Implementation of Machine Learning Algorithm for predicting user behavior and smart energy management

A greater interest arises in reducing our energy needs as electrical energy becomes more costly and the environmental effects of fossils become more deceptive. Objectives to find new ways of making our everyday lives more energy efficient have now became an essential part of the tussle to sustain our present quality of living. This project targets domestic usage which has a more direct approach in changing the way we consume energy. In this project we take up House Hold Loads as the application but this project can also be applied for large industrial loads. Smart energy metering and normalized energy data on load usage are one of the major goal setters for the future smart grid and improved energy efficiency in smart homes. Load Monitoring (LM) is essential for energy management and cost fixing. To obtain appliance-specific energy consumption statistics that can further be used to formulate load scheduling strategies for optimal energy utilization, disaggregation of Load is essential. Non-Intrusive Load Monitoring (NILM) is an alternative and best method for Load Disaggregation, as it can distinguish devices from the aggregated data measured at only a centralized location. In this paper we provide an experimental idea of using NILM technology by actually implementing sub-metering system for each load to forecast its futuristic development on the basis of bin packing algorithms and feedback systems controlled by the Machine Learning Algorithm to end up with an energy efficient smart home and smart grids.