Load Forecasting And Energy Saving Optimization Of Air Conditioning System In A University Auditorium

Public buildings are the main buildings for public activities,adhere to the high quality development of energy conservation and emission reduction is the top priority of the country.As a typical public building,college buildings integrate learning,office work,literary and artistic activities.According to the actual use,the energy consumption of the internal air conditioning system is high,resulting in energy waste.In view of the above problems,this paper takes the air conditioning system of a university auditorium as the research object,aiming at reducing the energy consumption of the air conditioning system,carries out research on the load forecasting,fuzzy control strategy,precooling and early shutdown time optimization of air conditioning system.Firstly,TRNSYS software was used to build a simulation platform for the central air conditioning system of the auditorium,and Pearson correlation coefficient was used to determine the factors affecting the cooling load of the air conditioning system in summer.Based on the idea of integrated model,a Bayesian optimization method and an improved crow search algorithm are proposed for optimization.the load prediction model of Elman neural network optimized by dual frame is established.Compared with the traditional BP neural network and the traditional Elman neural network,the optimized Elman neural network proposed in this paper has better prediction effect.Secondly,for the auditorium air conditioning system with nonlinear,large lag characteristics,the load forecasting and fuzzy control are combined,with the load deviation and load deviation change rate as input variables,and the speed of chilled water pump and fan as output variables,a dual-input and dual-output predictive fuzzy control strategy is established to optimize the energy saving control of the auditorium air conditioning system.Based on the co-simulation of TRNSYS and Matlab software,the energy consumption of each component of the air conditioning system is analyzed.The results show that compared with the traditional temperature control strategy,the proposed strategy has good energy-saving effect on the pump and fan of the air conditioning system.Finally,according to the characteristics of frequent use and irregular use time of the air conditioning system in the university auditorium,the precooling and early shutdown time of the air conditioning system are optimized.Based on the analysis of the influencing factors of precooling time and early shutdown time,the optimized Elman neural network was used to predict the precooling time and early shutdown time,and the prediction effect was verified by comparing with the traditional Elman neural network.At the same time,combined with the auditorium meeting arrangement information,compared with the traditional switching time.The results show that the energy consumption of the air conditioning system can be effectively reduced by using the precooling time and early shutdown time based on the fuzzy control strategy.Among them,the energy saving rate of the fan is 30.18%,the energy saving rate of the water pump is 21.93%,and the energy saving rate of the total energy consumption is 20.03%.To sum up,based on the load forecasting and energy-saving optimization method of air conditioning system proposed in this paper,for the central air conditioning system of university auditorium,on the one hand,more accurate load forecasting can be carried out to achieve energy-saving control of air conditioning system;On the other hand,it can predict the pre-cooling and early shutdown time of the air conditioning system according to the random arrangement of the meeting time of the auditorium,so as to reduce the waste of energy.