6G Wireless Networks: Vision, Requirements, Applications and Challenges

Kamble, Pradnya; Shaikh, Alam N.

doi:10.1109/icast55766.2022.10039549

Cited by 15 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-tier ultra-dense Heterogeneous Networks (HetNets), shown in Fig. 2, are considered the main architecture in future wireless communication networks and one of the most suitable solutions to respond to the ever-increasing traffic growth and heterogeneous traffic requirements in 5G and 6G [6], [9]. Fig.…”

Section: Resource Allocation In Heterogeneous Networkmentioning

confidence: 99%

“…6G is expected to further improve the three above-presented key parameters of the 5G network (eMBB, uRLLC, and mMTC) and since 5G presents trade-offs on latency, energy, throughput, and end-to-end reliability, 6G is excepted to jointly meet stringent network demands such as extremely high throughput, ultra-high reliability, and ultra-low latency [5], [6]. It is expected to support a connectivity density 10 times higher compared with 5G and offers a peak throughput 100 times faster than 5G [6]. The main differences between 5G and 6G networks are presented in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On optimizing resource allocation: A comparative performance evaluation of resource allocation strategies in 5G

Dobruna,

Fazliu,

Humar

et al. 2024

Preprint

View full text Add to dashboard Cite

Resource allocation continues to be a challenging issue in communication networks and its complexity is continuously increasing with the densification of the networks. Resource allocation strategies are numerous and varied, and the goal is to improve any or a number of targets, such as spectral and energy efficiency and overall throughput, among others. In this paper, selected algorithms for resource allocation in wireless communication networks are analyzed and simulations are executed to compare and highlight the importance of the way the resource algorithms are implemented to achieve efficient usage of the available spectrum. In addition, the performance of selected algorithms is evaluated in a multi-cell heterogeneous network and compared to eICIC, a widely-used interference mitigation technique used by communication networks. The results suggest that there is no single algorithm that visibly outperforms other candidates in terms of all performance criteria. Instead, their efficiency is always a consequence of a strategic choice of goals, and the targeted parameters are optimized at a price. Thus, the development and implementation of resource allocation algorithms must follow concrete usage scenarios and needs of the network and depend heavily on network performance requirements and parameters criteria.

show abstract

Section: Resource Allocation In Heterogeneous Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On optimizing resource allocation: A comparative performance evaluation of resource allocation strategies in 5G

Dobruna,

Fazliu,

Humar

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In the expanding world of wireless communication, managing network resources effectively and efficiently has become increasingly important. As the number and diversity of wireless devices continue to grow (e.g., with Internet of Things (IoT) devices), so does also the demand for better performance, throughput, and reliability in communication modules [39,40]. Channel selection, the process of choosing the most optimal path for data transmission, plays a fundamental role in maximizing these qualities in, e.g., WiFi [41].…”

Section: Simulation 9: Communication Applicationmentioning

confidence: 99%

Pioneering approaches for enhancing the speed of hierarchical LA by ordering the actions

Omslandseter

Jiao

Oommen

2023

Information Sciences

View full text Add to dashboard Cite

“…However, despite these efforts, the integration of AI/ML into several areas of the radio access network (RAN) has not yet been considered. One of these areas regards the medium access control (MAC) protocols, where the heterogeneous services expected by the 6G networks impose significant challenges on meeting the diversified quality of service (QoS) requirements [4]. The standardization bodies started to face this problem, and in [5] several improvements to the conventional radio access procedures are provided without taking into account AI/ML.…”

Section: Introductionmentioning

confidence: 99%

On Learning Generalized Wireless MAC Communication Protocols via a Feasible Multi-Agent Reinforcement Learning Framework

Miuccio,

Riolo,

Samarakoon

et al. 2024

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

Automatically learning medium access control (MAC) communication protocols via multiagent reinforcement learning (MARL) has received huge attention to cater to the extremely diverse realworld scenarios expected in 6G wireless networks. Several state-of-the-art solutions adopt the centralized training with decentralized execution (CTDE) learning method, where agents learn optimal MAC protocols by exploiting the information exchanged with a central unit. Despite the promising results achieved in these works, two notable challenges are neglected. First, these works were designed to be trained in computer simulations assuming an omniscient environment and neglecting communication overhead issues, thus making the implementation impractical in real-world scenarios. Second, the learned protocols fail to generalize outside of the scenario they were trained on. In this paper, we propose a new feasible learning framework that enables practical implementations of training procedures, thus allowing learned MAC protocols to be tailor-made for the scenario where they will be executed. Moreover, to address the second challenge, we leverage the concept of state abstraction and imbue it into the MARL framework for better generalization. As a result, the policies are learned in an abstracted observation space that contains only useful information extracted from the original high-dimensional and redundant observation space. Simulation results show that our feasible learning framework exhibits performance comparable to that of the infeasible solutions. In addition, the learning frameworks adopting observation abstraction offer better generalization capabilities, in terms of the number of UEs, number of data packets to transmit, and channel conditions.

show abstract

6G Wireless Networks: Vision, Requirements, Applications and Challenges

Cited by 15 publications

References 17 publications

On optimizing resource allocation: A comparative performance evaluation of resource allocation strategies in 5G

On optimizing resource allocation: A comparative performance evaluation of resource allocation strategies in 5G

Pioneering approaches for enhancing the speed of hierarchical LA by ordering the actions

On Learning Generalized Wireless MAC Communication Protocols via a Feasible Multi-Agent Reinforcement Learning Framework

Contact Info

Product

Resources

About