Multi-Agent Dynamic Resource Allocation in 6G in-X Subnetworks with Limited Sensing Information

Abstract

In this paper, we investigate dynamic resource selection in dense deployments of the recent 6G mobile in-X subnetworks (inXSs). We cast resource selection in inXSs as a multi-objective optimization problem involving maximization of the minimum capacity per inXS while minimizing overhead from intra-subnetwork signaling. Since inXSs are expected to be autonomous, selection decisions are made by each inXS based on its local information without signaling from other inXSs. A multi-agent Q-learning (MAQL) method based on limited sensing information (SI) is then developed, resulting in low intra-subnetwork SI signaling. We further propose a rule-based algorithm termed Q-Heuristics for performing resource selection based on similar limited information as the MAQL method. We perform simulations with a focus on joint channel and transmit power selection. The results indicate that: (1) appropriate settings of Q-learning parameters lead to fast convergence of the MAQL method even with two-level quantization of the SI, and (2) the proposed MAQL approach has significantly better performance and is more robust to sensing and switching delays than the best baseline heuristic. The proposed Q-Heuristic shows similar performance to the baseline greedy method at the 50th percentile of the per-user capacity and slightly better at lower percentiles. The Q-Heuristic method shows high robustness to sensing interval, quantization threshold and switching delay.

An Adaptive Biomimetic Ant Colony Optimization With 6G Integration for IoT Network Communication

“…Concurrently, Chai, Yang, and Li [23] underscored evolutionary algo- rithms' potential in network optimization, aligning with our ant colony optimization approach. Adeogun and Berardinelli [24] extended this perspective, examining 6G subnetworks and providing unique insights into resource allocation.…”

“…Possible limitations in specific communication systems [20] Intelligent sensing for multiple target tracking Constraints in real-world tracking scenarios [21] Transceiver beamforming optimization; Dual-functional radarcommunication Restricted to DFRC systems; Implementation complexity [22] Machine learning for network performance optimization Dependence on quality and availability of training data [23] Evolutionary algorithms in network optimization Generalizability concerns across diverse network scenarios [24] 6G in-X subnetworks; Resource allocation under limited sensing Exploration limited to specific subnetwork types [26] explored computational efficiency within UAV-based Mobile Edge Computing (MEC) by integrating GPU-based Particle Swarm Optimization (PSO) and Voronoi Diagrams. This confluence of technologies culminated in a refined MEC model, showcasing creative optimization applications.…”

Multi-Agent Deep Reinforcement Learning for Interference-Aware Channel Allocation in Non-Terrestrial Networks

“…This approach is particularly promising in the topic of DCA, where the collection of data becomes inefficient due to the high dimensionality of the state space resulting from the numerous uncertainties inherent in the environment. Particularly, recent study [33] proposed a model-free Multi-Agent Reinforcement Learning (MARL) independent Q-learning (IQL) table approach to solve the distributed DCA problem over orthogonal channels. While this work demonstrates the potential of a simple RL technique for addressing the DCA challenge, it is limited to small-scale systems due to the high dimensionality of the state space in the DCA problem.…”

Power Control for 6G In-Factory Subnetworks With Partial Channel Information Using Graph Neural Networks

“…Since subnetworks can be installed in any entity including robots and production modules, they will likely result in highly dense uncoordinated cellular deployment on the factory floor. The envisioned extreme density and large-scale deployment of subnetworks in a factory scenario requires novel methods to adequately manage the allocation of the limited radio resources [2], [8], [9]. Hence, efficient radio resource algorithms such as transmit power control (PC) are crucial to the vision of in-X subnetworks in the factory.…”