Optimizing the Weather Research and Forecasting Model Physics to Support Wind and Solar Energy Integration

Abstract:

To make a future run by renewable energy possible, we must design our power system to seamlessly collect, store, and transport the Earth’s naturally occurring flows of energy — namely the sun and the wind. In other words, we must merge meteorological and power systems modeling. Although many meteorological phenomena that affect wind and solar power production are well-studied in isolation, no coordinated effort has been undertaken to improve medium- and long-term power systems planning via forecasts. Here we present an AI-assisted methodology for optimizing the weather research and forecasting (WRF) model physics, using a genetic algorithm, for forecasting wind power density and solar irradiance. We then employ machine learning, training a random forest regressor from the genetic algorithm results, to identify what caused smaller errors in some WRF forecasts. We produce plots depicting the performance of key physics options to help guide energy researchers in quickly setting up an accurate forecast model.