Smart Home Energy Prediction with GRU Recurrent Neural Network Model

Nowadays, smart environment in the residential sector coined as ‘smart home’ catches all attention around the globe and emerged as a solution for the rising electricity demand. But, technology can only provide a methodology to deal with the usage of energy in a very deliberately manner but not at all enough, to change the way people are consuming the electrical energy in the housing sector. However, energy usage prediction plays a significant role to come up as an intelligence to the smart gird and helps in regulating the supply and demand of the electricity in housing sector. In this paper, our contribution is to predict the household energy consumption using gated rate unit recurrent neural network model. The root mean square error (RMSE) is used as a performance measure and able to attain smallest root mean square error for smart home energy data.