Reinforcement Learning for NOMA-ALOHA Under Fading

Abstract

We consider a non-orthogonal multiple access in a random-access ALOHA system, in which each user randomly accesses one out of different time slots and send uplink packets based on power differences. In the context of an asymmetric game, we propose a non-orthogonal multiple access ALOHA system based on multi-agent reinforcement learning tools that can help each user to find its best strategies of improving the rates of successful action choices. While taking into account not only collisions, but also fading, we analyze the mean rewards of actions under general settings and focus on the case that involves two different groups of users. To characterize the behaviors of accessing strategies, we apply multi-agent action value methods that consider either greedy or non-greedy actions, combined with an acceleration gradient descent. Our results show that in the proposed system, users employing the greedy action-based methods can be randomly divided into two groups of users and increase the rates of successful action choices. Interestingly, in relatively limited channels, such greedy methods turn many of users to be with a state of barring-access. In this case, the proposed acceleration, non-greedy action methods are shown to reduce such unfairness, at a loss of successful action rates.

A Multi-Agent Reinforcement Learning-Based Grant-Free Random Access Protocol for mMTC Massive MIMO Networks

“…[20] uses a deep RL algorithm optimizing the distribution of network resources such as spreading factor, transmission power, and channel, aiming to minimize the LoRaWAN energy transmission. Besides, several recent works have also applied RL algorithms for optimizing RA in non-orthogonal multiple access (NOMA) systems [21][22][23], in industrial edge-cloud networks [24], and in vehicle-to-everything (V2X) networks [25].…”

Multichannel Relay assisted NOMA-ALOHA with Reinforcement Learning based Random Access

“…Considering IoT transmission characteristics [4], adopting NOMA into slotted-ALOHA systems has been recently studied [5]- [8]. As the first work that applied NOMA to slotted-ALOHA, [5] studies the throughput enhancement perspective, and the analysis of throughput bounds of NOMA-ALOHA is investigated with derivation of lower bound of throughput in [6].…”

“…Since users would contend for the shared channel slots in NOMA-ALOHA, multiple studies were conducted on the channel access scheme. In [7], a non-cooperative game theory based approach is proposed to decide the mixed strategy for transmissions and a reinforcement learning (RL) based approach [9] for NOMA-ALOHA is studied in [8]. In [10], the use of RL for ALOHA systems is studied under random collision.…”