Author : Miss. Juveria Khan and Prof. Dr. Pramod Patil

In the last few years, the expanding energy utilization has imposed the development of solutions to save electricity. One of these arrangements has been, generating an energy saving policies which is based on forecasting of energy in smart environments. The main idea behind building this model is, the residences are instrumented with smart meters to monitor energy consumption and can be managed accordingly. Recent prediction models focuses on performance of the prediction, but for developing an efficient system, it is required to predict energy demand taking into account various conditions. In this paper we propose a model for predicting energy demand according to various situations using advanced machine learning framework. In this model we have an projector that defines proper state for a particular situation and using that defined state a predictor forecasts the energy demand. The proposed model generates utilization predictions for every 2 hours. Demonstrating the electric power consumption data for 5 years, the proposed system achieves a better performance.

Keywords: Electric energy; energy management system; energy consumption forecasting; energy prediction; machine learning.