Optimisation d’un micro réseau intelligent vert EOLIENNE/PV/BATTERIES/GROUPE ELECTROGENE connecté au réseau

Abstract

In this study, an improved energy management controller (EMC) is proposed for a hybrid system (HS), which consists of two renewable energy sources, a diesel generator, and energy storage system, batteries, in grid connected and standalone mode, The main contributions of this study are as follows : first, we developed an intelligent supervisory controller based on a recurrent neural network, namely Elman neural network (ENN), to alleviate the complexity and requirement of a rule-based structure or prior mathematical modeling. Second, we designed an energy management strategy (EMS) using Stateflow approach to extract the training and testing datasets for construction of the ENN controller. Various control strategies were applied to ensure the stability and reliability of the HS can be summarized as follows : DC bus control was achieved using Fuzzy logic control (FLC), which was applied to control the active and reactive grid powers. Second, the MPC was used to control the bidirectional converter in the battery to control the charge and discharge operations. the MPPT (Maximum power point)of the wind turbine has been achieved based on sliding mode control.The obtained results demonstrate that the proposed strategy offers the most advanced modeling features for EMCs to achieve high reliability and to minimize the computational complexity compared with classical strategies. The EMS proposed was compared with a multilayer perceptron neural network (MLPNN) strategy to evaluate their performances. The results indicated that the ENN controller was more accurate than the MLPNN. Thus, the strategy proposed is a suitable option to efficient energy management control based on a predictive model, as it is not very complex and does not require a high processing machine.