Message-Passing Based User Association and Bandwidth Allocation in HetNets With Wireless Backhaul

Lee, Hongju; Park, Junhee; Lee, Sang Hyun; Lee, Inkyu

doi:10.1109/twc.2022.3197843

Cited by 3 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimality of the algorithm depends on the properties of the problems. For problem (11), if it is a convex problem, then Algorithm 1 can obtain the optimal solution [10]. To validate whether problem ( 11) is convex or not, we only need to validate whether r Φ,ξ u is concave or not.…”

Section: A Optimal Bandwidth Allocation By Iterative Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Graph Neural Network-Based Bandwidth Allocation for Secure Wireless Communications

Hao,

Yeoh,

Liu

et al. 2023

2023 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

In this paper, we develop a deep learning-based bandwidth allocation policy that is: 1) scalable with the number of users and 2) transferable to different communication scenarios, such as non-stationary wireless channels, different quality-of-service (QoS) requirements, and dynamically available resources. To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN), with which the number of training parameters does not change with the number of users. To enable the generalization of the GNN, we develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios during meta-training. Next, during metatesting, a few samples are used to fine-tune the GNN with unseen communication scenarios. Simulation results demonstrate that our HML approach can improve the initial performance by 8.79%, and sampling efficiency by 73%, compared with existing benchmarks. After fine-tuning, our near-optimal GNN-based policy can achieve close to the same reward with much lower inference complexity compared to the optimal policy obtained using iterative optimization.

show abstract

Section: A Optimal Bandwidth Allocation By Iterative Algorithmmentioning

confidence: 99%

“…(Corresponding author: Changyang She.) complexity is generally too high to be implemented in real time [10][11][12]. To reduce the computational complexity, deep learning is a promising approach for 6G communications [13,14].…”

Section: Introductionmentioning

confidence: 99%

Graph Neural Network-Based Bandwidth Allocation for Secure Wireless Communications

Hao,

Yeoh,

Liu

et al. 2023

2023 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

show abstract

“…Tis approach can extremely improve the spectrum efciency while reducing uncovered areas. Due to these merits, wireless networks have evolved from HomNets to HetNets [1,2].…”

Section: Introductionmentioning

confidence: 99%

Cooperative Game-Based Resource Allocation Scheme for Heterogeneous Networks with eICIC Technology

Kim

2023

Journal of Computer Networks and Communications

View full text Add to dashboard Cite

Heterogeneous network (HetNet) is considered to be the most promising approach for increasing communication capacity. However, HetNet control problems are difficult due to their intertier interference. Recently, the enhanced intercell interference coordination (eICIC) technology is introduced to offer several benefits, including a more equitable traffic load distribution across the macro and embedded small cells. In this paper, we design a new resource allocation scheme for the eICIC-based HetNet. Our proposed scheme is formulated as a joint cooperative game to handle conflicting requirements. By adopting the ideas of Kalai and Smorodinsky solution (KSS), multicriteria Kalai and Smorodinsky solution (MCKSS), and sequential Raiffa solution (SRS), we develop a hybrid control algorithm for an adaptive resource sharing between different base stations. To effectively adjust the eICIC fraction rates, the concepts of MCKSS and SRS are applied in an interactive manner. For mobile devices in the HetNet, the assigned resource is distributed by using the idea of KSS. The key insight of our algorithm is to translate the originally competitive problem into a hierarchical cooperative problem to reach a socially optimal outcome. The main novelty of our approach is its flexibility to reach a reciprocal consensus under dynamic HetNet environments. Exhaustive system simulations illustrate the performance gains along different dimensions, such as system throughput, device payoff, and fairness among devices. The superiority of our proposed scheme is fully demonstrated in comparison with three other existing eICIC control protocols.

show abstract

Decentralized Learning Framework for Hierarchical Wireless Networks: A Tree Neural Network Approach

Kim,

Lee,

Hwang

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Message-Passing Based User Association and Bandwidth Allocation in HetNets With Wireless Backhaul

Cited by 3 publications

References 34 publications

Graph Neural Network-Based Bandwidth Allocation for Secure Wireless Communications

Graph Neural Network-Based Bandwidth Allocation for Secure Wireless Communications

Cooperative Game-Based Resource Allocation Scheme for Heterogeneous Networks with eICIC Technology

Decentralized Learning Framework for Hierarchical Wireless Networks: A Tree Neural Network Approach

Contact Info

Product

Resources

About