Industrial air conditioning energy consumption optimization method and system
By collecting data from different zones within the industrial area and performing parallel optimization, the problems of low efficiency and insufficient coordination in traditional air conditioning energy consumption optimization methods have been solved, achieving high-efficiency energy consumption control and improved energy utilization.
Patent Information
- Application Number
- CN202411178428.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-27
AI Technical Summary
Traditional industrial air conditioning energy consumption optimization methods are inefficient, unable to achieve precise dynamic adjustments, and lack an effective coordination mechanism between different air-conditioned areas, resulting in uneven energy consumption distribution and affecting overall energy utilization efficiency.
By dividing the target industrial area into zones, data from each energy consumption zone is collected and analyzed in real time. Multiple energy consumption data optimization nodes are used for parallel optimization, and the control modules of the air conditioning control system are matched in reverse to generate coordinated control parameters.
It achieves real-time and accurate energy consumption data, improves energy consumption optimization efficiency, reduces energy consumption levels, and enhances energy utilization efficiency and production cost control.
Smart Images

Figure CN118705726B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of energy consumption optimization, and in particular to an industrial air-conditioning energy consumption optimization method and system. Background Art
[0002] In the industrial production process, the air conditioning system is used to adjust the production environment temperature, humidity and other parameters to ensure the normal progress of the production process. It is crucial to production. However, there are still some technical problems in the traditional industrial air conditioning energy consumption management optimization method. On the one hand, the traditional energy consumption optimization method is often based on static models or empirical adjustments, and is usually an overall analysis. It is difficult to make accurate dynamic adjustments to the operating status of the industrial air conditioning system, which leads to low energy consumption optimization efficiency and cannot meet the needs of actual production. On the other hand, the industrial area usually contains multiple air conditioning energy consumption areas, and there is a lack of effective coordination and adjustment mechanisms between the areas, resulting in uneven energy consumption distribution. For example, some areas have too high energy consumption and some areas have insufficient energy consumption, which affects the overall energy utilization efficiency. Summary of the invention
[0003] This application provides an industrial air-conditioning energy consumption optimization method, aiming to solve the technical problems that traditional methods for optimizing energy consumption data of industrial areas are usually performed serially, with low efficiency, and lack of effective coordination mechanism between different air-conditioning areas, resulting in uneven energy consumption distribution and poor overall energy utilization efficiency.
[0004] In view of the above problems, the present application provides an industrial air conditioning energy consumption optimization method and system.
[0005] The first aspect disclosed in the present application provides an industrial air-conditioning energy consumption optimization method, the method comprising: obtaining Q air-conditioning energy consumption zones according to regional layout information of a target industrial zone, wherein the Q air-conditioning energy consumption zones correspond to Q air-conditioning control systems, Q≥2; deploying a data acquisition system, connected to the Q air-conditioning control systems respectively, to perform real-time energy consumption data acquisition, and obtain Q real-time energy consumption data sets; performing cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, P≥2; performing parallel optimization processing on the P energy consumption data clusters based on the P energy consumption data optimization nodes to generate P optimized energy consumption states; reversely matching a control module of the air-conditioning control system based on the P optimized energy consumption states to generate P air-conditioning control parameters, and performing coordinated control of the air-conditioning control system according to the P air-conditioning control parameters.
[0006] Another aspect disclosed in the present application provides an industrial air conditioning energy consumption optimization system, which is used for the above-mentioned industrial air conditioning energy consumption optimization method, and the system includes: an air conditioning energy consumption zone acquisition module, which is used to acquire Q air conditioning energy consumption zones according to the regional layout information of the target industrial zone, wherein the Q air conditioning energy consumption zones correspond to Q air conditioning control systems, Q ≥ 2; an energy consumption data acquisition module, which is used to deploy a data acquisition system, which is respectively connected to the Q air conditioning control systems to perform real-time energy consumption data acquisition and acquire Q real-time energy consumption data sets; an energy consumption data cluster generation module, which is used to generate energy consumption data clusters. A cluster generation module is used to perform cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, P≥2; a parallel optimization processing module is used to perform parallel optimization processing on the P energy consumption data clusters based on the P energy consumption data optimization nodes to generate P optimized energy consumption states; a coordination control module is used to reversely match the control module of the air-conditioning control system based on the P optimized energy consumption states to generate P air-conditioning control parameters, and coordinate control of the air-conditioning control system according to the P air-conditioning control parameters.
[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0008] By zoning the target industrial area and collecting and analyzing real-time data for each energy consumption area, the energy consumption of different energy consumption areas can be monitored in real time, improving the real-time and accuracy of energy consumption data; by using multiple energy consumption data optimization nodes for parallel optimization processing, multiple energy consumption data clusters can be processed at the same time, improving the optimization efficiency of energy consumption data, speeding up the optimization process, and thus reducing the cost of energy consumption optimization; by reverse matching the optimized energy consumption state, the corresponding air conditioning control parameters are generated, and the coordinated control of the air conditioning system is realized, which effectively reduces the energy consumption level and improves the energy utilization efficiency, thereby achieving the purpose of energy conservation and emission reduction. In summary, the above industrial air conditioning energy consumption optimization method realizes efficient energy consumption optimization and accurate energy consumption control through technologies such as real-time data analysis, parallel optimization processing and coordinated control, thereby improving the energy utilization efficiency and production cost control of the industrial air conditioning system.
[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1A schematic diagram of a process flow of an industrial air conditioning energy consumption optimization method is provided for an embodiment of the present application;
[0011] Figure 2 A schematic diagram of the structure of an industrial air conditioning energy consumption optimization system is provided for an embodiment of the present application.
[0012] Explanation of the reference numerals: air-conditioning energy consumption zone acquisition module 10 , energy consumption data acquisition module 20 , energy consumption data cluster generation module 30 , parallel optimization processing module 40 , coordination control module 50 . DETAILED DESCRIPTION
[0013] The embodiment of the present application provides an industrial air-conditioning energy consumption optimization method to solve the technical problems that the traditional method of optimizing the energy consumption data of industrial areas is usually performed serially, which is inefficient, and there is a lack of effective coordination mechanism between different air-conditioning areas, and the energy consumption distribution is uneven, resulting in poor overall energy utilization efficiency.
[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0015] Embodiment 1
[0016] like Figure 1 As shown, the embodiment of the present application provides an industrial air conditioning energy consumption optimization method, the method comprising:
[0017] According to the regional layout information of the target industrial zone, Q air conditioning energy consumption zones are obtained, wherein the Q air conditioning energy consumption zones correspond to Q air conditioning control systems, Q ≥ 2;
[0018] Collect the floor plan or building structure information of the target industrial zone, including the location, size, and purpose of the building. Based on the collected structural information, perform attribute analysis on the industrial zone to determine the location and characteristics of different functional areas, such as production areas, office areas, storage areas, etc. According to the results of regional attribute analysis, the industrial zone is divided into multiple air-conditioning energy consumption zones based on factors such as building structure, equipment layout, and personnel density. Each area has similar energy consumption characteristics and demand patterns, and each air-conditioning energy consumption area has a corresponding air-conditioning control system. Q is the number of air-conditioning energy consumption zones, and Q ≥ 2 means that the target industrial zone is divided into at least 2 areas to achieve distributed energy consumption control.
[0019] Deploy a data acquisition system, connect it to the Q air conditioning control systems respectively, collect real-time energy consumption data, and obtain Q real-time energy consumption data sets;
[0020] Select data acquisition equipment suitable for industrial air-conditioning control systems, including temperature sensors, humidity sensors, etc., to ensure that they can collect temperature, humidity and other related data in real time, deploy the selected data acquisition equipment to the location of each air-conditioning control system, connect the data acquisition system to each air-conditioning control system, and configure the parameters of the data acquisition system, including setting parameters such as sampling frequency and data transmission method. After the deployment is completed, start collecting the energy consumption data generated by each air-conditioning control system in real time, and obtain Q real-time energy consumption data sets, which will be used for subsequent energy consumption optimization analysis.
[0021] Performing cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, and P≥2;
[0022] Select a clustering algorithm suitable for processing real-time energy consumption data, such as K-means, hierarchical clustering, etc., determine the value of P according to the actual situation, that is, how many clusters the real-time energy consumption data needs to be divided into, use the selected clustering algorithm to perform cluster analysis on Q real-time energy consumption data sets, and divide the data into P energy consumption data clusters. The clustering process will assign data points to different clusters based on the similarity of energy consumption data, so that the energy consumption data in each cluster is highly similar and the differences between clusters are as large as possible. Correspond each energy consumption data cluster to an energy consumption data optimization node to ensure that each node is responsible for optimizing energy consumption data clusters with high similarity. These optimization nodes are used for subsequent energy consumption optimization processing.
[0023] Based on the P energy consumption data optimization nodes, the P energy consumption data clusters are optimized in parallel to generate P optimized energy consumption states;
[0024] P energy consumption data clusters are assigned to corresponding energy consumption data optimization nodes, and each node processes the data of one cluster, so that parallel data processing can be achieved and optimization efficiency can be improved. Each energy consumption data optimization node uses optimization algorithms, such as genetic algorithms, particle swarm algorithms, simulated annealing algorithms, etc., to optimize the energy consumption data clusters it is responsible for, so as to reduce energy consumption and improve energy utilization efficiency. After optimization, the corresponding optimized energy consumption states are generated, which reflect the energy consumption optimization results for each cluster, including information such as the adjusted air conditioning control parameters.
[0025] Based on the P optimized energy consumption states, a control module of the air-conditioning control system is reversely matched to generate P air-conditioning control parameters, and the air-conditioning control system is coordinated and controlled according to the P air-conditioning control parameters.
[0026] Reverse matching is performed on each optimized energy consumption state with the control module of the air-conditioning control system, which means determining appropriate control parameters according to the optimized energy consumption state to achieve the goal of optimizing energy consumption. According to the reverse matching results, corresponding air-conditioning control parameters are generated for each air-conditioning control system. These parameters include temperature setting value, wind speed control, humidity adjustment and other parameters to ensure that the air-conditioning system can be adjusted according to the optimized energy consumption state. The generated air-conditioning control parameters are applied to the corresponding air-conditioning control system for coordinated control, including setting the parameters to the corresponding air-conditioning equipment so that they can be adjusted according to the optimized energy consumption state to achieve overall energy consumption reduction and improved energy utilization efficiency.
[0027] Furthermore, according to the regional layout information of the target industrial zone, Q air conditioning energy consumption zones are obtained, including:
[0028] Acquiring regional attribute information according to the regional layout information;
[0029] Divide the target industrial zone into regions based on the regional attribute information to obtain multiple functional zones;
[0030] Performing regional characteristic analysis on the multiple functional zones, performing air conditioning energy consumption demand assessment based on the regional characteristic analysis results, and obtaining air conditioning energy consumption demand assessment results;
[0031] Based on the regional characteristic analysis result and the air-conditioning energy consumption demand assessment result, the multiple functional partitions are adjusted to obtain the Q air-conditioning energy consumption areas, wherein each air-conditioning energy consumption area has similar energy consumption characteristics and demand patterns.
[0032] Obtain regional layout information of the target industrial zone, such as building structure, equipment distribution, personnel flow, etc. This information can be obtained through floor plans, architectural drawings, etc., organize the collected information, and extract attribute information of each area, such as area size, purpose, personnel density, equipment type, etc.
[0033] Based on the acquired regional attribute information, the target industrial area is divided into multiple functional zones. The principle of division can be based on the functions, energy consumption characteristics, demand patterns and other factors of different regions. The divided functional zones include production areas, office areas, storage areas, equipment operation areas, etc. Each functional zone has relatively unique energy consumption attributes, so that subsequent energy consumption optimization work can be more targeted and effective.
[0034] Conduct characteristic analysis on each functional zone, including but not limited to area size, personnel density, equipment types and quantity, working environment requirements, etc., and analyze the usage and working mode of each functional zone, such as whether there is continuous production, whether there are peak periods, frequency of personnel activities, etc.
[0035] According to the results of regional characteristic analysis, the air-conditioning energy consumption demand of each functional zone is evaluated. Specifically, according to the characteristics of each functional zone, that is, the demand characteristics of different functional zones, the demand degree for the air-conditioning system is evaluated, including the requirements for temperature, humidity, ventilation, etc. Based on the air-conditioning energy consumption demand evaluation of each functional zone, the air-conditioning energy consumption demand evaluation results are obtained. These results reflect the energy consumption demand degree and specific requirements of each functional zone for the air-conditioning system.
[0036] Combining the regional characteristic analysis results and the air-conditioning energy consumption demand assessment results, the characteristics and energy consumption requirements of each functional zone can be determined, including temperature requirements, humidity requirements, personnel activity density, equipment operation conditions, etc. According to the analysis results, the strategy for adjusting the functional zones is determined, including merging similar functional zones to ensure that each adjusted area has similar energy consumption characteristics and demand patterns, and dividing the adjusted functional zones into Q air-conditioning energy consumption zones. This can simplify the subsequent energy consumption optimization work and improve the optimization efficiency.
[0037] Furthermore, cluster analysis is performed on the Q real-time energy consumption data sets to generate P energy consumption data clusters, including:
[0038] Performing data similarity calculation on the Q real-time energy consumption data sets, and matching multiple initial clustering clusters according to the calculation results;
[0039] Obtaining the limit energy consumption value of each initial clustering cluster in the Q real-time energy consumption data sets as the first clustering constraint;
[0040] Obtaining a stable energy consumption value of each initial cluster in the Q real-time energy consumption data sets as a second clustering constraint;
[0041] Based on the first clustering constraint and the second clustering constraint, a clustering search is performed to generate the P energy consumption data clusters.
[0042] The similarity calculation is performed on the data in Q real-time energy consumption data sets. The similarity calculation methods include Euclidean distance, cosine similarity, etc. These methods are used to calculate the similarity between different data points in the data set. According to the results of the similarity calculation, the data points with similar energy consumption characteristics are assigned to the same initial clustering cluster. In this way, multiple initial clustering clusters can be preliminarily determined, and each cluster contains similar data points.
[0043] For each initial clustering cluster, the energy consumption values of all data points in the cluster are obtained from Q real-time energy consumption data sets, and the limit values of these energy consumption values are calculated. The limit energy consumption values include the maximum value, minimum value, or value within a certain percentage range of the energy consumption values in the cluster. The limit energy consumption value of each initial clustering cluster is used as the first clustering constraint. These constraints are used for subsequent clustering analysis to help determine the boundaries of each energy consumption data cluster. The limit energy consumption value of each initial clustering cluster is recorded as the first clustering constraint.
[0044] For each initial clustering cluster, the energy consumption values of all data points in the cluster are obtained from Q real-time energy consumption data sets, and the stable values of these energy consumption values are calculated. The stable energy consumption value can be the average value or standard deviation of the energy consumption value in the cluster. The stable energy consumption value of each initial clustering cluster is used as the second clustering constraint. These constraints help the clustering algorithm to better distinguish different energy consumption data clusters and generate more stable and accurate clustering results. The stable energy consumption value of each initial clustering cluster is recorded as the second clustering constraint.
[0045] Using the first clustering constraint and the second clustering constraint, P clustering centers are initialized. These clustering centers are determined based on the extreme energy consumption value and the stable energy consumption value to ensure that each cluster has similar energy consumption characteristics and stability. Using clustering algorithms, such as K-means, hierarchical clustering, etc., according to the clustering center and the first clustering constraint and the second clustering constraint, a cluster search is performed on the real-time energy consumption data set. The algorithm assigns data points to different clustering clusters according to the distance between the data point and the clustering center and the constraint conditions. According to the clustering results, the center point of each clustering cluster is recalculated to ensure that they can better represent the characteristics of the cluster to which they belong. Multiple iterations are performed until the clustering center is stable, and finally P energy consumption data clusters are generated.
[0046] Furthermore, performing cluster search based on the first cluster constraint and the second cluster constraint further includes:
[0047] Obtain historical air conditioning energy consumption data for the target industrial area;
[0048] Based on the historical air conditioning energy consumption data, a distribution probability calculation of the limit energy consumption value and the stable energy consumption value is performed, and a constraint coefficient is generated according to the calculation result;
[0049] A weighted calculation of the first clustering constraint and the second clustering constraint is performed based on the constraint coefficient, and a cluster search is performed according to the weighted calculation result.
[0050] Collect air conditioning energy consumption data of the target industrial area over the past period of time. These data cover energy consumption in different time periods and various functional areas.
[0051] Based on the historical air-conditioning energy consumption data obtained, the probability distribution of the extreme energy consumption value and the stable energy consumption value are calculated respectively. This can be achieved through statistical analysis methods, such as histogram analysis, probability density estimation, etc. Specifically, for the extreme energy consumption value, the probability distribution of the aforementioned extreme energy consumption value in the historical data is calculated, which helps to determine the energy consumption upper limit of each cluster; for the stable energy consumption value, the probability distribution of statistical quantities such as the mean and standard deviation of the historical data is calculated, which helps to determine the energy consumption stability constraint of each cluster.
[0052] According to the calculated distribution probability of the extreme energy consumption value and the stable energy consumption value, the corresponding constraint coefficients are generated. These coefficients are used to adjust the parameters such as cluster center selection and cluster cluster boundary determination in the clustering algorithm to ensure that the generated energy consumption data clusters conform to the distribution characteristics of the historical energy consumption data.
[0053] The constraint coefficients obtained by calculating the distribution probability of historical data are used to perform weighted calculation on the first clustering constraint and the second clustering constraint, that is, the constraint coefficients are normalized so that the constraint coefficients of the first clustering constraint and the second clustering constraint are on the same calculation dimension and the sum is 1. The processed constraint coefficients are used as weights, and then the first clustering constraint and the second clustering constraint are multiplied by their corresponding weights respectively. In this way, the degree of influence of each constraint on the clustering result can be consistent with historical conditions.
[0054] Based on the first clustering constraint and the second clustering constraint obtained by weighted calculation, a clustering algorithm is used to perform clustering search on the real-time energy consumption data set. During the search process, the algorithm assigns data points to different clustering clusters according to the weighted constraints, which can accurately reflect the distribution characteristics of historical energy consumption data.
[0055] Furthermore, the method further comprises:
[0056] Obtain P energy consumption index levels of P energy consumption data optimization nodes;
[0057] Calculating energy consumption indicators for the P energy consumption data clusters to generate energy consumption levels;
[0058] Get the air conditioning control system under the same energy consumption level and establish a connection with the energy consumption data optimization node of the corresponding level.
[0059] Determine the key indicators for evaluating energy consumption, including total energy consumption, energy efficiency ratio, energy consumption volatility, etc., define them according to the actual situation, and formulate corresponding evaluation standards and grade divisions according to each energy consumption indicator. For example, the total energy consumption can be divided into three levels: low, medium, and high, and the energy efficiency ratio can be divided into excellent, good, and general levels. Among them, each energy consumption data optimization node is used to process an energy consumption level, which can improve the efficiency and accuracy of energy consumption processing.
[0060] For each energy consumption data cluster, statistical analysis is performed on the data based on the energy consumption of its internal data points, including calculation of total energy consumption, average energy consumption value, energy efficiency ratio, etc. According to the calculated energy consumption index value, the data cluster is divided into corresponding energy consumption levels.
[0061] According to the calculated energy consumption level information, the air-conditioning control system corresponding to the selected energy consumption level is identified from multiple air-conditioning control systems in the industrial zone, and a connection is established between the identified air-conditioning control system and the energy consumption data optimization node of the corresponding level. This can be achieved through a network connection, ensuring that the control system can send energy consumption data to the energy consumption data optimization node in real time and can receive information fed back by the energy consumption data optimization node.
[0062] Furthermore, based on the P energy consumption data optimization nodes, the P energy consumption data clusters are optimized in parallel to generate P optimized energy consumption states, including:
[0063] Acquire production environment demand information of the first energy consumption zone, wherein the production environment demand information includes a required temperature range, a required humidity range and a production time period;
[0064] Generate a first constraint space based on the required temperature range and the required humidity range, and generate a second constraint space based on the production period;
[0065] With the optimization goal of reducing energy consumption and energy waste, a search is performed in the first constraint space and the second constraint space, and the obtained optimal energy consumption state parameters are used as the first optimized energy consumption state.
[0066] Obtain the production environment demand information of the first energy consumption zone, including the required temperature range, required humidity range and production time period. Specifically, according to the production process requirements, determine the temperature demand range of the production environment of the first energy consumption zone, including the minimum and maximum temperatures required in the production process; similarly, according to the production process requirements, determine the humidity demand range of the production environment of the first energy consumption zone; according to the factory's operation schedule or production plan, determine the production time period of the first energy consumption zone, that is, the time range when production activities usually occur.
[0067] According to the required temperature range and the required humidity range, the range of the first constraint space is determined. Exemplarily, the required temperature range and the required humidity range are converted into a two-dimensional space, for example, with temperature as one axis and humidity as another axis to form an area, thereby generating the first constraint space.
[0068] According to the production period, the scope of the second constraint space is determined, which can be a subset of the time range of the production period, or a specific time period of the production period. The production period is usually a continuous time period, so the second constraint space can be a time interval. By generating the first constraint space and the second constraint space, constraint conditions are provided for the subsequent optimization process, that is, the subsequent optimization process is carried out within the constraint space to prevent parameters that do not meet production requirements.
[0069] Setting optimization goals includes reducing energy consumption and reducing energy waste. This means that during the search process, it is necessary to find ways to minimize energy consumption and reduce energy waste while meeting the needs of the production environment.
[0070] A search is performed within the first constraint space and the second constraint space to find state parameters that can minimize energy consumption and reduce energy waste. This can be achieved by using an optimization algorithm, such as a genetic algorithm, a simulated annealing algorithm, a particle swarm algorithm, etc., to evaluate each searched state parameter, calculate its corresponding energy consumption value and energy utilization efficiency, and select the optimal state parameter that can minimize the energy consumption value and reduce energy waste according to the set optimization goal. The obtained optimal energy consumption state parameter is used as the first optimized energy consumption state, that is, the state of minimizing energy consumption and reducing energy waste can be achieved within the production environment requirements of the first energy consumption zone.
[0071] Furthermore, searching and optimizing in the first constraint space and the second constraint space includes:
[0072] Randomly generate a plurality of first energy consumption state parameters in the first constraint space and the second constraint space, and perform energy consumption simulation;
[0073] Use the fitness evaluation function to perform fitness evaluation on the energy consumption simulation result to obtain multiple first fitnesses;
[0074] Compare multiple first fitness values, and retain the first energy consumption state parameter with a larger fitness as the current optimal energy consumption state parameter;
[0075] According to the multiple first fitnesses, a first iteration step length is calculated, and based on the first iteration step length, the multiple first energy consumption state parameters are updated and iterated to obtain multiple second energy consumption state parameters;
[0076] Initiate optimal replacement of the current optimal energy consumption state parameter with the multiple second energy consumption state parameters to obtain an updated current optimal energy consumption state parameter, or retain the original current optimal energy consumption state parameter;
[0077] Continue iterative optimization until convergence conditions are reached, and output the current optimal energy consumption state parameters at that time as the optimal energy consumption state parameters.
[0078] In the first constraint space and the second constraint space, a plurality of first energy consumption state parameters are randomly generated. These parameters are random combinations of temperature, humidity and air-conditioning working hours. For each generated parameter combination, energy consumption simulation is performed. This can be achieved by using a model or simulation software to simulate the energy consumption under given production environment conditions. During the simulation process, the working mode, energy consumption characteristics and actual needs of the air-conditioning system are combined to record the energy consumption simulation results of each parameter combination, including energy consumption value, energy utilization efficiency and other information. These simulation results are used for subsequent evaluation and optimization processes.
[0079] A fitness evaluation function is designed to evaluate the fitness of energy consumption simulation results according to their characteristics. The function quantitatively evaluates the simulation results according to the optimization objectives. For example, the fitness is evaluated according to the size of the energy consumption value and the level of energy utilization efficiency. The defined fitness evaluation function is applied to each energy consumption simulation result to calculate its corresponding fitness value to form multiple first fitness values. These fitness values reflect the quality of the simulation results and the degree of matching with the optimization objectives.
[0080] Compare multiple first fitness values and find the one with the largest fitness value. The fitness value represents the quality of the simulation results, so the simulation results with larger fitness values are considered to be better. The first energy consumption state parameter with the largest fitness value is retained and marked as the current optimal energy consumption state parameter. This parameter will be used as the optimal solution for the current search process. In this way, the optimal solution can be continuously updated during the optimization process, gradually moving towards the optimal energy consumption state parameter.
[0081] According to the values of the multiple first fitness values calculated previously, the first iteration step length is calculated. The calculation of the step length is determined according to factors such as the change in the current fitness value and the convergence speed. That is, when the fitness value change rate decreases and the convergence speed slows down, the iteration step length also becomes smaller to find the optimal solution.
[0082] Based on the calculated first iteration step, multiple first energy consumption state parameters are updated and iterated. This can be achieved by increasing or decreasing a certain step size on the original parameter value to obtain an updated parameter value. Based on the updated parameter value, multiple second energy consumption state parameters are obtained. These parameters will be used as initial parameters for the next round of iterations to continue the search and optimization process. In this way, the parameters can be continuously optimized to gradually find the optimal energy consumption state parameters.
[0083] Compare multiple second energy consumption state parameters with the current optimal energy consumption state parameters, compare their fitness values, and find out the parameters with better fitness values. If it is found that the fitness value of a second energy consumption state parameter is better, then this parameter is used as the updated current optimal energy consumption state parameter. Otherwise, the original current optimal energy consumption state parameter is kept unchanged, and the updated current optimal energy consumption state parameter and its fitness value are recorded. In this way, the parameters can be continuously optimized until the optimal energy consumption state parameter is found.
[0084] Define a convergence condition, such as reaching a specified number of iterations, the change in fitness value between the current optimal solution and the previous optimal solution is less than a set threshold, etc., so that it can be determined when to stop the iterative optimization. In each round of iteration, repeat the above optimization steps, update and iterate the current optimal energy consumption state parameters, and continue to optimize until the convergence condition is reached. When the convergence condition is met, output the current optimal energy consumption state parameter as the optimal energy consumption state parameter. This parameter is the optimal solution found after multiple rounds of iterative optimization that can minimize energy consumption and reduce energy waste under the current constraints.
[0085] Furthermore, the coordinated control of the air conditioning control system is performed according to the P air conditioning control parameters, and then, the method further includes:
[0086] Continuously monitoring the energy consumption of the Q air-conditioning energy consumption areas to obtain Q continuous energy consumption monitoring results;
[0087] When any continuous energy consumption monitoring result does not meet the corresponding expected energy consumption, an energy consumption deviation value is generated;
[0088] Compensation adjustment of corresponding air-conditioning control parameters is performed based on the energy consumption deviation value.
[0089] Corresponding energy consumption monitoring equipment is deployed in each air-conditioning energy consumption area to monitor the energy consumption of the area in real time. These data include relevant information such as power consumption and load changes, which are used to evaluate the energy consumption of the air-conditioning system. The Q air-conditioning energy consumption areas are continuously monitored to obtain Q continuous energy consumption monitoring results.
[0090] Set an expected energy consumption value for each air-conditioning energy consumption zone, that is, the expected energy consumption level. This expected energy consumption value can be determined based on actual needs, environmental conditions and energy-saving goals. Compare the monitoring results with the corresponding expected energy consumption values. When the monitoring results do not meet the expected energy consumption, calculate the energy consumption deviation value. The energy consumption deviation can be obtained by calculating the difference between the monitoring results and the expected energy consumption value, reflecting the gap between the actual energy consumption and the expected energy consumption. Based on the calculation results, generate an energy consumption deviation value, which indicates the degree of excess or deficiency of energy consumption for subsequent adjustment and optimization.
[0091] Analyze the generated energy consumption deviation value to determine the cause of the energy consumption deviation, such as improper temperature setting, air conditioning system failure, etc. According to the direction and size of the energy consumption deviation value, adjust the air conditioning control parameters accordingly. For example, if the energy consumption deviation is too high, you can consider adjusting the operating parameters of the air conditioning system to reduce energy consumption; if the energy consumption deviation is too low, you can increase energy consumption accordingly to meet production needs. According to the adjusted air conditioning control parameters, perform corresponding adjustment measures, including adjusting temperature settings, wind speed control, humidity adjustment and other parameters to make the energy consumption approach the expected value. In this way, dynamic adjustment and optimization of the air conditioning system can be achieved, energy consumption can be kept within a reasonable level, and energy utilization efficiency can be improved.
[0092] In summary, the industrial air conditioning energy consumption optimization method provided by the embodiment of the present application has the following technical effects:
[0093] 1. By zoning the target industrial area and collecting and analyzing real-time data for each energy consumption area, the energy consumption of different energy consumption areas can be monitored in real time, thus improving the real-time and accuracy of energy consumption data;
[0094] 2. By using multiple energy consumption data optimization nodes for parallel optimization processing, multiple energy consumption data clusters can be processed simultaneously, which improves the optimization efficiency of energy consumption data, speeds up the optimization process, and thus reduces the cost of energy consumption optimization;
[0095] 3. By reverse matching the optimized energy consumption state, the corresponding air-conditioning control parameters are generated, and the coordinated control of the air-conditioning system is realized, which effectively reduces the energy consumption level and improves the energy utilization efficiency, thereby achieving the purpose of energy conservation and emission reduction.
[0096] In summary, the above-mentioned industrial air-conditioning energy consumption optimization method achieves efficient energy consumption optimization and accurate energy consumption control through technologies such as real-time data analysis, parallel optimization processing and coordinated control, thereby improving the energy utilization efficiency and production cost control of the industrial air-conditioning system.
[0097] Embodiment 2
[0098] Based on the same inventive concept as the method for optimizing energy consumption of industrial air conditioners in the aforementioned embodiment, Figure 2 As shown, the present application provides an industrial air conditioning energy consumption optimization system, the system comprising:
[0099] An air conditioning energy consumption zone acquisition module 10, the air conditioning energy consumption zone acquisition module 10 is used to acquire Q air conditioning energy consumption zones according to the regional layout information of the target industrial zone, wherein the Q air conditioning energy consumption zones correspond to Q air conditioning control systems, Q ≥ 2;
[0100] An energy consumption data collection module 20, which is used to deploy a data collection system, is respectively connected to the Q air-conditioning control systems, collects real-time energy consumption data, and obtains Q real-time energy consumption data sets;
[0101] An energy consumption data cluster generation module 30, the energy consumption data cluster generation module 30 is used to perform cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, P ≥ 2;
[0102] A parallel optimization processing module 40, wherein the parallel optimization processing module 40 is used to perform parallel optimization processing on the P energy consumption data clusters based on the P energy consumption data optimization nodes to generate P optimized energy consumption states;
[0103] The coordination control module 50 is used to reversely match the control module of the air-conditioning control system based on the P optimized energy consumption states, generate P air-conditioning control parameters, and coordinate the control of the air-conditioning control system according to the P air-conditioning control parameters.
[0104] Furthermore, the system further comprises:
[0105] A region attribute information acquisition module, the region attribute information acquisition module is used to acquire region attribute information according to the region layout information;
[0106] A region division module, the region division module is used to divide the target industrial zone into regions based on the region attribute information to obtain a plurality of functional regions;
[0107] A demand assessment module, the demand assessment module is used to perform regional characteristic analysis on the multiple functional zones, perform air conditioning energy consumption demand assessment based on the regional characteristic analysis results, and obtain air conditioning energy consumption demand assessment results;
[0108] An energy consumption zone acquisition module is used to adjust the multiple functional partitions based on the regional characteristic analysis results and the air conditioning energy consumption demand assessment results to obtain the Q air conditioning energy consumption zones, wherein each air conditioning energy consumption zone has similar energy consumption characteristics and demand patterns.
[0109] Furthermore, the system further includes an energy consumption data cluster acquisition module to perform the following operation steps:
[0110] Performing data similarity calculation on the Q real-time energy consumption data sets, and matching multiple initial clustering clusters according to the calculation results;
[0111] Obtaining the limit energy consumption value of each initial clustering cluster in the Q real-time energy consumption data sets as the first clustering constraint;
[0112] Obtaining a stable energy consumption value of each initial cluster in the Q real-time energy consumption data sets as a second clustering constraint;
[0113] Based on the first clustering constraint and the second clustering constraint, a clustering search is performed to generate the P energy consumption data clusters.
[0114] Furthermore, the system further includes a cluster search module to perform the following operation steps:
[0115] Obtain historical air conditioning energy consumption data for the target industrial area;
[0116] Based on the historical air conditioning energy consumption data, a distribution probability calculation of the limit energy consumption value and the stable energy consumption value is performed, and a constraint coefficient is generated according to the calculation result;
[0117] A weighted calculation of the first clustering constraint and the second clustering constraint is performed based on the constraint coefficient, and a cluster search is performed according to the weighted calculation result.
[0118] Furthermore, the system further comprises a connection establishment module to perform the following operation steps:
[0119] Obtain P energy consumption index levels of P energy consumption data optimization nodes;
[0120] Calculating energy consumption indicators for the P energy consumption data clusters to generate energy consumption levels;
[0121] Get the air conditioning control system under the same energy consumption level and establish a connection with the energy consumption data optimization node of the corresponding level.
[0122] Furthermore, the system further includes a first optimized energy consumption state acquisition module to perform the following operation steps:
[0123] Acquire production environment demand information of the first energy consumption zone, wherein the production environment demand information includes a required temperature range, a required humidity range and a production time period;
[0124] Generate a first constraint space based on the required temperature range and the required humidity range, and generate a second constraint space based on the production period;
[0125] With the optimization goal of reducing energy consumption and energy waste, a search is performed in the first constraint space and the second constraint space, and the obtained optimal energy consumption state parameters are used as the first optimized energy consumption state.
[0126] Furthermore, the system further includes an optimal energy consumption state parameter acquisition module to perform the following operation steps:
[0127] Randomly generate a plurality of first energy consumption state parameters in the first constraint space and the second constraint space, and perform energy consumption simulation;
[0128] Use the fitness evaluation function to perform fitness evaluation on the energy consumption simulation result to obtain multiple first fitnesses;
[0129] Compare multiple first fitness values, and retain the first energy consumption state parameter with a larger fitness as the current optimal energy consumption state parameter;
[0130] According to the multiple first fitnesses, a first iteration step length is calculated, and based on the first iteration step length, the multiple first energy consumption state parameters are updated and iterated to obtain multiple second energy consumption state parameters;
[0131] Initiate optimal replacement of the current optimal energy consumption state parameter with the multiple second energy consumption state parameters to obtain an updated current optimal energy consumption state parameter, or retain the original current optimal energy consumption state parameter;
[0132] Continue iterative optimization until convergence conditions are reached, and output the current optimal energy consumption state parameters at that time as the optimal energy consumption state parameters.
[0133] Furthermore, the system further includes a compensation adjustment module to perform the following operation steps:
[0134] Continuously monitoring the energy consumption of the Q air-conditioning energy consumption areas to obtain Q continuous energy consumption monitoring results;
[0135] When any continuous energy consumption monitoring result does not meet the corresponding expected energy consumption, an energy consumption deviation value is generated;
[0136] Compensation adjustment of corresponding air-conditioning control parameters is performed based on the energy consumption deviation value.
[0137] Through the above-mentioned detailed description of an industrial air-conditioning energy consumption optimization method in this specification, technical personnel in this field can clearly know an industrial air-conditioning energy consumption optimization system in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0138] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for optimizing energy consumption of industrial air conditioners, characterized in that: The method comprises: According to the regional layout information of the target industrial zone, Q air conditioning energy consumption zones are obtained, wherein the Q air conditioning energy consumption zones correspond to Q air conditioning control systems, Q ≥ 2; Deploy a data acquisition system, connect it to the Q air conditioning control systems respectively, collect real-time energy consumption data, and obtain Q real-time energy consumption data sets; Performing cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, and P≥2; Performing parallel optimization processing on the P energy consumption data clusters based on the P energy consumption data optimization nodes to generate P optimized energy consumption states; Reversely matching the control module of the air-conditioning control system based on the P optimized energy consumption states, generating P air-conditioning control parameters, and performing coordinated control of the air-conditioning control system according to the P air-conditioning control parameters; Perform cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, including: Performing data similarity calculation on the Q real-time energy consumption data sets, and matching multiple initial clustering clusters according to the calculation results; Obtaining the limit energy consumption value of each initial clustering cluster in the Q real-time energy consumption data sets as the first clustering constraint; Obtaining a stable energy consumption value of each initial cluster in the Q real-time energy consumption data sets as a second clustering constraint; Based on the first clustering constraint and the second clustering constraint, a cluster search is performed to generate the P energy consumption data clusters; Based on the P energy consumption data optimization nodes, the P energy consumption data clusters are optimized in parallel to generate P optimized energy consumption states, including: Acquire production environment demand information of the first energy consumption zone, wherein the production environment demand information includes a required temperature range, a required humidity range and a production time period; Generate a first constraint space based on the required temperature range and the required humidity range, and generate a second constraint space based on the production period; With the optimization goal of reducing energy consumption and energy waste, a search is performed in the first constraint space and the second constraint space, and the obtained optimal energy consumption state parameters are used as the first optimized energy consumption state.
2. The method according to claim 1, characterized in that According to the regional layout information of the target industrial zone, Q air conditioning energy consumption zones are obtained, including: Acquiring regional attribute information according to the regional layout information; Divide the target industrial zone into regions based on the regional attribute information to obtain multiple functional zones; Performing regional characteristic analysis on the multiple functional zones, performing air conditioning energy consumption demand assessment based on the regional characteristic analysis results, and obtaining air conditioning energy consumption demand assessment results; Based on the regional characteristic analysis result and the air-conditioning energy consumption demand assessment result, the multiple functional partitions are adjusted to obtain the Q air-conditioning energy consumption areas, wherein each air-conditioning energy consumption area has similar energy consumption characteristics and demand patterns.
3. The method according to claim 1, characterized in that Based on the first clustering constraint and the second clustering constraint, performing clustering search further includes: Obtain historical air conditioning energy consumption data for the target industrial area; Based on the historical air conditioning energy consumption data, a distribution probability calculation of the limit energy consumption value and the stable energy consumption value is performed, and a constraint coefficient is generated according to the calculation result; A weighted calculation of the first clustering constraint and the second clustering constraint is performed based on the constraint coefficient, and a cluster search is performed according to the weighted calculation result.
4. The method according to claim 1, characterized in that Also includes: Obtain P energy consumption index levels of P energy consumption data optimization nodes; Calculating energy consumption indicators for the P energy consumption data clusters to generate energy consumption levels; Get the air conditioning control system under the same energy consumption level and establish a connection with the energy consumption data optimization node of the corresponding level.
5. The method according to claim 1, characterized in that Searching and optimizing in the first constraint space and the second constraint space includes: Randomly generate a plurality of first energy consumption state parameters in the first constraint space and the second constraint space, and perform energy consumption simulation; Use the fitness evaluation function to perform fitness evaluation on the energy consumption simulation result to obtain multiple first fitnesses; Compare multiple first fitness values, and retain the first energy consumption state parameter with a larger fitness as the current optimal energy consumption state parameter; According to the multiple first fitnesses, a first iteration step length is calculated, and based on the first iteration step length, the multiple first energy consumption state parameters are updated and iterated to obtain multiple second energy consumption state parameters; Initiate optimal replacement of the current optimal energy consumption state parameter with the multiple second energy consumption state parameters to obtain an updated current optimal energy consumption state parameter, or retain the original current optimal energy consumption state parameter; Continue iterative optimization until convergence conditions are reached, and output the current optimal energy consumption state parameters at that time as the optimal energy consumption state parameters.
6. The method according to claim 1, characterized in that The air conditioning control system is coordinated and controlled according to the P air conditioning control parameters, and then, the method further includes: Continuously monitoring the energy consumption of the Q air-conditioning energy consumption areas to obtain Q continuous energy consumption monitoring results; When any continuous energy consumption monitoring result does not meet the corresponding expected energy consumption, an energy consumption deviation value is generated; Compensation adjustment of corresponding air-conditioning control parameters is performed based on the energy consumption deviation value.
7. An industrial air conditioning energy consumption optimization system, characterized in that: A method for optimizing energy consumption of industrial air conditioners according to any one of claims 1 to 6, comprising: According to the regional layout information of the target industrial zone, Q air conditioning energy consumption zones are obtained, wherein the Q air conditioning energy consumption zones correspond to Q air conditioning control systems, Q ≥ 2; Deploy a data acquisition system, connect it to the Q air conditioning control systems respectively, collect real-time energy consumption data, and obtain Q real-time energy consumption data sets; Performing cluster analysis on the Q real-time energy consumption data sets to generate P energy consumption data clusters, wherein the P energy consumption data clusters correspond to P energy consumption data optimization nodes, and P≥2; Performing parallel optimization processing on the P energy consumption data clusters based on the P energy consumption data optimization nodes to generate P optimized energy consumption states; Based on the P optimized energy consumption states, a control module of the air-conditioning control system is reversely matched to generate P air-conditioning control parameters, and the air-conditioning control system is coordinated and controlled according to the P air-conditioning control parameters.
8. An industrial air conditioning energy consumption optimization system as claimed in claim 7, characterized in that: The system comprises: A region attribute information acquisition module, the region attribute information acquisition module is used to acquire region attribute information according to the region layout information; A region division module, the region division module is used to divide the target industrial zone into regions based on the region attribute information to obtain a plurality of functional regions; A demand assessment module, the demand assessment module is used to perform regional characteristic analysis on the multiple functional zones, perform air conditioning energy consumption demand assessment based on the regional characteristic analysis results, and obtain air conditioning energy consumption demand assessment results; An energy consumption zone acquisition module is used to adjust the multiple functional partitions based on the regional characteristic analysis results and the air conditioning energy consumption demand assessment results to obtain the Q air conditioning energy consumption zones, wherein each air conditioning energy consumption zone has similar energy consumption characteristics and demand patterns.
Citation Information
Patent Citations
Building energy consumption prediction method and system based on multiple linear regression and clustering analysis
CN117043794A
Multi-source data processing method and system used for industrial air conditioner compartment control
CN117232110A
Method for automatically dividing hot areas of air conditioning system based on clustering
CN117709606A
Method and system for adjusting and optimizing energy consumption of cutting equipment
CN118153430A
Air conditioner energy consumption prediction method and system based on multi-prediction-model error compensation
CN118536380A
