Scalable regression tree learning on Hadoop using OpenPlanet
Proceedings of third international workshop on MapReduce and its Applications Date
Coordinated clustering algorithms to support charging infrastructure design for electric vehicles
Proceedings of the ACM SIGKDD International Workshop on Urban Computing
Incorporating semantic knowledge into dynamic data processing for smart power grids
ISWC'12 Proceedings of the 11th international conference on The Semantic Web - Volume Part II
Toward data-driven demand-response optimization in a campus microgrid
Proceedings of the Third ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Buildings
Impact assessment of smart meter grouping on the accuracy of forecasting algorithms
Proceedings of the 28th Annual ACM Symposium on Applied Computing
Hi-index | 0.01 |
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%.