Efficient Residential Electric Load Forecasting via Transfer Learning and Graph Neural Networks
Bibliographic record
Abstract
The accurate short-term electric load forecasting (STLF) is critical for the safety and economical operation of modern electric power systems. Recently, the graph neural network (GNN) has been applied in STLF and achieved impressive success via utilizing spatial dependency between residential households to improve STLF. However, GNN based forecasting models require a large amount of training data to learn reliable forecasting models. For a newly built residential neighbourhood, the historical electric load data might be insufficient for the training of GNNs. Meanwhile, we can learn GNN based models on other areas, referred to as the source domains, with abundant data. In this paper, we propose to reuse the knowledge learned on the source domains to assist the model learning for an area that only a limited amount of data is available, referred to as the target domain. Specifically, we propose an attentive transfer framework to ensemble the GNN models trained from source domains and the GNN model trained on the target domain. The proposed framework can dynamically assign weights to different GNN based models based on the input data. Extensive experiments have been conducted on real-world datasets and shown the effectiveness of the proposed framework on different scenarios.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".