Conference paper · Book chapter
A Contextual Anomaly Detection Framework for Energy Smart Meter Data Stream
Sustainability, Department of Technology, Management and Economics, Technical University of Denmark1
Energy Systems Analysis, Sustainability, Department of Technology, Management and Economics, Technical University of Denmark2
Department of Technology, Management and Economics, Technical University of Denmark3
Sichuan University4
Southwest Jiaotong University5
Norwegian University of Science and Technology6
CITIES - Centre for IT-Intelligent Energy Systems, Centers, Technical University of Denmark7
Monitoring abnormal energy consumption is helpful for demand-side management. This paper proposes a framework for contextual anomaly detection (CAD) for residential energy consumption. This framework uses a sliding window approach and prediction-based detection method, along with the use of a concept drift method to identify the unusual energy consumption in different contextual environments.
The anomalies are determined by a statistical method with a given threshold value. The paper evaluates the framework comprehensively using a real-world data set, compares with other methods and demonstrates the effectiveness and superiority.
| Language: | English |
|---|---|
| Publisher: | Springer |
| Year: | 2020 |
| Pages: | 733-742 |
| Proceedings: | International Conference on Neural Information Processing (ICONIP 2020)International Conference on Neural Information Processing |
| Series: | Neural Information Processing - Letters and Reviews |
| ISBN: | 3030638227 , 3030638235 , 9783030638221 and 9783030638238 |
| ISSN: | 18650937 , 18650929 and 17382572 |
| Types: | Conference paper and Book chapter |
| DOI: | 10.1007/978-3-030-63823-8_83 |
| ORCIDs: | Liu, Xiufeng and Nielsen, Per Sieverts |
