Sep 2026· IEEE International Symposium on Personal, Indoor and Mobile Radio Communications· pp. 1-6· 0 citations· 20 references
TL;DR
The proposed Enhanced Confidence-Aided Q-learning NORA (ECQ-NORA) scheme is evaluated against state-of-the-art reinforcement learning algorithms and shows that as the system scales, ECQ-NORA outperforms the benchmark schemes with respect to throughput, fairness, and energy efficiency.
Abstract
The number of machine-type communication (MTC) devices in wireless networks continues to grow exponentially. To address this congestion challenge, Q-learning has been proposed as a promising solution for channel and power level selection in non-orthogonal multiple access with ALOHA (NOMA-ALOHA) systems. Nodes autonomously explore channel/power-level pairs to identify the optimal strategy in a distributed manner without channel state information (CSI), making them susceptible to collisions and channel fading. In this paper, we propose a Q-learning approach for non-orthogonal random access (NORA) networks. The proposed Enhanced Confidence-Aided Q-learning NORA (ECQ-NORA) scheme is evaluated against state-of-the-art reinforcement learning algorithms. Systems robust to congestion are critical for increasingly dense networks. We show that as the system scales, ECQ-NORA outperforms the benchmark schemes with respect to throughput, fairness, and energy efficiency.
In this research work, the authors propose a novel approach through a reinforcement learning-based algorithm which aims to optimize the performance of ultra-dense small cell networks in 5G and beyond systems. The RL agent that has been proposed is responsible for controlling the transmission power, spectrum overlay, an...
Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from multiple terminals. While multi-agent reinforcement learning (MARL) has been explored to optimize RA-based wireless networks, its reliance on experience-driven, distribute...
Myeung Suk Oh, Zhi-Yao Zhang, Alvaro Velasquez et al.· Proceedings of the Twenty-se...· 0 citations
Growing wireless traffic is increasing pressure on the congested radio-frequency spectrum. Optical wireless communication (OWC) provides a complementary solution by using the abundant unlicensed optical spectrum. However, indoor OWC networks are dynamic: users move, enter or leave the network, and subscribe to differen...
W. Ncube, A. Qidan, Taisir Elgorashi et al.· 0 citations
In slotted ALOHA with spatial reuse, each device-to-device (D2D) link controls how often it transmits and at what power. Learning-based designs that combine these decisions model reception as packet collisions with a few discrete power levels or target uplink access with successive interference cancellation. This study...
S. A. Abdullah· Journal of Al-Farabi for Eng...· 0 citations
This paper develops a tractable analytical framework for analyzing and optimizing the Age of Information (AoI) and validate the proposed AoI analysis via extensive simulations, demonstrating a tight agreement between analysis and simulation.
Yue-Qi Chen, Si-Qi Fan, Zhuo-Yi Zhao et al.· 0 citations
Spectrum efficiency (SE) and energy efficiency (EE) are two fundamental problems in the wireless resource management that need to be jointly optimized. Deep reinforcement learning (DRL) allows near-optimal policy learning via continuous interaction with the environment, which is suitable in complex, dynamic, and high-d...
Jia-Yi Liu· ITM Web of Conferences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.