<![CDATA[The Sun tracker consists of two energy types: proportional energy and operational energy. Proportional energy refers to the clean energy stored in the battery, while operational energy is used to support the mechanical performance of the sun tracking system. One of the main challenges in such systems is the high operational energy consumption, which can reduce the overall system efficiency. This study aims to develop a model to predict the proportional energy resulting from a dual-axis sun-tracker controller by implementing the Adaptive Neuro-Fuzzy Inference System (ANFIS). The method comprises analyzing the performance of the dual-axis sun tracker system and modeling the ANFIS. The performance of the dual-axis was investigated by observing the limitation of servo motor movement based on the difference in LDR sensor readings using threshold values of 50, 100, and 150. The ANFIS modeling was conducted by testing 24 configurations of membership functions to determine the most optimal structure. The results of the threshold value analysis show that a threshold value of 100 provides the best efficiency in generating proportional movement and energy. While modeling the ANFIS, the highest proportional energy was obtained using the Generalized Bell (belief) membership function type with a 9×9 configuration, yielding the lowest error value of 0.011692. Model validation using external test data showed an RMSE of 0.1128 and an MSE of 0.0127, indicating high predictive accuracy and good generalization capability. Implementing ANFIS control on the analyzed dual-axis PV system demonstrated an average increase in the proportional energy efficiency of 3%, from 90% to 93%. The findings indicate the effectiveness of ANFIS in enhancing the performance of the sun tracking system by adaptively adjusting to variations in light intensity.]]>
Copyrights © 2026
