Optimizing 5G Networks for Low-Latency Communication: A Reinforcement Learning-Based Approach

In the dynamic realm of Cyber-Physical Systems (CPS) and Industrial Internet of Things (IIoT) integration with 5G networks, optimizing network performance remains critical. This study investigates the application of reinforcement learning (RL) algorithms to minimize latency in 5G networks, focusing on edge selection in urban areas. Emphasizing the crucial role of latency reduction in enhancing network efficiency, the research employs real-time data processing and optimization strategies. DQN, PPO, and A2C RL algorithms are evaluated to determine the most effective approach for latency optimization. Results indicate that DQN achieves superior performance with stable convergence, underscoring the significance of algorithmic selection and hyperparameter tuning in complex network optimization tasks. This study highlights the potential for future research to explore alternative configurations aimed at further optimizing 5G network performance and promoting sustainability. The insights contribute to advancing 5G network development, particularly in latency reduction strategies within CPS and IIoT contexts.