ISSN :2582-9793
  • Subscribe

    • Joint Forecasting of Residential Energy Consumption and Solar Generation Using Advanced AI Architectures

    Original Research (Published On: 10-Mar-2026 )
    DOI : https://doi.org/10.54364/AAIML.2026.62286

    Milia Habib, Majd Al Ayoubi, Mohamad Kanaan and Zaher Merhi

    Adv. Artif. Intell. Mach. Learn., XX (XX):-

    1. Milia Habib: Department of Computer & Communications EngineeringLebanese International University

    2. Majd Al Ayoubi: Department of Computer & Communications Engineering, Lebanese International University

    3. Mohamad Kanaan: Department of Electrical Engineering Lebanese International University Beirut, Lebanon

    4. Zaher Merhi: Department of Computer & Communications Engineering Lebanese International University Beirut, Lebanon

    Download PDF Here

    DOI: 10.54364/AAIML.2026.62286

    Article History: Received on: 15-Dec-25, Accepted on: 03-Mar-26, Published on: 10-Mar-26

    Corresponding Author: Milia Habib

    Email: milia.habib@liu.edu.lb

    Citation: Milia Habib, et al. Joint Forecasting of Residential Energy Consumption and Solar Generation Using Advanced AI Architectures. Advances in Artificial Intelligence and Machine Learning. 2026. (Ahead of Print). https://dx.doi.org/10.54364/AAIML.2026.62286


    Abstract

        

    Smart homes, powered by advances in Artificial Intelligence (AI), offer improved convenience, energy efficiency, and personalized living experiences. This paper presents a machine learning–based Smart Home Energy Management System designed to predict both household electricity consumption and rooftop solar power generation. It incorporates a structured pipeline for data preprocessing and feature extraction, enriched with contextual variables such as weather conditions and calendar information. sequence-to-sequence learning using convolutional neural networks (CNNs) and long short-term memory (LSTM) architectures is implemented. For comparative evaluation, a robust tree-based model serves as a baseline. Model performance is evaluated using standard metrics, including MAE, RMSE, and R2 along with peak oriented metrics to assess ramp rate and peak fidelity. Additionally, a lightweight web front-end based is developed to provide real-time inference and interactive visualization for decision support. The results show that LSTM achieved the highest accuracy in global metrics and was therefore adopted as the system’s forecasting backbone.

    Statistics

       Article View: 10
       PDF Downloaded: 0