Assessing the Effectiveness of Supervised and Semi-supervised NILM Approaches in an Industrial Context
Bibliographic record
Abstract
Non-Intrusive Load Monitoring (NILM) is a technique that aims to estimate the energy consumption and operational status of individual appliances in a building by analyzing only the aggregate power usage data. This technique plays a crucial role in demand-side management and energy conservation efforts by providing detailed information about the energy consumption patterns of individual appliances. Naturally, NILM is considered as a supervised problem, that is a Regression and Classification problem. Various Deep Neural Network models have recently been developed for NILM regression and classification tasks. However, training deep neural networks requires a significant amount of labeled data and collecting consumption data over a prolonged period exposes consumers to severe privacy risks. Hence semi-Supervised learning is also used for NILM. Furthermore, most NILM research uses datasets from the residential sector, and only a handful of research uses datasets from tertiary sectors. This paper comprehensively studies the performance of supervised and semi-supervised NILM algorithms based on a tertiary sector dataset named the GreEn-ER dataset. The semi-supervised deep learning NILM method performs classification tasks, whereas the supervised method performs classification and regression NILM tasks simultaneously. Based on the analysis, it is concluded that the presented NILM algorithms can yield satisfactory results using the tertiary sector's consumption dataset. Additionally, the ideal input parameters that facilitates the performance of the both NILM algorithms are also noted.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".