Skip to Main Content
Neighboring regional transmission organizations (RTO) and 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 RTO/ISO and its neighbors. Effective forecasting of the amount of actual NI can improve grid operation efficiency and avoid the volatility of the energy markets due to changes of NI schedules. 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 effectiveness of these methods is compared using the 64 weeks of field measurement data from PJM. The objective is to explore the effectiveness of the prediction methods under different scenarios.