Name
Abstract | ||
|---|---|---|
In this paper, we propose an activity-enhanced load forecasting model at house-level. We focus on the impact of residents' daily activities on entire household's power consumption. The contribution of this paper is 3-fold: 1) a web-based system for collecting daily activity information in diary-style; 2) a correlation analysis between activities and power consumption and their information-theoretic relationship; 3) a personalized load forecasting study using different prediction algorithms and an activity recognition procedure as an enhancement. Both correlation and forecasting results show consistently that our collected activity information can contribute to estimate and predict the power consumption of individual households to varying degrees, in particular for 15 minutes ahead load forecasting. An extended forecasting model with an online activity recognition component can further reduce the forecasting error. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/ISC2.2015.7366172 | 2015 IEEE First International Smart Cities Conference (ISC2) |
Keywords | Field | DocType |
personalized load forecasting,activity information,activity-enhanced load forecasting model,power consumption,information-theoretic relationship,activity recognition procedure,online activity recognition component | Data mining,Random variable,Activity recognition,Function approximation,Computer science,Load forecasting,Correlation,Artificial intelligence,Probabilistic forecasting,Mutual information,Machine learning,Power consumption | Conference |
Citations | PageRank | References |
1 | 0.37 | 5 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yong Ding | 1 | 36 | 7.29 |
| Martin Alexander Neumann | 2 | 17 | 5.41 |
| erwin stamm | 3 | 1 | 0.37 |
| M. Beigl | 4 | 2034 | 311.09 |
| Sozo Inoue | 5 | 176 | 58.17 |
| xincheng pan | 6 | 1 | 0.37 |