Prediction of an Optimal Energy Usage Pattern Based on Occupant Behavior and Ambient Changes in Academic Buildings: A Case Study

Abstract

The fast economic development and population growth in developing countries is one of the main reasons for the increase in energy consumption worldwide. So, meeting up to the energy demand is becoming strenuous. This study focuses on the energy consumption pattern and prediction of an optimal energy usage pattern of an academic building due to occupant behavior and weather changes. Different energy usage pattern due to occupant behavior and ambient changes is analyzed. An optimal energy usage pattern due to different occupant behavior and weather changes is predicted. Three scenarios (All-on Scenario (current scenario), Random Scenario (proposed scenario) and Sequential Scenario (proposed scenario)) have been considered to analyze different energy usage pattern of appliances in an academic building. Different algorithms such as Exponential Smoothing, Auto-Regressive Moving Average (ARMA) and Auto-Regressive Integrated Moving Average (ARIMA) are used for the prediction. It has been observed that ARIMA has provided relatively better result than the other two. Therefore, ARIMA model is used for prediction of the energy demand for the next six years. The research findings demonstrate that the Sequential Scenario is the optimal energy usage pattern. Simulation result shows that if an academic building uses the Sequential Scenario it can save more than 5 lac taka per year. This study provides a guideline for the university authority as to how they can reduce their power consumption as well as consumption cost.