A Reliable Reinforcement Learning for Resource Allocation in Uplink NOMA-URLLC Networks

Abstract

In this paper, we propose a deep state-actionreward-state-action (SARSA) λ learning approach for optimising the uplink resource allocation in non-orthogonal multiple access (NOMA) aided ultra-reliable low-latency communication (URLLC). To reduce the mean decoding error probability in time-varying network environments, this work designs a reliable learning algorithm for providing a long-term resource allocation, where the reward feedback is based on the instantaneous network performance. With the aid of the proposed algorithm, this paper addresses three main challenges of the reliable resource sharing in NOMA-URLLC networks: 1) user clustering; 2) Instantaneous feedback system; and 3) Optimal resource allocation. All of these designs interact with the considered communication environment. Lastly, we compare the performance of the proposed algorithm with conventional Q-learning and SARSA Q-learning algorithms. The simulation outcomes show that: 1) Compared with the traditional Q learning algorithms, the proposed solution is able to converges within 200 episodes for providing as low as 10 −2 long-term mean error; 2) NOMA assisted URLLC outperforms traditional OMA systems in terms of decoding error probabilities; and 3) The proposed feedback system is efficient for the long-term learning process.

Resource allocation in paired users: Optimization‐assisted user grouping for fairness improvement of NOMA

“…On the other hand, rate fairness between users or QoS is another crucial issue that should be ensured in NOMA systems 11,12 . This is because if rate fairness or quality of service requirements are not placed on the system, all transmit power would be distributed to the single user with the best channel quality, resulting in utter unfairness among users and the conversion of NOMA to OMA 13–15 …”

“…11,12 This is because if rate fairness or quality of service requirements are not placed on the system, all transmit power would be distributed to the single user with the best channel quality, resulting in utter unfairness among users and the conversion of NOMA to OMA. [13][14][15] Many strategies for the optimization of resource allocation in a wireless multiuser OFDM system have been proposed and have shown promising results. However, such strategies have not been considered yet in a NOMA-based system where additional design constraints should be taken into account.…”

AI-Based Q-Learning Approach for Performance Optimization in MIMO-NOMA Wireless Communication Systems

“…The study [15] introduces a deep learning methodology, SARSA λ, for optimizing uplink random access in NOMA-assisted URLLC networks. The algorithm is designed to mitigate decoding inaccuracies in dynamic communication setups and tackles issues related to user grouping, RA optimization, and instantaneous feedback mechanisms.…”