<![CDATA[This research explores the integration of Reinforcement Learning (RL) with Edge Computing to optimize real-time Internet of Things (IoT) applications. The primary problem addressed is the challenge of latency and resource constraints in IoT systems, which hinder real-time decision-making. The objective of this study is to investigate how RL can enhance the performance of Edge Computing by optimizing resource allocation and improving real-time decision-making in IoT environments. A library research method was employed, focusing on secondary data from relevant books, journals, and previous studies related to Edge Computing, RL, and IoT systems. The findings reveal that Edge Computing significantly reduces latency by processing data closer to the source, while RL optimizes resource management and decision-making. However, challenges remain in terms of computational overhead and scalability, particularly in resource-constrained edge devices. The study concludes that the integration of RL and Edge Computing offers a promising solution to optimize real-time IoT applications, but further research is needed to address scalability, security, and energy efficiency for practical implementation. This combination has the potential to revolutionize IoT systems, making them smarter, faster, and more efficient in handling complex, real-time tasks.]]>
Copyrights © 2026
