Metraipolis › archive › dc_d4ed0bec1df4
Initialization Is Critical: Advancing Federated Short-Term Load Forecasting under Load Heterogeneity via Model Initialization — arXiv:2608.27791
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27791
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:06:26.889Z
- SHA-256 of the archived text
a33dc3bd8cb13cdd7a6ca384f6c5410ec0140bc2fc87b2f814daa2f564fab2c8- Stable URL of this page
https://metraipolis.com/documento/dc_d4ed0bec1df4
How to cite
Initialization Is Critical: Advancing Federated Short-Term Load Forecasting under Load Heterogeneity via Model Initialization — arXiv:2608.27791 — arXiv (en), https://arxiv.org/abs/2608.27791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d4ed0bec1df4 (Metraipolis archive dc_d4ed0bec1df4, sha256 a33dc3bd8cb13cdd7a6ca384f6c5410ec0140bc2fc87b2f814daa2f564fab2c8)
BibTeX
@misc{dcd4ed0bec1df4,
title = {Initialization Is Critical: Advancing Federated Short-Term Load Forecasting under Load Heterogeneity via Model Initialization — arXiv:2608.27791},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27791},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d4ed0bec1df4; sha256 a33dc3bd8cb13cdd7a6ca384f6c5410ec0140bc2fc87b2f814daa2f564fab2c8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Short-term load forecasting (STLF) provides essential information for numerous applications in modern power systems. However, accurate STLF often relies on fine-grained smart-meter data from distributed users, raising increasing concerns about data privacy. Federated learning (FL) has therefore emerged as a promising privacy-preserving paradigm for STLF. Nevertheless, this paper reveals structured heterogeneity in clients' load data. Specifically, clients exhibit different responses to exogenous factors and distinct temporal load profiles, which can degrade forecasting performance in FL. To mitigate these issues, this paper studies the role of model initialization in federated STLF, and proposes two initialization strategies from global and local perspectives. For global model initialization, when auxiliary public load data are available, a pretrained initialization strategy is developed to initialize the global model before federated training, thereby reducing client drift during the training process. For local model initialization, we propose SLIAvg, a sequential local initialization strategy that promotes a more consistent training process by allowing participating clients to start from progressively adapted models within each communication round. Since the proposed strategies only modify the initialization process, they are compatible with most existing FL frameworks and privacy-enhancing techniques. Experiments on real smart-meter data with two representative forecasting architectures demonstrate that the proposed strategies effectively improve forecasting performance, as evidenced by reduced client drift, improved convergence behavior, and lower forecasting errors. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2608.27791 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T10:50:25.777Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).