Individual renewable energy systems harnessed renewable energy sources such as solar, wind, hydro, tidal, geothermal, and biomass. These systems are individually not capable of meeting continuous energy demand due to intermittent sources. Therefore, two or more systems are combined to form hybrid renewable energy systems (HRES). This work focuses on HRES control operations based on predictive approaches to enhance the HRES system’s performance for stand-alone applications. In the first part, we have proposed a module temperature control system consisting of an adaptive model-predictive controller that manipulates water coolant flow rate on the module. The proposed control scheme results in a maximum improvement in the PV system efficiency of nearly 10 %. In the second part, we have addressed the issue of sensor failure by deploying a predictive model (solar irradiance, ambient temperature and wind speed) that provides an uninterrupted control and a preventive approach to reduce the possibility of system failure. In the third part, we develop data-driven models for wind turbine (WT) and reversible fuel cell (RFC) systems using a statistical approach. The models are compared with their true system and obtain a nearly similar response. These models are integrated with a photovoltaic (PV) system to reduce the effect of intermittent power generation / consumption in the HRES such that the reliability of the HRES is increased. Subsequently, we develop a predictive control scheme for HRES that successfully manipulates the RFC inlet flow rate to meet the load demand. However, HRES does not meet sustainability due to the less hydrogen generation by the RFC than the usage. Thus, the optimal size of PV and WT is determined based on uniform hydrogen generation and usage by the RFC for achieving the self-sustainability of the stand-alone HRES.