A constraint-based relocation framework is proposed and instantiate it for NILM as ReCo (Relocation by Coverage gain), which outperforms fixed-dwell and count-based schedules and a threshold rule using the same metric in every setting.
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.
A staged, accountable evaluation protocol that treats the evaluation of a deployed model as a measurement with declared reference levels and a quantified uncertainty and demonstrates the protocol on infrastructure-free geomagnetic localisation with smartphone-based recurrent classifiers in two real underground mines.
Benny Platte, Rico Thomanek, Christian Roschke et al.· 0 citations
Nonintrusive load monitoring (NILM) extracts appliance-level energy consumption from aggregate power measurements and is essential for smart metering systems. However, Transformer-based methods such as NILMFormer suffer from high computational complexity and distribution shifts across households, limiting edge deployme...
Lie-Quan Liang, Zhen-Yu Hao, Q. Pang et al.· IEEE Transactions on Instrum...· 0 citations
Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power t...
Xu-Dong Wang, Jia-Cheng Cui, Jun-Yu Xue et al.· 0 citations
The feedback processes to reduce the estimation discrepancy in NILM are discussed and a closed-loop learning approach is proposed that may significantly improve the accuracy of NILM, and it is applicable for practical applications.
Li-Ping Chen, Zhao-Yu Wen, Cen Li et al.· Electrical Engineering· 0 citations
Data collection using Unmanned Aerial Vehicles (UAVs) is challenging when LoRa IoT Devices (IoTDs) duty-cycle to conserve battery. Under energy constraints, a UAV must decide which IoTDs to visit, in what order, where to hover, and how many times to probe each node, while time-based data freshness decays. Tractably sol...
A UAV inspecting a live 750 kV corridor needs a LoRa uplink in which towers repeatedly cross the line of sight. The LoRaWAN adaptive data rate (ADR) infers each decision from recently decoded frames, so a sustained obstruction starves its evidence window and its spreading-factor choice drifts toward cheap transmissions...
Long-Qiang Luo, Duo Wang, Ming Chen et al.· Electronics· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026