An Efficient Regional Short-Term Load Forecasting Model for Smart Grid Energy Management

The conventional grid has experienced a transition towards smart grid with the advancements in metering infrastructure and increasing usage of renewable energy sources. In smart grid, the energy management system relies heavily on an accurate short-term load forecasting at regional level for an efficient planning and operations of grid. In this paper, we propose an efficient model for regional short-term load forecasting using machine learning techniques in parallel. This model uses feasible machine learning techniques such as support vector regressor (SVR) and random forest (RF) as base predictors. The forecasting results of RF and SVR are averaged to derive final outcome. The performance of the proposed model is validated using load data collected from different regions such as Goa, Maharashtra and Mumbai in India.