Neighboring independent system operators (ISOs) exchange electric power to enable efficient and reliable operation of the grid. Net interchange (NI) schedule is the sum of the transactions (in MW) between an ISO and its neighbors. Effective forecasting of the amount of actual NI can improve grid operation efficiency. This paper presents results of a preliminary investigation into various methods of prediction that may result in improved prediction accuracy. The methods studied are linear regression, forward regression, stepwise regression, and support vector machine (SVM) regression. The work to date is not yet conclusive. The hope is to explore the effectiveness of other prediction methods and apply all methods to at least one new data set. This should enable more confidence in the conclusions.
Revised: June 6, 2013 |
Published: July 26, 2012
Citation
Ferryman T.A., D.J. Haglin, M. Vlachopoulou, J. Yin, C. Shen, F.K. Tuffner, and G. Lin, et al. 2012.Net Interchange Schedule Forecasting of Electric Power Exchange for RTO/ISOs. In IEEE Power and Energy Society General Meeting, July 22-26, 2012, San Diego, California. Piscataway, New Jersey:Institute of Electrical and Electronic Engineers.PNNL-SA-84231.doi:10.1109/PESGM.2012.6344738