Study On Overall Optimization Operation Of Central Air Conditioning System In Commercial Buildings

The construction of large commercial buildings is an important product of the vigorous development of urban economy,which causes the problem of high energy consumption of buildings increasingly prominent.Central air conditioning system is the key energy consumption equipment.The existing regulation and control methods are mainly based on the water system or the end of air conditioning,which lacks the overall regulation and control means,and cannot meet the dynamic change of building load,leading to excessive energy consumption of the system,and the central air conditioning system has a large energy saving space.This paper carries out innovative research on building central air conditioning system modeling,building cooling load forecasting and overall optimization operation strategy,and takes the central air conditioning refrigeration system of a large commercial building in Jinan as an example to verify the proposed method.The specific contents are as follows:Firstly,the working principle of the whole central air conditioning system is introduced.Five main equipment models of chiller,circulating water pump,cooling tower and terminal air conditioning are established respectively,and the thermal response characteristics of terminal air conditioning are described.Based on the operating data of the actual air conditioning system,the least square method is used for parameter identification.By fully considering the operating conditions of each chiller unit under normal operation,startup and shutdown,the chiller model under three operating conditions is obtained,which improves the accuracy of the model and lays a foundation for the subsequent research on the overall optimal operation strategy of the central air conditioning system.Secondly,the meteorological factors affecting the cooling load of commercial buildings were analyzed by using the Person correlation analysis method,and the input characteristics of the prediction model were determined.Then,the GA-LSTM short-term cooling load prediction model was established by optimizing the LSTM network parameters using the genetic algorithm,which improved the performance ceiling of the deep learning algorithm.The experimental results show that the prediction accuracy of GA-LSTM model is significantly improved compared with other RNN and LSTM models.Furthermore,based on the energy consumption model of each equipment in the central air conditioning system,based on the building cooling load prediction results,with the lowest energy consumption of the system as the optimization objective,water supply temperature,operating frequency and the number of equipment running as optimization variables,considering the temperature dynamic change trend of comfort level,using the adaptive genetic algorithm to solve,get the system hourly operating parameters of the optimal value.The energy consumption of the whole central air conditioning system is reduced by 12.63%.Finally,based on the above research,the central air conditioning system optimization operation software is developed.The whole software Lab VIEW is the basic framework,including data reading,storage,model parameter identification,cooling load prediction,system operation optimization and many functions.The software is deployed in a large commercial building in Jinan,and the functions are verified.