A Novel HPSOSA for Kernel Function Type and Parameter Optimization of SVR in Rainfall Forecasting

摘要

In this paper, a novel co-evolution algorithm is presented to optimize the type of kernel function and the kernel parameter setting of Support Vector Regression (SVR) for rainfall prediction based on hybrid Particle Swarm Optimization and Simulated Annealing (HPSOSA), namely HPSOSA-SVR. The HPSOSA algorithm is carried out the metropolis process of SA into the movement mechanism and parallel processing of PSO. By combining the two methods, the HPSOSA algorithm has the advantage of both fast calculation and searching in the direction of the global optimum solution, helping PSO jump out of local optima, avoiding into the local optimal solution early and leading to a good solution quality. The developed HPSOSA-SVR model is being applied for monthly rainfall forecasting. Experimental results reveal that the predictions using the proposed approach are consistently better than those obtained using the other methods presented in this study in terms of the same measurements.