Wind Forecasting Using Various Neural Networks in Machine Learning

Abstract

Wind Power Forecasting, as the name applies is a process in which data of past is used to tell what kind of output can be expected from a wind turbine in the foreseeable future. Machine learning, can be said to be a derivation of artificial intelligence that makes it possible for the system to learn automatically and improve upon itself from faults, without needing to tell the system to do it, is used to make wind forecasting better. Artificial Neural Network, are an application of Machine learning and they are able to mimic the decision making abilities of a brain to a certain extent. The various kinds of neural networks that were applied in this paper - Adaptive Neuro Fuzzy Interference System, a type of artificial neural network that takes all of the inputs and all of the outputs of the data into consideration, Multi-Layer Perceptron in which the entire networks has many layers which contain parameters and weights, Nonlinear Autoregressive Exogenous Model, in which there are multiple feedbacks for better relations of the values and Long Short term Memory which can add and remove new info while working.