Energy Efficiency of Server-Centric PON Data Center Architecture for Fog Computing

Mohamed, Sanaa Hamid; El-Gorashi, Taisir E. H.; Elmirghani, Jaafar M. H.

doi:10.1109/icton.2018.8473877

Cited by 21 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 2 provides the shuffling completion time results for a maximum server rate of 1000 Mbytes/s and input data ranging from 1 to 20 GBytes in different DCNs. The subfigures, show the results in [12], and [13] for the cases where all links are working, in addition to the completion time results under 2 or 3 cases of links failures in each DCN. For the Spine-and-Leaf architecture, the degradation due to links 1-3 disconnection is less than 2-6 because the latter is more utilized due to serving the flows to 3 reduce workers compared to 1 reduce worker by links 1-3.…”

Section: Methodsmentioning

confidence: 99%

“…In this paper, we examine single and multi-link non-fatal failures in several DCNs and their effect on the performance of MapReduce shuffling operations. We compare the completion time results in [12] and [13] under no link failures to the results under several link failures for electronic, hybrid, and optical DCNs, in addition to a server-centric Passive Optical Networks (PON)-based DCN design proposed as part of the work in [14]- [19]. The rest of this paper is organized as follows.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of Link Failures on the Performance of MapReduce in Data Center Networks

Mohamed

El-Gorashi

Elmirghani

2018

2018 20th International Conference on Transparent Optical Networks (ICTON)

Self Cite

View full text Add to dashboard Cite

In this paper, we utilize Mixed Integer Linear Programming (MILP) models to determine the impact of link failures on the performance of shuffling operations in MapReduce when different data center network (DCN) topologies are used. For a set of non-fatal single and multi-links failures, the results indicate that different DCNs experience different completion time degradations ranging between 5% and 40%. The best performance under links failures is achieved by a server-centric PON-based DCN.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Impact of Link Failures on the Performance of MapReduce in Data Center Networks

Mohamed

El-Gorashi

Elmirghani

2018

2018 20th International Conference on Transparent Optical Networks (ICTON)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors of [33], [34] evaluated the methodologies that can be used to provide energy efficient clouds to process the IoT data, while the authors in [34], [35] discussed energy efficient content sharing. The energy efficiency of the networks supporting different services was optimized in [36][37][38][39][40][41][42][43][44].…”

Section: Literature Reviewmentioning

confidence: 99%

Resilient Service Embedding in IoT Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

The Internet of Things (IoT) can support a significant number of services including those in smart homes and the automation of industries and public utilities. However, the growth of these deployments has posed a significant challenge especially in terms of how to build such deployments in a highly resilient manner. The IoT devices are prone to unpredicted failures and cyber-attacks, i.e. various types of damage, unreliable wireless connections, limited transmission power, computing ability, and storage space. Thus resilience is essential in IoT networks and in the services they support. In this paper, we introduce a new approach to resilience in IoT service embedding, based on traffic splitting. Our study assesses the power consumption associated with the services embedded and the data delivery time. The results are compared to recent approaches in resilience including redundancy and replication approaches. We constructed an optimization model whose goal is to determine the optimum physical resources to be used to embed the IoT virtual topology, where the latter is derived from a business process (BP). The embedding process makes use of the service-oriented architecture (SOA) paradigm. The physical resources of interest include IoT links and devices. The model made use of mixed integer linear programming (MILP) with an objective function that aimed to minimize both the total power consumption and the traffic latency. The optimization results show that the power consumption is reduced and the data delivery time is reduced in the service embedding approach where the proposed traffic splitting approach is employed resulting in the selection of energy efficient nodes and routes in the IoT network. Our methods resulted in up to 35% power saving compared to current methods and reduced the average traffic latency by up to 37% by selecting energy-efficient nodes and routes in IoT networks and by optimizing traffic flow to minimize latency.

show abstract

“…Studies have been conducted in optimising power efficiency and architectures in data centres and core networks to be able to fulfil the rapidly increasing demand for data rates and energy efficiency [1]- [10]. Several challenges and issues have risen with conventional data centres which resulted in several researches to develop alternative designs and approaches to provide solutions for scalability, reliability and efficiency in current data centres [11]- [18], [22]- [41].…”

Section: Introductionmentioning

confidence: 99%

TDM/WDM over AWGR Based Passive Optical Network Data Centre Architecture

Eltraify

Musa

Elmirghani

2019

2019 21st International Conference on Transparent Optical Networks (ICTON)

Self Cite

View full text Add to dashboard Cite

Passive Optical Data Centre Networks have been developed due to the performance limitations in current data centres to provide high performance within data centre networks. An AWGR based passive optical network data centre architecture is evaluated using a TDM/WDM multiple access technique to provision the flow of traffic among the network efficiently. A Mixed Integer Linear Programming model is developed to optimise resource allocation in the architecture. Using WDM-TDM as a multiple access technique helps in solving issues such as oversubscription and congestion by allowing servers to make simultaneous transmissions of packets in different time slots. The results show that the provisioning / allocation of resource within the architecture is improved with improvements of up to 75% in resource utilisation. WDM-TDM PON-BASED DATA CENTRE ARCHITECTUREIn this architecture each PON Cell contains two AWGRs as shown in Figure.1, to provision full interconnection between the 4 racks. Each rack contains 32 servers, using 4 different wavelengths. A 1: N AWGR connects the racks and the OLT. The network interface card of each server contains an array of photo detectors for wavelength detection and tuneable lasers for wavelength selection [11].Inter-rack communication is done through the direct AWGR link or through the OLT. The AWGR selects the wavelength for transmission according to the location of the destination server, and servers communicate according to an AWGR wavelength routing interconnection map. The availability of alternative routes provides multi-path routing and enhances load balancing at high traffic load [11].

show abstract

Energy Efficiency of Server-Centric PON Data Center Architecture for Fog Computing

Cited by 21 publications

References 26 publications

Impact of Link Failures on the Performance of MapReduce in Data Center Networks

Impact of Link Failures on the Performance of MapReduce in Data Center Networks

Resilient Service Embedding in IoT Networks

TDM/WDM over AWGR Based Passive Optical Network Data Centre Architecture

Contact Info

Product

Resources

About