QMA: A Resource-efficient, Q-learning-based Multiple Access Scheme for the IIoT

@article{Meyer2021QMAAR,
  title={QMA: A Resource-efficient, Q-learning-based Multiple Access Scheme for the IIoT},
  author={Florian Meyer and Volker Turau},
  journal={2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS)},
  year={2021},
  pages={864-874}
}
  • Florian MeyerV. Turau
  • Published 11 January 2021
  • Computer Science, Business
  • 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS)
Many MAC protocols for the Industrial Internet of Things, such as IEEE 802.15.4 and its extensions, require contention-based channel access for management traffic, e.g., for slot (de)allocations and broadcasts. In many cases, subtle but hidden patterns characterize this secondary traffic, but present contention-based protocols are unaware of these patterns and therefore cannot exploit them. Especially in dense networks, these protocols often do not provide sufficient throughput and reliability… 
[PDF] Semantic Reader

References

SHOWING 1-10 OF 24 REFERENCES

ALOHA and Q-Learning based medium access control for Wireless Sensor Networks

A novel Medium Access Control (MAC) protocol named ALOHA and Q-Learning based MAC with Informed Receiving (ALOHA-QIR) for Wireless Sensor Networks (WSNs) obtains significant improvements in throughput, delay and energy efficiency.

A multi-state Q-learning based CSMA MAC protocol for wireless networks

This paper proposes agents with combined personalities of cautiousness and aggressiveness, which leads to different agents personalities ranging from cautious agents with risk aversion to aggressive risky agents in a multi-state Q-learning model.

Use of Q-learning approaches for practical medium access control in wireless sensor networks

Q-Learning Aided Resource Allocation and Environment Recognition in LoRaWAN With CSMA/CA

The wireless environment around LoRaWAN nodes are learned, and the knowledge is utilized for resource allocation in order to improve PDR performance and the numerical results elucidate that the proposed scheme can improve average P DR performance by about 20% compared to the random resource allocation scheme.

RL-MAC: A QoS-Aware Reinforcement Learning based MAC Protocol for Wireless Sensor Networks

This paper introduces RL-MAC, a novel adaptive media access control protocol for wireless sensor networks (WSN) that employs a reinforcement learning framework that achieves high throughput and low power consumption for a wide range of traffic conditions.

Application of reinforcement learning to medium access control for wireless sensor networks

Implications of decentralized Q-learning resource allocation in wireless networks

This work proposes a stateless variation of Q-learning, which is applied to exploit spatial reuse in a wireless network, and allows networks to modify both their transmission power and the channel used solely based on the experienced throughput.

CoRL: Collaborative Reinforcement Learning-Based MAC Protocol for IoT Networks

A reinforcement learning-based MAC protocol was proposed to provide high throughput and alleviate the collision problem, and a collaboratively predicted Q-value was proposed for nodes to update their value functions by using communications trial information of other nodes.

Constructing Customized Multi-Hop Topologies in Dense Wireless Network Testbeds

The results show that preset topologies of various types can be built even in dense wireless testbeds, and proposed algorithms to generate topologies with desired properties are provided as open-source software.

Learning to Schedule Communication in Multi-agent Reinforcement Learning

A multi-agent deep reinforcement learning framework, called SchedNet, in which agents learn how to schedule themselves, how to encode the messages, and how to select actions based on received messages, which is capable of deciding which agents should be entitled to broadcasting their messages.