Adaptive and computational intelligence control of distributed energy sources and microgrids

The expanding electrification of domestic and industrial loads, as well as the penetration of renewable energy sources (such as wind, solar, fuel cell, and hydroelectric power plants), as well as transportation (electric vehicles), provide challenges to today's electrical power distribution systems. The intermittent nature of power demands and renewable energy sources make a complex distribution power system. The objective of this thesis is to develop artificial intelligence-based, robust, and adaptive control systems for real-time control of renewable energy sources (photovoltaic solar panels and fuel cell) and microgrids. A new adaptive neural fuzzy maximum power tracking technique for photovoltaic solar panels is designed with B-spline functions. With B-spline functions, the performance of photovoltaic solar panels is significantly improved in terms of conversion efficiency and dynamic response. The conversion efficiency of photovoltaic solar panels is increased by around 17.14%. Another important contribution of this thesis is the control of the solid oxide fuel cell. An adaptive wavelets control is developed for the solid oxide fuel cell system. The proposed controller provides better performance in terms of output voltage, fuel utilization, fuel flow, conversion efficiency, and dynamic response as compared to conventional controllers. The conversion efficiency of solid oxide fuel cell is increased by around 5.04% with the proposed controller. Finally, an adaptive neural fuzzy based control technique is designed for energy management in microgrids. The proposed energy management system managed power flow and power sharing among microgrid system's components to meet the load requirements for 24 hours. Consequently, the maximum power tracking performance and the performance of photovoltaic solar panels, and fuel cells are increased with the solutions developed in this thesis, as well as efficiency under the same operating conditions.