loading page

Bare Demo of IEEEtran.cls for Conferences
  • Rahul Mohan
Rahul Mohan

Corresponding Author:[email protected]

Author Profile

Abstract

Renewable energy sources, such as solar, offer many environmental advantages over fossil fuels for electricity generation, but the energy produced by them fluctuate with changing weather conditions. Electric utility companies need accurate forecasts of solar energy production in order to have the right balance of renewable and fossil fuels available. Errors in the forecast could lead to large expenses for the utility from excess fuel consumption or emergency purchases of electricity from neighboring utilities. Currently, significant amount of utilities are only able to obtain net power readings (production from the solar panels subtracted from electric consumption) from a home. However, the inability to differentiate solar production and consumption leads to the utility not knowing how much electricity to put into the grid and unnecessary costs. We collected solar panel and historical weather data from hundreds of homes and each of their local weather stations. We describe a new method to predict solar panel genera- tion with a Radial Basis Function (RBF) and ANOVA kernel SVM ensemble. We demonstrate the superiority and practicability of our solution on real life solar panel data from across the world in diverse climates, and how this approach can save utilities thousands of dollars in electricity costs by accurately differentiating from consumption and production in net power readings.