CN112415924A - Energy-saving optimization method and system for air conditioning system - Google Patents
Energy-saving optimization method and system for air conditioning system Download PDFInfo
- Publication number
- CN112415924A CN112415924A CN202011189834.3A CN202011189834A CN112415924A CN 112415924 A CN112415924 A CN 112415924A CN 202011189834 A CN202011189834 A CN 202011189834A CN 112415924 A CN112415924 A CN 112415924A
- Authority
- CN
- China
- Prior art keywords
- air conditioner
- energy consumption
- individual
- load prediction
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2638—Airconditioning
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Air Conditioning Control Device (AREA)
Abstract
The invention discloses an energy-saving optimization method of an air conditioning system, which comprises the following steps: acquiring a load prediction model of an air conditioner and a data set required by an energy consumption model of the air conditioner; preprocessing the data set; constructing an air conditioner load prediction model and determining the air conditioner load; constructing an air conditioner energy consumption model according to an air conditioner load prediction result; the method and the device have the advantages that the total energy consumption is the lowest as an objective function of the air conditioner energy consumption model to optimize the equipment parameters, the optimization of the equipment operation parameters is realized by constructing the air conditioner load prediction model and the air conditioner energy consumption model and adopting a differential evolution optimization method, and finally the energy-saving optimization of the air conditioner system is realized.
Description
Technical Field
The invention belongs to the technical field of energy conservation, and particularly relates to an energy-saving optimization method and system for an air conditioning system.
Background
With the continuous acceleration of the urbanization process in China, the number of urban building buildings is increased, and various office buildings, shopping malls, apartments and the like provide comfortable and efficient office and living environments for people. However, the development of the building industry has led to the increasing of building energy consumption, and according to data, the building energy consumption accounts for more than 27% of the total social energy consumption, and some regions are close to 40%, while two thirds of the building energy consumption is the energy consumption of an air conditioning system. At present, China is in an energy transformation stage, a green low-carbon concept is practiced, and the implementation of energy-saving and emission-reduction measures is a necessary trend for promoting green development. How to improve the energy utilization efficiency and reduce the energy consumption of the air conditioner is very important for building energy conservation. Therefore, it is urgently needed to design an energy-saving optimization method for a central air-conditioning system, which is used for constructing an energy consumption model through a big data technology and searching working condition parameters of the air-conditioning system under the lowest energy consumption, so that the energy consumption of the air-conditioning system is continuously reduced, and the energy conservation of a building is realized.
In the existing research, the energy-saving optimization of the air conditioning system is mostly embodied in the research of the optimization control technology of the air conditioning system. With the application of building automation systems, intelligent control technologies and the like, the air conditioning system is dynamically adjusted through the research on data acquisition and control of air conditioning system equipment in the industry. The total energy consumption of most of the air conditioning systems is obtained through mechanism analysis and calculation, and then the equipment operation parameters in the mathematical formula are optimized by using intelligent optimization algorithms such as a genetic ant colony algorithm, a genetic algorithm, an artificial bee colony algorithm and the like, so that the lowest equipment energy consumption operation parameters are obtained. In addition, part of researches are carried out, and the accurately predicted air conditioning load is added in a mechanism analysis formula to serve as a parameter, so that the air conditioning system can be intelligently changed according to the air conditioning load demand.
In the current research, most of the air conditioning energy consumption is calculated by using a mechanism principle, however, the air conditioning system is a nonlinear, dynamic and complex system, the total energy consumption of the system changes along with the change of the environment and seasons, and the system has time-varying property and randomness and is difficult to accurately express by using a mathematical function expression. In the current research, although some researches utilize a prediction algorithm to predict the air conditioner energy consumption, the input characteristics are not fully selected, the influence of other factors such as weather, buildings, personnel density and the like on the air conditioner energy consumption is not considered, and the prediction of the air conditioner load is ignored. And although some researches have been carried out on the prediction of the air conditioner load, the prediction result precision of the method is not high, the problems of overfitting and the like exist, the method is still substituted into a mathematical formula of mechanism analysis finally, and if the load prediction is not accurate enough, the target function of the total energy consumption of the air conditioner is influenced to a great extent.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an energy-saving optimization method for an air conditioning system, which can perform energy-saving optimization on the air conditioning system.
The technical problem to be solved by the invention is realized by the following technical scheme:
in a first aspect, an energy-saving optimization method for an air conditioning system is provided, which includes:
acquiring a data set required by air conditioner load prediction;
preprocessing the data set;
constructing an air conditioner load prediction model and determining the air conditioner load;
constructing an air conditioner energy consumption model according to an air conditioner load prediction result;
and optimizing the equipment parameters by taking the total energy consumption as an objective function of the air conditioner energy consumption model.
With reference to the first aspect, further, the preprocessing the data set includes:
removing missing values in the data set;
performing data transformation on the data set;
carrying out normalization processing on the data set after data transformation;
and performing feature selection on the normalized data set to obtain a first feature set used for being input when an air conditioner load prediction model is established and a second feature set used for being input when an air conditioner energy consumption model is established.
With reference to the first aspect, further, the constructing of the air-conditioning load prediction model specifically includes:
and taking the first feature set as the input of the LSTM neural network, setting the feature dimension of the neural network as the feature number of the first feature set, setting the number of network layers as 1, and training the LSTM neural network through a torch.
With reference to the first aspect, further, the constructing an air conditioner energy consumption model according to the air conditioner load prediction result specifically includes: and taking the first feature set, the air conditioner load prediction result and the second feature set as the input of a random forest regressor to train the random forest regressor to obtain an air conditioner energy consumption model.
In combination with the first aspect, further, the air-conditioning energy consumption model is initialized by a differential evolution method, the equipment operation parameters to be optimized in the characteristic set need to be input, the initialized parameter values and the characteristic values in the characteristic set except the equipment operation parameters are used as the input of the air-conditioning energy consumption model to obtain the air-conditioning energy consumption, and then the equipment operation parameters with the lowest air-conditioning energy consumption are obtained by optimizing through the differential evolution method.
With reference to the first aspect, further, the optimizing the device parameter includes: the method comprises the following steps of initializing an air conditioner energy consumption model by a differential evolution method, inputting equipment operation parameters to be optimized in a characteristic set, obtaining air conditioner energy consumption by taking initialized parameter values and characteristic values except the equipment operation parameters in the characteristic set as the input of the air conditioner energy consumption model, and obtaining the equipment operation parameters consumed by the lowest air conditioner energy by optimizing by the differential evolution method, wherein the method specifically comprises the following steps:
initializing a population and solving each candidate solution XiThe corresponding total air conditioner energy consumption is expressed as a fitness value, the individual is subjected to real number coding and substituted into an air conditioner energy consumption model to calculate the fitness value corresponding to each individual;
starting optimization iteration, firstly carrying out mutation, and randomly selecting X to be removed from the population in the g-th iterationi(g) Other 3 individuals Xp1(g),Xp2(g),Xp3(g) P1 ≠ p2 ≠ p3 ≠ i, and the generated mutation vector is Hi(g)＝Xp1(g)+F(Xp2(g)-Xp3(g) F) is a scaling factor, 0.5 is taken;
mixing Xi(g) And variant individual Hi(g) Performing cross operation to obtain cross individual Ui(g) Setting cr by adaptively adjusted crossover probabilitymin＝0.1，crmaxCalculate individual X as 0.6iIs a fitness value fiAnd the average value of the current population fitness
The fitness values of the worst individual and the optimal individual in the current population are respectively fmaxAnd fminThen adapting criThe calculation formula is as follows:
generating individual U with dimension N and null valuei(g)，Ui(g) Has a j-th value of Ui,j(g) Randomly generating a rand (0,1), and mutating the individual H when the random value is less than the cross probabilityi(g) Value of j in the sequence is assigned to Ui(g) Otherwise, will Xi(g) To Ui(g) The formula is as follows:
selecting and operating, if the fitness value of the crossed individuals is smaller than that of the parent individuals, selecting and reserving the crossed individuals, if the crossed individuals are not optimal, not updating the individuals at this time, and selecting new individuals X'i(g) The formula is as follows:
and when the maximum iteration times are met or the minimum energy consumption value is reached, terminating the iteration, and outputting the optimal individual according to the corresponding fitness value, wherein the value of the optimal individual is the optimal operation parameter combination for the operation of the air-conditioning system.
In a second aspect, an energy-saving optimization system for an air conditioning system is provided, which includes:
a data processing module: the system comprises a data set used for acquiring a data set required by air conditioner load prediction;
preprocessing the data set;
a modeling module: the method is used for constructing an air conditioner load prediction model and determining the air conditioner load; constructing an air conditioner energy consumption model according to an air conditioner load prediction result;
an optimizing module: and optimizing the equipment parameters by taking the total energy consumption as an objective function of the air conditioner energy consumption model.
The invention has the beneficial effects that: the invention forms an energy-saving optimization method and system of an air conditioning system by establishing methods of air conditioning load prediction, modeling of an energy consumption model of the air conditioning system and optimization of operation parameters of equipment of the air conditioning system. Predicting the air conditioner load by using an LSTM algorithm, determining the refrigeration demand in advance and improving the accuracy of predicting the air conditioner load; based on a random forest regression algorithm, continuously taking the input characteristics and the prediction result of the air conditioner load prediction model as the input of the air conditioner energy consumption model, and establishing a nonlinear air conditioner energy consumption model; the method utilizes the self-adaptive differential evolution method with global optimization capability and better robustness to dynamically optimize the equipment operation parameters, and solves the problem of local convergence of other optimization algorithms. The method carries out optimization simulation calculation on the air conditioning system on the premise of meeting the requirements, and dynamically searches the equipment operation parameters with the lowest energy and time consumption of the system. The method provides reference for setting the operation parameters of the air conditioner for air conditioner operators such as buildings, hotels, business buildings and the like, can effectively reduce the energy consumption of the air conditioning system, and realizes the energy-saving optimization of the air conditioning system.
Drawings
FIG. 1 is a flow chart of an energy-saving optimization method of an air conditioning system according to the present invention;
FIG. 2 is an input characteristic diagram of an air conditioning load prediction model and an energy consumption model according to the present invention;
FIG. 3 is a flowchart of the present invention for optimizing using a differential evolution algorithm.
Detailed Description
To further describe the technical features and effects of the present invention, the present invention will be further described with reference to the accompanying drawings and detailed description.
Example 1
As shown in fig. 1 to 3, the energy-saving optimization method for an air conditioning system of the present invention includes the following steps:
step one, acquiring a data set
Acquiring historical meteorological data with time characteristics, building parameters, personnel number, air conditioner maintaining temperature, air conditioner load, operation parameters of a refrigerating unit, a cooling water pump, a freezing water pump and a cooling tower fan of an air conditioning system and total air conditioner energy consumption data in a period of time, wherein the specific data are as follows: the meteorological data comprises outdoor temperature, outdoor humidity, air pressure, wind speed, wind direction and illumination intensity; the building parameters comprise the number of building rooms and the indoor area; the equipment operation parameters comprise cold load rate, cooling water supply temperature, cooling water flow, cooling water pump frequency, chilled water supply temperature, chilled water flow, chilled water pump frequency, cooling tower fan air flow, cooling tower fan frequency and water chilling unit power.
Step two, preprocessing the data set
Because the data acquisition of the equipment has various factors such as certain network, acquisition equipment and the like, the acquired data cannot be directly applied to data analysis, and the data needs to be preprocessed, and the method specifically comprises the following steps:
1) firstly, removing missing values in a data set, arranging data of the data set into a data input matrix according to granularity of 24h every 1h every day, adding operation time t, date of the day, air conditioner load of the previous day th, outdoor temperature of t-1h, outdoor humidity of t-1h, illumination intensity of t-1h, air conditioner load of t-2h, total energy consumption of the t-1h air conditioner, total energy consumption of the previous day th air conditioner, cooling water flow of t-1h and cooling water flow of t-1h as columns of the input matrix, and deleting rows with null values.
2) Data conversion is carried out, and the fact that the air conditioning load can be influenced by the personnel density is found by calculating the correlation coefficient of the personnel number, the indoor area and the air conditioning load and calculating the personnel density which is the correlation coefficient of the personnel number/the indoor area and the air conditioning load; data is converted into a numerical value which can be used as input, the time of the day is assigned to be 0-23, the date of the day is converted into whether the date is a holiday, the holiday is assigned to be 0, and the working day is 1.
3) In order to eliminate the dimension relation between the numerical values, the numerical values are normalized by adopting a min-max normalization method and utilizing a formula
Performing calculation, wherein max is the maximum value in the data, min is the minimum value in the data, and xmFor some kind of original value of sample data, xm *For the normalized value of some kind of data of the sample, the result value is finally mapped to [0,1 ]]In the meantime.
4) Since the accuracy of prediction can be improved by using the features closely related to the prediction result as input, and the redundant features easily increase the amount of model calculation, feature selection is required. In order to obtain the input characteristics of an air conditioner load prediction model and an air conditioner energy consumption model, the correlation coefficients of a data set, the air conditioner load and the total air conditioner energy consumption are respectively calculated, the characteristics with low correlation are deleted, finally, the input matrix of the air conditioner load prediction model is a characteristic set 1 (a first characteristic set), and the characteristic set 1 comprises population density, air conditioner maintaining temperature, operation time t, current date, previous day th air conditioner load, t-1h outdoor temperature, t-1h outdoor humidity, t-1h illumination intensity, t-1h air conditioner load and t-2h air conditioner load. Through analysis of a data set and total energy consumption of the air conditioner, an input matrix of a total energy consumption model of the air conditioner simultaneously considers the influence of air conditioner load on the total energy consumption, and a finally obtained energy consumption characteristic set of the air conditioner comprises all characteristics of a characteristic set 1, a prediction result of the air conditioner load and a characteristic set 2 (a second characteristic set), wherein the characteristic set 2 comprises cooling water supply temperature, chilled water supply temperature, cooling water pump frequency, chilled water pump frequency, cooling tower fan frequency, cold load rate, water chilling unit power, total energy consumption of the air conditioner for t-1h, total energy consumption of the air conditioner for the previous day th, cooling water flow for t-1h and cooling water flow for t-1h, and the total input characteristics are shown in a.
Step three, constructing an air conditioner load prediction model based on LSTM
The LSTM algorithm is a circulating neural network in a specific form, a forgetting gate mechanism is added, the long-term memory function is achieved, and the problem that the RNN cannot handle long-distance dependence is solved. The method comprises the steps of using a torch.nn.LSTM interface in a pyrtch machine learning library, setting input characteristic dimensions, namely the number input _ size of a feature set 1 to be 10, setting network layer numbers num _ layers to be 1, carrying out model training by using a torch.optim.Adam optimization algorithm, calculating prediction accuracy under different hidden layer dimension values, selecting a proper hidden layer dimension, finally constructing an air conditioner load prediction model, and determining the air conditioner load at the future t moment.
Step four, establishing an air conditioner energy consumption model based on random forest
The Random Forest (RF) algorithm is a bagging integrated learning algorithm with a decision tree as a base learner, if the Forest integrated by a regression decision tree is called a Random Forest regressor, the Random Forest regression can improve the prediction accuracy and control the occurrence of overfitting, and has strong anti-jamming capability and generalization capability. The method utilizes random forest regression to predict the energy consumption of the air conditioner, utilizes random forest regressor in an integrated algorithm module ensemble in a machine learning library sklern to construct a nonlinear model between the characteristics of equipment operation parameters and the like and the total energy consumption of the air conditioner, takes the energy consumption characteristic set of the air conditioner as model input, sets the number of trees as n _ estimators as 10, and sets the classification standard criterion of each decision tree as 'mse'. And finally, establishing a random forest regression model between the historical data equipment operation parameters and the total air conditioner energy consumption, and calculating to obtain the total air conditioner energy consumption by inputting the values of the current equipment operation parameters.
Step five, optimizing equipment parameters based on self-adaptive DE algorithm
The Differential Evolution Algorithm (DE) is a population-based adaptive global optimization Algorithm, and belongs to an Evolution Algorithm, and includes operations of mutation, intersection and selection, and simulates the process of cooperation and competition of individuals in a population. In the process of each iterative optimization of the DE algorithm, firstly, mutation operation is carried out, one or more individual genes are selected from father individuals as a base, and then differences of different individuals are selected to form differential genes; secondly, adding the gene as the base and the differential gene to obtain a new individual; and finally, calculating the fitness values of the parent individuals and the child individuals, performing selection operation in the parent individuals and the child individuals, comparing the crossed individuals with the parent individuals, and selecting the individuals with the better fitness values to be reserved to the next generation.
The invention utilizes DE algorithm to optimize the running parameters of air-conditioning equipment, determines the running parameters of the equipment needing optimization in the characteristic set of the energy consumption of the air-conditioner (the parameters are in the characteristic set), and other residual characteristic values are the actual values at the moment of t-1, utilizes the DE algorithm to initialize the values of the parameters, takes the initialized parameter values and the residual characteristic values as input, brings the input values into an RF energy consumption model of the air-conditioner to obtain the energy consumption of the air-conditioner, and then continuously optimizes through the DE algorithm to obtain the running parameters of the equipment with the lowest energy consumption of the air-conditioner, and the specific process is shown in figure 3, and the specific:
1) determining the equipment operation parameters to be optimized as cooling water supply temperature, chilled water supply temperature, cooling water pump frequency, chilled water pump frequency and cooling tower fan frequency, obtaining the constraint conditions of equipment operation, namely the maximum and minimum values of the parameters, and setting the optimization range of the parameters. Each individual of the DE algorithm represents a candidate solution of a problem to be solved, the population individual number M is set to be 10, the individual dimensionality N is 5, the maximum iteration number G is 50, and each individual X is set to be 10 according to the number of optimization parameters being 5i＝(xi,1,xi,2,…,xi,N)，i＝1,2,…,M。
2) Initializing the population, each candidate solution XiThe corresponding total energy consumption of the air conditioner is the fitness value fi＝f(Xi). And carrying out real number coding on the individuals, and substituting the individuals into the RF air-conditioning energy consumption model to calculate the fitness value corresponding to each individual.
3) The optimization iteration begins with the mutation first. In the G-th iteration, G is 1,2, …, and X is randomly selected from the populationi(g) Other 3 individuals Xp1(g),Xp2(g),Xp3(g) P1 ≠ p2 ≠ p3 ≠ i, and the generated mutation vector is Hi(g)＝Xp1(g)+F(Xp2(g)-Xp3(g) Where F is the scaling factor, 0.5 is taken.
4) Mixing Xi(g) And variant individual Hi(g) Performing cross operation to obtain cross individual Ui(g) In that respect The invention adopts the self-adaptive adjustment of the cross probability to set crmin＝0.1，crmaxCalculate individual X as 0.6iIs a fitness value fiAnd the average value of the current population fitness
The fitness values of the worst individual and the optimal individual in the current population are respectively fmaxAnd fmin. Then the cr is adaptediThe calculation formula is as follows:
generating individual U with dimension N and null valuei(g)，Ui(g) Has a j-th value of Ui,j(g) Randomly generating a rand (0,1), and mutating the individual H when the random value is less than the cross probabilityi(g) Value of j in the sequence is assigned to Ui(g) Otherwise, will Xi(g) To Ui(g) In that respect The formula is as follows:
5) and selecting and operating, if the fitness value of the crossed individuals is smaller than that of the parent individuals, selecting and reserving the crossed individuals, and if the crossed individuals are not optimal, not updating the individuals at this time. Selected novel individuals Xi' (g) the formula is as follows:
6) and when the maximum iteration times are met or the minimum energy consumption value is reached, terminating the iteration, and outputting the optimal individual according to the corresponding fitness value, wherein the value of the optimal individual is the optimal operation parameter combination for the operation of the air-conditioning system.
And step six, forming an air conditioning system optimization control strategy.
And calculating the running values of the cooling water supply temperature, the chilled water supply temperature, the cooling water pump frequency, the chilled water pump frequency and the cooling tower fan frequency when the total energy consumption of the air conditioning system is the lowest, and combining the actual operation condition to form an air conditioning system optimization control strategy in the modes of frequency conversion, water temperature variation, flow variation, unit start-stop and the like.
Example 2
The invention also provides an energy-saving optimization system of the air conditioning system, which comprises the following components:
a data processing module: the system comprises a data set used for acquiring a data set required by air conditioner load prediction;
preprocessing the data set;
a modeling module: the method is used for constructing an air conditioner load prediction model and determining the air conditioner load; constructing an air conditioner energy consumption model according to an air conditioner load prediction result;
an optimizing module: and optimizing the equipment parameters by taking the total energy consumption as an objective function of the air conditioner energy consumption model.
The invention solves the problems of air conditioner load prediction, modeling of an air conditioner system energy consumption model and optimization control of air conditioner system equipment operation parameters, and provides an energy-saving optimization method and system for an air conditioner system on the premise that the air conditioner system can intelligently collect data and a water pump and a water tower are provided with or additionally provided with a variable frequency control system. And meanwhile, optimizing the equipment parameters by using a self-adaptive differential evolution method with global optimization capability, and finally forming a set of intelligent analysis and decision-making air conditioning system optimization control method to realize energy-saving optimization of the air conditioning system.
The above embodiments do not limit the present invention in any way, and all technical solutions obtained by taking equivalent substitutions or equivalent changes fall within the scope of the present invention.
Claims (6)
1. An energy-saving optimization method for an air conditioning system is characterized by comprising the following steps:
acquiring a data set required by an air conditioner load prediction model and an air conditioner energy consumption prediction model;
preprocessing the data set;
constructing an air conditioner load prediction model and determining the air conditioner load;
constructing an air conditioner energy consumption model according to an air conditioner load prediction result;
and optimizing the equipment parameters by taking the total energy consumption as an objective function of the air conditioner energy consumption model.
2. The energy-saving optimization method of the air conditioning system according to claim 1, characterized in that: the preprocessing the data set comprises:
removing missing values in the data set;
performing data transformation on the data set;
carrying out normalization processing on the data set after data transformation;
and performing feature selection on the normalized data set to obtain a first feature set used for being input when an air conditioner load prediction model is established and a second feature set used for being input when an air conditioner energy consumption model is established.
3. The energy-saving optimization method of the air conditioning system according to claim 2, characterized in that: the method for constructing the air conditioner load prediction model specifically comprises the following steps:
and taking the first feature set as the input of the LSTM neural network, setting the feature dimension of the neural network as the feature number of the first feature set, setting the number of network layers as 1, and training the LSTM neural network through a torch.
4. The energy-saving optimization method of the air conditioning system according to claim 3, characterized in that: the method for constructing the air conditioner energy consumption model according to the air conditioner load prediction result specifically comprises the following steps: and taking the first feature set, the air conditioner load prediction result and the second feature set as the input of a random forest regressor to train the random forest regressor to obtain an air conditioner energy consumption model.
5. The energy-saving optimization method of the air conditioning system according to claim 1, characterized in that: the optimizing of the device parameters comprises: initializing an air conditioner energy consumption model by a differential evolution method, wherein the equipment operation parameters to be optimized in a characteristic set need to be input, obtaining the air conditioner energy consumption by taking initialized parameter values and characteristic values except the equipment operation parameters in the characteristic set as the input of the air conditioner energy consumption model, and then optimizing by the differential evolution method to obtain the equipment operation parameters consuming the lowest air conditioner energy, specifically:
initializing a population and solving each candidate solution XiThe corresponding total air conditioner energy consumption is expressed as a fitness value, the individual is subjected to real number coding and substituted into an air conditioner energy consumption model to calculate the fitness value corresponding to each individual;
starting optimization iteration, firstly carrying out mutation, and randomly selecting X to be removed from the population in the g-th iterationi(g) Other 3 individuals Xp1(g),Xp2(g),Xp3(g) P1 ≠ p2 ≠ p3 ≠ i, and the generated mutation vector is Hi(g)＝Xp1(g)+F(Xp2(g)-Xp3(g) F) is a scaling factor, 0.5 is taken;
mixing Xi(g) And variant individual Hi(g) Performing cross operation to obtain cross individual Ui(g) Setting cr by adaptively adjusted crossover probabilitymin＝0.1，crmaxCalculate individual X as 0.6iIs a fitness value fiAnd the average value of the current population fitness
The fitness values of the worst individual and the optimal individual in the current population are respectively fmaxAnd fminThen adapting criThe calculation formula is as follows:
generating individual U with dimension N and null valuei(g)，Ui(g) Has a j-th value of Ui,j(g) Randomly generating a rand (0,1), and mutating the individual H when the random value is less than the cross probabilityi(g) Value of j in the sequence is assigned to Ui(g) Otherwise, will Xi(g) To Ui(g) The formula is as follows:
selecting and operating, if the fitness value of the crossed individuals is smaller than that of the parent individuals, selecting and reserving the crossed individuals, if the crossed individuals are not optimal, not updating the individuals at this time, and selecting a new individual Xi' (g) the formula is as follows:
and when the maximum iteration times are met or the minimum energy consumption value is reached, terminating the iteration, and outputting the optimal individual according to the corresponding fitness value, wherein the value of the optimal individual is the optimal operation parameter combination for the operation of the air-conditioning system.
6. An energy-saving optimization system of an air conditioning system is characterized by comprising:
a data processing module: the system comprises a data set used for acquiring a data set required by air conditioner load prediction;
preprocessing the data set;
a modeling module: the method is used for constructing an air conditioner load prediction model and determining the air conditioner load; constructing an air conditioner energy consumption model according to an air conditioner load prediction result;
an optimizing module: and optimizing the equipment parameters by taking the total energy consumption as an objective function of the air conditioner energy consumption model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011189834.3A CN112415924A (en) | 2020-10-30 | 2020-10-30 | Energy-saving optimization method and system for air conditioning system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011189834.3A CN112415924A (en) | 2020-10-30 | 2020-10-30 | Energy-saving optimization method and system for air conditioning system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112415924A true CN112415924A (en) | 2021-02-26 |
Family
ID=74828729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011189834.3A Pending CN112415924A (en) | 2020-10-30 | 2020-10-30 | Energy-saving optimization method and system for air conditioning system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112415924A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033016A (en) * | 2021-04-12 | 2021-06-25 | 北京信息科技大学 | Hybrid-based central air conditioner load prediction method and device |
| CN113282122A (en) * | 2021-05-31 | 2021-08-20 | 西安建筑科技大学 | Commercial building energy consumption prediction optimization method and system |
| CN113361188A (en) * | 2021-05-10 | 2021-09-07 | 国网河北省电力有限公司营销服务中心 | Multi-target power distribution network dynamic reconstruction method, device and terminal |
| CN113612660A (en) * | 2021-08-03 | 2021-11-05 | 宜宾电子科技大学研究院 | LSTM network flow prediction method based on population self-adaptive differential evolution |
| CN113739365A (en) * | 2021-08-31 | 2021-12-03 | 广州汇电云联互联网科技有限公司 | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium |
| CN114322208A (en) * | 2021-12-15 | 2022-04-12 | 合肥工业大学 | Intelligent park air conditioner load regulation and control method and system based on deep reinforcement learning |
| CN116294089A (en) * | 2023-05-23 | 2023-06-23 | 浙江之科云创数字科技有限公司 | Air conditioning system control method and device, storage medium and electronic equipment |
| CN117232110A (en) * | 2023-11-14 | 2023-12-15 | 博纳环境设备(太仓)有限公司 | Multi-source data processing method and system for industrial air conditioner sub-bin control |
| CN117439146A (en) * | 2023-12-06 | 2024-01-23 | 广东车卫士信息科技有限公司 | Data analysis control method and system for charging pile |
| CN117928052A (en) * | 2024-03-25 | 2024-04-26 | 烟台市市级机关服务中心 | Energy-saving control method and system for central air conditioner |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102980272A (en) * | 2012-12-08 | 2013-03-20 | 珠海派诺科技股份有限公司 | Air conditioner system energy saving optimization method based on load prediction |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| CN108361937A (en) * | 2018-01-18 | 2018-08-03 | 上海广岚机电设备有限公司 | Intelligent central air conditioner energy-saving control method and system |
| CN108489012A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Cold source of air conditioning energy efficiency model control method based on load prediction and constraint |
| US20180260714A1 (en) * | 2017-03-10 | 2018-09-13 | Yun Li | Global optimization, search and machine learning method based on the lamarckian principle of inheritance of acquired characteristics |
| CN109959123A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | A kind of energy-saving method for air conditioner based on genetic algorithm and shot and long term memory Recognition with Recurrent Neural Network |
| CN110440396A (en) * | 2019-07-11 | 2019-11-12 | 雄安达实智慧科技有限公司 | The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration |
-
2020
- 2020-10-30 CN CN202011189834.3A patent/CN112415924A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102980272A (en) * | 2012-12-08 | 2013-03-20 | 珠海派诺科技股份有限公司 | Air conditioner system energy saving optimization method based on load prediction |
| CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
| US20180260714A1 (en) * | 2017-03-10 | 2018-09-13 | Yun Li | Global optimization, search and machine learning method based on the lamarckian principle of inheritance of acquired characteristics |
| CN108361937A (en) * | 2018-01-18 | 2018-08-03 | 上海广岚机电设备有限公司 | Intelligent central air conditioner energy-saving control method and system |
| CN108489012A (en) * | 2018-01-30 | 2018-09-04 | 深圳市新环能科技有限公司 | Cold source of air conditioning energy efficiency model control method based on load prediction and constraint |
| CN109959123A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | A kind of energy-saving method for air conditioner based on genetic algorithm and shot and long term memory Recognition with Recurrent Neural Network |
| CN110440396A (en) * | 2019-07-11 | 2019-11-12 | 雄安达实智慧科技有限公司 | The central air-conditioning global optimization energy-saving control method and system of cloud side end collaboration |
Non-Patent Citations (2)
| Title |
|---|
| 于丹等: "数据分布特性对空调系统能耗预测的影响", 《科学技术与工程》 * |
| 彭华等: "智能计算在中央空调水系统优化控制中的应用研究", 《科技通报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113033016A (en) * | 2021-04-12 | 2021-06-25 | 北京信息科技大学 | Hybrid-based central air conditioner load prediction method and device |
| CN113033016B (en) * | 2021-04-12 | 2021-10-22 | 北京信息科技大学 | Hybrid-based central air conditioner load prediction method and device |
| CN113361188A (en) * | 2021-05-10 | 2021-09-07 | 国网河北省电力有限公司营销服务中心 | Multi-target power distribution network dynamic reconstruction method, device and terminal |
| CN113282122A (en) * | 2021-05-31 | 2021-08-20 | 西安建筑科技大学 | Commercial building energy consumption prediction optimization method and system |
| CN113612660A (en) * | 2021-08-03 | 2021-11-05 | 宜宾电子科技大学研究院 | LSTM network flow prediction method based on population self-adaptive differential evolution |
| CN113612660B (en) * | 2021-08-03 | 2023-12-08 | 宜宾电子科技大学研究院 | LSTM network traffic prediction method based on population self-adaptive differential evolution |
| CN113739365A (en) * | 2021-08-31 | 2021-12-03 | 广州汇电云联互联网科技有限公司 | Central air-conditioning cold station group control energy-saving control method, device, equipment and storage medium |
| CN114322208B (en) * | 2021-12-15 | 2023-08-18 | 合肥工业大学 | Intelligent park air conditioner load regulation and control method and system based on deep reinforcement learning |
| CN114322208A (en) * | 2021-12-15 | 2022-04-12 | 合肥工业大学 | Intelligent park air conditioner load regulation and control method and system based on deep reinforcement learning |
| CN116294089A (en) * | 2023-05-23 | 2023-06-23 | 浙江之科云创数字科技有限公司 | Air conditioning system control method and device, storage medium and electronic equipment |
| CN116294089B (en) * | 2023-05-23 | 2023-08-18 | 浙江之科云创数字科技有限公司 | Air conditioning system control method and device, storage medium and electronic equipment |
| CN117232110A (en) * | 2023-11-14 | 2023-12-15 | 博纳环境设备(太仓)有限公司 | Multi-source data processing method and system for industrial air conditioner sub-bin control |
| CN117232110B (en) * | 2023-11-14 | 2024-04-09 | 博纳环境设备(太仓)有限公司 | Multi-source data processing method and system for industrial air conditioner sub-bin control |
| CN117439146A (en) * | 2023-12-06 | 2024-01-23 | 广东车卫士信息科技有限公司 | Data analysis control method and system for charging pile |
| CN117439146B (en) * | 2023-12-06 | 2024-03-19 | 广东车卫士信息科技有限公司 | Data analysis control method and system for charging pile |
| CN117928052A (en) * | 2024-03-25 | 2024-04-26 | 烟台市市级机关服务中心 | Energy-saving control method and system for central air conditioner |
| CN117928052B (en) * | 2024-03-25 | 2024-06-07 | 烟台市市级机关服务中心 | Energy-saving control method and system for central air conditioner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112415924A (en) | Energy-saving optimization method and system for air conditioning system | |
| Jallal et al. | A hybrid neuro-fuzzy inference system-based algorithm for time series forecasting applied to energy consumption prediction | |
| CN111735178B (en) | Air conditioner energy saving system based on elite and SVR regression algorithm and optimization method | |
| Song et al. | Hourly heat load prediction model based on temporal convolutional neural network | |
| CN103912966B (en) | A kind of earth source heat pump refrigeration system optimal control method | |
| CN114692265B (en) | Zero-carbon building optimization design method based on deep reinforcement learning | |
| Jin et al. | A data-driven model predictive control for lighting system based on historical occupancy in an office building: Methodology development | |
| CN110805997A (en) | Energy-saving control method for central air-conditioning system | |
| CN112070262B (en) | Air conditioner load prediction method based on support vector machine | |
| CN111649457B (en) | Dynamic predictive machine learning type air conditioner energy-saving control method | |
| CN107909220A (en) | Electric heating load prediction method | |
| CN112561728A (en) | Attention mechanism LSTM-based comprehensive energy consumption cost optimization method, medium and equipment | |
| Liu et al. | Identifying the most significant input parameters for predicting district heating load using an association rule algorithm | |
| Song et al. | An indoor temperature prediction framework based on hierarchical attention gated recurrent unit model for energy efficient buildings | |
| CN113268913B (en) | Intelligent building air conditioner cooling machine system operation optimization method based on PSO-ELM algorithm | |
| CN111598225A (en) | Air conditioner cold load prediction method based on adaptive deep confidence network | |
| CN112524751A (en) | Dynamic air conditioning system energy consumption prediction model construction and prediction method and device | |
| Qin et al. | Energy-efficient heating control for nearly zero energy residential buildings with deep reinforcement learning | |
| CN116989442A (en) | Central air conditioner load prediction method and system | |
| CN115577828A (en) | Air conditioner refrigerating station system group control method based on data-driven modeling and optimization | |
| CN116227883A (en) | Intelligent household energy management system prediction decision-making integrated scheduling method based on deep reinforcement learning | |
| CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
| Sun et al. | Research on prediction of housing prices based on GA-PSO-BP neural network model: evidence from Chongqing, China | |
| CN117628659A (en) | Predictive regulation and control method for multi-system cooperative operation of heating ventilation air conditioner | |
| CN111473480A (en) | Central air conditioner energy-saving control method based on decision tree classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |
|
| RJ01 | Rejection of invention patent application after publication |