Title :
Improving Energy Use Forecast for Campus Micro-grids Using Indirect Indicators
Author :
Aman, Saima ; Simmhan, Yogesh ; Prasanna, Viktor K.
Author_Institution :
Dept. of Comput. Sci., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
The rising global demand for energy is best addressed by adopting and promoting sustainable methods of power consumption. We employ an informatics approach towards forecasting the energy consumption patterns in a university campus micro-grid which can be used for energy use planning and conservation. We use novel indirect indicators of energy that are commonly available to train regression tree models that can predict campus and building energy use for coarse (daily) and fine (15-min) time intervals, utilizing 3 years of sensor data collected at 15min intervals from 170 smart power meters. We analyze the impact of individual features used in the models to identify the ones best suited for the application. Our models show a high degree of accuracy with CV-RMSE errors ranging from 7.45% to 19.32%, and a reduction in error from baseline models by up to 53%.
Keywords :
distributed power generation; energy conservation; energy consumption; power meters; CV-RMSE errors; campus micro-grids; energy conservation; energy consumption patterns forecasting; energy demand; energy use forecast; energy use planning; indirect indicators; power consumption; sensor data; smart power meters; time 15 min; time 3 year; Analytical models; Buildings; Data models; Load modeling; Mathematical model; Predictive models; Regression tree analysis; energy forecast models; energy informatics;
Conference_Titel :
Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4673-0005-6
DOI :
10.1109/ICDMW.2011.95
