EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

ML-Based Demand Forecasting: Lessons from Temporal and Weather-Driven Energy Models

Hitesh Acharya

American Journal of AI Cyber Computing Management · 24.02.2023 · 3 (1) · 38-44

DOI: 10.64751/ajaccm.v3i1.445 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of AI Cyber Computing Management, online erschienen am 24.02.2023. Verfasst von Hitesh Acharya. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate energy demand forecasting is essential for grid stability, generation planning, market operations, and renewable integration. This paper presents a practical engineering framework for ML-based energy demand forecasting that systematically incorporates temporal decomposition and weather-driven exogenous variables. Drawing on research conducted between 2020 and 2021, we evaluate multiple approaches from classical statistical methods (ARIMA, Prophet) through gradient-boosted models (XGBoost, LightGBM) to deep learning architectures (LSTM, TCN, Temporal Fusion Transformer). The framework introduces structured weather feature engineering capturing non-linear temperature-demand relationships, wind chill effects, humidity-corrected cooling demand, and solar irradiance impacts. Experimental evaluation on hourly data from two regional grids (36 months) demonstrates that weather-augmented deep learning reduces MAPE by 18.4% compared to temporal-only baselines and 31.2% compared to statistical methods. We present failure mode analysis for extreme weather, holidays, and COVID-19 structural shifts, along with production deployment strategies including uncertainty quantification, model selection heuristics, and operational monitoring.

Zitieren

APA

Acharya, H. (2023). ML-Based Demand Forecasting: Lessons from Temporal and Weather-Driven Energy Models. American Journal of AI Cyber Computing Management, 3(1), 38-44. https://doi.org/10.64751/ajaccm.v3i1.445

Vancouver

Acharya H. ML-Based Demand Forecasting: Lessons from Temporal and Weather-Driven Energy Models. American Journal of AI Cyber Computing Management. 2023;3(1):38-44. doi:10.64751/ajaccm.v3i1.445

BibTeX
@article{Acharya2023,
  author = {Acharya, Hitesh},
  title = {ML-Based Demand Forecasting: Lessons from Temporal and Weather-Driven Energy Models},
  journal = {American Journal of AI Cyber Computing Management},
  year = {2023},
  volume = {3},
  number = {1},
  pages = {38--44},
  doi = {10.64751/ajaccm.v3i1.445}
}
Kostenlos starten →