Contribution à l’étude de la stabilité des grands réseaux électriques dans un marché de l’électricité dérégulé en présence des sources d’énergie renouvelable par la logique floue

Abstract

In recent years the demand for electric energy continues to grow, leading modern electrical networks to work near their stability limit, which increases the likely level of risk of voltage instability. In such situation, fast and accurate assessment of voltage stability is necessary in order to prevent large-scale blackouts. Due to its ability to learn offline and produce accurate results on-line, machine learning techniques (e.g., Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS)) are widely applied for on-line voltage stability monitoring. In this thesis, a new ANFIS model with optimized parameters selection via Moth-Flame Optimization (MFO) algorithm is proposed to estimate the line voltage stability index (Lmn) of power system. The input features of the hybrid ANFIS-MFO model are provided in the form of voltage magnitudes and voltage phase angles, which are assumed to be gathered from weak buses in the system. The second part of this thesis focuses on application of MFO algorithm to enhance voltage stability of power system based on the solving of Optimal Power Flow (OPF) problem incorporating wind power generators. In order to prove the effectiveness of the proposed methods, the IEEE-30 bus and the Algerian 114-bus systems are used. The obtained results demonstrate the superior performance of the proposed methods compared with other existing techniques in the literature