ReCo optimizes when to move sensor kits for better home appliance data
ReCo: When to Relocate Sensor Kits under Deployment Constraints -- A NILM Case Study
Machine Learning
Summary
Collecting detailed energy use data in homes requires moving a limited number of sensor kits to different houses. The authors studied how to decide when to stay at the current home or move the sensor to another to gather the most useful information. They created a method called ReCo that predicts the value of data from each house and chooses to relocate sensors to maximize new insights about appliance use. Tests showed ReCo outperforms fixed schedules by focusing on more valuable homes and times, not just collecting more data.
What this means in practice
- •For energy monitoring companies: Schedule sensor deployments in homes to improve training data diversity and enhance appliance-level energy disaggregation accuracy.$Commercial implications: Improves sensor deployment efficiency in smart energy products sold to utilities and consumers.
- •For smart building teams: Plan sensor placement timing to capture varied appliance operation patterns under deployment constraints in buildings.
Tested on one dataset.
Authors
Haokun Chen, Yu Tong, Yehai Chen
Abstract
Many sensing tasks obtain training labels only by deploying instruments in the field. With a limited number of sensor kits, a collection deadline, and measurement downtime at every move, the collector must repeatedly decide whether to stay at the current site or relocate. We study this decision in non-intrusive load monitoring (NILM), which estimates the power drawn by individual appliances from a home's main meter and is trained on data from homes temporarily fitted with appliance-level sub-meters. In NILM, appliance usage varies with the appliance, season and climate, and the value of new data depends on how diverse the combinations of target operation and background load are. To address this, we propose a constraint-based relocation framework and instantiate it for NILM as ReCo (Relocation by Coverage gain). ReCo counts new operating regimes in a joint target-background feature space, forecasts each home's future gain from the data collected so far, and each night weighs the gain of staying against the gain of moving elsewhere after the downtime. In replayed deployments on the Plegma dataset under two kit counts and two downtime costs, ReCo outperforms fixed-dwell and count-based schedules and a threshold rule using the same metric in every setting. Its advantage is not explained by collecting more days alone and reflects allocating the days to more valuable homes and periods.