FORECASTING OF INDIVIDUAL ELECTRICITY USAGE USING SMART METER DATA

Forecasting electricity usage is an important task to provide intelligence to the smart gird. The customers will benefit from metering solutions through greater understanding of their own energy consumption and future projections, allowing them to better manage costs of their usage. In this proof of concept paper, we show the approach for short term electricity load forecasting for 24 hours ahead, calculated on the individual household level. In this context authors will develop an approach to the analysis and prediction using Multivariate Adaptive Regression Splines (MARSplines).