(Université M'Hamed Bougara Boumerdès : Faculté de Technologie, 2025) Faradji, Mohamed; Layadi, Toufik Madani(Directeur de thèse)
The transition toward smart grids demands sophisticated optimization techniques to
enhance efficiency, stability, and demand responsiveness. This thesis contributes to
smart grid optimization by leveraging advanced optimization and computational
intelligence methods, including Particle Swarm Optimization (PSO), Artificial
Neural Networks (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS).
The study focuses on two critical areas: demand-side management (DSM) for peak
load reduction and load frequency control (LFC) for grid stability. A hybrid PSO-
ANN framework is proposed for DSM to predict and optimize energy consumption
patterns, while ANFIS-based controllers are designed for robust LFC under dynamic
load conditions. Simulation results demonstrate superior performance compared to
conventional methods, with significant improvements in demand response accuracy
and frequency regulation. The findings underscore the potential of AI-driven
optimization in advancing smart grid resilience and operational efficiency
