collect real-time environmental status data through various hardware devices hanging on the FSU, and then send the real-time environmental status data to the edge device. The real-time environmental status data may include: temperature sensor temperature, air conditioner return air setting temperature, air conditioner working status, compressor status, etc.

[0059] Further, please refer to Figure 2 The interactive relationship between the edge device and the FSU in the air conditioning energy-saving control method of this application is described. Figure 2 This is a schematic diagram of the system architecture of the air conditioning energy-saving control method of this application.

[0060] like Figure 2 As shown, the edge device can be connected to the FSU through network communication, and the FSU and the downstream hardware devices (computer room air-cooled precision air conditioners, computer room ambient temperature sensors, and smart meters) can communicate through RS-485.

[0061] The edge device includes Oasis software module and algorithm service. Oasis software is used to interact with FSU to obtain device data. Therefore, the Oasis software module can be responsible for managing the communication interface between the algorithm service and FSU to ensure the smooth transmission of data flow. Users can configure the working parameters of the Oasis software module according to the actual situation of the computer room to adapt to the operating environment of different computer rooms.

[0062] The algorithm service communicates with the Oasis software network to obtain environmental status data in real time, and generates instructions corresponding to the control parameters to the Oasis software. The Oasis software then sends the instructions to the FSU, and finally the FSU device sends them to specific air-conditioning equipment to complete air-conditioning control.

[0063] In addition, when deploying algorithm services on edge devices, SQLite3 can be used as a storage database. SQLite3 can achieve efficient energy-saving control by sharing device data and resources with Oasis software. SQLite3 is an embedded lightweight database suitable for running on edge devices with limited resources. Compared with other large database systems (such as MySQL or PostgreSQL), SQLite3 occupies very little memory and computing resources, and can meet the real-time and data storage requirements of the air conditioning energy-saving control algorithm in the computer room. SQLite3 can efficiently process minute-level data, such as temperature sensor data, air conditioning operation status data, and meter data, and supports fast query and data processing, reducing the computing burden running on edge devices.

[0064] Specifically, the edge device collects the air conditioning and environmental data of the computer room through the FSU, and can process and execute energy-saving control strategies in real time on the edge device, thereby reducing dependence on the cloud and achieving fast response and low latency.

[0065] It should be noted that the candidate control parameters can be several groups of air conditioning input parameters generated in advance based on the genetic algorithm. The algorithm includes the following steps: ① Initialize the parameter population and set the fitness function (i.e., the energy consumption minimization target). ② Generate a new generation of parameters through selection, crossover and mutation operations. ③ Iterate and optimize until the set target optimization conditions are met, and determine the candidate control parameters based on the iterated parameter population.

[0066] It should be understood that in the iterative optimization of the genetic algorithm, the upper and lower limits of the air-cooled air conditioning temperature adjustment of the algorithm output action can be limited, for example, limited to between 20-26 degrees, and the parameters are configurable; the air-cooled air conditioning control power on and off operation of the algorithm output action can also be limited, the number of shutdowns can be counted, the total shutdown value can be specified, and the issuance is prohibited when the threshold is reached.

[0067] It should also be noted that in order to ensure the lightweight implementation of the genetic algorithm, the algorithm complexity can be reduced through parallel and incremental optimization: in each iteration, only the most relevant parameters are optimized, and an early stopping mechanism is introduced to avoid the genetic algorithm from performing too many invalid calculations on edge devices, ensuring the optimal energy consumption configuration with minimal resource consumption, further reducing the computational burden running on edge devices.

[0068] It should be noted that the temperature prediction sub-model and the energy consumption prediction sub-model in the preset parameter decision model can be constructed based on the Long Short-Term Memory (LSTM) network respectively.

[0069] In the specific implementation, the real-time environmental status data and alternative control parameters are input into the preset parameter decision model, which can use LSTM to roll-forward the changes in the temperature and energy consumption of the computer room at various time points in the future (for example, within 30 minutes).

[0070] Step S20: performing temperature prediction according to the real-time environmental status data in combination with candidate control parameters through the temperature prediction sub-model, and determining candidate control parameters based on the temperature prediction result.

[0071] It should be understood that by inputting the real-time environmental status data and the alternative control parameters into the temperature prediction sub-model, the temperature prediction sub-model can be used to predict the environmental temperature state of the computer room after the alternative control parameters are executed. Since the number of the above-mentioned alternative control parameters may not be unique, preliminary screening can be performed among the alternative control parameters based on their corresponding predicted environmental temperature states to obtain candidate control parameters.

[0072] Step S30: performing energy consumption prediction according to the real-time environmental status data and the candidate control parameters through the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction result.

[0073] It should be understood that by inputting the real-time environmental status data and the candidate control parameters into the energy consumption prediction sub-model, the environmental energy consumption status of the computer room after the candidate control parameters are executed can be predicted by the energy consumption prediction sub-model. Also, since the number of the above-mentioned candidate control parameters may not be unique, further screening can be performed among the candidate control parameters based on their corresponding predicted environmental energy consumption status, and finally the target control parameters can be determined.

[0074] It should also be noted that in the above process of determining the target control parameters based on the real-time environmental status data and the alternative control parameters, the candidate control parameters can be first determined through the energy consumption prediction sub-model and then input into the temperature prediction sub-model to obtain the target control parameters, or the alternative control parameters can be input into the energy consumption prediction sub-model and the temperature prediction sub-model respectively to directly predict the ambient temperature state and the predicted ambient energy consumption state for comprehensive analysis to determine the target control parameters. This embodiment does not impose any restrictions on this.

[0075] Step S40: sending the target control parameter to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs an air conditioning control operation according to the target control parameter.

[0076] In the specific implementation, the edge device transmits the target control parameters to the FSU through the Oasis software module, and then the FSU sends the target control parameters to each air-conditioning device to complete the air-conditioning control operation.

[0077] This embodiment makes parameter decisions by responding to real-time environmental status data through edge devices, which can reduce dependence on the cloud and achieve fast response and low latency; and specifically makes predictions based on the temperature prediction sub-model and the energy consumption prediction sub-model to determine the target control parameters, thereby optimizing the energy consumption of the air-conditioning system while ensuring the temperature safety of the computer room, and effectively improving the utilization efficiency of air-conditioning resources.

[0078] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 3 , Figure 3 This is a flow chart of the second embodiment of the air conditioning energy-saving control method of the present application.

[0079] In this embodiment, in order to specifically illustrate the construction process of the preset parameter decision model, before step S10, the following steps are also included: Steps S01 to S03:

[0080] Step S01: Acquire historical environmental status data, and determine whether the historical environmental status data meets a preset data volume condition, wherein the historical environmental status data includes historical air-conditioning operation data and corresponding historical temperature data and historical electric meter energy consumption data.

[0081] It should be understood that the edge device can also collect and store historical environmental status data through the FSU. After the algorithm service in the edge device is started, the edge device can periodically check whether the stored historical environmental status data meets the historical data length required for model training (for example: at least one week of data). When the data volume condition is met, model training can be started.

[0082] Step S02: If yes, the historical environmental status data is packaged to obtain a training data set.

[0083] It should be noted that a temperature training data set can be constructed based on the historical 24-hour minute-by-minute temperature data, air-conditioning operating parameters (working status, return air set temperature), and smart meter parameters (main equipment power consumption and air-conditioning power consumption); an energy consumption training data set can be constructed based on air-conditioning operating parameters and the historical 24-hour minute-by-minute air-conditioning energy consumption data.

[0084] Step S03: training the initial temperature prediction sub-model and the initial energy consumption prediction sub-model respectively according to the training data set to obtain a temperature prediction sub-model and an energy consumption prediction sub-model.

[0085] It should be noted that the initial temperature prediction sub-model and the initial energy consumption prediction sub-model can be constructed based on LSTM respectively. By training LSTM to make rolling predictions of the room temperature and energy consumption changes at various time points in the future (e.g., within 30 minutes), it is possible to determine target control instructions based on the temperature prediction results and energy consumption prediction results.

[0086] It is understandable that the training process is controlled by setting the number of training rounds or error loss threshold in the model training to ensure the accuracy of the model. After the training is completed, the model parameters will be saved and automatically updated every week to ensure that the temperature prediction sub-model and energy consumption prediction sub-model in the preset parameter decision model always have high prediction accuracy.

[0087] It should also be noted that during the model training process, model compression techniques can be used: quantization and pruning, which can reduce the size and computation of the model, so that the model training process can run efficiently on resource-constrained edge devices while maintaining high accuracy. In addition, model training and updating do not need to be performed frequently (can be set to once a week), which further reduces the occupation of edge device resources and ensures that edge devices can focus on real-time energy-saving control rather than large-scale model calculations in daily operation.

[0088] In addition, you can refer to Figure 4 The training process of the preset parameter decision model in the air conditioning energy-saving control method of the present application is described. Figure 4 Schematic diagram of the training process of the preset parameter decision model in the air conditioning energy-saving control method of this application.

[0089] exist Figure 4 In the process, first determine whether the historical environmental status data stored in the edge device meets the historical data length requirement (at least one week) required for model training; when the training requirements are met, the historical environmental status data is processed (cleaned and uniformly packaged) to serve as training data for the model.

[0090] The temperature prediction sub-model and the energy consumption prediction sub-model are trained separately through the training data, and the training process is controlled by the set number of training rounds or error loss threshold to ensure the accuracy of the model. After the training is completed, the model parameters are saved.

[0091] When the latest model parameters are generated, the preset parameter decision model can be iteratively updated based on the latest model parameters. The edge device can regularly obtain the latest environmental status data of the computer room based on the pre-configured decision parameter delivery time, and input it into the latest parameter decision model. The policy model outputs the optimized target control parameters based on these latest data.

[0092] Further, in order to specifically explain how to determine the target control parameters from the candidate control parameters according to the real-time environmental status data, step S20 specifically includes: steps S201 to S203.

[0093] Step S201: input the real-time environmental status data and the candidate control parameters into the temperature prediction sub-model to obtain a temperature prediction result.

[0094] Step S202: Determine whether the temperature prediction result meets a preset temperature safety condition.

[0095] Step S203: If yes, the alternative control parameter is determined as a candidate control parameter.

[0096] It should be understood that the candidate control parameters can be multiple sets of air conditioning input parameters generated by the above genetic algorithm. Each candidate control parameter is input into the temperature prediction sub-model, and the temperature prediction sub-model can predict the ambient temperature state of the computer room at various time points in the future after executing each candidate control parameter in the current temperature state, that is, the predicted ambient temperature state.

[0097] Then, it can be determined whether each predicted ambient temperature state meets the preset temperature safety condition, which can be a temperature threshold or temperature range set based on equipment operation requirements, environmental comfort or safety standards; if the predicted ambient temperature state meets the temperature safety condition, the corresponding alternative control parameters can be determined as candidate control parameters.

[0098] Accordingly, step S30 specifically includes steps S301 to S303:

[0099] Step S301: input the real-time environmental status data and the candidate control parameters into the energy consumption prediction sub-model to obtain an energy consumption prediction result.

[0100] Step S302: Determine whether the energy consumption prediction result meets a preset minimum energy consumption condition.

[0101] Step S303: If yes, the candidate control parameter is determined as the target control parameter.

[0102] It is understandable that the above-mentioned candidate control parameters can also be input into the energy consumption prediction sub-model, which predicts the environmental energy consumption state of the computer room at various future time points after executing each candidate control parameter in the current energy consumption state, i.e., the predicted environmental energy consumption state.

[0103] Then, it can be determined whether each predicted environmental energy consumption state meets the preset minimum energy consumption condition, which can be set based on energy saving goals, cost-benefit analysis or environmental impact assessment. If the predicted environmental energy consumption state indicates that future energy consumption can be maintained at the lowest energy consumption level unique to the minimum energy consumption condition or reach the preset energy saving goal, the candidate control parameters corresponding to these predicted environmental energy consumption states can be determined as target control parameters.

[0104] This embodiment obtains historical environmental status data and determines whether the historical environmental status data meets the preset data volume condition. The historical environmental status data includes: historical air conditioning operation data and corresponding historical temperature sensing data and historical electric meter energy consumption data; if so, the historical environmental status data is packaged and processed to obtain a training data set; the initial temperature prediction sub-model and the initial energy consumption prediction sub-model are trained according to the training data set to obtain a temperature prediction sub-model and an energy consumption prediction sub-model. In this embodiment, by constructing a temperature prediction model and an energy consumption prediction model, and automatically iterating and updating the model parameters every week, it is ensured that the model always has a high prediction accuracy, thereby optimizing the energy consumption of the air conditioning system while ensuring the temperature safety of the computer room, greatly reducing the energy consumption of air conditioning operation, and achieving the purpose of energy conservation and emission reduction.

[0105] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the first and second embodiments can be referred to the above description, and will not be described in detail later. Figure 5 , Figure 5 This is a flow chart of the third embodiment of the air conditioning energy-saving control method of the present application.

[0106] In this embodiment, in order to further ensure the security of the target control parameters to be issued, the target control parameters may be subjected to security detection. Therefore, step S40 specifically includes: steps S401 to S402:

[0107] Step S401: parse the target control parameter, and determine whether the target control parameter complies with a preset safety parameter range according to the parsing result.

[0108] It should be understood that the edge device can parse the target control parameters to understand their specific meaning and expected effect, for example by verifying the parameter values ​​to ensure that each parameter value is identifiable and executable.

[0109] It should be noted that the preset safety parameter range may include the upper and lower limit ranges of each adjustable parameter item in each air-conditioning equipment, such as: upper and lower limits of temperature, humidity, pressure, voltage, etc., as well as any other parameter items related to the safe operation of the air-conditioning equipment in the computer room.

[0110] Step S402: When the target control parameter meets the preset safety parameter range, the target control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

[0111] It should be noted that if the target control parameter exceeds the preset safety parameter range, the edge device can prevent the target control parameter from being sent for execution, and may trigger an alarm or take other safety measures, such as falling back to a safe state or notifying maintenance personnel. Alternatively, it can return to the temperature prediction or energy consumption prediction steps to redefine the target control parameter.

[0112] It should be understood that when the target control parameters meet the preset safety parameter range, they can be directly sent to the FSU to perform corresponding air conditioning control operations, such as: temperature set point, changing wind speed or mode, etc., to ensure that the computer room environment meets the predetermined safety and efficiency standards.

[0113] In addition, in order to ensure the safe operation of air-conditioning equipment in the computer room in real time, a safety protection mechanism can also be introduced into the above-mentioned air-conditioning energy-saving algorithm: after obtaining the real-time environmental status data, determine whether the real-time environmental status data meets the preset danger warning conditions; when the real-time environmental status data meets the preset danger warning conditions, obtain the corresponding safety policy; and then determine the forced control parameters according to the safety policy, and send the forced control parameters to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air-conditioning control operation according to the forced control parameters.

[0114] It should be noted that the danger warning condition can be a predefined condition for identifying a possible threat to the safety of the computer room, such as a potential high temperature warning or other dangerous situation. The safety policy can be a predefined action to be taken in a specific dangerous situation and the corresponding mandatory control parameters, which can include immediately lowering the temperature, increasing ventilation, shutting down specific equipment, etc., to ensure that the computer room environment is quickly restored to a safe state.

[0115] In the specific implementation, when the edge device identifies that the ambient temperature in the computer room is higher than the preset safety temperature, it can immediately enable the preset safety policy to send the forced control parameters to the FSU, so that the FSU adjusts the air-conditioning operation status according to the received forced control parameters, restores the computer room to a safe state, and avoids potential failures of the equipment caused by overheating and other problems.

[0116] In addition, you can also refer to Figure 6 The practical application process of the air conditioning energy-saving control method of this application is described in full process. Figure 6 This is a schematic diagram of the entire process of the air conditioning energy-saving control method of this application.

[0117] exist Figure 6In the process, the edge device obtains real-time environmental status data from the FSU, and determines whether the real-time environmental status data meets the preset danger alarm conditions; if so, the preset safety policy is directly enabled to send mandatory control parameters to the FSU, forcibly adjust the air-conditioning operation status, and restore the computer room to a safe state; if not, the air-conditioning input parameters are generated by combining the genetic algorithm and optimized to obtain several candidate control parameters, which are then input into the temperature prediction model and the energy consumption prediction model together with the real-time environmental status data, and the target control parameters are determined according to the temperature prediction results and the energy consumption prediction results, and finally the target control parameters that pass the safety test are sent to the FSU. In this way, the energy consumption of the air-conditioning system is optimized, the air-conditioning operation energy consumption is greatly reduced, and the purpose of energy saving and emission reduction is achieved while ensuring the temperature safety of the computer room.

[0118] In this embodiment, before the target control parameters are issued, the target control parameters are analyzed, and it is determined whether the target control parameters meet the preset safety parameter range according to the analysis results; therefore, when the target control parameters meet the preset safety parameter range, the target control parameters are sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs air conditioning control operations according to the target control parameters. And when the real-time environmental status data meets the preset danger alarm conditions, the corresponding safety policy is obtained; the forced control parameters are determined according to the safety policy, and the forced control parameters are sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs air conditioning control operations according to the forced control parameters. This embodiment introduces a safety protection mechanism into the energy-saving algorithm to ensure that the air-conditioning system can respond immediately and execute the safety policy in emergency situations (such as high temperature alarms), prevent abnormal situations caused by improper control parameters or sudden changes in the environment, and ensure the safe and stable operation of the computer room environment.

[0119] In addition, an embodiment of the present application further proposes a storage medium, on which an air-conditioning energy-saving control program is stored. When the air-conditioning energy-saving control program is executed by a processor, the steps of the air-conditioning energy-saving control method described above are implemented.

[0120] The present application also provides an air conditioning energy saving control device, please refer to Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the air conditioning energy-saving control device of the present application, and the device includes:

[0121] The data acquisition module 701 is used to acquire real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes a temperature prediction sub-model and an energy consumption prediction sub-model.

[0122] The model prediction module 702 is used to perform temperature prediction according to the real-time environmental status data combined with the alternative control parameters through the temperature prediction sub-model, and determine the candidate control parameters based on the temperature prediction results; perform energy consumption prediction according to the real-time environmental status data combined with the candidate control parameters through the energy consumption prediction sub-model, and determine the target control parameters based on the energy consumption prediction results.

[0123] The instruction issuing module 703 is used to send the target control parameter to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

[0124] This embodiment makes parameter decisions by responding to real-time environmental status data through edge devices, which can reduce dependence on the cloud and achieve fast response and low latency; and specifically makes predictions based on the temperature prediction sub-model and the energy consumption prediction sub-model to determine the target control parameters, thereby optimizing the energy consumption of the air-conditioning system while ensuring the temperature safety of the computer room, and effectively improving the utilization efficiency of air-conditioning resources.

[0125] The embodiment of the present application also provides an air conditioning energy-saving control system, the system comprising: a plurality of air conditioning devices, a dynamic environment monitoring unit and an edge device;

[0126] The dynamic environment monitoring unit is used to collect real-time environmental status data and send the real-time environmental status data to the edge device;

[0127] The edge device is used to receive real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes a temperature prediction sub-model and an energy consumption prediction sub-model;

[0128] The edge device is further used to perform temperature prediction according to the real-time environmental status data in combination with the candidate control parameters through the temperature prediction sub-model, and determine the candidate control parameters based on the temperature prediction result;

[0129] The edge device is further used to perform energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction sub-model, and determine the target control parameters based on the energy consumption prediction result;

[0130] The edge device is further used to send the target control parameter to the dynamic environment monitoring unit;

[0131] The dynamic environment monitoring unit is also used to receive the target control parameters and perform corresponding air-conditioning control operations on each of the air-conditioning devices according to the target control parameters.

[0132] The air-conditioning energy-saving control system provided in the present application can solve the technical problems of the air-conditioning energy-saving control method, and the beneficial effects of the air-conditioning energy-saving control system provided in the present application are the same as the beneficial effects of the air-conditioning energy-saving control method provided in the above-mentioned embodiment. The other technical features in the air-conditioning energy-saving control system are the same as the features disclosed in the above-mentioned embodiment method, and will not be repeated here.

[0133] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other elements in the process, method, article or system including the element.

[0134] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0135] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0136] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An air conditioning energy-saving control method, characterized in that: The method is applied to an edge device, and the method comprises: Acquire real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model; Performing temperature prediction according to the real-time environmental status data in combination with candidate control parameters through the temperature prediction sub-model, and determining the candidate control parameters based on the temperature prediction result; Performing energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction result; The target control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs an air conditioning control operation according to the target control parameter.

2. The method according to claim 1, characterized in that Before the step of obtaining real-time environmental status data, the method further includes: Acquire historical environmental status data, and determine whether the historical environmental status data meets a preset data volume condition, the historical environmental status data including: historical air-conditioning operation data and corresponding historical temperature data and historical electric meter energy consumption data; If yes, the historical environmental status data is packaged to obtain a training data set; The initial temperature prediction sub-model and the initial energy consumption prediction sub-model are trained respectively according to the training data set to obtain a temperature prediction sub-model and an energy consumption prediction sub-model.

3. The method according to claim 1, characterized in that Before the step of inputting the real-time environmental status data and the candidate control parameters into the preset parameter decision model, the method includes: Initialize parameter population based on preset genetic algorithm and determine target optimization conditions; The parameter population is iteratively optimized until the iterative result meets the target optimization condition, and then the candidate control parameters are determined according to the iterated parameter population.

4. The method according to claim 1, characterized in that The step of performing temperature prediction according to the real-time environmental status data in combination with candidate control parameters by the temperature prediction sub-model, and determining the candidate control parameters based on the temperature prediction result, comprises: Inputting the real-time environmental status data and the alternative control parameters into the temperature prediction sub-model to obtain a temperature prediction result; Determining whether the temperature prediction result meets the preset temperature safety condition; If so, the alternative control parameter is determined as the candidate control parameter.

5. The method according to claim 4, characterized in that The step of performing energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters by the energy consumption prediction sub-model, and determining the target control parameters based on the energy consumption prediction result includes: Inputting the real-time environmental status data and the candidate control parameters into the energy consumption prediction sub-model to obtain an energy consumption prediction result; Determining whether the energy consumption prediction result meets the preset minimum energy consumption condition; If so, the candidate control parameter is determined as the target control parameter.

6. The method according to claim 1, characterized in that The step of sending the target control parameter to the dynamic environment monitoring unit so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter includes: Analyze the target control parameters, and determine whether the target control parameters meet the preset safety parameter range according to the analysis results; When the target control parameter meets the preset safety parameter range, the target control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

7. The method according to claim 1, characterized in that After the step of obtaining real-time environmental status data, the method further includes: When the real-time environmental status data meets the preset danger warning conditions, obtaining the corresponding safety strategy; A mandatory control parameter is determined according to the security policy, and the mandatory control parameter is sent to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs an air conditioning control operation according to the mandatory control parameter.

8. An air conditioning energy-saving control device, characterized in that: The device comprises: A data acquisition module is used to acquire real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model; A model prediction module, configured to perform temperature prediction according to the real-time environmental status data in combination with the candidate control parameters through the temperature prediction submodel, and determine the candidate control parameters based on the temperature prediction results; perform energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction submodel, and determine the target control parameters based on the energy consumption prediction results; The instruction issuing module is used to send the target control parameter to the dynamic environment monitoring unit, so that the dynamic environment monitoring unit performs the air conditioning control operation according to the target control parameter.

9. An air conditioning energy-saving control system, characterized in that: The system includes: a number of air conditioning devices, a dynamic environment monitoring unit and an edge device; The dynamic environment monitoring unit is used to collect real-time environmental status data and send the real-time environmental status data to the edge device; The edge device is used to receive real-time environmental status data, and input the real-time environmental status data and alternative control parameters into a preset parameter decision model, wherein the preset parameter decision model includes: a temperature prediction sub-model and an energy consumption prediction sub-model; The edge device is further used to perform temperature prediction according to the real-time environmental status data in combination with the candidate control parameters through the temperature prediction sub-model, and determine the candidate control parameters based on the temperature prediction result; The edge device is further used to perform energy consumption prediction according to the real-time environmental status data in combination with the candidate control parameters through the energy consumption prediction sub-model, and determine the target control parameters based on the energy consumption prediction result; The edge device is further used to send the target control parameter to the dynamic environment monitoring unit; The dynamic environment monitoring unit is also used to receive the target control parameters and perform corresponding air-conditioning control operations on each of the air-conditioning devices according to the target control parameters.

10. A storage medium, characterized in that: The storage medium stores an air-conditioning energy-saving control program, and when the air-conditioning energy-saving control program is executed by the processor, the steps of the air-conditioning energy-saving control method according to any one of claims 1 to 7 are implemented.

Images