Publication
Pattern-Based Contextual Anomaly Detection in HVAC Systems
Mohsin Munir; Steffen Erkel; Andreas Dengel; Sheraz Ahmed
In: 2017 IEEE International Conference on Data Mining Workshops. IEEE International Conference on Data Mining Workshops (ICDMW-2017), November 18-21, New Orleans, LA, USA, Pages 1066-1073, ISBN 978-1-5386-3800-2, IEEE, 2017.
Abstract
This paper presents detailed anomaly detection evaluation on operational time-series data of Internet of Things (IoT) based household devices in general and Heating, Ventilation and Air Conditioning (HVAC) systems in specific. Due to the number of issues observed during evaluation of widely used distance-based, statistical-based, and cluster-based anomaly detection techniques, we also present a pattern-based approach for anomaly detection in HVAC time-series data. The usage and number of IoT based HVAC systems are enormously increasing and will have a major share in IoT based household devices in the near future. The operational and usage log of these devices contains different sensor values logged with time, containing normal data points, and long-term anomalies. The state-of-the-art methods for anomaly detection are unable to detect these long-term anomalies, which reflect the deteriorating effect of a sensor. The presented approach overcomes this problem by building a knowledge base of long/short -term patterns based on normal data points which keep growing over the time. In addition to the detected anomalies and in contrast to the existing methods, the presented method gives meaningful anomaly score for a number of HVAC systems. We evaluate the presented approach on real operational data, collected over the period of 2.5 years. Evaluation results show that the presented approach outperforms the state-of-the-art methods for anomaly detection with the area under the curve (AUC) value of 99.4%. Discord detection results of the proposed technique on another dataset from a different domain show the generic and adaptive nature of our technique.