Indonesia has an enormous geographical area with a wide range of energy resources. However, due to the variations in power demand and population density of the different segments of the country, power networks based on centralized energy generation sources are not efficient or ideal in many cases. Therefore, distributed energy resources such as Renewable Energy Resources (RES) can be implemented to provide low- cost energy solutions for localized power production. However, highly coordinated, real-time capable energy storage systems are required as localized energy production often relies upon variable, fluctuating power sources, which impacts the grid performance and increases the difficulty in maintaining the stability and power quality of the system. Therefore, energy storage systems such as Battery Energy Storage Systems (BESS) have a crucial role in the localized selfsufficient power production schemes as without them, localized energy systems would fail to provide stable and reliable power. Legacy battery technologies such as lead-acid or lead-gel battery technologies are attractive due to their low cost, but the typical charging/discharging cycle profile of energy storage systems would curtail the long-term durability of such legacy battery technologies. Many factors such as temperature, charging/discharging cycles, and other time-dependent variables affect the performance of the storage systems, and therefore, enlistment, prioritization, and optimization of these variables can make it possible to obtain satisfactory performance levels alongside longer service life from BESS utilizing legacy battery technologies. In the field of power and energy systems optimizations that include complex computing, the implementation of Machine Learning (ML) and Artificial Intelligence (AI) has exhibited significant contributions in recent times. Therefore, we propose implementing ML and AI to optimize the performance of the BESS, which will lead to low-cost, independent energy system solutions for remote or rural applications

Renewable Energy Systems, Battery Charging Optimizations, Machine Learning

• Prof. Bens Pardamean, B.Sc., M.Sc., Ph.D

• Prof. Fergyanto E. Gunawan, Dr. Eng

• Safarudin Gazali Herawan, S.T., M.Eng., PhD

• Christian Harito, S.T., Ph.D

• Dr. Muhammad Asrol, S.T.P., M.Si.

• Anak Agung Ngurah Perwira Redi, S.Kom., M.B.A, Ph.D.