Accurate short-term load forecasting is important for running power systems efficiently and managing smart grids. In this study, we present an improved Temporal Convolutional Network (TCN) model and compare eight optimization algorithms: Adam, AdaBelief, RAdam, Ranger, AdamP, NovoGrad, Adan, and SAM. We used hourly electricity load data from Denmark to test each optimizer under the same settings and with three different random seeds to ensure a fair and reliable comparison. All optimizers showed strong predictive accuracy, with root mean square error (RMSE) values between 0.03 and 0.05. Adan and AdamP had the lowest errors and were the most stable. These results show that the choice of optimizer has a big impact on how well TCN models learn and generalize. Our framework offers a solid benchmark for building adaptive and reliable forecasting systems for future smart grids.
Hmeda Musbah, Abdussalam Mohamed, Hamed H. Aly· 2026 IEEE Canadian Atlantic...· 0 citations
A novel operational condition monitor that has a data-driven predictive mechanism for determining the instant states of each tidal stream turbine is proposed, reducing in uncertainty and the association with real-time operating conditions, which enable optimal scheduling decisions.
Ali Fituri, Abdelouahed Gherbi, Hmeda Musbah· Journal of Marine Science an...· 0 citations
This paper proposes an electromagnetic (EM) environment classification framework that enables unmanned aerial vehicles (UAVs) and robotic platforms to perceive EM conditions as structured environmental states rather than unmodeled noise or isolated sensor faults. A physics-inspired, imbalanced multi-class dataset with nine EM-related features and six representative EM environment classes is generated to emulate realistic operating conditions spanning clean, disturbed, and hostile regimes. Heterogeneous classifiers—including Random Forest, Gradient Boosting, support vector machine (SVM) with radial basis function kernel, and a cost-sensitive feature-wise long short-term memory (LSTM) network—are trained using standardized features, stratified splits, and class-weighted learning to address minority yet safety-critical EM states. A stacked ensemble that fuses the probabilistic outputs of all base learners through a logistic regression meta-classifier achieves the best overall performance, with macro-averaged precision, recall, and F1-score of 0.9642, 0.9062, and 0.9319, respectively, outperforming individual models under statistically validated comparisons. The results demonstrate that multi-sensor EM awareness, implemented via ensemble learning, can provide robust and balanced classification of degraded and hostile EM environments, establishing EM perception as a key capability for resilient autonomous operation; future work will transition from synthetic to real robotic and flight data and integrate EM awareness into higher-level planning and control.
Abdussalam Mohamed, Hmeda Musbah, Hamed H. Aly· 2026 IEEE Canadian Atlantic...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
