Link Scheduling Using Graph Neural Networks

Zhao, Zhongyuan; Verma, Gunjan; Rao, Chirag; Swami, Ananthram; Segarra, Santiago

doi:10.1109/twc.2022.3222781

Cited by 18 publications

(5 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a resource provisioning scheme, they considered the problem of optimizing and managing the resource. The authors formulated the resource allocation based on the Graph Convolutional Networks (GCNs) [18]. They have proved that the proposed method gains significant improvement concerning communication complexity in wireless networks [19].…”

Section: Related Workmentioning

confidence: 99%

Effective Resource Allocation Technique to Improve QoS in 5G Wireless Network

et al. 2023

View full text Add to dashboard Cite

A 5G wireless network requires an efficient approach to effectively manage and segment the resource. A Centralized Radio Access Network (CRAN) is used to handle complex distributed networks. Specific to network infrastructure, multicast communication is considered in the performance of data storage and information-based network connectivity. This paper proposes a modified Resource Allocation (RA) scheme for effectively handling the RA problem using a learning-based Resource Segmentation (RS) technique. It uses a modified Random Forest Algorithm (RFA) with Signal Interference and Noise Ratio (SINR) and position coordinates to obtain the position coordinates of end-users. Further, it predicts Modulation and Coding Schemes (MCS) for establishing a connection between the end-user device and the Remote Radio Head (RRH). The proposed algorithm depends on the accuracy of positional coordinates for the correctness of the input parameters, such as SINR, based on the position and orientation of the antenna. The simulation analysis renders the efficiency of the proposed technique in terms of throughput and energy efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Effective Resource Allocation Technique to Improve QoS in 5G Wireless Network

et al. 2023

View full text Add to dashboard Cite

show abstract

“…These researcher considered the issue of controlling and optimizing the resource while using a strategy for resource supply. The resource allocation was created by the authors using GCNs [ 40 ]. They showed that the suggested technique greatly lowers the wireless networks’ communication complexity [ 41 ].…”

Section: Related Workmentioning

confidence: 99%

Contextual Cluster-Based Glow-Worm Swarm Optimization (GSO) Coupled Wireless Sensor Networks for Smart Cities

Ramesh,

Srivani,

Mahdal

et al. 2023

Sensors

View full text Add to dashboard Cite

The cluster technique involves the creation of clusters and the selection of a cluster head (CH), which connects sensor nodes, known as cluster members (CM), to the CH. The CH receives data from the CM and collects data from sensor nodes, removing unnecessary data to conserve energy. It compresses the data and transmits them to base stations through multi-hop to reduce network load. Since CMs only communicate with their CH and have a limited range, they avoid redundant information. However, the CH’s routing, compression, and aggregation functions consume power quickly compared to other protocols, like TPGF, LQEAR, MPRM, and P-LQCLR. To address energy usage in wireless sensor networks (WSNs), heterogeneous high-power nodes (HPN) are used to balance energy consumption. CHs close to the base station require effective algorithms for improvement. The cluster-based glow-worm optimization technique utilizes random clustering, distributed cluster leader selection, and link-based routing. The cluster head routes data to the next group leader, balancing energy utilization in the WSN. This algorithm reduces energy consumption through multi-hop communication, cluster construction, and cluster head election. The glow-worm optimization technique allows for faster convergence and improved multi-parameter selection. By combining these methods, a new routing scheme is proposed to extend the network’s lifetime and balance energy in various environments. However, the proposed model consumes more energy than TPGF, and other protocols for packets with 0 or 1 retransmission count in a 260-node network. This is mainly due to the short INFO packets during the neighbor discovery period and the increased hop count of the proposed derived pathways. Herein, simulations are conducted to evaluate the technique’s throughput and energy efficiency.

show abstract

“…Recent research has employed Graph Neural Networks (GNNs) as an innovative solution to overcome challenges in wireless networks. Zhao et al [45] addressed the issue of link scheduling in these networks. They conceptualized the problem as a maximum weight independent set issue, and put efficient approximations for the problem, based on a GNN and guided tree search.…”

Section: B Joint Routing and Tdma Link Schedulingmentioning

confidence: 99%

Deep Learning for MANET Routing

Danilchenko,

Azoulay,

Reches

et al. 2023

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

Power control and scheduling are among the most well-known resource allocation challenges in wireless networks, and are often solved as optimization problems with constraints. However, solving these optimization challenges by using optimal algorithms often incurs a significant time complexity, which creates considerable discrepancies between the theoretical results and real-time processing required. In this study, we propose a novel machine learning-based perspective to address this issue. We propose a scheduling and power control deep neural network SPCDNet method and its modification SPCDNet R . SPCDNet solves the scheduling problem for point-to-point transmission requests while SPCDNet R solves the more complex problem, where the input transmission list is composed of ordered routes which should be satisfied. Both SPCDNet and SPCDNet R are trained in a supervised manner and show near-optimal performance on the test set. Our results demonstrate that SPCDNet and SPCDNet R can serve as a computationally inexpensive solution (regarding time complexity), compared with state-of-the-art schemes, while showing to be near-optimal approximation solutions to the time scheduling and power control challenges. Moreover, we found that both SPCDNet and SPCDNet R reach efficient solutions for large problem instances, even though they were trained on small problems.

show abstract

Link Scheduling Using Graph Neural Networks

Cited by 18 publications

References 93 publications

Effective Resource Allocation Technique to Improve QoS in 5G Wireless Network

Effective Resource Allocation Technique to Improve QoS in 5G Wireless Network

Contextual Cluster-Based Glow-Worm Swarm Optimization (GSO) Coupled Wireless Sensor Networks for Smart Cities

Deep Learning for MANET Routing

Contact Info

Product

Resources

About