Research On Load Forecasting And Multi-objective Optimization Operation Of Ice Storage Air Conditioning For A Mall In Xi’an

Ice storage air conditioning has been widely applied in air conditioning field because of its advantages of "shifting peak and valley filling",balancing the power grid and reducing the operation cost of air conditioning.However,the lack of reasonable operation strategy in the actual operation of ice storage air conditioning leads to low running efficiency,resulting in the waste of energy and high cost of operation.Therefore,it is very important to optimize the operational strategy of ice storage air conditioning.The accurate prediction of air conditioning load is the prerequisite for the realization of the economic and energy saving operation of the ice storage air conditioning system.Therefore,the paper studies the ice storage air conditioning load forecasting and multi target operation strategy for a mall in Xi’an.The main contents are as follows:Firstly,targeting the ice storage air conditioning system process of the target building,the whole day running energy consumption model and the ice storage chilling /release cooling model are established,which lays the foundation for the establishment of the multi-objective optimization operation model of ice storage air conditioning.Secondly,according to the working days and rest days in summer,the cold load forecasting model of ice storage air conditioning BP neural network and the combination prediction model of GA-BP cold load are established.After model validation,the results show that the GA-BP combined forecasting model is more effective whether they are working days or rest days.Therefore,the prediction of air conditioning cooling load is based on GA-BP combined forecasting model.Finally,a multi-objective optimization operation model was established with the goal of minimizing the energy consumption loss rate and the minimum operating cost of ice storage air conditioners.The adaptive penalty function is used to deal with multi-objective constraints,and based on the predicted cold load demand,a multi-objective particle swarm optimization algorithm is used to optimize the operation strategy.The simulation results show that the use of this optimization strategy to guide the operation of the system compared to the current operation strategy of the target building can save 8.86% of the operating costs for the users,and reduce the loss of energy consumption by 12.07%.In short,the research work of the dissertation can not only solve the load forecast of an ice storage air conditioner in a mall in Xi’an and the present problems in the operation of the system,but also provide guidance and reference for the economic and energy-saving operation of ice storage air conditioners in similar buildings in Xi’an.