AI based Modeling & Optimization of IRC-Enhanced Solar GT Trigeneration Systems using ANN-Evolutionary Algorithm

A trigeneration system is a unified energy framework that concurrently yields three modes of energy: electricity, heating, and cooling. Solar-based Gas Turbine (GT) trigeneration systems, particularly those incorporating intercooling and reheating, are attracting significant attention due to their enhanced performance. In the present study, solar-based GT trigeneration cycle incorporating intercooling and reheating (SBIRGT) is investigated. The SBIRGT comprises a parabolic trough collector (PTC) field, pneumatic compressor, ignition chamber, gas turbine, and a single-effect LiBr absorption cooling system. Two critical productivity indicators—power output and energy efficiency—have been analyzed. Artificial Neural Networks (ANNs) were employed to develop predictive models for these outputs. To determine the optimal values for both responses, widely recognized nature-inspired optimization techniques were applied, including Rao’s sequential optimization methods and Differential Evolution (DE). Among the four strategies explored, the most effective approach has been identified and recommended under the purview of this study.