Scholarlink

<p>This study addresses the challenge of dynamic load forecasting in Morocco by leveraging advanced machine learning techniques. Using state-of-the-art models such as PLCNet LSTM and random forest with walk-forward validation, this research aims to enhance forecasting precision while addressing gaps in literature concerning urban energy systems. The models were trained and validated on a robust dataset collected from smart meters in Moroccan cities, including Laayoune, Boujdour, Marrakech, and Foum Eloued, ensuring quality and preprocessing transparency. By optimizing hyperparameters and evaluating multiple algorithms, the study highlights Random Forest’s robustness in specific zones and PLCNet LSTM’s capability to capture intricate nonlinear data patterns. The findings emphasize theoretical contributions to load forecasting methodologies, practical managerial strategies for urban energy management, and policy recommendations to foster sustainable energy practices in Morocco.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-driven load forecasting for urban energy optimization in morocco

  • 期刊论文

  • 发表日期：

    2025年4月18日

查看全文
  • Mouad Bensalah,
  • Abdellatif Hair

摘要

This study addresses the challenge of dynamic load forecasting in Morocco by leveraging advanced machine learning techniques. Using state-of-the-art models such as PLCNet LSTM and random forest with walk-forward validation, this research aims to enhance forecasting precision while addressing gaps in literature concerning urban energy systems. The models were trained and validated on a robust dataset collected from smart meters in Moroccan cities, including Laayoune, Boujdour, Marrakech, and Foum Eloued, ensuring quality and preprocessing transparency. By optimizing hyperparameters and evaluating multiple algorithms, the study highlights Random Forest’s robustness in specific zones and PLCNet LSTM’s capability to capture intricate nonlinear data patterns. The findings emphasize theoretical contributions to load forecasting methodologies, practical managerial strategies for urban energy management, and policy recommendations to foster sustainable energy practices in Morocco.