Optimizing　photovoltaic　(PV)　cell/module　modeling　is　key　to　advancing　solar　power　and　achieving　net　zero　carbon　goals.　Challenges　in　accurate　PV　parameter　estimation　arise　from　environmental　variability,　aging,　and　incomplete　manufacturer　data.　Traditional　Arithmetic　Optimization　Algorithm　(AOA)　often　struggles　with　premature　convergence　due　to　imbalanced　exploration　and　exploitation.　This　paper　presents　an　enhanced　AOA　variant,　incorporating　chaotic　maps　and　oppositional-based　learning　to　better　balance　the　optimization　process.　Our　extensive　simulations　show　that　this　improved　AOA　variant　significantly　enhances　accuracy　and　robustness　in　PV　cell/module　parameter　estimation　compared　to　the　conventional　method.　©　The　2024　International　Conference　on　Artificial　Life　and　Robotics　(ICAROB2024).