Non-Intrusive Load Monitoring: A Computationally Efficient Hybrid Event Detection Algorithm

Abstract

Non-intrusive load monitoring is widely appreciated technique for managing segregated-level energy-efficiency. Event detection algorithms play a crucial role in non-intrusive load monitoring applications. This paper proposes a new unsupervised hybrid event detection algorithm that tracks the difference and standard deviation of the aggregated load data. To evaluate the performance of the proposed algorithm, simulations are carried out on 24 hours of real-world load data from a single household having diverse load elements. This paper also assessed the sensitivity of the input parameter on the performance of the proposed event detector. The proposed hybrid event detection algorithm performed well and accomplished highly promising results.