Predicting octane numbers relying on principal component analysis and artificial neural network

Improved chimpanzee algorithm based on CEEMDAN combination to optimize ELM short-term wind speed prediction

The world energy structure dominated by fossil energy has brought about the depletion of fossil energy and a series of environmental pollution problems. The development of new energy has become the direction of joint efforts of China and other countries in the world. Wind energy is an important part of new energies. Accurate wind speed prediction can effectively reduce the adverse impact of wind farm fluctuation on power system. To solve the problem of low and poor accuracy of short-term wind speed prediction, a hybrid prediction model based on improved optimized extreme learning machine (ELM) is provided in this paper. The wind speed series are decomposed by using the Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), the phase space of each modal component is reconstructed to obtain some new time series, and thus to enhance the stability of the wind speed series. Also, the improved chimpanzee optimization algorithm (CHOA) is used to determine the optimal value of the extreme learning machine (ELM) so as to predict the processed wind speed sequence. Through related empirical analysis and comparisons with other models, the hybrid prediction model reduces wind speed prediction error and improves the accuracy of wind speed prediction accuracy effectively.