Hybrid forecasting model for smart grid using exogenous variables

Smart grids augment the existing power grids with information and communication technology to enable enhanced monitoring and control. Power grid resilience and failure management have always been problems that have intrigued researchers and policymakers, who want to ensure the services offered are up to the mark and consumers can rely on the system. To improve the quality of service, data analytics, and forecasting can help with predictive analytics. Forecasting in smart grids can ensure that the optimal relationship between power generation and consumption can be optimized effectively. Hybrid forecasting, including multi-criteria forecasting, has shown promising results. In this paper, we outline exogenous variables from weather data that can be used in real-time hybrid forecasting of the smart grid in an energy management system. The framework presented in this work presents a base model for enhancing the quality of service in smart grid forecasting.