Event-Detection Algorithms for Low Sampling Nonintrusive Load Monitoring Systems Based on Low Complexity Statistical Features

• Published in: IEEE transactions on instrumentation and measurement Vol. 69; no. 3; pp. 751 - 759
• Main Authors: Rehman, Attique Ur, Lie, Tek Tjing, Valles, Brice, Tito, Shafiqur Rahman
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Complexity; Computer simulation; Data acquisition; Energy conservation; Energy monitoring; Event detection; Feature extraction; Home appliances; Load modeling; Microsoft Windows; Monitoring; nonintrusive load monitoring (NILM); Sensitivity analysis; smart grids (SGs); Steady-state
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2019.2904351

One of the key techniques toward energy efficiency and conservation is nonintrusive load monitoring (NILM) which lies in the domain of energy monitoring. Event detection is a core component of event-based NILM systems. This paper proposes two new low-complexity and computationally fast algorithms that detect the variations of load data and return the time occurrences of the corresponding events. The proposed algorithms are based on the phenomenon of a sliding window (SW) that tracks the statistical features of the acquired aggregated load data. The performance of the proposed algorithms is evaluated using real-world data and a comparative analysis has been carried out with one of the recently proposed event detection algorithms. Based on the simulations and sensitivity analysis, it is shown that the proposed algorithm can provide the results of up to 93% and 88% in terms of recall and precision, respectively.