A Deep Reinforcement Learning-Based TCP Congestion Control Algorithm: Design, Simulation, and Evaluation
This addresses congestion control problems in modern networks for network engineers and researchers, but it is incremental as it applies an existing method (Deep Q-Networks) to a specific domain.
The paper tackles TCP congestion control by designing a deep reinforcement learning algorithm that optimizes the congestion window, resulting in significant improvements over TCP New Reno in latency and throughput with better adaptability to changing network conditions.
This paper presents a novel TCP congestion control algorithm based on Deep Reinforcement Learning. The proposed approach utilizes Deep Q-Networks to optimize the congestion window (cWnd) by observing key network parameters and taking real-time actions. The algorithm is trained and evaluated within the NS-3 network simulator using the OpenGym interface. The results demonstrate significant improvements over traditional TCP New Reno in terms of latency and throughput, with better adaptability to changing network conditions. This study emphasizes the potential of reinforcement learning techniques for solving complex congestion control problems in modern networks.