TCP-QNCC: congestion control algorithm based on deep Q-network
Explore this paper's citation graph
Summary
This paper model network congestion control as a Markov decision process and optimize congestion control strategies using a deep Q network in deep reinforcement learning, proposing a congestion control algorithm, QNCC, that is purely data-driven and does not rely on any assumptions.
- Type
- article
- Published
- 2023-10-16
- Cited by
- 1
- References
- 11
- OpenAlex
- https://openalex.org/W4387664165
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:264170863
Keywords
Network congestion, Network traffic control, Computer science, Computer network, Packet loss
References
- CUBIC: a new TCP-friendly high-speed TCP variant
- Binary increase congestion control (BIC) for fast long-distance networks
- TCP Vegas: new techniques for congestion detection and avoidance
- Deep Q-learning From Demonstrations
- QTCP: Adaptive Congestion Control with Reinforcement Learning
- Improving TCP Congestion Control with Machine Intelligence
- Pantheon: the training ground for Internet congestion-control research
- The CoCo-Beholder: Enabling Comprehensive Evaluation of Congestion Control Algorithms
- OpenAI Gym
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- 2017 USENIX Annual Technical Conference (USENIX ATC'17)
Cited by
No citing papers recorded for this paper.
Related papers
- A Review on Active Queue Management Techniques of Congestion Control
- Simulation and Application of Wireless Network Congestion Control
- Early Rate Adaptation Protocol in DiffServ for Multimedia Applications
- A Wireless Network Congestion Control Mechanism based on Price Regulation
- Analysis of Congestion Control Strategy for Wireless Network
- A survey on congestion control mechanisms in packet switch networks
- QoS-aware end-to-end adaptive congestion detection and control for VoIP
- Congestion Control Protocols in Wireless Sensor Networks: a comprehensive Survey
- Comparative Study on New AQM Mechanisms for Congestion Control