- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper proposes OFAN, a conditional NILM framework that appends an appliance embedding to the input of a transformer backbone so that one shared model can disaggregate multiple appliances. OFAN is instantiated on BERT4NILM and NILMformer and evaluated on UK-DALE and REFIT with five seeds.OFAN is literally a single conditioned model plus a small embedding table, reducing stored parameters for five appliances from 9.7M to about 1.9M for BERT4NILM.
Critical strengths
- This paper presents an extensive empirical study. It separates the effects of the conditioning token, joint training, and query type, and uses paired confidence intervals over five seeds.
- OFAN shows useful transfer learning analysis. The zero-shot transfer experiment, conditioning on the training signature without target-home data, is a practically interesting result for the NILM community.
Critical weaknesses
- This paper shows limited methodological novelty. NILM is a mature field, and appending a learned embedding to a transformer input is a standard conditioning mechanism closely related to FiLM and QueryNILM. The paper does not introduce a new architecture or learning algorithm.
- The evaluation is too narrow to validate scalability. The main experiments cover only four or five appliance categories from two UK datasets, with one held-out test house for UK-DALE and two for REFIT.
- The deployment motivation is storage on constrained smart meters, but the paper counts parameters only and does not measure on-device memory or latency, which may be unacceptable in deployment.
Questions for authors
- Given QueryNILM’s substantially smaller parameter count and comparable or better index-query performance on REFIT, what practical advantage does OFAN offer?