Techno-Economic Assessment of Solar Farm Output Optimization Using Artificial Neural Networks (ANN): A Case Study from Pahang, Malaysia

Abstract

The integration of Artificial Neural Networks (ANN) into renewable energy management has become increasingly vital for enhancing operational efficiency and supporting sustainable economic development. This study investigates the application of ANN modeling for predicting and optimizing output power at the string level of a large-scale solar farm in Pahang, Malaysia. Using MATLAB-based simulations and real operational data collected from January to November 2023, the study analyzes the relationship between photovoltaic (PV) module temperature and power output to improve prediction accuracy and management decision-making. The optimized ANN model achieved a strong predictive performance with an R² of 0.95 and an RMSE of 0.10, demonstrating its capability to capture nonlinear system behavior under tropical climate conditions. The findings suggest that accurate power forecasting not only enhances technical reliability but also contributes to better resource allocation, maintenance planning, and overall economic efficiency in large-scale solar operations. This research provides a scalable framework for integrating intelligent modeling tools into renewable energy asset management strategies, aligning with broader sustainability and energy policy objectives.