Advanced Metering Infrastructure (AMI) is a technological system comprising smart meters, communication networks, and data management systems that enable real-time energy consumption data collection. This data is used to analyze usage patterns, identify peak load periods, determine dynamic tariffs, and optimize energy distribution. The system also forms the basis for applying machine learning models to predict future energy consumption and optimize electricity tariff pricing. This research aims to examine how AMI can improve energy consumption data accuracy, support dynamic tariff implementation, and reduce operational costs using machine learning algorithms such as Random Forest and XGBoost. The study also explores the challenges of AMI deployment and strategies to enhance customer participation. By utilizing real-time data and machine learning predictions, AMI allows for timely tariff adjustments, encourages efficient energy consumption, and reduces peak load. The results show that AMI, combined with machine learning and dynamic tariffs, can yield cost savings for both utility companies and consumers, while contributing to environmental sustainability by reducing carbon emissions. Despite challenges, collaboration between governments, utilities, and consumers can ensure the system's success and sustainability. This study provides valuable insights into the benefits and challenges of AMI and offers recommendations for future development, making AMI a key component in building a more efficient and sustainable energy system.
Kurniyanto et al. (Wed,) studied this question.