SnakeGrid: A Snake Learning-Assisted Secure and Privacy-Preserving Scheme for Smart Grid Load Forecasting in Zero-Touch Networks
Bibliographic record
Abstract
As smart grids advance toward increased automation and decentralization, they face mounting challenges in secure data sharing, privacy protection, and efficient model training—especially given the surge of sensitive, heterogeneous data from IoT-enabled components. Traditional federated learning methods often suffer from high communication costs, synchronization issues, and susceptibility to adversarial attacks. To overcome these limitations, this paper introduces a novel framework that integrates Snake Learning, Blockchain, and Zero-Touch Network technologies for scalable, trustworthy, and privacy-preserving load forecasting. The framework leverages Knowledge Distillation to handle device-level data heterogeneity and employs Krum-based aggregation to defend against model poisoning. Elliptic Curve Diffie-Hellman encryption secures data transmissions, while a consortium blockchain ensures transparency, immutability, and auditability of key events. Smart contracts further enable decentralized trust management and enforce governance policies among participants. Extensive evaluation on a real-world electricity load dataset shows the framework achieves a 39.6% reduction in Mean Squared Error, a 17.5% drop in Mean Absolute Error, and a 22.2% improvement in Root Mean Squared Error over leading baselines, while cutting communication overhead by over 66%.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".