Energy Management Framework for 5G Ultra-Dense Networks Using Graph Theory

Daas, Mosheer J.; Jubran, Mohammad; Hussein, Mohammed Salah

doi:10.1109/access.2019.2957378

Cited by 18 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, a firefly algorithm was developed in 7 , where joint optimization of the area spectral efficiency and energy efficiency was formulated to determine the optimal system parameters for a two-tier ultra-dense HetNet. Moreover, a cooperative energy optimization scheme for 5G ultra-dense HetNet using graph theory was proposed in 8 , where a graph representation of the network was first developed, followed by applying graph theory to determine the order of SC nodes to which power-off/on procedures are applied.…”

Section: Related Workmentioning

confidence: 99%

“…Research has been conducted for optimized cell switching solutions in CDSA HetNets, and analytical models and heuristic algorithms were developed with a priori knowledge of the environment 6 – 8 . However, such approaches usually face the NP-hardness solving issue due to the problem formation complexity and computational overhead for complex scenarios, and have limited generalization capability adapting to the dynamic environment of wireless networks 9 , 10 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph neural network-based cell switching for energy optimization in ultra-dense heterogeneous networks

Tan

Bremner

Kernec

et al. 2022

Sci Rep

View full text Add to dashboard Cite

The development of ultra-dense heterogeneous networks (HetNets) will cause a significant rise in energy consumption with large-scale base station (BS) deployments, requiring cellular networks to be more energy efficient to reduce operational expense and promote sustainability. Cell switching is an effective method to achieve the energy efficiency goals, but traditional heuristic cell switching algorithms are computationally demanding with limited generalization abilities for ultra-dense HetNet applications, motivating the usage of machine learning techniques for adaptive cell switching. Graph neural networks (GNNs) are powerful deep learning models with strong generalization abilities but receive little attention for cell switching. This paper proposes a GNN-based cell switching solution (GBCSS) that has a smaller computational complexity than existing heuristic algorithms. The presented performance evaluation uses the Milan telecommunication dataset based on real-world call detail records, comparing GBCSS with a traditional exhaustive search (ES) algorithm, a state-of-the-art learning-based algorithm, and the baseline without cell switching. Results indicate that GBCSS achieves a 10.41% energy efficiency gain when compared with the baseline and achieves 75.76% of the optimal performance obtained with ES algorithm. The results also demonstrate GBCSS’ significant scalability and generalization abilities to differing load conditions and the number of BSs, suggesting this approach is well-suited to ultra-dense HetNet deployment.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Graph neural network-based cell switching for energy optimization in ultra-dense heterogeneous networks

Tan

Bremner

Kernec

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Two heuristic algorithms were proposed: the first is a centralized user association algorithm for minimizing the switching cost while the second is an enhanced heuristic for further reduction in the energy consumption of the network. A cooperative energy optimization scheme for 5G UDNs using graph theory was proposed in [28]. The network was first represented as a graph after which the graph theory is employed to determine the switching off/on pattern of the SBSs in the network.…”

Section: Related Workmentioning

confidence: 99%

A Lightweight Cell Switching and Traffic Offloading Scheme for Energy Optimization in Ultra-Dense Heterogeneous Networks

Abubakar¹,

Mollel²,

Öztürk³

et al. 2021

Preprint

View full text Add to dashboard Cite

One of the major capacity boosters for 5G networks is the deployment of ultra-dense heterogeneous networks (UDHNs). However, this deployment results in tremendous increase in the energy consumption of the network due to the large number of base stations (BSs) involved. In addition to enhanced capacity, 5G networks must also be energy efficient for it to be economically viable and environmentally friendly. Dynamic cell switching is a very common way of reducing the total energy consumption of the network but most of the proposed methods are computationally demanding which makes them unsuitable for application in ultra-dense network deployment with massive number of BSs. To tackle this problem, we propose a lightweight cell switching scheme also known as Threshold-based Hybrid cEll swItching Scheme (THESIS) for energy optimization in UDHNs. The developed approach combines the benefits of clustering and exhaustive search (ES) algorithm to produce a solution whose optimality is close to that of the ES (which is guaranteed to be optimal), but is computationally more efficient than ES and as such can be applied for cell switching in real networks even when their dimension is large. The performance evaluation shows that the THESIS produces a significant reduction in the energy consumption of the UDHN and is able to reduce the complexity of finding a near-optimal solution from exponential to polynomial complexity.

show abstract

“…GT explores the relationship between the structural properties and the eigenvalues and eigenvectors of the corresponding matrices [11]. GT has been widely applied in various areas, including data analysis [11]- [13], communication [14], [15], traffic networks [16], [17], and energy networks [18], [19]. Typically, GT represents a network in a mathematical graph as G = G(V, E), where V denotes vertices (e.g., demand nodes, reservoirs, and tanks in a WDN) with n elements, and E represents edges (e.g., pipes, pumps, and valves in a WDN) with m elements [5].…”

Section: Introductionmentioning

confidence: 99%

Shortest-Path-Based Two-Phase Design Model for Hydraulically Efficient Water Distribution Network: Preparing for Extreme Changes in Water Availability

Lee

Jung

2021

IEEE Access

View full text Add to dashboard Cite

Environmental issues can cause changes in source water availability in water distribution networks (WDNs). Thus, an efficient connection between the source and consumers is important for securing water serviceability, which can generally be achieved by minimizing energy losses. In this study, a novel two-phase design (TPD) model is proposed to design an energy-efficient WDN by maximizing a hydraulic geodesic index (HGI), which is the weighted shortest path from the source to the demand node. Before applying the TPD model for WDN design, a correlation analysis between the system HGI, hydraulic performance, and graph theory indices is conducted using 33 J-City networks to verify the proposed HGI. Next, the TPD model is used to determine the optimal layout of the grid network (Phase I). Based on this layout, the optimal diameter set is identified in Phase II. The TPD is thereafter compared with the traditional single-phase design (SPD) model, which determines the optimal layout and diameter simultaneously, and a least-cost model for each phase in the grid network layout and pipe-sizing problem. The correlation analysis clearly indicates that the system HGI with the weighted graph theory successfully determines the hydraulic performance without any hydraulic analysis. Furthermore, TPD is advantageous for designing energy-efficient, hydraulically and structurally sustainable, and resilient networks, as compared to SPD and the least-cost model. The TPD model is expected to provide a better opportunity to prepare for extreme water availability changes by enhancing the hydraulic performance and efficiency through a better connection between the source and nodes.

show abstract

Energy Management Framework for 5G Ultra-Dense Networks Using Graph Theory

Cited by 18 publications

References 21 publications

Graph neural network-based cell switching for energy optimization in ultra-dense heterogeneous networks

Graph neural network-based cell switching for energy optimization in ultra-dense heterogeneous networks

A Lightweight Cell Switching and Traffic Offloading Scheme for Energy Optimization in Ultra-Dense Heterogeneous Networks

Shortest-Path-Based Two-Phase Design Model for Hydraulically Efficient Water Distribution Network: Preparing for Extreme Changes in Water Availability

Contact Info

Product

Resources

About