Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring

TLDR

Understanding household appliance power consumption is crucial for energy conservation, yet it is difficult to quantify load usage at different operational states, and while smart meters provide free sensing data, the high cost of dedicated sensors limits adoption. The authors aim to develop a load disaggregation algorithm that employs a super‑state hidden Markov model and a Viterbi variant to preserve load dependencies and disaggregate multi‑state appliances efficiently. Their sparse Viterbi algorithm computes large super‑state matrices efficiently and runs in real time on inexpensive embedded processors with low sampling rates.

Abstract

Understanding how appliances in a house consume power is important when making intelligent and informed decisions about conserving energy. Appliances can turn ON and OFF either by the actions of occupants or by automatic sensing and actuation (e.g., thermostat). It is also difficult to understand how much a load consumes at any given operational state. Occupants could buy sensors that would help, but this comes at a high financial cost. Power utility companies around the world are now replacing old electro-mechanical meters with digital meters (smart meters) that have enhanced communication capabilities. These smart meters are essentially free sensors that offer an opportunity to use computation to infer what loads are running and how much each load is consuming (i.e., load disaggregation). We present a new load disaggregation algorithm that uses a super-state hidden Markov model and a new Viterbi algorithm variant which preserves dependencies between loads and can disaggregate multi-state loads, all while performing computationally efficient exact inference. Our sparse Viterbi algorithm can efficiently compute sparse matrices with a large number of super-states. Additionally, our disaggregator can run in real-time on an inexpensive embedded processor using low sampling rates.