Deep Reinforcement Learning-Assisted Federated Learning for Robust Short-Term Load Forecasting in Electricity Wholesale Markets
Bibliographic record
Abstract
Short-term load forecasting (STLF) plays a pivotal role in operational efficiency of power plants. Leveraging data from utility companies for STLF in a wholesale market presents challenges. Notably, data sharing reluctance from utility companies, driven by privacy considerations, limits the availability of valuable forecasting information. Concurrently, due to the growing reliance on information and communication technologies, data integrity attacks (DIAs) and communication noise are emerging as a significant concern, which is largely overlooked in existing research. We propose an innovative approach combining deep reinforcement learning (DRL) with federated learning (FL) to construct a robust STLF model that meets privacy constraints and operates efficiently. By employing FL, we facilitate collaboration between the power plant and multiple utility companies to generate a STLF model for the power plant, circumventing the need for direct access to raw data from utility companies, thereby preserving data privacy. To counteract model degradation induced by DIAs and noise in communication channels, we incorporate DRL into our methodology. Simulation outcomes affirm the efficacy of our proposed approach, demonstrating its capacity to deliver accurate and resilient STLF for power plants, even in the presence of DIAs and communication noise.
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".