UNet-NILM: A deep neural network for multi-tasks appliances state detection and power estimation in NILM

UNet-NILM proposes a multi-task U-Net inspired architecture for simultaneous appliance state detection and power estimation in non-intrusive load monitoring, achieving state-of-the-art results on UK-DALE and REFIT datasets.

nilm
deep learning
appliance detection
energy disaggregation
multi-task learning
Author

Anthony Faustine and Pereira, Lucas and Bousbiat, Hafsa and Kulkarni, Shridhar

Published

November 18, 2020

Doi
Abstract

Non-Intrusive Load Monitoring (NILM) is the task of decomposing aggregate power consumption into individual appliance-level signals. Existing deep learning approaches for NILM typically address either appliance state detection or power estimation as separate tasks, limiting their practical utility. This paper proposes UNet-NILM, a multi-task deep neural network architecture inspired by the U-Net encoder-decoder design for semantic segmentation. UNet-NILM simultaneously detects appliance ON/OFF states and estimates per-appliance active power consumption from aggregate mains readings. We evaluate the approach on the UK-DALE and REFIT datasets across five target appliances. Results show that UNet-NILM achieves state-of-the-art performance on both tasks simultaneously, demonstrating that joint optimisation of detection and estimation objectives is mutually beneficial. The proposed architecture offers a practical step toward deployable NILM systems that provide both appliance status and fine-grained energy consumption data.