Abderaouf Bahi

Abderaouf Bahi, Amel Ourici, Ibtissem Gasmi et al.

Accurate forecasting of renewable energy generation is essential for efficient grid management and sustainable power planning. However, traditional supervised models often require access to labeled data from the target site, which may be unavailable due to privacy, cost, or logistical constraints. In this work, we propose FreeGNN, a Continual Source-Free Graph Domain Adaptation framework that enables adaptive forecasting on unseen renewable energy sites without requiring source data or target labels. Our approach integrates a spatio-temporal Graph Neural Network (GNN) backbone with a teacher--student strategy, a memory replay mechanism to mitigate catastrophic forgetting, graph-based regularization to preserve spatial correlations, and a drift-aware weighting scheme to dynamically adjust adaptation strength during streaming updates. This combination allows the model to continuously adapt to non-stationary environmental conditions while maintaining robustness and stability. We conduct extensive experiments on three real-world datasets: GEFCom2012, Solar PV, and Wind SCADA, encompassing multiple sites, temporal resolutions, and meteorological features. The ablation study confirms that each component memory, graph regularization, drift-aware adaptation, and teacher--student strategy contributes significantly to overall performance. The experiments show that FreeGNN achieves an MAE of 5.237 and an RMSE of 7.123 on the GEFCom dataset, an MAE of 1.107 and an RMSE of 1.512 on the Solar PV dataset, and an MAE of 0.382 and an RMSE of 0.523 on the Wind SCADA dataset. These results demonstrate its ability to achieve accurate and robust forecasts in a source-free, continual learning setting, highlighting its potential for real-world deployment in adaptive renewable energy systems. For reproducibility, implementation details are available at: https://github.com/AraoufBh/FreeGNN.

Abderaouf Bahi, Mourad Boughaba, Ibtissem Gasmi et al.

Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing multi-domain approaches frequently fail to isolate the distinct contribution of cross-domain interactions from those arising within individual domains, limiting their ability to build rich and transferable user representations. In this work, we propose MOSAIC, a Multi-Domain Orthogonal Session Adaptive Intent Capture framework that explicitly factorizes user preferences into three orthogonal components: domain-specific, domain-common, and cross-sequence-exclusive representations. Our approach employs a triple-encoder architecture, where each encoder is dedicated to one preference type, enforced through domain masking objectives and adversarial training via a gradient reversal layer. Representational alignment and mutual independence constraints are jointly optimized to ensure clean preference separation. Additionally, a dynamic gating mechanism modulates the relative contribution of each component at every timestep, yielding a unified and temporally adaptive session-level user representation. We conduct extensive experiments on two large-scale real-world benchmarks spanning multiple domains and interaction types. The ablation study validates that each component domain-specific encoding, domain-common modeling, cross-sequence representation, and dynamic gating contributes meaningfully to the overall performance. Experimental results demonstrate that MOSAIC consistently outperforms state-of-the-art baselines in recommendation accuracy, while simultaneously providing interpretable insights into the interplay between domain-specific and cross-domain preference signals. These findings highlight the potential of orthogonal preference decomposition as a principled strategy for next-generation multi-domain recommender systems.

Abderaouf Bahi, Ibtissem Gasmi

This paper examines the deployment of seven different neural network architectures CNN, RNN, GNN, Autoencoder, Transformer, NCF, and Siamese Networks on three distinct datasets: Retail E-commerce, Amazon Products, and Netflix Prize. It evaluates their effectiveness through metrics such as accuracy, recall, F1-score, and diversity in recommendations. The results demonstrate that GNNs are particularly adept at managing complex item relationships in e-commerce environments, whereas RNNs are effective in capturing the temporal dynamics that are essential for platforms such as Netflix.. Siamese Networks are emphasized for their contribution to the diversification of recommendations, particularly in retail settings. Despite their benefits, issues like computational demands, reliance on extensive data, and the challenge of balancing accurate and diverse recommendations are addressed. The study seeks to inform the advancement of recommendation systems by suggesting hybrid methods that merge the strengths of various models to better satisfy user preferences and accommodate the evolving demands of contemporary digital platforms.

Abderaouf Bahi, Amel Ourici

This paper explores the implementation of a Deep Reinforcement Learning (DRL)-optimized energy management system for e-commerce data centers, aimed at enhancing energy efficiency, cost-effectiveness, and environmental sustainability. The proposed system leverages DRL algorithms to dynamically manage the integration of renewable energy sources, energy storage, and grid power, adapting to fluctuating energy availability in real time. The study demonstrates that the DRL-optimized system achieves a 38\% reduction in energy costs, significantly outperforming traditional Reinforcement Learning (RL) methods (28\%) and heuristic approaches (22\%). Additionally, it maintains a low SLA violation rate of 1.5\%, compared to 3.0\% for RL and 4.8\% for heuristic methods. The DRL-optimized approach also results in an 82\% improvement in energy efficiency, surpassing other methods, and a 45\% reduction in carbon emissions, making it the most environmentally friendly solution. The system's cumulative reward of 950 reflects its superior performance in balancing multiple objectives. Through rigorous testing and ablation studies, the paper validates the effectiveness of the DRL model's architecture and parameters, offering a robust solution for energy management in data centers. The findings highlight the potential of DRL in advancing energy optimization strategies and addressing sustainability challenges.

Moutaz Bellah Bentrad, Adel Ghoggal, Tahar Bahi et al.

The diagnosis of induction machines has traditionally relied on model-based methods that require the development of complex dynamic models, making them difficult to implement and computationally expensive. To overcome these limitations, this paper proposes a model-free approach using Graph Neural Networks (GNNs) for fault diagnosis in induction machines. The focus is on detecting multiple fault types -- including eccentricity, bearing defects, and broken rotor bars -- under varying severity levels and load conditions. Unlike traditional approaches, raw current and vibration signals are used as direct inputs, eliminating the need for signal preprocessing or manual feature extraction. The proposed GNN-ASE model automatically learns and extracts relevant features from raw inputs, leveraging the graph structure to capture complex relationships between signal types and fault patterns. It is evaluated for both individual fault detection and multi-class classification of combined fault conditions. Experimental results demonstrate the effectiveness of the proposed model, achieving 92.5\% accuracy for eccentricity defects, 91.2\% for bearing faults, and 93.1\% for broken rotor bar detection. These findings highlight the model's robustness and generalization capability across different operational scenarios. The proposed GNN-based framework offers a lightweight yet powerful solution that simplifies implementation while maintaining high diagnostic performance. It stands as a promising alternative to conventional model-based diagnostic techniques for real-world induction machine monitoring and predictive maintenance.

Abderaouf Bahi, Amel Ourici

This paper investigates the feasibility of human mobility in The Line, a proposed 170-kilometer linear smart city in NEOM, Saudi Arabia. To assess whether citizens can move freely within this unprecedented urban topology, we develop a hybrid simulation framework that integrates agent-based modeling, reinforcement learning, supervised learning, and graph neural networks. The simulation captures multi-modal transportation behaviors across 50 vertical levels and varying density scenarios using both synthetic data and real-world traces from high-density cities. Our experiments reveal that with the full AI-integrated architecture, agents achieved an average commute time of 7.8 to 8.4 minutes, a satisfaction rate exceeding 89 percent, and a reachability index of over 91 percent, even during peak congestion periods. Ablation studies confirmed that the removal of intelligent modules such as reinforcement learning or graph neural networks significantly degrades performance, with commute times increasing by up to 85 percent and reachability falling below 70 percent. Environmental modeling further demonstrated low energy consumption and minimal CO2 emissions when electric modes are prioritized. The findings suggest that freedom of movement is not only conceptually achievable in The Line, but also operationally realistic if supported by adaptive AI systems, sustainable infrastructure, and real-time feedback loops.