One-against-all and one-against-one multiclass Support Vector Machine algorithms for wind speed prediction

Authors: Wani, M.A. and Bhat, H.F.

Journal: International Journal of Renewable Energy Research

Volume: 8

Issue: 2

Pages: 909-915

eISSN: 1309-0127

Abstract:

Wind speed prediction has several applications and various atmospheric parameters like temperature, humidity, pressure, wind direction can be used to predict it. A number of methods using mathematical and biological models have been proposed by various researchers to predict the wind speed. This work explores the use of oneagainst- all (OVA) and one-against-one (OVO) multiclass Support Vector Machine (SVM) algorithms for wind speed prediction. The paper also makes contribution by proposing a synergistic approach that combines the OVA and OVO algorithms for improving the performance of the system for wind speed prediction application. The algorithms are tested on wind speed data having hundreds of samples of training and test data sets. The results of employing the two algorithms and the proposed synergistic approach are compared for wind speed prediction application and results indicate that one-against-one algorithm produces better results than the one-against-all algorithm and the proposed Synergistic approach produces better results than both the algorithms.

Source: Scopus