Joint Feature Selection of Power Load in Time Domain and Frequency Domain Based on Whale Optimization Algorithm

Accurate classification of power load is the premise demand-side response capability evaluation, which great significance for management. Therefore, this study proposes a selection method joint characteristics in time domain and frequency based on whale optimization algorithm. The electrical measurement data six typical equipment are selected to form original identification dataset. Firstly, features extracted, then screened by Whale algorithm (WOA). Finally, feature information used as input verify performance WOA under back propagation neural network (BP), extreme learning machine (ELM), support vector (SVM), k-nearest neighbor (KNN), decision tree (DT), naive Bayesian (NB) classifiers. results show that can effectively screen out 15 most helpful attributes identification, not only improve accuracy but also reduce cost algorithm, reference value further strategy. At same time, it intelligent dispatching system improving economic operation system.