Hybrid model based on wavelet support vector machine and modified genetic algorithm penalizing Gaussian noises for power load forecasts

摘要

In view of the dissatisfactory capability of the ε;-insensitive loss function in field of white (Gaussian) noise of multi-dimensional load series, a new wavelet ν-support vector machine with Gaussian loss function which is called Wg-SVM is put forward to penalize the Gaussian noises. To seek the optimal parameters of Wg-SVM, modified genetic algorithm (GA) is proposed to optimize parameters of Wg-SVM. The results of application in load forecasts show that the forecasting approach based on the Wg-SVM model is effective and feasible, the comparison between the method proposed in this paper and other ones is also given, which proves this method is better than other SVM methods.