Comparative Analysis of Markov Chain and Polynomial Regression for the Prognostic Evaluation of Wind Power

EasyChair Preprint 2494

Abstract

Humanity’s quest to comprehend the nature has led to increasing demand in predictive sciences. Much of this is due to the exponential growth of energy production and the ever increasing power prices. Regions with power productions that are carried out with imported coal and oil will be more self-sustaining if alternative sources of power generation such as wind power is discharged. In this paper two predictive models, Markov Chain and Regression are implemented to predict wind power. In the first model, Markov Chains with 15 and 30 states has been constructed for the short- term forecast of the wind power. Following this a second order polynomial regression with independent variable as wind speed and dependent variable as wind power has been implemented for the medium-term forecast of wind power. A comparative study of both the models has been made to give a picture of the best model that suits the forecast. The geographical region under study is a wind farm in Chitradurga, Karnataka. The wind speed values have been sampled at an interval of 10 minutes for a period of 3 years starting from 1st January 2010 to 31st December 2012. Various forecasting errors have been enumerated to audit the credibility of the models.

Keyphrases: Forward Selection Procedure, Markov chains, Transition Diagram, correlation, polynomial regression, regression analysis, stochastic models, transition matrix

@booklet{EasyChair:2494,
  author    = {Mounika Yakasiri and M. Anuradha and B. K. Keshavan},
  title     = {Comparative Analysis of Markov Chain and Polynomial Regression for the Prognostic Evaluation of Wind Power},
  howpublished = {EasyChair Preprint 2494},
  year      = {EasyChair, 2020}}