Control method and device for fusion scheduling efficient refrigerating machine room system and storage medium

Abstract

The invention discloses a control method and device for a fusion scheduling efficient refrigerating machine room system and a storage medium, and relates to the technical field of central air conditioner control. The method comprises the steps that operation data of all edge end devices and sensor data in all areas are obtained; calculating the energy efficiency index of each subsystem based on the operation data, the distribution weight of the subsystem corresponding to each equipment type, the comfort coefficient associated with each region and the sensor data in each region; according to the energy efficiency index, a control strategy of each subsystem is formulated in combination with the cooling capacity prediction data associated with each region; and performing reverse decomposition on the control strategy to obtain control parameters of the edge end equipment in each region, and issuing the control parameters to the edge end equipment in the corresponding region. The technical defect that when the cold source machine room is dispatched, the refrigeration effect of the central air conditioner is poor is overcome, and the overall energy utilization rate and the refrigeration effect are improved.

Description

Technical Field

[0001] The present application relates to the field of central air-conditioning control technology, and in particular to a control method, device and storage medium for a fusion-scheduling high-efficiency refrigeration room system. Background Art

[0002] Central air conditioning is the main energy-consuming system in buildings. Its cooling source system includes a multi-module cooling station module, and the cooling station module accounts for up to 80% of the energy consumption of central air conditioning. Therefore, controlling the energy consumption of the cooling source system is helpful for energy conservation and emission reduction.

[0003] In related technologies, cold source systems generally use PLC (Programmable Logic Controller) or DDC (Direct Digital Control) modules to build basic control logic, and PLC and DDC modules rely on PID (Proportional Integral Derivative Control Algorithm) algorithms. However, the parameters of the PID algorithm are fixed and are not suitable for processing nonlinear data relationships, making it difficult to adjust adaptively, resulting in poor cooling effects of central air conditioners when scheduling the cold source room.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present application is to provide a control method for an integrated scheduling high-efficiency refrigeration room system, aiming to solve the technical problem of poor refrigeration effect of central air conditioning when scheduling a cold source room.

[0006] To achieve the above-mentioned purpose, the present application proposes a control method for a fusion-scheduling high-efficiency refrigeration room system, the method comprising: acquiring operation data of each edge device and sensor data in each area; Calculate the energy efficiency index of each subsystem based on the operating data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area; According to the energy efficiency index and in combination with the cooling capacity prediction data associated with each of the areas, a control strategy for each of the subsystems is formulated; The control strategy is reversely decomposed to obtain control parameters of the edge devices in each of the areas, and the control parameters are sent to the edge devices in the corresponding areas.

[0007] In one embodiment, the edge terminal hub receives the start instruction and parses the corresponding service information according to the start instruction; Based on the service information, configure a logical mapping relationship between the edge device corresponding to the start instruction and the service; Based on the basic parameters of the edge device, the basic parameters are adjusted in combination with the logical mapping relationship to generate the policy parameters; The policy parameters are configured on the corresponding edge devices, and the edge devices are controlled to operate according to the corresponding policy parameters.

[0008] In one embodiment, the operation raw data of each of the edge devices and the sensor raw data returned by the sensors in each of the areas are obtained; Data preprocessing is performed based on the operation raw data and the sensor raw data to generate the operation data and the sensor data, and the operation data and the sensor data are stored in a data pool.

[0009] In one embodiment, based on the sensor data, basic features corresponding to the sensor data are extracted, and the basic features are converted into derived features; Based on the derived features, a comfort evaluation model is generated by modeling using a random forest algorithm; The comfort evaluation model uses the basic features and user feedback information as training samples, and optimizes the comfort evaluation model through the training samples; The comfort evaluation model calculates the comfort coefficient of the current environment according to the sensor data.

[0010] In one embodiment, based on the operation data, energy efficiency analysis is performed on each of the subsystems to determine an energy efficiency ratio of each of the subsystems to the overall system; Performing weighted fitting according to the rated energy consumption of the edge devices in each of the subsystems, and combining the allocation weights, obtaining an energy efficiency priority coefficient of each of the subsystems; The energy efficiency index is generated based on the energy efficiency priority coefficient, the sensor data, the comfort coefficient and the energy efficiency ratio.

[0011] In one embodiment, based on the operation data, energy efficiency analysis is performed on each of the subsystems to determine an energy efficiency ratio of each of the subsystems to the overall system; The cooling demand prediction model is based on historical cooling demand samples, and a multivariate linear regression algorithm is trained and verified to generate a cooling demand prediction model; The cooling demand prediction model calculates the cooling demand prediction data of the current environment based on the operating data.

[0012] In one embodiment, a particle swarm optimization algorithm is performed based on each of the subsystems, and several global optimal solutions are obtained by combining the energy efficiency index and the cooling capacity prediction data; By comparing and judging the global optimal solutions, a target global optimal solution is obtained; Analyze the target global optimal solution to obtain the corresponding target local optimal solution of each of the subsystems; The control strategy of each of the subsystems is generated according to the target local optimal solution.

[0013] In one embodiment, based on the control strategy corresponding to each of the subsystems, the edge control strategy corresponding to each of the regions is generated by each of the edge-end hubs; Reversely decompose the edge control strategy, generate the control parameters of the edge devices in each of the areas, and send the control parameters to the corresponding edge devices; The edge device operates based on the corresponding control parameters.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a fusion-scheduling high-efficiency refrigeration room device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the control method of the fusion-scheduling high-efficiency refrigeration room system as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the control method of the integrated scheduling high-efficiency refrigeration room system as described above are implemented.

[0016] The present application provides a control method for an integrated and dispatched high-efficiency refrigeration room system, including obtaining the operating data of each edge device and the sensor data in each area; calculating the energy efficiency index of each subsystem based on the operating data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area; formulating the control strategy of each subsystem according to the energy efficiency index and the cooling capacity prediction data associated with each area; reversely decomposing the control strategy to obtain the control parameters of the edge device in each area, and sending the control parameters to the edge device in the corresponding area. This solution realizes the "perception-decision-execution" closed-loop optimization of the building energy system through the integrated dispatch of each subsystem and the overall system, combined with data analysis and strategy regulation, and improves the continuous expansion capability of the cold source in the direction of reducing costs and increasing efficiency.

[0017] To summarize, this application analyzes the related data of each area, adjusts the control strategy of each subsystem, and then schedules the control parameters of the edge equipment, seeking the global optimal energy efficiency without sacrificing user comfort or even improving user comfort. It overcomes the technical defect of poor cooling effect of central air conditioning when scheduling the cold source room, and improves the global energy utilization and cooling effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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.

[0019] 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.

[0020] Figure 1 This is a flow chart of the first embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 2 This is a flow chart of a second embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 3 This is a flow chart of a third embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 4 This is a flow chart of a fourth embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 5 This is a flowchart of a fifth embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 6 This is a flow chart of a sixth embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 7 This is a flow chart of the seventh embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Figure 8 This is a flow chart of an eighth embodiment of a control method for integrating and scheduling a high-efficiency refrigeration room system of the present application; Fig. 9 This is the architecture diagram of the closed-loop control of the fusion scheduling high-efficiency refrigeration room system for this application; Fig.10 A flowchart of the module for integrating and scheduling high-efficiency refrigeration room system for this application; Fig.11 This is a structural diagram of the edge device of this application; Fig.12 This is a schematic diagram of the structure of the high-efficiency refrigeration room equipment integrated with the scheduling for this application.

[0021] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0022] 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.

[0023] In the related technology, the cold source system generally uses PLC or DDC modules to build the basic control logic, and PLC and DDC modules rely on PID algorithm. However, the parameters of PID algorithm are fixed, which is not suitable for processing nonlinear data relationships, and thus difficult to adjust adaptively, resulting in poor cooling effect of central air conditioning when scheduling the cold source room.

[0024] The present application provides a solution: firstly, the operation data of each edge device and the sensor data in each area are obtained, and then based on the operation data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area, the energy efficiency index of each subsystem is calculated, and then according to the energy efficiency index, combined with the cooling prediction data associated with each area, the control strategy of each subsystem is formulated, and finally, the control parameters of the edge device in each area are obtained by reverse decomposing the control strategy, and the control parameters are sent to the edge device in the corresponding area. It overcomes the technical defect of poor cooling effect of central air conditioning when scheduling the cold source room, and improves the overall energy utilization and cooling effect.

[0025] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a fusion scheduling high-efficiency refrigeration room device, a fusion scheduling high-efficiency refrigeration room system, etc. The following takes the fusion scheduling high-efficiency refrigeration room system as an example to illustrate this embodiment and the following embodiments.

[0026] 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.

[0027] The present application embodiment provides a control method for a fusion scheduling high-efficiency refrigeration room system, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system in the present application.

[0028] In this embodiment, the control method of the integrated scheduling high-efficiency refrigeration room system includes steps S10 to S40: Step S10, obtaining the operating data of each edge device and the sensor data in each area.

[0029] In this embodiment, each area is a single air conditioning operation system, including an edge hub and edge devices covered by the edge hub. The edge devices are electromechanical devices that maintain the operation of air conditioning in each area. Operation data are various parameter data of edge devices during operation. Sensor data are environmental data received by sensors in the area.

[0030] As an optional implementation, the operating raw data of each edge device and the sensor raw data related to each area are collected through the edge hub, and the collected operating raw data and sensor raw data are pre-processed such as data cleaning, data supplementation, and data missing supplementation to obtain operating data and sensor data.

[0031] Step S20, calculating the energy efficiency index of each subsystem based on the operating data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area.

[0032] In this embodiment, the subsystem is composed of a class of edge devices of the same type or the same function, such as a cooling subsystem, a freezing subsystem, and a chiller. The allocation weight of the subsystem is a dynamic adjustment coefficient set for each subsystem based on business priority or energy consumption ratio, which is used to quantify its impact on the overall energy efficiency. In the calculation of the energy efficiency index, the energy consumption of each subsystem is allocated by allocating weights. The comfort coefficient is a quantitative indicator calculated by environmental parameters such as temperature, humidity, and air flow rate, which reflects the threshold range of user satisfaction with the regional environment. The energy efficiency index is a comprehensive evaluation parameter generated by combining energy consumption data, equipment efficiency, and environmental requirements, which is used to measure the effective output of the subsystem under unit energy consumption.

[0033] As an optional implementation method, based on the operating data of each edge device, the energy efficiency of the same type of edge devices is summed and compared with the energy efficiency of the overall system to obtain the energy efficiency ratio of each subsystem. The sensor data obtains the current comfort coefficient through the preset comfort calculation rule, and is compared with the comfort coefficient associated with the area. The current comfort coefficient is not lower than the comfort coefficient associated with the area as the bottom line, and then weighted fitting is performed based on the rated energy consumption of the edge devices in each subsystem, which is used as the upper limit of the operating energy consumption of the edge devices. Finally, the energy efficiency index is generated through the energy efficiency ratio and the allocation weights of each subsystem according to the preset energy efficiency index rules, such as energy efficiency index = energy efficiency ratio of each subsystem × allocation weight - (current comfort coefficient - comfort coefficient associated with the area).

[0034] Step S30, formulating a control strategy for each of the subsystems according to the energy efficiency index and in combination with the cooling capacity prediction data associated with each of the areas.

[0035] In this embodiment, the cooling capacity prediction data is a regional future cooling demand prediction value generated based on historical operation data and machine learning models. The control strategy is an equipment operation rule formulated according to energy efficiency goals and cooling capacity requirements to minimize energy consumption under the constraints of ensuring comfort.

[0036] As an optional implementation method, based on the energy efficiency index as the minimum standard, the operation of the subsystem is adjusted in combination with the cooling capacity prediction data. The cooling subsystem, refrigeration subsystem and chiller are taken as three particle groups through the particle swarm optimization algorithm, and their global optimal solutions are calculated respectively. For example, reducing the speed of the cooling tower fan by 20% and adjusting the frequency of the refrigeration pump to 45Hz can save 18% of electricity and meet the cooling capacity demand. The target global optimal solution is determined by comparison, and the control strategy of each subsystem is generated based on the target global optimal solution.

[0037] Step S40, reversely decompose the control strategy to obtain control parameters of the edge devices in each of the areas, and send the control parameters to the edge devices in the corresponding areas.

[0038] In this embodiment, reverse decomposition is to decompose the global control strategy into device-level executable instructions through mathematical inversion or rule engine. The edge device control parameters are parameter values ​​that drive the operation of the device and must meet the boundary conditions for safe operation of the device.

[0039] As an optional implementation method, the control strategy of each subsystem is disassembled through a distributed optimization algorithm, and then the edge control strategy is generated by the edge hub. The control parameters of the edge devices in each area are reversely decomposed according to the edge control strategy, and the control parameters are sent to the edge devices. The edge devices detect the adaptability of the control parameters. If the adaptability test passes, the edge devices operate according to the corresponding control parameters. If the adaptability test fails, the alarm is uploaded and the "minimum parameters" are operated.

[0040] For example, the air-conditioning system collects real-time operating data such as the current and wind speed of the air-conditioning main unit through the edge center installed on each floor, monitors the environmental status of each area with temperature and humidity sensors and infrared passenger flow counters, and uses edge computing nodes to correlate equipment energy consumption with room temperature changes to generate an "electricity consumption-temperature deviation" analysis indicator. Based on the comfort requirements of conference rooms and shops and the cooling capacity forecast curve for the next two hours, the system uses an optimization algorithm to automatically generate strategies such as a 15% frequency reduction of the chilled water pump and intermittent start and stop of the fresh air unit. Finally, these instructions are converted into temperature setting values ​​(26±0.3℃) and valve opening parameters (55%~70%) for specific equipment, and are sent to the corresponding regional controller in real time through the Internet of Things platform for execution, thereby dynamically maintaining the indoor environment while reducing energy consumption by 18% compared to the traditional mode, and triggering the filter cleaning warning twice.

[0041] By analyzing the related data of each area, adjusting the control strategy of each subsystem, and then scheduling the control parameters of the edge equipment, the global optimal energy efficiency is sought without sacrificing user comfort or even improving user comfort. This overcomes the technical defect of poor cooling effect of central air conditioning when scheduling the cold source room, and improves the global energy utilization and cooling effect.

[0042] Based on any of the above embodiments, in Embodiment 2 of the present application, refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system in this application. Before step S10, steps A11 to A14 are also included: In step A11, the edge hub receives the start-up instruction and parses the corresponding business information according to the start-up instruction.

[0043] In this embodiment, the edge hub is an intelligent decision-making node deployed on the device side, which is responsible for receiving and parsing cloud commands, coordinating local devices to perform tasks, and assisting the cloud in collecting various data. The startup command is a structured command defined in a lightweight data exchange format for users to turn on the air conditioner in the area, including business information. Business information is the information given by the user, including the functions that need to be run.

[0044] As an optional implementation method, after receiving the startup instruction from the user, the edge center extracts the business information in the startup instruction through the built-in protocol parsing module and verifies the data integrity. If the data is complete, the logical mapping relationship corresponding to the business information is configured. If the data is incomplete, it is configured according to the preset logical mapping relationship.

[0045] Step A12: Based on the service information, configure a logical mapping relationship between the edge device corresponding to the start instruction and the service.

[0046] In this embodiment, the logical mapping relationship between the edge device and the business is based on a preset rule library or script framework, mapping the parsed instructions into specific edge device actions, defining the association rules between device parameters and business requirements, and realizing dynamic parameter adaptation through conditional judgment or function mapping.

[0047] As an optional implementation method, based on business information, the edge hub will automatically and dynamically bind each business instruction with a list of qualified edge devices. The specific process is: the business rule engine parses the trigger conditions in the instruction, matches the device attribute library, such as device ID, installation location, and function type to generate a "business-device" logical mapping relationship.

[0048] Step A13: Based on the basic parameters of the edge device, the basic parameters are adjusted in combination with the logical mapping relationship to generate the policy parameters.

[0049] In this embodiment, the basic parameters of the edge device are the hardware performance and operation configuration preset by the device before leaving the factory, which constitute the functional baseline of the device. The policy parameters are the optimized and generated device operation control values, which are used to guide the device to execute specific business policies.

[0050] As an optional implementation method, the edge center will first read the basic parameters of the device and combine them with the logical mapping relationship. For example, if the service of cooling to 24 degrees Celsius is executed, the cold air at 24 degrees Celsius will be continued for 2 minutes, etc. The conditional logic is converted into mathematical constraints through the rule engine or script parsing, and the policy parameters that can be executed by the device are dynamically calculated, such as the power setting value range = (rated upper limit × 0.8, current load × 1.2).

[0051] Step A14, configuring the policy parameters on the corresponding edge device, and controlling the edge device to operate according to the corresponding policy parameters.

[0052] In this embodiment, the edge device operates based on the policy parameters under the guidance of the corresponding policy parameters.

[0053] As an optional implementation, by writing various policy parameters into each edge device, the operating mechanism of the edge device is generated according to the policy parameters, so that the edge device runs according to the operating mechanism and detects the operating status, and the operating status is fed back to the edge hub in real time.

[0054] For example, in the central air-conditioning system, the edge thermostat is initially set to a fixed output of 24°C in cooling mode, a medium-speed fan gear and a compressor base frequency of 40Hz. The system is based on the preset "temperature difference-adjustment coefficient" logical mapping, combined with real-time collected indoor carbon dioxide concentration, thermal imaging data of pedestrian flow and perceived temperature forecasts released by the meteorological station, and dynamically generates optimization strategy parameters through a fuzzy control algorithm, ultimately achieving temperature fluctuation control in the office area within ±0.3°C.

[0055] Due to the regulation of the edge center, the air conditioners in each area can operate autonomously and optimize strategies, which improves the operating efficiency of the system.

[0056] Based on any of the above embodiments, in Embodiment 3 of the present application, refer to Figure 3 , Figure 3 This is a flow chart of the third embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system in this application. Step S10 includes steps B11 to B12: Step B11, obtaining the original operation data of each edge device and the original sensor data transmitted back by the sensors in each area.

[0057] In this embodiment, the raw operation data is the initial data directly collected by the edge device during operation without filtering, processing or aggregation. The sensor raw data refers to the unprocessed environmental data directly obtained by the sensor.

[0058] As an optional implementation, the operating raw data of each edge device and the sensor raw data in each area are obtained through the edge hub set up in each area, and the obtained sensor raw data is associated with the obtained area to obtain the sensor raw data of the area.

[0059] Step B12: performing data preprocessing based on the raw operation data and the raw sensor data to generate the operation data and the sensor data, and storing the operation data and the sensor data in a data pool.

[0060] In this embodiment, data preprocessing is an operation process of cleaning basic data, removing sensor transient noise, normalizing and filling missing values, and linearly interpolating to complete breakpoint data.

[0061] As an optional implementation, the operation raw data and sensor raw data are cleaned, normalized, and missing values ​​are filled to generate the operation data of the edge device and the sensor data of the associated area, and the operation data and the sensor data are stored in a data pool.

[0062] For example, the central air-conditioning system automatically collects operating data such as power consumption and wind speed of each device through the edge hub in each area, and connects temperature and humidity sensors to count the real-time temperature and flow of people in each area. The system first cleans the data to remove erroneous values, and then calculates the average energy consumption and room temperature change trend every 10 minutes, generating "peak electricity consumption period" and "optimal temperature setting" analysis results, and finally encrypts these data and stores them in the database. When the flow of people in a certain area increases significantly, the system automatically lowers the air-conditioning temperature and reduces the wind volume in idle areas to achieve overall power saving while keeping the indoor temperature stable.

[0063] Since the operating data and sensor data of each area are automatically collected and stored for analysis, it provides a data basis for the prediction of control strategies and fusion scheduling, and improves the response efficiency of the system.

[0064] Based on any of the above embodiments, in Embodiment 4 of the present application, refer to Figure 4 , Figure 4 This is a flow chart of the fourth embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application. Before step S20, it also includes steps C11 to C14: Step C11: extracting basic features corresponding to the sensor data based on the sensor data, and converting the basic features into derived features.

[0065] In this embodiment, the basic features are calculated from the corresponding environmental indicators, which are the maximum value, average value and weighted value of the environmental indicators, etc., reflecting the surface characteristics of the data. The derived features are composite indicators generated through mathematical operations or domain knowledge.

[0066] As an optional implementation method, the environmental indicators in the sensor data are extracted through the sensor data obtained by the edge center. The environmental indicators are basic features, such as temperature, humidity, and wind speed. The basic features are further subjected to more complex calculations, such as analyzing data fluctuation patterns and periodic changes (for example, equivalent temperature (Teq=Ta-0.4(RH-50)), wind chill index (WCI=13.12+0.6215Ta-11.37v0.16+0.3965Tav0.16), and temperature and humidity entropy (S=Ta×RH / 100), where Ta represents air temperature (Ta), RH represents relative humidity (RH), expressed in percentage (%), v represents wind speed (v), and Tav represents the interaction term between Ta and v, which refers to the multiplication of Ta and v. It is necessary to ensure that the wind speed unit matches the formula) to generate derived features.

[0067] Step C12, based on the derived features, a comfort evaluation model is generated by modeling using a random forest algorithm.

[0068] In this embodiment, the random forest algorithm is a machine learning method based on the integration of multiple decision trees. It improves the robustness of the model through voting mechanism or average prediction and is suitable for modeling high-dimensional features and nonlinear relationships. The comfort evaluation model evaluates comfort through sensor data and user feedback information.

[0069] As an optional implementation method, the standardized derived feature data set is first divided into a training set and a validation set according to the timestamp, and the random forest algorithm is input for multi-tree parallel training. The feature importance is evaluated by the Gini coefficient and the node splitting rule is optimized. After the training is completed, cross-validation is used to calculate the accuracy of the comfort model. If the accuracy is greater than 90%, it is set as the comfort evaluation model. If the accuracy does not meet the standard, training continues.

[0070] Step C13: The comfort evaluation model uses the basic features and user feedback information as training samples, and optimizes the comfort evaluation model through the training samples.

[0071] In this embodiment, user feedback information is completed by users voluntarily uploading evaluations and ratings, etc. The training samples are paired data sets containing sensor data and user feedback, which are used for learning and optimization of the comfort evaluation model.

[0072] As an optional implementation, the basic features are aligned with the user feedback information by timestamp, a labeled training sample set is generated through sliding window aggregation, noise data is removed, and the comfort assessment model is optimized and trained using the training sample set.

[0073] Step C14: the comfort evaluation model calculates the comfort coefficient of the current environment according to the sensor data.

[0074] In this embodiment, the comfort coefficient is a numerical indicator that quantifies the comfort level of the environment and can be mapped to a graded label or a recommended control action.

[0075] As an optional implementation method, based on the environmental data collected by sensors in real time, such as temperature, humidity, PM2.5, and light intensity, the data is first cleaned and standardized, such as eliminating abnormal mutation values ​​and unifying units to obtain sensor data. These features are input into the pre-trained random forest model, and the current derived features are weighted and summed through multiple decision trees, such as comfort coefficient = temperature × temperature weight + humidity × humidity weight + wind speed × wind speed weight, and the comfort coefficient of 0 to 100 points is output.

[0076] For example, the central air-conditioning system deploys temperature and humidity sensors, carbon dioxide concentration detection modules and fan status monitoring units on each floor to collect real-time operating data such as equipment current and wind speed, extract basic features through the edge center, and generate derived features based on the formula. The comfort model is trained by integrating historical user APP scores through the random forest algorithm. When a sudden increase in carbon dioxide in the conference room is detected, the comfort assessment model triggers the linkage control of increasing the air volume and adjusting the cold water valve opening to 65%, and sends the control parameters to the corresponding edge device.

[0077] Due to the training and application of the comfort assessment model, the system is able to reduce costs and increase efficiency of cold source rooms through the integration of AI and other technologies such as the Internet of Things without reducing user comfort, and enhance the continuous expansion capabilities of cold sources in the direction of reducing costs and increasing efficiency.

[0078] Based on any of the above embodiments, in Embodiment 5 of the present application, refer to Figure 5 , Figure 5 This is a flowchart of the fifth embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system in this application. Step S20 includes steps D11 to D13: Step D11, based on the operating data, performing energy efficiency analysis on each of the subsystems to determine the energy efficiency ratio of each of the subsystems to the overall system.

[0079] In this embodiment, energy efficiency analysis is to evaluate the energy utilization efficiency of equipment or systems through mathematical models and identify inefficient operating conditions. The energy efficiency ratio is the ratio of the energy efficiency of each subsystem to the energy efficiency of the entire system.

[0080] As an optional implementation method, based on the operating data of the subsystems of the central air conditioner such as the cooling tower, refrigeration pump, and chiller, such as the cooling water inlet and outlet temperature, the water pump flow and power, and the compressor COP (global coefficient of performance) value, the energy efficiency ratio is first calculated according to the subsystem, for example, cooling tower energy efficiency = heat dissipation ÷ power consumption, chiller energy efficiency = cooling capacity ÷ input power, and then the energy efficiency value of each subsystem is compared with the design value or the historical optimal value to obtain the deviation. The deviation is calculated, for example, the current energy efficiency of the cooling tower is only 80% of the design value. Finally, the weighted energy efficiencies of all subsystems are integrated, for example, the cooling tower weight is 30%, the chiller weight is 50%, and the weighted sum is used to calculate the energy efficiency ratio of the overall system, for example, the overall system energy efficiency ratio = cooling tower energy efficiency × cooling tower deviation × cooling tower + chiller energy efficiency × chiller deviation × chiller weight. Finally, the energy efficiency ratio of each subsystem is compared with the energy efficiency ratio of the overall system to obtain the energy efficiency ratio of each subsystem and the overall system.

[0081] Step D12, performing weighted fitting according to the rated energy consumption of the edge devices in each of the subsystems, and combining the allocation weights to obtain the energy efficiency priority coefficient of each of the subsystems.

[0082] In this embodiment, the rated energy consumption is the calibrated value of the energy consumption per unit time of the device under standard working conditions. Weighted fitting is to generate a comprehensive index by superimposing the rated energy consumption of the edge devices by weight through a linear combination or a nonlinear model. The energy efficiency priority coefficient is a numerical indicator that quantifies the urgency of energy efficiency optimization of the subsystem, which is calculated by the ratio of weighted energy consumption to energy efficiency standard.

[0083] As an optional implementation method, the energy efficiency standard is obtained by weighted fitting the rated energy consumption of the edge devices in each subsystem according to the preset energy consumption weight. For example, the energy efficiency standard of each device is calculated according to the formula "energy efficiency standard = rated energy consumption × fitting weight", and then the energy consumption of each edge device of the same type is weighted and summed in combination with the allocation weights of each subsystem to obtain the total weighted energy consumption base, and finally the energy efficiency priority coefficient is calculated using "total weighted energy consumption base ÷ actual energy consumption of the subsystem".

[0084] Step D13, generating the energy efficiency index based on the energy efficiency priority coefficient, the sensor data, the comfort coefficient and the energy efficiency ratio.

[0085] In this embodiment, the allocation weights will change dynamically according to the comfort coefficient and user feedback information, and an adaptive trade-off between energy efficiency and comfort is achieved through dynamic weights.

[0086] As an optional implementation, the current comfort coefficient is first calculated through sensor data, such as temperature, humidity and wind speed, and the formula comfort compensation value = current comfort - comfort associated with the area is used. Then, based on the energy efficiency priority coefficient, sensor data and comfort coefficient compensation value, the three types of data are normalized, for example, unified into 0-1 values, and then the comprehensive energy efficiency index is calculated according to dynamic weights, such as energy efficiency ratio accounting for 50%, comfort compensation value accounting for 30% and priority coefficient accounting for 20%.

[0087] For example, a central air-conditioning system collects the operating current, valve opening and energy consumption data of chillers, cooling towers and fan coils in real time through edge hubs deployed in various regions, and aggregates the data to the cloud in combination with environmental data from temperature and humidity sensors, carbon dioxide sensors and infrared passenger flow sensors. It uses a sliding window algorithm to calculate the energy efficiency ratio of each subsystem and the regional comfort coefficient, and then generates the subsystem energy efficiency priority coefficient based on the weighted fitting and dynamic adjustment factor of the equipment's rated energy consumption. It then uses a fuzzy rule engine to integrate the energy efficiency priority coefficient and the comfort coefficient to generate a global energy efficiency index, triggering a genetic algorithm to solve the optimal control parameter combination.

[0088] By conducting energy efficiency analysis on the sensor data associated with each area and combining it with the comfort coefficients of each subsystem and each area, the energy consumption of the cold source system can be reduced without reducing user comfort, thereby improving the cooling and energy-saving effects of the system.

[0089] Based on any of the above embodiments, in Embodiment 6 of the present application, refer to Figure 6 , Figure 6 This is a flow chart of the sixth embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application. Before step S30, it also includes steps E11 to E13: Step E11, based on the sensor data and the comfort coefficient, combined with user feedback information, correlation analysis is performed to build a cooling capacity prediction model.

[0090] In this embodiment, the cooling capacity prediction model is a cooling capacity prediction model that is built by collecting data from various dimensions and analyzing the correlation with user feedback information without sacrificing comfort.

[0091] As an optional implementation method, based on sensor data and comfort coefficient, combined with historical user feedback data, firstly, a training set is constructed through timestamp alignment and data cleaning, and then the key features are screened using the Pearson correlation coefficient. Next, a long short-term memory neural network model is used to train the prediction model with time series features and user feedback data labels. Finally, the cooling capacity prediction model is obtained through detection during training and fine-tuning of preset parameters.

[0092] Step E12: The cooling demand prediction model is trained and verified by a multivariate linear regression algorithm based on historical cooling demand samples to generate a cooling demand prediction model.

[0093] In this embodiment, the cooling demand prediction model mainly collects the chilled water supply and return water temperature difference, flow rate and historical cooling demand as the main features, and combines external features such as climate environment (weather, indoor and outdoor air temperature and humidity, wind speed), crowd density, time period sequence, etc., selects a multivariate linear regression algorithm for training modeling and verification, and generates a cooling demand prediction model.

[0094] As an optional implementation method, based on historical cooling demand samples, the system will first clean the data and normalize the feature variables, for example, unify them into 0-1 values, and then divide the training set and the validation set into 7:3. The relationship between the features and cooling demand is fitted through a multivariate linear regression algorithm (the formula is cooling demand = a×temperature difference+b×people density+c×equipment efficiency+intercept term, where a, b and c are constant terms). The least squares method is used to optimize the coefficients and calculate the R² (goodness of fit) score and residual analysis to verify the reliability of the model. After the training is completed, the cooling demand prediction model is derived.

[0095] Step E13: the cooling demand prediction model calculates the cooling prediction data of the current environment based on the operating data.

[0096] In this embodiment, the future cooling demand value output by the model is used to pre-adjust the operating state of the equipment, and can also be output as a cooling demand forecast curve for the next 24 hours after calculation by the model.

[0097] As an optional implementation method, the operating data of each subsystem is collected in real time, such as cooling water flow, refrigeration pump power, and terminal temperature setting value. The data is first cleaned to filter abnormal sensor jumps, fill in missing time periods, and perform standardization processing, such as unifying the temperature into degrees Celsius and converting the power into kilowatts. The processed data is then input into a pre-trained cooling demand prediction model, combined with historical load curves and external variables, such as weather forecasts and pedestrian flow forecasts, and the cooling demand forecast for future time periods is calculated through the internal weights of the model (formulas such as cooling demand = a×temperature difference+b×pedestrian density+c×equipment efficiency+intercept term, a, b, and c are constant terms).

[0098] For example, by real-time collection of central air-conditioning system equipment operation data, sensor data and user feedback information, after data cleaning, a multivariate linear regression model is constructed based on historical cooling demand samples by mining the statistical correlation between variables, and the regression coefficients are optimized through cross-validation and the feature weights are quantified to generate a cooling demand prediction model to calculate the cooling demand in future time periods in real time. The equipment pre-control instructions are dynamically generated based on the prediction results, and an encrypted communication protocol is used to ensure the safe transmission of control instructions. The effectiveness of the strategy is verified through the digital twin system, ultimately achieving multi-objective collaborative control to improve the matching of cooling supply and demand, reduce energy consumption and optimize user comfort.

[0099] Because the cooling demand prediction model is trained and training samples are collected for training and optimization, the system can quickly predict future cooling demand through the cooling demand prediction model, prepare equipment response and control strategies in advance, and improve the response speed and scheduling efficiency of the system.

[0100] Based on any of the above embodiments, in Embodiment 7 of the present application, refer to Figure 7 , Figure 7 This is a flow chart of the seventh embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application. Step S30 includes steps F11 to F14: Step F11, performing a particle swarm optimization algorithm based on each of the subsystems, combining the energy efficiency index and the cooling capacity prediction data, to obtain several global optimal solutions.

[0101] In this embodiment, the particle swarm optimization algorithm is a global optimization algorithm based on swarm intelligence. By simulating the foraging behavior of bird flocks, iteratively updating the particle position and speed, and finding the multi-objective optimal solution set. The global optimal solution is a solution set that satisfies the constraints in the multi-objective optimization and whose fitness reaches a preset threshold.

[0102] As an optional implementation of the particle swarm optimization algorithm, the particle swarm optimization algorithm is used. In the present invention, the cooling subsystem, the freezing subsystem, and the chiller in the above dimensions are taken as three particle swarms, and their local optimal solutions and global optimal solutions are calculated respectively. The range constraints are imposed on each input variable, and the standard particle swarm optimization algorithm is used for calculation.

[0103] Step F12, obtaining a target global optimal solution by comparing and judging the global optimal solutions.

[0104] In this embodiment, the target global optimal solution is obtained by comparing and judging various global optimal solutions, and selecting the solution set with the highest fitness as the target global optimal solution.

[0105] As an optional implementation method, the system will first collect multiple global optimal solutions calculated by different optimization algorithms, score each solution based on the preset weight rules, and then compare the scores to select the solution with the highest total score as the target solution. At the same time, it will verify whether the solution meets the actual constraints. After verification, it will be determined as the target global optimal solution.

[0106] Step F13, analyzing the target global optimal solution to obtain the corresponding target local optimal solution of each of the subsystems.

[0107] In this embodiment, the target local optimal solution is a parameter combination that optimizes the fitness function of each subsystem under the condition that the global constraints are satisfied at the entire system level.

[0108] As an optional implementation method, the global optimal solution of the entire system is decomposed into local optimization problems of each subsystem through the decomposition and coordination method, and the local optimal solution of each subsystem is iteratively solved by a distributed optimization algorithm. It is dynamically adjusted through Pareto front screening and model predictive control. If it is judged that if the operation according to the local optimal solution can ensure that the local solution meets the energy efficiency index and the comfort coefficient, it is defined as the target local optimal solution. If not, it is readjusted.

[0109] Step F14: generating the control strategy of each of the subsystems according to the target local optimal solution.

[0110] In this embodiment, a control strategy for specifically controlling edge devices is generated according to a target local optimal solution, and each edge device is integrated and scheduled to execute the corresponding control strategy.

[0111] As an optional implementation, based on the local optimal solution of the target, such as the air-conditioning subsystem needs to maintain 26℃±0.5℃ and the energy efficiency ratio is improved by 12%, and the refrigeration pump frequency is adjusted to 45Hz, the mathematical optimization parameters, such as temperature set value and frequency adjustment step, are first converted into control instructions that can be recognized by the equipment. Combined with the real-time operating status of the subsystem, such as the current temperature deviation, water pump load rate and safety thresholds, such as voltage fluctuation limit and compressor start and stop interval, a specific control strategy is generated through the rule engine, such as reducing the compressor power in this area by 1 level.

[0112] Exemplarily, the particle swarm optimization algorithm is used to perform multi-objective collaborative optimization of each subsystem, the energy efficiency index is used as the fitness function, the cooling capacity prediction data is integrated to construct a multidimensional solution space, and an iterative search is performed to generate a Pareto optimal solution set that satisfies the maximum energy efficiency and the balance between cooling capacity supply and demand. The non-inferior solution screening mechanism is combined with the business constraint comparison to determine the target global optimal solution, and the global solution is mapped to the subsystem level through the decomposition and coordination method. The Lagrange multiplier is used to process the coupling constraints and parse the local optimal parameter combination of the corresponding subsystem. The equipment control strategy is constructed based on the local optimal solution, and the optimization parameters are converted into executable instructions through the protocol conversion engine. The digital twin system is simultaneously deployed for strategy pre-verification and dynamic compensation mechanism, ultimately achieving closed-loop coordination of system-level energy efficiency optimization and equipment-level refined control.

[0113] By optimizing the definition of the values ​​of each variable, the calculation process, and the verification of the output, the global optimal solution is finally obtained through polynomial judgment comparison and other methods, and the global optimal solution of each dimension corresponding to the global optimal solution is decomposed, and then the fitting of each dimension is converted to the parameter level, and the entire calculation process is taken over and formed into a closed loop. This improves the matching degree of cooling supply and demand and reduces energy consumption costs, thereby improving the operating efficiency and energy saving effect of the system.

[0114] Based on any of the above embodiments, in Embodiment 8 of the present application, refer to Figure 8 , Figure 8 This is a flow chart of the eighth embodiment of the control method for integrating and scheduling a high-efficiency refrigeration room system of the present application. Step S40 includes steps G11 to G13: Step G11, based on the control strategy corresponding to each of the subsystems, generate the edge control strategy corresponding to each of the regions through each of the edge-end hubs.

[0115] In this embodiment, the edge control policy is an edge device control rule dynamically generated for a specific area.

[0116] As an optional implementation method, based on the control strategies of each subsystem, the edge hub will first receive the superior policy instructions, integrate the real-time sensor data in the area and the status of the edge devices in the area, and adapt the strategy through a rule engine or a lightweight reinforcement learning model to ensure that the edge devices can generate executable edge control strategies under conditions such as not exceeding the rated power.

[0117] Step G12, reversely decompose the edge control strategy, generate the control parameters of the edge devices in each of the areas, and send the control parameters to the corresponding edge devices.

[0118] In this embodiment, the control strategy is transmitted to the corresponding edge device through the Internet of Things connection channel.

[0119] As an optional implementation method, the edge hub will first break down the operating requirements of specific devices by region based on the overall control strategy, and then automatically convert the parameters that need to be adjusted for each device into control parameters that the device can recognize through the edge computing node, and securely push them to the edge devices in the corresponding area through the Internet of Things channel.

[0120] Step G13, the edge device operates based on the corresponding control parameters.

[0121] In this embodiment, the control parameter is associated with the device number of the corresponding edge device, so that the edge hub can send the control parameter to the corresponding edge device.

[0122] As an optional implementation method, after the edge device receives the control parameters sent by the edge center, it will first automatically parse the instructions and verify the permissions and format, then adjust the internal operation mode, and monitor its own status in real time to see if it matches the target parameters. If the deviation is too large, it will immediately send back an alarm message. During normal operation, it will regularly report the execution effect to the edge center. If there is a network interruption, it will maintain basic operation according to the preset "bottom line strategy".

[0123] Exemplarily, the subsystem-level control strategy is used to drive the edge hubs in each region to generate edge control strategies that are adapted to the local area. Based on the regional device topology and real-time operating status, the dynamic load balancing algorithm and the constraint satisfaction model are used to reversely parse the strategies into device-level control parameters. The parameters are encapsulated into device executable instructions through the protocol conversion engine. After the edge device executes the instructions, feedback data is collected in real time and a compensation mechanism is triggered based on the feedback data.

[0124] As an optional implementation of the closed-loop control architecture of the fusion scheduling high-efficiency refrigeration room system, refer to Fig. 9 , Fig. 9This is the architecture diagram of the closed-loop control of the integrated scheduling high-efficiency refrigeration room system for this application. The closed-loop control architecture of the fusion scheduling high-efficiency refrigeration room system takes data preprocessing as the core starting point, covering equipment management (such as equipment registration and status monitoring), multi-dimensional configuration (parameter threshold setting) and energy efficiency analysis (historical energy consumption pattern mining). The processed data is driven by the model and algorithm iteration verification module (including data synchronization and version control) to drive the cooling capacity prediction model (based on time series load analysis), comfort evaluation model and energy efficiency evaluation module (energy efficiency index generation). Then, the particle swarm optimization algorithm is used to integrate multi-dimensional goals (energy efficiency index, comfort, cooling capacity demand) to generate a dynamic control strategy, which is passed to the execution module (through I / O board protocol conversion) to link the cooling subsystem (cooling tower fan speed regulation), chiller (compressor frequency regulation) and refrigeration subsystem (water valve opening control). At the same time, the acquisition module feeds back the equipment status and environmental data to the preprocessing layer in real time through the sensor network (temperature, humidity, flow, current), forming a closed-loop control loop of "data acquisition-strategy optimization-execution regulation-effect feedback". The overall architecture is clearly layered, and the modules are coupled through standardized interfaces to achieve full-link intelligent management and control from strategy generation to precise execution of physical equipment.

[0125] As an optional implementation of the fusion scheduling high-efficiency refrigeration room system module, refer to Fig.10 , Fig.10 This is a flowchart of the integrated scheduling of the high-efficiency refrigeration room system module for this application. The execution process of the integrated scheduling of the high-efficiency refrigeration room system module is to collect data of various dimensions collected by the acquisition module through the transformation of various electromechanical equipment in the cold station and the installation of sensors.

[0126] The cooling prediction module collects data from various dimensions and correlates and analyzes it with user feedback data to build a cooling prediction model based on the premise of not losing comfort. The cooling demand prediction model mainly collects the temperature difference between supply and return water of chilled water, flow rate and historical cooling demand as the main features. At the same time, it combines external features such as climate environment (weather, indoor and outdoor air temperature and humidity, wind speed), crowd density, time series, etc., selects multivariate linear regression algorithm for training modeling and verification, and generates a cooling demand prediction model. When the model is applied, the chilled water supply and return water temperature difference, flow rate, climate environment data for the next 24 hours, current crowd density and other data are input, and the cooling demand prediction curve for the next 24 hours is output after model calculation. Every day, the actual cooling curve data and the cooling demand prediction curve data are merged as model iteration training data for model iteration training.

[0127] The evaluation module needs to build a comfort evaluation model and energy efficiency evaluation analysis. The comfort evaluation model uses indicators such as temperature, humidity, wind speed, and human comfort feedback as samples to train its more general model, and the model is preset in the system. By installing indoor temperature, humidity, and wind speed sensors, the corresponding environmental indicators are collected as basic features, and the basic features are converted into derived features, namely: equivalent temperature, wind chill index, temperature and humidity entropy; and the comfort evaluation model is generated through random forest algorithm modeling. Basic features: temperature, humidity, wind speed, derived features: equivalent temperature (Teq=Ta-0.4(RH-50)), where equivalent temperature (Teq, Thermal Equivalent), air temperature (Ta, Air Temperature), relative humidity (RH, Relative Humidity), wind chill index (WCI=13.12+0.6215Ta-11.37v0.16+0.3965Tav0.16), where wind chill index (WCI, Wind Chill Index), wind speed (v, Wind Speed), temperature and humidity entropy (S=Ta×RH / 100), where temperature and humidity entropy (S, Summer Heat-Humidity Index). The system uses the environmental indicators collected by each sensor as input in real time to calculate the comfort coefficient of the current environment in real time. Energy efficiency evaluation analysis includes and performs energy efficiency analysis on the cooling subsystem, refrigeration subsystem, and chiller. Since smart meters are installed on each subsystem, the energy efficiency ratio of each subsystem and the whole system can be obtained in real time through the actual real-time cooling output and real-time power. Weighted fitting is performed according to the rated energy consumption of the electromechanical equipment covered in each subsystem, and each subsystem is given an energy efficiency priority coefficient. When each subsystem participates in the global optimization in the future, the weighted index is used.

[0128] The strategy module is the core module for the system to integrate various subsystems, perform global optimization analysis and formulate control strategies. This module needs to integrate multiple dimensional optimal paths, such as: cooling subsystem, refrigeration subsystem, chiller, cooling demand forecast, comfort assessment, energy efficiency assessment and other dimensional indicators as input. The fusion strategy module adopts the particle swarm optimization algorithm. In the present invention, the cooling subsystem, refrigeration subsystem and chiller in the above dimensions are taken as three particle swarms, and their local optimal solutions and global optimal solutions are calculated respectively. Range constraints are imposed on each input variable. The standard particle swarm optimization algorithm is used for calculation, and the algorithm is as follows:

[0129]

[0130] in, is called the inertia factor, and It is called the acceleration constant and is generally taken as [0,4]. and is a random number with a value range of [0,1]. The dth dimension representing the individual extreme value of the ith variable. represents the dth dimension of the global optimal solution. Represents the updated state value of the system in the dth dimension / component at the i-th iteration / time. It represents the state value of the system in the dth dimension / component at the i-1th iteration / moment. The above algorithm is used to calculate the individual optimal solution and the global optimal solution for the above five dimensions in real time.

[0131] The three dimensions can be used to extract real-time power data from smart meter devices that are independently managed in the three dimensions, that is, the initial values ​​of the X variables in the three dimensions.

[0132] The non-particle coefficient values ​​are as follows: and : Initialize the value to 1.5; and : Generated by rand() function; and :Then determine whether to update after evaluating through the fitness function; The w in the algorithm is the inertia factor. In order to stably converge to the global optimal solution, the more common linear subtraction is used for iteration in the selection of the inertia factor.

[0133] t in, is the inertia weight of the ith particle at the tth iteration, , is the maximum and minimum value of the inertia weight, and N is the maximum number of iterations set in the initial setting (initially set to 2000).

[0134] The above algorithm calculates the power of the three dimensions, stores them and verifies them. The verification is calculated by the fitness function, and the fitness function Fitness is as follows: Fitness = +

[0135] in, is the sum of the energy consumption of the three-dimensional subsystems, Right now ; is the comfort penalty term, that is, the standard deviation between the comfort and the target value, and is the weight coefficient of comfort, which is dynamically adjusted according to factors such as season, day and night, sunny and rainy days, etc. Indicates cooling power, which is the power consumption used to reduce the ambient temperature. Indicates the refrigeration power, which is the power consumption for deep cooling (below 0°C). Indicates the total power of the unit, which is the power consumption for the overall operation of the unit; This penalty item mainly considers the fluctuation of indoor temperature and humidity. Its conversion algorithm is as follows:

[0136] This is the equipment performance penalty item, which mainly analyzes the energy efficiency curve of the chiller and water pump and the current equipment load. is the weight coefficient of this item; It is a parameter safety range penalty item, that is, it regulates the legal range of parameters of each device. If it is not within the range, the penalty item is strengthened for correction. is the weight coefficient of this item. represents the sum of squares of indoor temperature changes, Represents the sum of squares of changes in relative humidity.

[0137] Whether it is a centrifugal, screw or magnetic suspension type of chiller, the equipment has its efficient operation load range. When the current real-time load of the equipment is not in the efficient load range, a performance penalty value will be generated. The energy consumption data after each particle swarm iteration is passed through the fitness function to determine whether it is the individual optimal or global optimal solution. If so, the corresponding variables are updated, that is, (Individual Optimum) or (Global Optimum).

[0138] There are two situations in which this algorithm can end its iteration process: (1) By calculating the global coefficient of performance (COP) in real time, if the difference between the two adjacent COPs in the last 30 iterations is less than 1e-4, the particle swarm iteration can be terminated; (2) When the number of iterations is greater than or equal to the initially set N value, the particle swarm iteration can be terminated; By defining the values ​​of each variable, optimizing the calculation process, and optimizing factors such as output verification, the global optimal solution is finally obtained through polynomial judgment and comparison, and the global optimal solution of each dimension corresponding to the global optimal solution is decomposed. Each dimension is then fitted and converted to the parameter level, taking over the entire calculation process and forming a closed loop.

[0139] The global optimal solution is converted to the execution module, which needs to decompose it into the parameters of each control unit, as follows: Control parameters corresponding to the cooling control unit: cooling tower fan frequency, cooling water pump frequency, water circuit solenoid valve closing degree, increase or decrease the number of cooling towers; Control parameters corresponding to the refrigeration control unit: refrigeration water pump frequency, water circuit solenoid valve closing degree; Control parameters corresponding to the chiller unit: refrigeration water supply temperature setting, refrigeration water temperature difference setting, increase or decrease the number of chillers; The three subsystem dimensions convert power consumption into parameters. Since the relationship between each model of equipment will be different, it is necessary to collect and accumulate historical data to fit its relationship. After the early data fitting, the global optimal power consumption data of each subsystem can be converted into equipment parameters and sent to the control module.

[0140] The core of the control module is to execute the instructions and parameters that each control object needs to send from the execution strategy module, and at the same time ensure the atomic execution of the execution actions of the control objects, and can roll back in real time. In the previous section, the global optimum is converted into the parameters of each control device, and the control instructions are issued in different ways.

[0141] The feedback module includes device and sensor feedback data and user feedback data. The device and sensor feedback data mainly refers to whether the changes in environmental indicators after the device parameters are adjusted converge to the target value. User feedback data is mainly used in the continuous operation of the system, so that the system can obtain negative samples for system iteration in a timely manner.

[0142] As an optional cloud-edge implementation method, this system operates in a cloud-edge linkage manner. The cloud focuses on the full process management and maintenance of equipment digitization, as well as the relevant configuration required for business applications. In addition, the cloud is responsible for the preprocessing of data samples after collection, the verification of historical cooling prediction models, and the optimization of global optimization algorithms. The edge hub is deployed on-site in the computer room, responsible for communicating with various electromechanical equipment and IoT sensors, and issuing control instructions to each edge device. In addition, the edge hub will periodically synchronize the models and algorithms iterated by the cloud to the local, and the actual parameters on site are also calculated on this side through the model and algorithm. The edge hub can operate independently from the cloud.

[0143] As an implementation method of an optional edge device structure, refer to Fig.11 , Fig.11 The structure diagram of the edge device of this application is as follows: the edge device has the ability to connect to the Internet of Things, and then passes through the LAN switch to the data terminal unit (DTU), and then the DTU sends parameter instructions to the edge device, such as Fig.11The blue dotted path in the figure. If the edge device does not have IoT capabilities, the signal is sent to the edge device through the I / O board inside the edge. Fig.11 In the middle orange dotted path, edge devices with IoT capabilities include chillers and smart water meters, and edge devices without IoT capabilities include temperature sensors, temperature and humidity sensors, wind sensors, pressure difference switches, inverters, and relay switches. In the past, the control logic and instruction issuance of edge devices in the industry were all interacted with the equipment through DDC or PLC related equipment, but in the present invention, the above two methods will replace the original mode to make its control more scalable.

[0144] By analyzing and issuing subsystem control strategies, closed-loop precise control of global strategy - regional instructions - equipment actions is achieved, multi-objective collaborative optimization is achieved, and the overall collaborative efficiency and operational efficiency of the system are improved.

[0145] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the drone inspection method based on smart poles of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0146] The present application provides a fusion-scheduling high-efficiency refrigeration room device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the control method of the fusion-scheduling high-efficiency refrigeration room system in the above-mentioned embodiment one.

[0147] Reference below Fig.12 , which shows a schematic diagram of the structure of the fusion scheduling high-efficiency refrigeration room equipment suitable for implementing the embodiment of the present application. The fusion scheduling high-efficiency refrigeration room equipment in the embodiment of the present application may include but is not limited to mobile terminals such as refrigeration rooms, laptops, digital broadcast receivers, personal digital assistants (PDA, Personal Digital Assistant), tablet computers (PAD, Portable Application Description), portable multimedia players (PMP, Portable Media Player:), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.12 The fusion-scheduling high-efficiency refrigeration room equipment shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0148] like Fig.12As shown, the fusion scheduling high-efficiency refrigeration room equipment may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. In the random access memory 1004, various programs and data required for the operation of the fusion scheduling high-efficiency refrigeration room equipment are also stored. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the fusion scheduling high-efficiency refrigeration room equipment to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a fusion scheduling high-efficiency refrigeration room equipment with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0149] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0150] The fusion-scheduling high-efficiency refrigeration room equipment provided by the present application adopts the control method of the fusion-scheduling high-efficiency refrigeration room system in the above-mentioned embodiment, which can solve the technical problem of poor refrigeration effect of the central air conditioner when scheduling the cold source room. Compared with the prior art, the beneficial effects of the fusion-scheduling high-efficiency refrigeration room equipment provided by the present application are the same as the beneficial effects of the control method of the fusion-scheduling high-efficiency refrigeration room system provided by the above-mentioned embodiment, and other technical features in the fusion-scheduling high-efficiency refrigeration room equipment are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0151] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0152] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0153] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, the computer-readable program instructions being used to execute the control method for the fusion-scheduling high-efficiency refrigeration room system in the above-mentioned embodiment.

[0154] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM, Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM, CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, radio frequencies (RF, Radio Frequency), etc., or any suitable combination of the above.

[0155] The computer-readable storage medium may be included in the fusion-scheduling high-efficiency refrigeration room equipment; or may exist independently without being assembled into the fusion-scheduling high-efficiency refrigeration room equipment.

[0156] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the fusion-scheduling high-efficiency refrigeration room equipment, the fusion-scheduling high-efficiency refrigeration room equipment: obtains the operating data of each edge device and the sensor data in each area; based on the operating data, the allocation weight of the subsystem corresponding to each device type, the comfort coefficient associated with each area, and the sensor data in each area, calculates the energy efficiency index of each subsystem; formulates the control strategy of each subsystem according to the energy efficiency index and the cooling capacity prediction data associated with each area; reversely decomposes the control strategy to obtain the control parameters of the edge device in each area, and sends the control parameters to the edge device in the corresponding area.

[0157] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0158] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0160] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned control method for the fusion scheduling high-efficiency refrigeration room system, and can solve the technical problem that the refrigeration effect of the central air conditioner is not good when scheduling the cold source room. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the control method for the fusion scheduling high-efficiency refrigeration room system provided in the above-mentioned embodiment, and will not be repeated here.

[0161] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A control method for integrating scheduling of high-efficiency refrigeration room system, characterized in that: The method comprises: Obtain the operating data of each edge device and the sensor data in each area; Calculate the energy efficiency index of each subsystem based on the operating data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area; According to the energy efficiency index and in combination with the cooling capacity prediction data associated with each of the areas, a control strategy for each of the subsystems is formulated; The control strategy is reversely decomposed to obtain control parameters of the edge devices in each of the areas, and the control parameters are sent to the edge devices in the corresponding areas.

2. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: Before the step of obtaining the operating data of each edge device and the sensor data in each area, the step further includes: The edge terminal hub receives the start instruction and parses the corresponding business information according to the start instruction; Based on the service information, configure a logical mapping relationship between the edge device corresponding to the start instruction and the service; Based on the basic parameters of the edge device, the basic parameters are adjusted in combination with the logical mapping relationship to generate the policy parameters; The policy parameters are configured on the corresponding edge devices, and the edge devices are controlled to operate according to the corresponding policy parameters.

3. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: The step of obtaining the operating data of each edge device and the sensor data in each area includes: Acquire the original operation data of each edge device and the original sensor data transmitted by the sensors in each area; Data preprocessing is performed based on the operation raw data and the sensor raw data to generate the operation data and the sensor data, and the operation data and the sensor data are stored in a data pool.

4. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: Before the step of calculating the energy efficiency index of each subsystem based on the operation data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area, the step further includes: Based on the sensor data, extract basic features corresponding to the sensor data, and convert the basic features into derived features; Based on the derived features, a comfort evaluation model is generated by modeling using a random forest algorithm; The comfort evaluation model uses the basic features and user feedback information as training samples, and optimizes the comfort evaluation model through the training samples; The comfort evaluation model calculates the comfort coefficient of the current environment according to the sensor data.

5. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: The step of calculating the energy efficiency index of each subsystem based on the operation data, the allocation weight of each device type corresponding to the subsystem, the comfort coefficient associated with each area, and the sensor data in each area includes: Based on the operating data, performing energy efficiency analysis on each of the subsystems to determine an energy efficiency ratio of each of the subsystems to the overall system; Performing weighted fitting according to the rated energy consumption of the edge devices in each of the subsystems, and combining the allocation weights, obtaining an energy efficiency priority coefficient of each of the subsystems; The energy efficiency index is generated based on the energy efficiency priority coefficient, the sensor data, the comfort coefficient and the energy efficiency ratio.

6. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: Before the step of formulating the control strategy of each of the subsystems according to the energy efficiency index and the cooling capacity prediction data associated with each of the regions, the step further includes: Based on the sensor data and the comfort coefficient, a correlation analysis is performed in combination with user feedback information to build a cooling capacity prediction model; The cooling demand prediction model is based on historical cooling demand samples, and a multivariate linear regression algorithm is trained and verified to generate a cooling demand prediction model; The cooling demand prediction model calculates the cooling demand prediction data of the current environment based on the operating data.

7. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 6 is characterized in that: The step of formulating the control strategy of each subsystem according to the energy efficiency index and the cooling capacity prediction data associated with each area includes: Based on each of the subsystems, a particle swarm optimization algorithm is performed, and several global optimal solutions are obtained by combining the energy efficiency index and the cooling capacity prediction data; By comparing and judging the global optimal solutions, a target global optimal solution is obtained; Analyze the target global optimal solution to obtain the corresponding target local optimal solution of each of the subsystems; The control strategy of each of the subsystems is generated according to the target local optimal solution.

8. The control method of the integrated scheduling high-efficiency refrigeration room system according to claim 1 is characterized in that: The step of reversely decomposing the control strategy to obtain control parameters of the edge devices in each of the areas, and sending the control parameters to the edge devices in the corresponding areas includes: Based on the control strategy corresponding to each of the subsystems, the edge control strategy corresponding to each of the regions is generated through each of the edge-end hubs; Reversely decompose the edge control strategy, generate the control parameters of the edge devices in each of the areas, and send the control parameters to the corresponding edge devices; The edge device operates based on the corresponding control parameters.

9. A fusion-scheduling high-efficiency refrigeration room equipment, characterized in that: The fusion-scheduling high-efficiency refrigeration room equipment includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the control method of the fusion-scheduling high-efficiency refrigeration room system as described in any one of claims 1 to 8.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the control method of the fusion scheduling high-efficiency refrigeration room system according to any one of claims 1 to 8 are implemented.

Images