Deep Learning Based Load Forecasting: from Research to Deployment -- Opportunities and Challenges

Electricity load forecasting for buildings and campuses is becoming increasingly important as the penetration of distributed energy resources grows. Efficient operation and dispatch of DERs requires reasonably accurate prediction of future energy consumption in order to conduct near-real-time optimized dispatch of on-site generation and storage assets. Load forecasting has traditionally been done by electric utilities for load pockets spanning large geographic areas and therefore has not been a common practice in the buildings' and campuses' operational arena. Given the growing trends of research and prototyping in the grid-interactive efficient buildings domain, characteristics beyond simple algorithm forecast accuracy are important in determining the algorithm's true utility for the smart buildings. These other characteristics include the overall design of the deployed architecture and the operational efficiency of the forecasting system. In this work, we present a deep-learning-based load forecasting system that predicts the building load at one-hour interval for 18 hours in the future. We also present the challenges associated with the real-time deployment of such systems as well as the research opportunities presented by a fully functional forecasting system that has been developed within the National Renewable Energy Laboratory's Intelligent Campus program.