A Deep Reinforcement Learning-Based TCP Congestion Control Algorithm: Design, Simulation, and Evaluation
By: Efe Ağlamazlar, Emirhan Eken, Harun Batur Geçici
Potential Business Impact:
Speeds up internet in crowded networks
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.
Similar Papers
A Reinforcement Learning Framework for Application-Specific TCP Congestion-Control
Networking and Internet Architecture
Helps internet traffic go faster for any app.
Learning-Based vs Human-Derived Congestion Control: An In-Depth Experimental Study
Networking and Internet Architecture
Makes internet faster and smoother for everyone.
Congestion Control System Optimization with Large Language Models
Networking and Internet Architecture
AI makes internet faster by fixing traffic jams.