Application of Urban Water Demand Prediction Model by Using Particle Swarm Algorithm Based on Simulated Annealing

Abstract

Water demand prediction is a complicated multifactor, multi-level non-linear system influenced by the urban population, industrial and economic level. The results of the prediction accuracy have a greater uncertainty and ambiguity. As a new cluster intelligent evolutionary algorithms, particle swarm optimization (PSO) is easy to understand, easy to implement ,and it is very suitable for non-linear model parameters fitting problems. At the same time, we will introduce the simulated annealing mechanism into particle swarm optimization algorithm, constructed the optimization algorithm of simulated annealing particle swarm (SA-PSO). In the paper, the optimization algorithm of simulated annealing particle swarm (SA-PSO) is applied to the field of water demand prediction. Example show that compared with the particle swarm algorithm, simulated annealing particle swarm optimization achieves a high prediction accuracy for urban water demand prediction, and it is strong applicability in the water demand forecast.