Heat Distribution of Heat Exchange Station in District Heating System based on Load Forecasting

Abstract

District heating system is the main way of heating in cities and towns in China. The development of district heating system still has the problems of low intelligence and low control accuracy, and there is the imbalance of heat supply and demand in heat distribution. Resulting in the energy consumed by the district heating system can account for more than half of the total energy consumption of the building. In order to alleviate this imbalance, this paper studies the control of heat distribution of each heat exchange station in the primary network. The heat model of primary network is established by recurrent neural network (RNN), and the data set used for modeling is the operation data of heat exchange station in reality. Combined with the heat load prediction model, a heat distribution strategy was proposed to optimize the primary flow of the heat exchange station. According to the predicted value, chaotic particle swarm optimization (CPSO) algorithm is used to optimize the primary flow sequence of each heat exchange station, and then the primary flow is adjusted to control the heat distribution of the secondary network. Finally, Simulink simulation model is used to simulate the water supply temperature of the secondary side of the heat exchange station. And analyze the operation status of the secondary side, the results verify the effectiveness of the strategy. The model simulation results show that the heat distribution scheme proposed in this paper can effectively distribute the heat of the heat exchange station according to the heat demand.