Multipath TCP Meets Reinforcement Learning: A Novel Energy-Efficient Scheduling Approach in Heterogeneous Wireless Networks

Dong, Pingping; Shen, Rongcheng; Wang, Qian; Zhang, Dian; Zuo, Yuning; Yang, Wenjun; Zhang, Lianming

doi:10.1109/mwc.013.2100658

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to conventional methods, reinforcement learning (RL) schemes leverage AI agents that learn efficient policies through experience interacting with the environment. This review highlights the exciting potential of multi-agent deep RL to overcome the limitations of conventional techniques for energy-aware MPTCP scheduling in heterogeneous wireless networks [44].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Energy-Aware MPTCP Scheduling in Heterogeneous Wireless Networks Using Multi-Agent Deep Reinforcement Learning Techniques

Arain,

Qiu,

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper proposes an energy-efficient scheduling scheme for multi-path TCP (MPTCP) in heterogeneous wireless networks, aiming to minimize energy consumption while ensuring low latency and high throughput. Each MPTCP sub-flow is controlled by an agent that cooperates with other agents using the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. This approach enables the agents to learn decentralized policies through centralized training and decentralized execution. The scheduling problem is modeled as a multi-agent decision-making task. The proposed energy-efficient scheduling scheme, referred to as EE-MADDPG, demonstrates significant energy savings while maintaining lower latency and higher throughput compared to other state-of-the-art scheduling techniques. By adopting a multi-agent deep reinforcement learning approach, the agents can learn efficient scheduling policies that optimize various performance metrics in heterogeneous wireless networks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Parameter sharing and transfer learning help overcome challenges in multi-agent RL. Dong et al 2023 [44], proposes MPTCP-RL, a reinforcement learning-based multi-path scheduler that adaptively selects the optimal path set to improve aggregate throughput and reduce energy consumption compared to existing mechanisms.…”

Section: Related Workmentioning

confidence: 99%

Energy-Aware MPTCP Scheduling in Heterogeneous Wireless Networks Using Multi-Agent Deep Reinforcement Learning Techniques

Arain,

Qiu,

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…8,9 Wang et al proposed CMT-MQ, 10 a RL-based scheduling algorithm that considers the requirements of different types of services to optimise the scheduler's performance. Dong et al 11 proposed MPTCP-RL, which adopts deep RL to ensure that the sender can adaptively select the optimal path set based on path characteristics and energy consumption. However, they are not optimised for the out-of-order problem at the MPTCP connection level.…”

Section: Introductionmentioning

confidence: 99%

“…et al proposed CMT-MQ,10 a RL-based algorithm that schedules data based on different types of services to meet various QoS requirements. Dong et al11 proposed MPTCP-RL to guarantee low energy consumption T A B L E 1 Survey of works related to MPTCP scheduling in dynamic network. They further utilise the MPTCP transmission model to select the transmission paths for higher throughput and lower flow completion time.…”

mentioning

confidence: 99%

URLM: Utilising reinforcement learning to schedule subflows in MPTCP

Lin

Zhou

et al. 2023

Int J Communication

View full text Add to dashboard Cite

Summary Parallel transmission in multiple access networks using MultiPath TCP (MPTCP) greatly enhances the throughput. However, critical packet disorder is commonly observed due to traffic fluctuation and path diversity. Although several predictive scheduling algorithms have been proposed to solve this problem, they cannot accommodate prediction accuracy and real‐time adaptation simultaneously in a dynamic network environment. The time overhead in modifying scheduling parameters to adapt to network changes leads to performance degradation in throughput and packet disorder. In this study, we propose a scheduling algorithm called Utilising Reinforcement Learning to Schedule Subflows in MPTCP (URLM). We apply reinforcement learning to select an optimal scheduling parameter in real time, which brings significant time benefits for modifying the parameters. The simulation comparison experiments show that URLM reduces the average number of out‐of‐order packets and the time overhead in adapting to network changes while improving global throughput.

show abstract