Economic Impacts of Performance Optimization in Large-Scale Solar Farms: A Case Study Using Artificial Neural Networks in Eastern Malaysia

Abstract

This study aims to improve the performance analysis of a large-scale solar farm in Eastern Malaysia by using an Artificial Neural Network (ANN) approach. The study's goal is to optimize the solar farm's energy output by considering critical aspects such as weather, string level, shadowing, and dirt buildup. An ANN-based predictive model will be created to properly forecast energy output, allowing for exact diagnosis of possible difficulties and the implementation of corrective steps to improve overall system performance. The project will also entail the creation of an innovative monitoring and control system designed to continually track and analyze the solar farm's performance indicators. This technology will allow for real-time modifications, ensuring that the solar farm functions at maximum efficiency. The suggested technique intends not only to increase the solar farm's performance and dependability, but also to contribute to its long-term and economically feasible operation. This study aims to establish a baseline for the successful management of solar farms in the region by incorporating ANN approaches for predictive analysis and real-time monitoring, thereby minimizing environmental impact and promoting renewable energy. From the result, it is suggested that that the model's predictions closely align with the actual power output trend throughout the day, indicating the neural network's ability to capture the general pattern and variability in solar power generation.