PROJECT TITLE :

Particle swarm optimisation aided least-square support vector machine for load forecast with spikes

ABSTRACT:

This study developed a load forecasting system for electrical market participants. Combining the least-square support vector machine (LSSVM) and particle swarm optimisation (PSO), a LSSVM_PSO was proposed for the solving process. The masses, temperature, and relative humidity of the Taipower system were collected in the Excel Database. Knowledge mining techniques is employed to get meaningful patterns, with the PSO applied to regulate learning rates. The forecasting error will be reduced throughout the training process to enhance each the accuracy and reliability, where even the spikes were nicely followed. The support vector regression, LSSVM, radial basis perform neural network and therefore the proposed LSSVM_PSO were all developed and compared to test the convergence and performance. Simulation results demonstrated the effectiveness of the proposed technique in an exceedingly price volatile setting.