Air conditioning system optimization control method and device based on load point table and genetic algorithm
By combining load point table and genetic algorithms, the central air conditioning system parameters are optimized in real time, and the problems of waste of energy and poor real-time performance of traditional air conditioning systems are solved, achieving efficient adaptive optimization control.
Patent Information
- Application Number
- CN202411277669.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-12
AI Technical Summary
Traditional air conditioning systems are based on load peaks when designed, resulting in waste of energy during actual operation. The existing energy-saving optimization methods require a large amount of sample data and complex calculations, which have poor real-time performance and are difficult to achieve adaptive optimization.
Using a method based on load point table and genetic algorithm, the central air conditioning system model is constructed, the initial load point table is generated, the optimization parameters are solved using the genetic algorithm, and the load point table is updated to adjust the system parameters in real time to improve the adaptive optimization performance.
Realize high-accuracy modeling and real-time optimization control of central air-conditioning systems, improve adaptive optimization performance and real-time performance of optimization solutions, avoid local optimal solutions, find global optimal or approximate optimal solutions, and balance energy saving and User experience.
Smart Images

Figure CN118935681A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of central air-conditioning control, and in particular to an air-conditioning system optimization control method and device based on a load point table and a genetic algorithm. Background Art
[0002] With the growth of people's demand for environmental comfort and the development of social and economic levels, people's requirements for indoor environment are getting higher and higher. As the main equipment for effectively regulating the temperature and humidity in buildings, central air-conditioning systems play an important role in people's daily lives and are inseparable from people's lives. In my country, the energy consumption of central air-conditioning systems accounts for more than 40% of the total energy consumption in the construction industry. For traditional air-conditioning systems, the design of air-conditioning systems is usually based on the load peak, and the various operating parameters of the air-conditioning system are set to the values under full-load operation. However, in actual operation, full-load operation rarely occurs, resulting in a large amount of unnecessary energy waste.
[0003] A Chinese patent with publication number CN110805997A discloses a method for energy-saving control of a central air-conditioning system, the method comprising the following steps: obtaining equipment operation data and building load data of the air-conditioning system; performing data preprocessing on the data; learning the preprocessed data through a neural network to obtain a system energy efficiency model; optimizing the operating state optimization parameters through a genetic algorithm based on the system energy efficiency model; optimizing the operation of the air-conditioning system based on the operating state optimization parameters. However, the optimization method provided by the above application usually requires a large amount of sample data for research and modeling, and the optimal solution usually requires extremely complex calculations. At the same time, these methods for energy-saving optimization control usually have poor real-time performance and take a long time to search for the optimal solution. Therefore, it is very necessary to provide an air-conditioning system optimization control method and device based on a load point table and a genetic algorithm to improve the adaptive optimization performance of the central air-conditioning system. Summary of the invention
[0004] In view of this, the present invention proposes an air conditioning system optimization control method and device based on a load point table and a genetic algorithm. By combining the load point table and the genetic algorithm, the initial load point table is used to give relevant parameters as the range of the genetic algorithm to solve the individual, and then the genetic algorithm is used to solve the optimization parameters, and the load point table is further updated to improve the adaptive optimization performance of the central air conditioning system.
[0005] The present invention provides an air conditioning system optimization control method based on a load point table and a genetic algorithm, the method comprising:
[0006] Constructing a central air-conditioning system model, and collecting a historical operation data set in the central air-conditioning system model, wherein the historical operation data set includes system performance indicators, system temperature parameters, and equipment operation parameters;
[0007] Based on the system performance index, the system temperature parameter and the equipment operation parameter, an initial load point table is generated, and a stability threshold and system efficiency corresponding to the total load of all systems are obtained, wherein the system performance index includes the total load of the system under different time series;
[0008] Based on the system total load and the sliding window algorithm, a system steady-state interval corresponding to the system total load is obtained, and a steady-state load value in each system steady-state interval is calculated;
[0009] updating the initial load point table according to the steady-state load value, the system efficiency and the optimization constraint condition to obtain an updated load point table;
[0010] The updated load point table and the genetic algorithm are used to optimize the operating parameters of the central air-conditioning system model to obtain the optimized parameters, and the system temperature parameters and equipment operating parameters in the central air-conditioning system are adjusted and corrected according to the optimized parameters.
[0011] On the basis of the above technical scheme, preferably, the system performance indicators include the energy consumption of the cold water circulation system, the energy conversion efficiency of the cold water circulation system and the total system load, the system temperature parameters include the cooling water inlet and outlet temperature difference, the chilled water supply and return temperature difference, the cooling water outlet temperature and the chilled water supply temperature, and the equipment operation parameters include the water pump speed, the number of chillers turned on, the number of cooling pumps turned on, the number of freezing pumps turned on and the number of cooling tower fans turned on.
[0012] On the basis of the above technical solution, preferably, the method of obtaining the system steady-state interval corresponding to the system total load based on the system total load and the sliding window algorithm, and calculating the steady-state load value in each system steady-state interval, specifically includes:
[0013] Setting a sliding window size and moving the sliding window over a time series of the total system load;
[0014] According to the steady-state judgment conditions, determine whether the sliding windows under different time series are steady-state transition intervals;
[0015] A plurality of steady-state transition intervals that continuously meet the steady-state determination condition are integrated into one steady-state interval, an average load value within the steady-state interval is calculated, and the average load value is used as the steady-state load value of the steady-state interval.
[0016] More preferably, based on the system total load and the sliding window algorithm, obtaining the system steady-state interval corresponding to the system total load, and calculating the steady-state load value in each system steady-state interval specifically includes:
[0017] Setting a sliding window size and moving the sliding window over a time series of the total system load;
[0018] According to the steady-state judgment conditions, determine whether the sliding windows under different time series are steady-state transition intervals;
[0019] A plurality of steady-state transition intervals that continuously meet the steady-state determination condition are integrated into one steady-state interval, an average load value within the steady-state interval is calculated, and the average load value is used as the steady-state load value of the steady-state interval.
[0020] More preferably, the updating of the initial load point table according to the steady-state load value, the system efficiency and the optimization constraint condition specifically includes:
[0021] In the steady-state data segment corresponding to the steady-state load value, calculating the steady-state system efficiency corresponding to the steady-state data segment, wherein the system steady-state interval includes a plurality of steady-state data segments;
[0022] Selecting a data point corresponding to the maximum steady-state system efficiency, and subtracting the steady-state load value corresponding to the data point from the steady-state load value of the operating point in the initial load point table to obtain a steady-state load difference;
[0023] Determining whether the steady-state load difference is less than or equal to a preset load difference;
[0024] If the steady-state load difference is less than or equal to the preset load difference, the data point is selected to replace the operating point corresponding to the steady-state load value.
[0025] More preferably, the method further comprises:
[0026] If the steady-state load difference is greater than the preset load difference, the data point is directly stored in the initial load point table.
[0027] More preferably, the optimizing process of the operating parameters of the central air conditioning system model by using the updated load point table and the genetic algorithm to obtain the optimized parameters specifically includes:
[0028] Initializing the original parameters input into the genetic algorithm, wherein the original parameters include gene encoding mode, population size, number of iterations, energy consumption and thermal comfort index;
[0029] Determining the fitness function of the genetic algorithm according to the energy consumption and the thermal comfort index, and using the fitness function to evaluate each individual in the population, and sorting the individuals in the population according to fitness;
[0030] Performing a crossover operation on random individuals in the population to generate offspring individuals, and performing a mutation operation on each offspring individual to generate a new genome to merge and update the population;
[0031] If the number of iterations of the genetic algorithm reaches a preset number of iterations, the iteration process of the genetic algorithm is terminated, the individual with the highest fitness in the last generation population is selected as the optimal solution, and the optimization parameters are obtained through decoding.
[0032] In a second aspect of the present application, an air conditioning system optimization control device based on a load point table and a genetic algorithm is provided, wherein the air conditioning system optimization control device comprises a data acquisition module, a load update module and a parameter optimization module, wherein:
[0033] The data acquisition module is used to build a central air-conditioning system model and collect historical operation data sets in the central air-conditioning system model, wherein the historical operation data sets include system performance indicators, system temperature parameters, and equipment operation parameters;
[0034] The load update module is used to generate an initial load point table based on the system performance index, the system temperature parameter and the equipment operation parameter, and obtain the stability judgment threshold and system efficiency corresponding to all system total loads, wherein the system performance index includes the system total load under different time series; based on the system total load and the sliding window algorithm, obtain the system steady-state interval corresponding to the system total load, and calculate the steady-state load value in each system steady-state interval; according to the steady-state load value, the system efficiency and the optimization constraint condition, update the initial load point table to obtain an updated load point table;
[0035] The parameter optimization module is used to optimize the operating parameters of the central air-conditioning system model using the updated load point table and the genetic algorithm to obtain optimized parameters, and to adjust and correct the system temperature parameters and equipment operating parameters in the central air-conditioning system according to the optimized parameters.
[0036] In a third aspect of the present application, an electronic device is provided, comprising a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.
[0037] In a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of an air-conditioning system optimization control method based on a load point table and a genetic algorithm.
[0038] The air conditioning system optimization control method based on load point table and genetic algorithm provided by the present invention has the following beneficial effects compared with the prior art:
[0039] (1) By using digital twin technology to build a central air-conditioning system model, the central air-conditioning system of a large building was modeled and simulated, and a highly accurate and high-precision model was established. At the same time, the load point table and the genetic algorithm were combined. Based on the initial load point table of the historical operation data set, the initial load point table was used to give the relevant parameters as the range of the genetic algorithm to solve the individual. The genetic algorithm was then used to solve the optimization parameters, and the load point table was further updated to control the central air-conditioning system in real time, so as to improve the adaptive optimization performance of the central air-conditioning system, the real-time performance of the optimization scheme, and the convergence speed;
[0040] (2) By initializing the original parameters and customizing the fitness function, the specific air-conditioning system is accurately modeled and optimized to achieve the best balance between energy saving and user experience. The combination of sorting selection, crossover and mutation operations greatly improves the algorithm's ability to explore the solution space. It can not only quickly converge to a high-quality solution, but also effectively avoid falling into the local optimum, thereby finding the global optimal or approximate optimal solution in a complex parameter space. By setting a preset number of iterations and a mechanism for selecting the optimal individual, the consumption of computing resources is controlled while ensuring the optimization quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present invention 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, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0042] Figure 1 A schematic diagram of the steps of an air conditioning system optimization control method based on a load point table and a genetic algorithm provided by the present invention;
[0043] Figure 2 A schematic diagram of the structure of the air conditioning system optimization control device provided by the present invention;
[0044] Figure 3 This is a schematic structural diagram of an electronic device provided by the present invention.
[0045] Explanation of the accompanying drawings: 1. Air conditioning system optimization control device; 11. Data acquisition module; 12. Load update module; 13. Parameter optimization module; 2. Electronic device; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. DETAILED DESCRIPTION
[0046] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0047] Before introducing the embodiments of the present invention, some terms and their abbreviations involved in the embodiments of the present invention are first defined and explained.
[0048] Simstore simulation software is a simulation platform developed based on FORTRAN language. It is a design system that integrates the original components such as heat and power in classic industrial systems. Simstore software comes with a typical component library, which is used in the same way as most simulation systems. And the software can realize data interaction between the simulation platform and the control platform through the OPC protocol. This protocol is a standard widely used in the automation industry. It provides a safe and interoperable data exchange method, while improving the speed and accuracy of data transmission. The software mainly consists of three parts: PowerBuilder, CtrlBuilder and gView. The PowerBuilder part is used by users to develop multi-component thermal system simulation. It can quickly and stably solve the pressure and flow of the thermal system by combining the mass, momentum and gas pressure equations in a matrix to meet the accuracy requirements of the process industry system simulation model. CtrlBuilder can simulate and model the analog and digital control in the simulation process, including basic control algorithm modules and control adjustment functions, and the model development is simple and convenient. gView is a screen configuration software developed for monitoring and simulation fields to realize data visualization of the simulation system. Simstore simulation software focuses on simulating and optimizing HVAC systems in buildings. It provides a powerful and comprehensive set of tools to optimize the design, operation and management of HVAC systems through advanced simulation technology.
[0049] The present invention discloses an air conditioning system optimization control method based on a load point table and a genetic algorithm, referring to Figure 1 The method includes steps S1 to S5.
[0050] Step S1, constructing a central air-conditioning system model, and collecting a historical operation data set in the central air-conditioning system model, the historical operation data set including system performance indicators, system temperature parameters, and equipment operation parameters.
[0051] In this step, the Simstore simulation platform is used to establish a digital twin model based on the actual structure of a large building and the composition of the central air-conditioning system. First, the energy consumption mathematical model of the chiller, cooling water pump and refrigeration water pump is fitted by the operation data obtained from the actual building; according to the energy consumption mathematical model of each device, the cooling water loop, refrigeration water loop and chiller loop of the air-conditioning water system are built based on the Simstore software; then, the simulated energy consumption is compared with the measured energy consumption. If the average error rate of the energy consumption of each device is within 10%, the air-conditioning water system experimental platform can be used as a simulation platform for energy-saving optimization experiments, that is, the central air-conditioning system model.
[0052] In this embodiment, the system performance indicators include the energy consumption of the cold water circulation system, the energy conversion efficiency of the cold water circulation system and the total system load. The system temperature parameters include the cooling water inlet and outlet temperature difference, the chilled water supply and return temperature difference, the cooling water outlet temperature and the chilled water supply temperature. The equipment operation parameters include the water pump speed, the number of chillers turned on, the number of cooling pumps turned on, the number of freezing pumps turned on and the number of cooling tower fans turned on.
[0053] Step S2, based on system performance indicators, system temperature parameters and equipment operating parameters, generate an initial load point table, and obtain the stability threshold and system efficiency corresponding to the total load of all systems. The system performance indicators include the total load of the system under different time series.
[0054] In one example, the collected historical operation data is sorted by time series. The data is divided into three categories: system performance indicators, system temperature parameters, and equipment operation parameters. The system performance indicators include load value points and optimal system efficiency. The system temperature parameters include the cooling water inlet and outlet temperature difference, the chilled water supply and return temperature difference, the cooling water outlet temperature, the chilled water supply temperature, and the wet bulb temperature. The equipment operation parameters include the number of chillers turned on, the number of cooling pumps turned on, the number of chiller pumps turned on, and the number of cooling tower fans turned on.
[0055] Divide the total load range of the system into several intervals, for example, according to 10% or 20% load rate. Perform cluster analysis on the data in each load interval, and use algorithms such as K-means or hierarchical clustering to find the typical operating state under similar load conditions. Select the most representative point in each cluster as the load point. The representativeness can be judged based on the distance to the cluster center or other correlation indicators. For each selected load point, extract the corresponding system temperature parameters and equipment operation parameters.
[0056] Step S3, based on the total system load and the sliding window algorithm, obtain the system steady-state interval corresponding to the total system load, and calculate the steady-state load value in each system steady-state interval.
[0057] This step also includes steps S31 to S33.
[0058] Step S31, setting the sliding window size, and moving the sliding window on the time series of the total system load.
[0059] In this step, according to the changing characteristics of the total system load (speed of change and periodicity) and the response time and stabilization time of the system, select a suitable time span as the sliding window size, such as 30 minutes, 1 hour or 2 hours. Ensure that the total system load data is arranged in chronological order, check whether the time interval of the data is consistent, and if not, perform interpolation. Place the sliding window at the starting position of the time series, and the number of data points contained in the sliding window is equal to the window size divided by the data collection interval. Define the sliding step size, usually the time interval of one data point, and move the window from the beginning of the time series according to the defined step size. For each sliding window position, extract the total system load data within the sliding window, and stop sliding when the sliding window reaches the end of the time series.
[0060] Step S32: judging whether the sliding windows under different time series are steady-state transition intervals according to the steady-state judgment condition.
[0061] In this embodiment, the steady-state judgment conditions specifically include: obtaining the change in the chilled water supply temperature and the change in the cooling water return temperature for each adjustment cycle in the historical operation data set; judging whether the change in the chilled water supply temperature and the change in the cooling water return temperature are less than the temperature change threshold for 10 consecutive adjustment cycles; if the change in the chilled water supply temperature and the change in the cooling water return temperature are less than the temperature change threshold for 10 consecutive adjustment cycles, determining that the sliding window is a steady-state transition interval.
[0062] Step S33, integrating multiple steady-state transition intervals that continuously meet the steady-state determination condition into one steady-state interval, calculating the average load value in the steady-state interval, and using the average load value as the steady-state load value of the steady-state interval.
[0063] In this step, all sliding windows that are determined to be steady-state transition intervals in S32 are traversed, and adjacent steady-state transition intervals are checked. If they are continuous in time, they are marked as a group. For each group of continuous steady-state transition intervals, they are merged into a larger steady-state interval, and the start time and end time of each integrated steady-state interval are recorded. For each integrated steady-state interval, all system total load data within the time range are extracted. The arithmetic average of the system total load data in each steady-state interval is performed: steady-state load value = Σ (all load values in the interval) / number of data points in the interval. The calculated average load value is assigned to the corresponding steady-state interval as the representative steady-state load value of the interval.
[0064] Step S4, updating the initial load point table according to the steady-state load value, system efficiency and optimization constraints to obtain an updated load point table.
[0065] This step also includes steps S41 to S45.
[0066] Step S41, in a steady-state data segment corresponding to a steady-state load value, calculating a steady-state system efficiency corresponding to the steady-state data segment, wherein the system steady-state interval includes a plurality of steady-state data segments.
[0067] In this step, within each system steady-state interval, multiple steady-state data segments are divided according to predefined standards (such as time length, data fluctuation range), and each steady-state data segment should represent the stable operating state of the system under a specific load. For each steady-state data segment, relevant operating parameters are extracted, including but not limited to cooling capacity, input power, chilled water supply and return water temperature, cooling water inlet and outlet water temperature, compressor operating parameters, and water pump and fan operating parameters. If the duration of the steady-state data segments is different, you can consider using time-weighted average to calculate the efficiency. Weighted efficiency = Σ(efficiency of each segment × duration of the segment) / total duration. The system efficiency calculation formula is: COP = cooling capacity / (power consumption of chiller + power consumption of chilled water pump + power consumption of cooling water pump + power consumption of cooling tower fan).
[0068] Step S42, selecting a data point corresponding to the maximum steady-state system efficiency, and subtracting the steady-state load value corresponding to the data point from the steady-state load value of the operating point in the initial load point table to obtain a steady-state load difference.
[0069] In this step, the system efficiency of all steady-state data segments calculated in step S41 is summarized to create a data set containing steady-state load values, system efficiency, and related operating parameters. Traverse the sorted efficiency data to find the data point with the maximum system efficiency value. If there are multiple points with the same maximum efficiency, you can choose a point with a higher load or a longer duration. In the initial load point table, find the operating point closest to the optimal steady-state load value. You can use a binary search or nearest neighbor algorithm to improve the search efficiency.
[0070] Step S43, determining whether the steady-state load difference is less than or equal to a preset load difference.
[0071] Step S44: if the steady-state load difference is less than or equal to the preset load difference, a data point is selected to replace the operating point corresponding to the steady-state load value.
[0072] In this step, the original operating point data is removed and new data point information is inserted at the corresponding position to ensure that the order of the load point table (usually sorted by load value) remains unchanged after insertion.
[0073] Step S45: if the steady-state load difference is greater than the preset load difference, the data point is directly stored in the initial load point table.
[0074] Step S5, optimizing the operating parameters of the central air-conditioning system model by using the updated load point table and the genetic algorithm to obtain the optimized parameters, and adjusting and correcting the system temperature parameters and equipment operating parameters in the central air-conditioning system according to the optimized parameters.
[0075] This step also includes steps S51 to S54.
[0076] Step S51, initializing the original parameters input into the genetic algorithm, wherein the original parameters include gene encoding mode, population size, number of iterations, energy consumption and thermal comfort index.
[0077] In this step, gene encoding can be performed and encoded in the following ways, such as binary encoding, where each gene is represented by 0 or 1; real number encoding, where real numbers are directly used to represent genes; integer encoding: integers are used to represent genes. Determine the chromosome length, that is, the number of genes contained in each individual. For example, for air conditioning systems, genes include parameters such as temperature set points and wind speeds. Determine the number of individuals in the initial population, which is usually between 50 and 200. Set the maximum number of iterations of the algorithm, which is usually between 100 and 1000, and set stop conditions, such as reaching the maximum number of iterations or meeting specific convergence criteria. Select PMV (predicted mean vote count) or PPD (predicted percentage of dissatisfaction) as the thermal comfort assessment model. According to the selected encoding method, randomly generate the initial population to ensure that the initial population covers different areas of the solution space and increases diversity.
[0078] Step S52, determining the fitness function of the genetic algorithm according to the energy consumption and thermal comfort indexes, and using the fitness function to evaluate each individual in the population, and sorting the individuals in the population according to their fitness.
[0079] In this step, the multi-objective fitness function can be expressed as: f(x) = w 1 ×E(x)+w 2 ×C(x)
[0080] Among them, E(x) represents the energy consumption index, C(x) represents the thermal comfort index, and w 1 and w 2 is the weight coefficient used to balance the importance of the two objectives.
[0081] Step S53, performing a crossover operation on random individuals in the population to generate offspring individuals, and performing a mutation operation on each offspring individual to generate a new genome to merge and update the population.
[0082] In one example, the entire population is sorted from high to low according to the fitness values of the individuals in the population, and a selection ratio is set, such as selecting the top 60% of individuals. The top N individuals are selected from the sorted population, where N is the population size multiplied by the selection ratio. These selected individuals will participate in subsequent crossover operations as parents. The selected individuals are randomly paired, a crossover point is randomly selected on the chromosome, and the new individuals generated by the crossover are saved. A smaller mutation probability (such as 0.01) is set, and mutation is performed on each offspring individual, each gene position is traversed, and a random number is generated. If it is less than the mutation probability, the gene is changed. The constructed new population includes the offspring generated by the crossover mutation and the retained elite individuals. If the number of new individuals is insufficient, some individuals can be added from the original population, and the size of the new population is ensured to be consistent with the initial setting.
[0083] Step S54: if the number of iterations of the genetic algorithm reaches the preset number of iterations, the iteration process of the genetic algorithm is terminated, the individual with the highest fitness in the last generation population is selected as the optimal solution, and the optimization parameters are obtained by decoding.
[0084] In one example, according to the load value table, the control parameters are encoded with the range of control parameters given in the load point table to obtain the genotype of the parameters. Different genotypes represent different individuals to generate the first generation population. After the first generation population is generated, the fitness function is designed according to energy consumption and thermal comfort. Each individual calculates its fitness function, and individuals are selected according to the level of fitness to ensure that the genes of individuals with high fitness are more likely to be retained, so as to realize the selection process. Then, the selected parent chromosomes are combined and crossed in pairs to produce offspring individuals. The offspring have a certain probability of gene mutation, and finally a new population is generated through selection, crossover, and mutation. In this way, a population with higher and higher overall fitness is evolved from generation to generation. In the process of selection, the environment is more likely to retain individuals with higher fitness, and the genes on individual chromosomes are more likely to be passed on to offspring, so the offspring population has a high probability of being more adapted to the environment than the parents. After the population is iterated to the specified number of times, the optimal chromosome in the last generation population is decoded and regarded as the optimal solution, thereby obtaining the latest control parameters.
[0085] By adopting digital twin technology to construct a central air-conditioning system model, the central air-conditioning system of a large building was modeled and simulated, and a highly accurate and high-precision model was established. At the same time, the load point table and genetic algorithm were combined. Based on the initial load point table based on the historical operation data set, the relevant parameters in the initial load point table were given as the range of individuals for the genetic algorithm to solve. The genetic algorithm was then used to solve the optimization parameters, and the load point table was further updated to control the central air-conditioning system in real time, so as to improve the adaptive optimization performance of the central air-conditioning system, the real-time performance of the optimization scheme, and the convergence speed.
[0086] Based on the above method, the embodiment of the present application discloses a data processing device combining retention enhancement and mosaic enhancement, referring to Figure 2 The air conditioning system optimization control device 1 includes a data acquisition module 11, a load update module 12 and a parameter optimization module 13, wherein:
[0087] The data acquisition module 11 is used to construct a central air-conditioning system model and collect historical operation data sets in the central air-conditioning system model, where the historical operation data sets include system performance indicators, system temperature parameters, and equipment operation parameters;
[0088] The load update module 12 is used to generate an initial load point table based on system performance indicators, system temperature parameters and equipment operation parameters, and obtain the stability threshold and system efficiency corresponding to the total load of all systems, and the system performance indicators include the total load of the system under different time series; based on the total load of the system and the sliding window algorithm, obtain the system steady-state interval corresponding to the total load of the system, and calculate the steady-state load value in each system steady-state interval; according to the steady-state load value, system efficiency and optimization constraints, update the initial load point table to obtain an updated load point table;
[0089] The parameter optimization module 13 is used to optimize the operating parameters of the central air-conditioning system model by using the updated load point table and the genetic algorithm to obtain the optimized parameters, and to adjust and correct the system temperature parameters and equipment operating parameters in the central air-conditioning system according to the optimized parameters.
[0090] In an example, system performance indicators include the energy consumption of the cold water circulation system, the energy conversion efficiency of the cold water circulation system, and the total system load; system temperature parameters include the cooling water inlet and outlet temperature difference, the chilled water supply and return temperature difference, the cooling water outlet temperature, and the chilled water supply temperature; equipment operating parameters include water pump speed, the number of chillers turned on, the number of cooling pumps turned on, the number of freezing pumps turned on, and the number of cooling tower fans turned on.
[0091] In one example, the load update module 12 is used to set the sliding window size and move the sliding window on the time series of the total system load; according to the steady-state judgment condition, determine whether the sliding window under different time series is a steady-state transition interval; integrate multiple steady-state transition intervals that continuously meet the steady-state judgment condition into a steady-state interval, calculate the average load value in the steady-state interval, and use the average load value as the steady-state load value of the steady-state interval.
[0092] In one example, the steady-state determination condition specifically includes:
[0093] Obtain the change in chilled water supply temperature and cooling water return temperature for each adjustment cycle in the historical operation data set;
[0094] Determine whether the change in the chilled water supply temperature and the change in the cooling water return temperature are less than the temperature change threshold value within 10 consecutive adjustment cycles;
[0095] If the change in the chilled water supply temperature and the change in the cooling water return temperature are both less than the temperature change threshold for 10 consecutive adjustment cycles, the sliding window is determined to be a steady-state transition interval.
[0096] In one example, the load update module 12 is used to calculate the steady-state system efficiency corresponding to the steady-state data segment corresponding to the steady-state load value, wherein the system steady-state interval includes multiple steady-state data segments; select the data point corresponding to the maximum steady-state system efficiency, and subtract the steady-state load value corresponding to the data point from the steady-state load value of the operating point in the initial load point table to obtain a steady-state load difference; determine whether the steady-state load difference is less than or equal to a preset load difference; if the steady-state load difference is less than or equal to the preset load difference, select the data point to replace the operating point corresponding to the steady-state load value.
[0097] In one example, the load updating module 12 is configured to directly store the data point into the initial load point table if the steady-state load difference is greater than a preset load difference.
[0098] In one example, the parameter optimization module 13 is used to initialize the original parameters input into the genetic algorithm, wherein the original parameters include gene encoding mode, population size, number of iterations, energy consumption and thermal comfort index; determine the fitness function of the genetic algorithm according to the energy consumption and thermal comfort index, and use the fitness function to evaluate each individual in the population, and sort the individuals in the population according to the fitness; perform a crossover operation on random individuals in the population in pairs to generate offspring individuals, and perform a mutation operation on each offspring individual to generate a new genome and merge and update the population; if the number of iterations of the genetic algorithm reaches the preset number of iterations, the iterative process of the genetic algorithm is terminated, and the individual with the highest fitness in the last population is selected as the optimal solution, and the optimization parameters are obtained through decoding.
[0099] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 2 may include: at least one processor 21 , at least one network interface 24 , a user interface 23 , a memory 25 , and at least one communication bus 22 .
[0100] The communication bus 22 is used to realize the connection and communication between these components.
[0101] The user interface 23 may include a display screen (Display) and a camera (Camera), and the optional user interface 23 may also include a standard wired interface and a wireless interface.
[0102] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0103] Among them, the processor 21 may include one or more processing cores. The processor 21 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 25, and calling data stored in the memory 25. Optionally, the processor 21 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 21 can integrate one or more combinations of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 21, and it can be implemented separately through a chip.
[0104] Among them, the memory 25 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 25 includes a non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 25 may also be optionally at least one storage device located away from the aforementioned processor 21. As Figure 3 As shown, the memory 25 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of an air conditioning system optimization control method based on a load point table and a genetic algorithm.
[0105] exist Figure 3 In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 21 can be used to call the application program of the air-conditioning system optimization control method based on the load point table and the genetic algorithm stored in the memory 25. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.
[0106] A computer-readable storage medium stores instructions, which, when executed by one or more processors, enable the computer to execute one or more methods in the above-mentioned embodiments.
[0107] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0108] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0110] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0111] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0112] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0113] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any variation, use or adaptive change of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the technical field that are not recorded in the present disclosure.
[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. An air conditioning system optimization control method based on load point table and genetic algorithm, It is characterized in that The method comprises: Constructing a central air-conditioning system model, and collecting a historical operation data set in the central air-conditioning system model, wherein the historical operation data set includes system performance indicators, system temperature parameters, and equipment operation parameters; Based on the system performance index, the system temperature parameter and the equipment operation parameter, an initial load point table is generated, and a stability threshold and system efficiency corresponding to the total load of all systems are obtained, wherein the system performance index includes the total load of the system under different time series; Based on the system total load and the sliding window algorithm, a system steady-state interval corresponding to the system total load is obtained, and a steady-state load value in each system steady-state interval is calculated; updating the initial load point table according to the steady-state load value, the system efficiency and the optimization constraint condition to obtain an updated load point table; The updated load point table and the genetic algorithm are used to optimize the operating parameters of the central air-conditioning system model to obtain the optimized parameters, and the system temperature parameters and equipment operating parameters in the central air-conditioning system are adjusted and corrected according to the optimized parameters.
2. The method according to claim 1, It is characterized in that The system performance indicators include the energy consumption of the cold water circulation system, the energy conversion efficiency of the cold water circulation system and the total system load; the system temperature parameters include the cooling water inlet and outlet temperature difference, the chilled water supply and return temperature difference, the cooling water outlet temperature and the chilled water supply temperature; the equipment operation parameters include the water pump speed, the number of chillers turned on, the number of cooling pumps turned on, the number of freezing pumps turned on and the number of cooling tower fans turned on.
3. The method according to claim 1, It is characterized in that The step of obtaining a system steady-state interval corresponding to the system total load based on the system total load and a sliding window algorithm, and calculating a steady-state load value in each system steady-state interval, specifically includes: Setting a sliding window size and moving the sliding window over a time series of the total system load; According to the steady-state judgment conditions, determine whether the sliding windows under different time series are steady-state transition intervals; A plurality of steady-state transition intervals that continuously meet the steady-state determination condition are integrated into one steady-state interval, an average load value within the steady-state interval is calculated, and the average load value is used as the steady-state load value of the steady-state interval.
4. The method according to claim 3, It is characterized in that The steady-state determination conditions specifically include: Obtain the change in chilled water supply temperature and cooling water return temperature for each adjustment cycle in the historical operation data set; Determine whether the change in the chilled water supply temperature and the change in the cooling water return temperature are both less than the temperature change threshold value within 10 consecutive adjustment cycles; If the chilled water supply temperature change and the cooling water return temperature change are both less than the temperature change threshold for 10 consecutive adjustment cycles, the sliding window is determined to be a steady-state transition interval.
5. The method according to claim 1, It is characterized in that The updating of the initial load point table according to the steady-state load value, the system efficiency and the optimization constraint condition specifically includes: In the steady-state data segment corresponding to the steady-state load value, calculating the steady-state system efficiency corresponding to the steady-state data segment, wherein the system steady-state interval includes a plurality of steady-state data segments; Selecting a data point corresponding to the maximum steady-state system efficiency, and subtracting the steady-state load value corresponding to the data point from the steady-state load value of the operating point in the initial load point table to obtain a steady-state load difference; Determining whether the steady-state load difference is less than or equal to a preset load difference; If the steady-state load difference is less than or equal to the preset load difference, the data point is selected to replace the operating point corresponding to the steady-state load value.
6. The method according to claim 5, It is characterized in that The method further comprises: If the steady-state load difference is greater than the preset load difference, the data point is directly stored in the initial load point table.
7. The method according to claim 1, It is characterized in that The method of optimizing the operating parameters of the central air conditioning system model by using the updated load point table and the genetic algorithm to obtain the optimized parameters specifically includes: Initializing the original parameters input into the genetic algorithm, wherein the original parameters include gene encoding mode, population size, number of iterations, energy consumption and thermal comfort index; Determining the fitness function of the genetic algorithm according to the energy consumption and the thermal comfort index, and using the fitness function to evaluate each individual in the population, and sorting the individuals in the population according to fitness; Performing a crossover operation on random individuals in the population to generate offspring individuals, and performing a mutation operation on each offspring individual to generate a new genome to merge and update the population; If the number of iterations of the genetic algorithm reaches a preset number of iterations, the iteration process of the genetic algorithm is terminated, the individual with the highest fitness in the last generation population is selected as the optimal solution, and the optimization parameters are obtained through decoding.
8. An air conditioning system optimization control device based on load point table and genetic algorithm, It is characterized in that The air conditioning system optimization control device (1) comprises a data acquisition module (11), a load update module (12) and a parameter optimization module (13), wherein: The data acquisition module (11) is used to construct a central air-conditioning system model and collect a historical operation data set in the central air-conditioning system model, wherein the historical operation data set includes system performance indicators, system temperature parameters and equipment operation parameters; The load updating module (12) is used to generate an initial load point table based on the system performance index, the system temperature parameter and the equipment operation parameter, and obtain a stability judgment threshold and a system efficiency corresponding to all system total loads, wherein the system performance index includes the system total load under different time series; based on the system total load and the sliding window algorithm, obtain a system steady-state interval corresponding to the system total load, and calculate a steady-state load value in each system steady-state interval; according to the steady-state load value, the system efficiency and the optimization constraint condition, update the initial load point table to obtain an updated load point table; The parameter optimization module (13) is used to optimize the operating parameters of the central air-conditioning system model using the updated load point table and the genetic algorithm to obtain optimized parameters, and to adjust and correct the system temperature parameters and equipment operating parameters in the central air-conditioning system according to the optimized parameters.
9. An electronic device, It is characterized in that The electronic device (2) comprises a processor (21), a memory (25), a user interface (23) and a network interface (24), wherein the memory (25) is used to store instructions, the user interface (23) and the network interface (24) are used to communicate with other devices, and the processor (21) is used to execute the instructions stored in the memory (25) so that the electronic device (2) executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Adjusting method and device for running parameters of central air conditioner
CN106979583A
Central air conditioner control method and device based on genetic algorithm and load online correction
CN108489013A
Self-adaptive deep learning optimization energy-saving control algorithm for central air-conditioning cold supply system
CN114543273A
System and method for predicting building thermal loads
US20050192915A1
Low-cost commissioning method and system for air conditioning system based on existing large-scale public building
WO2020107851A1
Cited By
Load prediction and optimal distribution-based optimal control method for cold storage central air conditioner
CN119508979A
Data compression method, device and system based on parameter optimization and storage medium
CN119808545A
