A Power Consumption Reduction Scheme in Hose-Model Networks with Bundled Links

Ba, Seydou; Ouédraogo, Ihsen Aziz; Oki, Eiji

doi:10.1109/greencom-ithings-cpscom.2013.32

Cited by 3 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The energy savings were significant, reducing energy consumption by 79% compared with a normal network. Another study, in [54], investigated energy reduction in clustered links using a mixed-integer linear programming (MILP) model, showing a 50% reduction compared with shortest-path routing. In [55], the use of link aggregation activation and deactivation was studied using linear programming (LP) optimization, and it was shown how to find the most energy-efficient link configuration for all links of a BE.…”

Section: Work Related To Energy Efficiency In Link Aggregation Groups...mentioning

confidence: 99%

A Novel Traffic Prediction Method Using Machine Learning for Energy Efficiency in Service Provider Networks

Rau

Soto

Zabala-Blanco

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper presents a systematic approach for solving complex prediction problems with a focus on energy efficiency. The approach involves using neural networks, specifically recurrent and sequential networks, as the main tool for prediction. In order to test the methodology, a case study was conducted in the telecommunications industry to address the problem of energy efficiency in data centers. The case study involved comparing four recurrent and sequential neural networks, including recurrent neural networks (RNNs), long short-term memory (LSTM), gated recurrent units (GRUs), and online sequential extreme learning machine (OS-ELM), to determine the best network in terms of prediction accuracy and computational time. The results show that OS-ELM outperformed the other networks in both accuracy and computational efficiency. The simulation was applied to real traffic data and showed potential energy savings of up to 12.2% in a single day. This highlights the importance of energy efficiency and the potential for the methodology to be applied to other industries. The methodology can be further developed as technology and data continue to advance, making it a promising solution for a wide range of prediction problems.

show abstract

Section: Work Related To Energy Efficiency In Link Aggregation Groups...mentioning

confidence: 99%

A Novel Traffic Prediction Method Using Machine Learning for Energy Efficiency in Service Provider Networks

Rau

Soto

Zabala-Blanco

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Parts of this paper were partially presented at the 2013 IEEE International Conference on Green Computing and Communications (GreenCom 2013) [10].…”

Section: Acknowledgmentsmentioning

confidence: 99%

“…This paper presents a power consumption reduction scheme for bundled cable networks under the hose model. It is an extended version of our work presented in [10]. Our approach is to selectively deactivate as many cables as possible while still guaranteeing that the network can route the traffic loads.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reducing the power consumption of hose‐model networks with bundled links

Ouédraogo

Oki

2015

IET Networks

Self Cite

View full text Add to dashboard Cite

Given the exponential growth in telecommunication networks, more and more attention is being paid to their share in the global energy consumption. Reducing networks' power consumption has become a major concern. However, the often overprovisioned wired core network is still overlooked. In core networks, pairs of routers are typically connected by multiple physical cables that form one logical bundled link participating in the intra-domain routing protocol. To reduce the energy consumption of core networks with bundled cables, the authors propose a scheme to deactivate the maximum possible number of cables, and associated equipment, while considering hose-model traffic. A similar approach has been presented for the pipe model, where the exact traffic matrix is assumed to be known. Owing to traffic uncertainty, however, it is difficult for network operators to have exact knowledge of the traffic matrix. This traffic uncertainty can be avoided by using the hose model, which specifies only the upper bounds of the egress/ingress traffic from/to a node. They introduce a mixed integer linear problem formulation that yields the optimal solution and a more practical and near optimal heuristic algorithm for large networks. The author's performance evaluation results show that it offers up to 50% power reduction.

show abstract

A Green and Robust Optimization Strategy for Energy Saving Against Traffic Uncertainty

Ouédraogo

Oki

2016

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

A Power Consumption Reduction Scheme in Hose-Model Networks with Bundled Links

Cited by 3 publications

References 8 publications

A Novel Traffic Prediction Method Using Machine Learning for Energy Efficiency in Service Provider Networks

A Novel Traffic Prediction Method Using Machine Learning for Energy Efficiency in Service Provider Networks

Reducing the power consumption of hose‐model networks with bundled links

A Green and Robust Optimization Strategy for Energy Saving Against Traffic Uncertainty

Contact Info

Product

Resources

About