A low complexity nonlinear pseudo inverse neural network for short-term wind power prediction

Abstract

This paper proposes three different efficient wind power prediction algorithms, i.e., Chebyshev neural network (CNN), Legendre neural network (LNN), trigonometric functional link artificial neural net (trigonometric FLANN), passed through functional expansion block (FEB) and trained by ridge pseudo inverse neural net (R-PINN), for 10 minutes, 30 minutes and 60 minutes ahead prediction. Learning speed rate and computational scalability are very essential in the prediction purpose. Conventional algorithms, such as hybrid models, statistical approaches, and intelligent systems based algorithms are less accurate because they require updation of hidden layer in each iteration. On the contrary, the proposed R-PINN-based prediction algorithm computes the output weight vector in a chunk, where the hidden layer is not being updated. Hence the essential features such as the learning speed and computational scalability has been significantly improved. This allows a faster response. In a comparison study all algorithms are verified using R-PINN technique and it is found that LNN model gives best output results among all algorithms. This is distinguished clearly in the MATLAB%Editor environment and has been illustrated in the simulation and result section by graphical representations.