Development of Intelligent Forecasting Technique for Residential Loads in Smart Grid

Around the globe, the power sector has seen major developments in terms of infrastructure and its operations, turning the legacy power grid into what is known as the Smart Grid. Some of the major factors causing these changes are ever-increasing population, aging legacy power equipment, Carbon-di-Oxide (CO2) emissions, inability to incorporate alternate power sources (renewable energy), etc. As part of the developments, the Smart Grid has deployed a communication enabled energy measurement device called the Smart Meter. Smart Meters generate an enormous amount of data at a faster rate that contains valuable information related to electrical consumption pattern of customers and the associated load demand. Analyzing the Smart Meter data for the mutual benefit of the energy suppliers and its consumers is a data science problem, namely Smart Meter Data Analytics (SMDA). SMDA is an emerging research area in Smart Grid Systems. Among the applications of SMDA, residential load forecasting becomes crucial in the present scenario as the world is moving towards smart cities and smart buildings. In this context, the residential customers play a significant role in the energy saving programs. They are expected to take part in demand response (DR) programs by the Utilities in order to balance the energy supply and demand. This can be done by Utilities offering appropriate incentives to customers that would reduce their energy bill. With the availability of live or instant data analytics, a Utility can customize these incentives to better balance the supply and demand. An accurate estimate of energy bill in advance could help the customers' budgeting. Statistical analysis and visual presentation of energy consumption will enable the customers to understand their consumption behavior and adjust their energy