Power flow management of grid Connected transformerless hybrid Renewable energy system using a cfann technique

Abstract

Due to the increased global public awareness, the necessity of environmental protection and less dependency on fossil fuels for power generation technologies becomes a vital part to satisfy the rising energy requirements. The integration of Renewable Energy Sources (RES) with the traditional power plants and hybrid power plants can help to assure a continual supply of power under diverse conditions of Power Quality (PQ). For the increasing number of RESs, new strategies for the operation and management of the electricity grid are needed to improve the reliability and quality of the power supply. Hybrid Renewable Energy Resources (HRES) encompasses different processes such as process selection, topology types, interconnection, load connection, control strategies, and schemes for protection during normal and faulty conditions. They include Photovoltaic (PV), Wind Turbine (WT), and Diesel Generator (DG). The grid topology facilitates positive changes to meet power demand and reduce environmental pollution. newlineFor grid-connected HRES systems, different control approaches have been presented in the literature. In order to address the power flow management (PFM) in grid connected HRES systems, artificial intelligence (AI) like neural networks (NN), fuzzy logic (FL) and metaheuristic optimization algorithms can be designed to improve the EMS. With this motivation, this thesis focuses on the design of PFM of grid connected HRES and grid connected transformerless HRES systems using AI techniques. The proposed research work aims to reduce system errors, improve system security, manage power and control the converters. In this aspect, the major research contribution of the thesis is discussed in the following newline