A novel approach for routing optimization in 5G optical networks

Abstract Optical Networks form the core network of 5G networks. Efficient routing implementation is essential for optimizing the 5G optical core network performance. A new approach to routing is proposed through an RL agent, which is an extended version of the TD3 algorithm with features such as averaging of losses, Prioritized Experience Replay (PER), and annealing of priorities to enhance the trade-off between exploration and exploitation in RL. The approach is validated using experimental evaluation with an OMNeT++ simulator to check the effectiveness of the proposed algorithm in optimizing the latency, throughput, and energy in network routing. It significantly outperforms existing agents based on Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO), and State-Action-Rewards-State-Action (SARSA) algorithms. A detailed comparison with the existing algorithms demonstrates that there was a reduction in latency and energy and increase in throughput. The proposed algorithm outperformed DDPG, PPO, and SARSA algorithms, achieving a 76 % reduction in network delays, a 2.6 % reduction in energy consumption, and 1.8 % improvement in throughput and thus contributes to the ongoing efforts of addressing the routing and energy challenges in dynamic 5G Optical networks.