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%. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICDMW.2011.95 | ICDM Workshops |
Keywords | Field | DocType |
energy consumption pattern,high degree,building energy use,university campus micro-grid,energy use planning,indirect indicators,campus micro-grids,global demand,power consumption,cv-rmse error,improving energy use forecast,baseline model,smart power meter,energy conservation | Econometrics,Decision tree,Data mining,Energy conservation,Smart power,Metre,Industrial engineering,Computer science,Ranging,Energy accounting,Energy consumption,Energy informatics | Conference |
Citations | PageRank | References |
20 | 3.44 | 2 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Saima Aman | 1 | 227 | 18.13 |
Yogesh Simmhan | 2 | 1904 | 134.15 |
Viktor K. Prasanna | 3 | 7211 | 762.74 |