MACHINE LEARNING-DRIVEN ENHANCEMENT OF CONCENTRATED SOLAR POWER SYSTEMS: A HYBRID ANN AND GA APPROACH

Abstract

The imperative for efficient and sustainable energy systems has spotlighted the need to enhance the thermal performance of Concentrated Solar Power (CSP) technologies. This paper introduces a novel AI-powered control architecture designed to optimize the thermal dynamics of parabolic trough CSP collectors under fluctuating environmental conditions. The framework incorporates a hybrid model combining Artificial Neural Networks (ANN) with Genetic Algorithms (GA) to predict, regulate, and adapt system parameters such as fluid flow rate and receiver temperature. Real-time data-driven optimization enables superior heat exchange performance, reduced thermal losses, and enhanced responsiveness. Simulation outcomes demonstrate a substantial improvement in thermal efficiency, energy yield, and system adaptability compared to traditional fixed-control schemes. The proposed methodology exemplifies the transformative role of AI in fostering resilient, intelligent, and high-performance solar thermal infrastructures suitable for deployment in hot climate zones.