Towards Adaptive Packet Scheduler with Deep-Q Reinforcement Learning

The traditional way to design a packet scheduler is usually based on the prior knowledge of networking environments. With advanced networking technologies, we propose a Deep-Q (DQ) learning framework for packet scheduler to take advantage of more available information. The packet scheduler optimizes the application-specific quality of service (QoS) requirements, and adapt to the changing network environment. The DQ framework integrates the online Q-learning algorithm and a deep neural network, making it applicable to problems of large size. Without any prior training or network traffic models, the DQ-based scheduler progressively learns a good policy in real-time, based directly on the available observations.

• Publication year

  2020

• Venue

  International Conference on Computing, Networking and Communications

• Publication date

  2020-02-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICNC47757.2020.9049807
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• ReLeS: A Neural Adaptive Multipath Scheduler based on Deep Reinforcement Learning

  2019cited by this paper
• A Reinforcement Learning Approach for Multipath TCP Data Scheduling

  2019cited by this paper
• Improved Adam Optimizer for Deep Neural Networks

  2018cited by this paper
• Towards 5G: A Reinforcement Learning-Based Scheduling Solution for Data Traffic Management

  2018cited by this paper
• Designing Neural Network Architectures using Reinforcement Learning

  2016cited by this paper
• Human-level control through deep reinforcement learning

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Playing Atari with Deep Reinforcement Learning

  2013cited by this paper
• Optimal Scheduling over Time-Varying Channels with Traffic Admission Control: Structural Results and Online Learning Algorithms

  2013cited by this paper
• Virtualized network infrastructure using OpenFlow

  2010cited by this paper
• Q -Learning with Linear Function Approximation

  2007cited by this paper
• Network routing based on reinforcement learning in dynamically changing networks

  2005cited by this paper
• Resources

  1998cited by this paper
• Markov Decision Processes: Discrete Stochastic Dynamic Programming

  1994cited by this paper
• End-to-end arguments in system design

  1984cited by this paper

• Learning-Based Traffic Scheduling in Non-Stationary Multipath 5G Non-Terrestrial Networks

  2023cites this paper
• Toward a Fully-Observable Markov Decision Process With Generative Models for Integrated 6G-Non-Terrestrial Networks

  2023cites this paper
• Traffic Scheduling in Non-Stationary Multipath Non-Terrestrial Networks: A Reinforcement Learning Approach

  2023cites this paper
• Actor-Critic Scheduling for Path-Aware Air-to-Ground Multipath Multimedia Delivery

  2022cites this paper
• Towards AI-enabled traffic management in multipath TCP: A survey

  2021cites this paper