Throughput and Latency in the Distributed Q-Learning Random Access mMTC Networks

2021/10/30 by Giovanni Maciel Ferreira Silva, Silva, Giovanni Maciel Ferreira, Taufik Abrão +1
Engineering · Computer Science · #Wireless Body Area Networks #IoT and Edge/Fog Computing #Energy Efficient Wireless Sensor Networks

paper · pdf · doi:10.48550/arxiv.2111.00299

Abstract

In mMTC mode, with thousands of devices trying to access network resources sporadically, the problem of random access (RA) and collisions between devices that select the same resources becomes crucial. A promising approach to solve such an RA problem is to use learning mechanisms, especially the Q-learning algorithm, where the devices learn about the best time-slot periods to transmit through rewards sent by the central node. In this work, we propose a distributed packet-based learning method by varying the reward from the central node that favors devices having a larger number of remaining packets to transmit. Our numerical results indicated that the proposed distributed packet-based Q-learning method attains a much better throughput-latency trade-off than the alternative independent and collaborative techniques in practical scenarios of interest. In contrast, the number of payload bits of the packet-based technique is reduced regarding the collaborative Q-learning RA technique for achieving the same normalized throughput.

Related

• TinyQMIX: Distributed Access Control for mMTC via Multi-agent Reinforcement Learning
• Learning Random Access Schemes for Massive Machine-Type Communication with MARL
• Distributed Learning for Reliable and Timely Communication in 6G Industrial Subnetworks
• Dynamic Multichannel Access via Multi-agent Reinforcement Learning: Throughput and Fairness Guarantees
• Medium Access using Distributed Reinforcement Learning for IoTs with\n Low-Complexity Wireless Transceivers