Load Forecasting And Energy Saving Optimization Of Central Air Conditioning System In Metro Station

The central air-conditioning system,as a large energy consumer of the subway station,runs under heavy load for a long time,causing a large amount of energy waste.How to reduce the operating energy consumption of the central air-conditioning system under the premise of meeting the thermal comfort requirements of the metro station becomes the key to energy saving in the subway station.In view of the large energy consumption of the central air-conditioning system of the metro station,this paper studies the load forecasting and optimization control of the air-conditioning system with the aim of energy saving in the central air-conditioning system.Mainly completed the following work:Firstly,according to the characteristics of the central air-conditioning system load of metro station,there are many characteristics,such as associated,transformation and coupling relationship.By analyzing the structural model of air-conditioning load of subway station,the influence of station air-conditioning load and various factors is analyzed.Regularity,the direct factors affecting the air conditioning load of the station and their relationship are obtained.Secondly,the application of BP neural network to the air conditioning load forecasting of metro stations has the problems of slow convergence rate and easy to fall into local minimum.The genetic algorithm(GA)and particle swarm optimization(PSO)are combined with BP neural network to utilize GA and PSO.The algorithm optimizes the weights and thresholds of BP neural network,and establishes the BP neural network metro station air load forecasting model based on GA and PSO hybrid optimization algorithm.The experimental results show that the proposed method can effectively predict the future time of the metro station air conditioning system.Load,the predicted relative error is within 6%.Finally,aiming at the characteristics of time-varying,hysteresis and non-linearity of the central air-conditioning chilled water system of the metro station,the conventional PID and fuzzy control are combined to design a fuzzy PID controller for the airconditioning chilled water system of the metro station,and the particle swarm optimization algorithm(PSO)is used.Dynamic adjustment of controller parameters to compensate for the inadequacy of fuzzy controller parameters is difficult to adapt to complex conditions.Matlab simulation experiments show that the fuzzy PID control optimized by particle swarm optimization(PSO)has small overshoot,short adjustment time and strong anti-disturbance control effect,which provides new control for optimal control of central air conditioning chilled water system in metro station.