Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987265
Sourav Medya, L. Cherkasova, Ambuj K. Singh
Many HPC and modern large graph processing applications belong to a class of scale-out applications, where the application dataset is partitioned and processed by a cluster of machines. Assessing the application scalability is one of the primary goals during such application implementation. Typically, in the design phase, programmers are limited by a small size cluster available for their experiments. Therefore, predictive modeling is required for the analysis of the application scalability and its performance in a larger cluster. While in an increased size cluster, each node will process a smaller portion of the original dataset, a higher communication volume between a larger number of nodes may cripple the application scalability and provide diminishing performance benefits. One of the main challenges is the analysis of bandwidth demands due to an increased communication volume in a larger size cluster. In this paper1, we introduce a novel regression-based approach to assess the scalability and performance of a distributed memory program for execution in a large-scale cluster. Our solution involves 1) a limited set of traditional experiments performed in a small size cluster and 2) an additional set of similar experiments performed with an “interconnect bandwidth throttling” tool, which exposes the bandwidth impact on the application performance. These measurements are used in creating an ensemble of analytical models for performance and scalability analysis. Using a linear regression approach, step by step, we incorporate into the model the following important parameters: i) the number of cluster nodes and application processes, ii) the dataset size, and iii) interconnect bandwidth. We demonstrate our solution, its power, and accuracy using a popular Graph500 benchmark, which implements a Breadth First Search algorithm on large, synthetically generated graphs. By utilizing measurements collected in a 32-node cluster, we are able to project the program performance in a large size cluster with hundreds of nodes. The proposed approach and derived models help to provide an early feedback to programmers on the scalability and efficiency of their solution.
{"title":"Predictive modeling and scalability analysis for large graph analytics","authors":"Sourav Medya, L. Cherkasova, Ambuj K. Singh","doi":"10.23919/INM.2017.7987265","DOIUrl":"https://doi.org/10.23919/INM.2017.7987265","url":null,"abstract":"Many HPC and modern large graph processing applications belong to a class of scale-out applications, where the application dataset is partitioned and processed by a cluster of machines. Assessing the application scalability is one of the primary goals during such application implementation. Typically, in the design phase, programmers are limited by a small size cluster available for their experiments. Therefore, predictive modeling is required for the analysis of the application scalability and its performance in a larger cluster. While in an increased size cluster, each node will process a smaller portion of the original dataset, a higher communication volume between a larger number of nodes may cripple the application scalability and provide diminishing performance benefits. One of the main challenges is the analysis of bandwidth demands due to an increased communication volume in a larger size cluster. In this paper1, we introduce a novel regression-based approach to assess the scalability and performance of a distributed memory program for execution in a large-scale cluster. Our solution involves 1) a limited set of traditional experiments performed in a small size cluster and 2) an additional set of similar experiments performed with an “interconnect bandwidth throttling” tool, which exposes the bandwidth impact on the application performance. These measurements are used in creating an ensemble of analytical models for performance and scalability analysis. Using a linear regression approach, step by step, we incorporate into the model the following important parameters: i) the number of cluster nodes and application processes, ii) the dataset size, and iii) interconnect bandwidth. We demonstrate our solution, its power, and accuracy using a popular Graph500 benchmark, which implements a Breadth First Search algorithm on large, synthetically generated graphs. By utilizing measurements collected in a 32-node cluster, we are able to project the program performance in a large size cluster with hundreds of nodes. The proposed approach and derived models help to provide an early feedback to programmers on the scalability and efficiency of their solution.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115902421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987389
Nasim Beigi Mohammadi, Hamzeh Khazaei, Mark Shtern, C. Barna, Marin Litoiu
In this paper, we present an architecture and implementation for self-managing cloud application using overlay networks and software defined networking (SDN). Through real world experiments on Amazon EC2 and Smart Applications on Virtual Infrastructure (SAVI) cloud, we demonstrate how our management mechanism autonomously maintains SLAs of application scenarios without provisioning extra resources.
{"title":"Implementation of self-managing applications on cloud using overlay networks","authors":"Nasim Beigi Mohammadi, Hamzeh Khazaei, Mark Shtern, C. Barna, Marin Litoiu","doi":"10.23919/INM.2017.7987389","DOIUrl":"https://doi.org/10.23919/INM.2017.7987389","url":null,"abstract":"In this paper, we present an architecture and implementation for self-managing cloud application using overlay networks and software defined networking (SDN). Through real world experiments on Amazon EC2 and Smart Applications on Virtual Infrastructure (SAVI) cloud, we demonstrate how our management mechanism autonomously maintains SLAs of application scenarios without provisioning extra resources.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"346 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124265403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987418
Maha Mdini, Alberto Blanc, G. Simon, Jerome Barotin, Julien Lecoeuvre
For a successful and efficient network supervision, an Anomaly Detection System is essential. In this paper, our goal is to develop a simple, practical, and application-domain specific approach to identify anomalies in the input/output data of network probes. Since data are periodic and continuously evolving, it is not possible to use threshold-based approaches. We propose an algorithm based on pattern recognition to help mobile operators detect anomalies in real time. The algorithm is unsupervised and easily configurable with a small number of tuning parameters. After weeks of deployment in a production network monitoring system, we obtain satisfactory results: we detect major anomalies with low error rate.
{"title":"Monitoring the network monitoring system: Anomaly Detection using pattern recognition","authors":"Maha Mdini, Alberto Blanc, G. Simon, Jerome Barotin, Julien Lecoeuvre","doi":"10.23919/INM.2017.7987418","DOIUrl":"https://doi.org/10.23919/INM.2017.7987418","url":null,"abstract":"For a successful and efficient network supervision, an Anomaly Detection System is essential. In this paper, our goal is to develop a simple, practical, and application-domain specific approach to identify anomalies in the input/output data of network probes. Since data are periodic and continuously evolving, it is not possible to use threshold-based approaches. We propose an algorithm based on pattern recognition to help mobile operators detect anomalies in real time. The algorithm is unsupervised and easily configurable with a small number of tuning parameters. After weeks of deployment in a production network monitoring system, we obtain satisfactory results: we detect major anomalies with low error rate.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"393 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124398379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987326
Morteza Moghaddassian, H. Bannazadeh, A. Leon-Garcia
Auto-scaling is a key challenge and benefit in cloud computing infrastructures where applications are deployed on one or more virtual machines (VMs) to balance efficiency in use against delivered performance. In different scenarios, there may be a need for either horizontal or vertical scaling. Therefore, scaling is an important operation of cloud management systems. One way to enable scaling as an automated service is to use a model to predict the VM's future state as a function of time. However, this method is not completely feasible, because the performance of a VM is so dynamic and depends on many parameters. A simpler approach to enable auto-scaling is to use real-time utilization data of VM's and a set of fixed thresholds to execute scaling when thresholds are crossed. However, this method is prone to false positive decisions. Uses this paper, we propose an adaptive method that uses threshold-based mechanisms to control the auto-scaling process and leverages the accuracy and precision given by threshold-based methods to reduce the number of false positives. We present performance results, comparing the fixed threshold methods with our proposed method. We show that our method frequently correctly triggers scaling process in situations where fixed threshold based measurement methods fail.
{"title":"Adaptive auto-scaling for virtual resources in software-defined infrastructure","authors":"Morteza Moghaddassian, H. Bannazadeh, A. Leon-Garcia","doi":"10.23919/INM.2017.7987326","DOIUrl":"https://doi.org/10.23919/INM.2017.7987326","url":null,"abstract":"Auto-scaling is a key challenge and benefit in cloud computing infrastructures where applications are deployed on one or more virtual machines (VMs) to balance efficiency in use against delivered performance. In different scenarios, there may be a need for either horizontal or vertical scaling. Therefore, scaling is an important operation of cloud management systems. One way to enable scaling as an automated service is to use a model to predict the VM's future state as a function of time. However, this method is not completely feasible, because the performance of a VM is so dynamic and depends on many parameters. A simpler approach to enable auto-scaling is to use real-time utilization data of VM's and a set of fixed thresholds to execute scaling when thresholds are crossed. However, this method is prone to false positive decisions. Uses this paper, we propose an adaptive method that uses threshold-based mechanisms to control the auto-scaling process and leverages the accuracy and precision given by threshold-based methods to reduce the number of false positives. We present performance results, comparing the fixed threshold methods with our proposed method. We show that our method frequently correctly triggers scaling process in situations where fixed threshold based measurement methods fail.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114448886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987458
Hisham Allahem, S. Sampalli
Premature birth is the leading cause of death in children under 5 years. Furthermore, surviving children can have a lifetime of disability such as hearing and vision loss or learning difficulties. Research suggests that monitoring uterine contractions can help in evaluating the health and progress of pregnancy, and also determine if the pregnant woman is in labour, and consequently mitigate the effects of premature labour. In this paper, we propose a safe, simple and low-cost system to monitor pregnant women who are at high risk of premature labour. Our system consists of a wireless body sensor network to non-invasively monitor the uterine contractions and trigger a warning via a smartphone if the readings are outside the normal thresholds. We have designed a proof-of-concept prototype and tested it for reliability, performance and power consumption.
{"title":"Framework to monitor pregnant women with a high risk of premature labour using sensor networks","authors":"Hisham Allahem, S. Sampalli","doi":"10.23919/INM.2017.7987458","DOIUrl":"https://doi.org/10.23919/INM.2017.7987458","url":null,"abstract":"Premature birth is the leading cause of death in children under 5 years. Furthermore, surviving children can have a lifetime of disability such as hearing and vision loss or learning difficulties. Research suggests that monitoring uterine contractions can help in evaluating the health and progress of pregnancy, and also determine if the pregnant woman is in labour, and consequently mitigate the effects of premature labour. In this paper, we propose a safe, simple and low-cost system to monitor pregnant women who are at high risk of premature labour. Our system consists of a wireless body sensor network to non-invasively monitor the uterine contractions and trigger a warning via a smartphone if the readings are outside the normal thresholds. We have designed a proof-of-concept prototype and tested it for reliability, performance and power consumption.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115036964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987334
Omer Narmanlioglu, E. Zeydan
In this paper, we propose a novel cellular network architecture including network virtualization controller for mobile core and backhaul sharing. Software-Defined Networking (SDN) based network virtualization is applied into Evolved Packet System (EPS) architecture of Long Term Evolution (LTE) networks. After virtualization of all evolved Node-Bs (eNodeBs) associated with different Mobile Operators (MOs) as a consequence of mobile core and backhaul sharing, the performances of eNodeB assignment mechanisms with the use of quality-of-service (QoS)-aware and QoS-unaware scheduling algorithms are investigated and compared with currently deployed static eNodeB distributions through Monte-Carlo simulations. Jain's fairness index, Shannon capacity and satisfied-MO-ratio are considered as the key performance indicators (KPIs). The results reveal that our proposed architecture outperforms the currently deployed network architecture as depending on proper scheduler selection.
本文提出了一种新的蜂窝网络架构，包括移动核心网络虚拟化控制器和回程共享。基于软件定义网络(SDN)的网络虚拟化技术被应用到LTE (Long Term Evolution)网络的EPS (Evolved Packet System)架构中。作为移动核心和回程共享的结果，对与不同移动运营商(MOs)相关的所有进化节点b (eNodeB)进行虚拟化后，研究了使用服务质量(QoS)感知和QoS不感知调度算法的eNodeB分配机制的性能，并通过蒙特卡洛模拟与当前部署的静态eNodeB分布进行了比较。将Jain公平性指数、Shannon容量和满足mo -ratio作为关键绩效指标。结果表明，我们提出的体系结构优于当前部署的网络体系结构，这取决于适当的调度程序选择。
{"title":"Network virtualization for Mobile Operators in Software-Defined based LTE networks","authors":"Omer Narmanlioglu, E. Zeydan","doi":"10.23919/INM.2017.7987334","DOIUrl":"https://doi.org/10.23919/INM.2017.7987334","url":null,"abstract":"In this paper, we propose a novel cellular network architecture including network virtualization controller for mobile core and backhaul sharing. Software-Defined Networking (SDN) based network virtualization is applied into Evolved Packet System (EPS) architecture of Long Term Evolution (LTE) networks. After virtualization of all evolved Node-Bs (eNodeBs) associated with different Mobile Operators (MOs) as a consequence of mobile core and backhaul sharing, the performances of eNodeB assignment mechanisms with the use of quality-of-service (QoS)-aware and QoS-unaware scheduling algorithms are investigated and compared with currently deployed static eNodeB distributions through Monte-Carlo simulations. Jain's fairness index, Shannon capacity and satisfied-MO-ratio are considered as the key performance indicators (KPIs). The results reveal that our proposed architecture outperforms the currently deployed network architecture as depending on proper scheduler selection.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116469850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987305
O. Komolafe
The increasing volume and importance of point-to-multipoint traffic in virtualized data centers means the deployment of IP multicast is increasingly attractive. However, concerns about the ability of switches and routers based on commodity hardware to support the conventional IP multicast control plane and data plane, especially when there are thousands of participants in the multicast group communication, results in the infrequent deployment of IP multicast in data centers. This paper discusses the evolution of data center architectures towards the virtualized architectures in which technologies such as VXLAN, VXLAN-GPE, GENEVE, STT and NVGRE are used to build emulated Layer 2 networks that will support multi-tenancy at scale. These technologies are described and compared in terms of a number of factors, with emphasis laid on the manner in which they support multicast. Lastly, innovative approaches that have been proposed to circumvent the obstacles to deploying multicast in the data center IP fabric are also discussed and evaluated.
{"title":"IP multicast in virtualized data centers: Challenges and opportunities","authors":"O. Komolafe","doi":"10.23919/INM.2017.7987305","DOIUrl":"https://doi.org/10.23919/INM.2017.7987305","url":null,"abstract":"The increasing volume and importance of point-to-multipoint traffic in virtualized data centers means the deployment of IP multicast is increasingly attractive. However, concerns about the ability of switches and routers based on commodity hardware to support the conventional IP multicast control plane and data plane, especially when there are thousands of participants in the multicast group communication, results in the infrequent deployment of IP multicast in data centers. This paper discusses the evolution of data center architectures towards the virtualized architectures in which technologies such as VXLAN, VXLAN-GPE, GENEVE, STT and NVGRE are used to build emulated Layer 2 networks that will support multi-tenancy at scale. These technologies are described and compared in terms of a number of factors, with emphasis laid on the manner in which they support multicast. Lastly, innovative approaches that have been proposed to circumvent the obstacles to deploying multicast in the data center IP fabric are also discussed and evaluated.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126150323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987268
Rafael Hansen da Silva, Weverton Cordeiro, L. Gaspary
One of the main challenges in Information Centric Networks (ICN) is providing access control to content publication and retrieval. Most of the existing approaches often consider a single user acting as publisher within a group. When dealing with multiple publishers, they may lead to a combinatorial explosion of cryptographic keys. Approaches that focus on multiple publishers, on the other hand, rely on specific network architectures and/or changes to operate. In this paper we propose a novel solution, supported by attribute-based encryption, for managing content access control. In our solution, we introduce secure content distribution groups, in which any member user can publish to and retrieve from. Unlike previous work, our solution keeps the number of cryptographic keys proportional to the number of group members, and may even be adopted gradually in any ICN architecture. The proposed solution is evaluated with respect to the overhead it imposes, number of required keys, and efficiency of content dissemination. In contrast to existing approaches, it offers higher access control flexibility, while reducing key management process complexity (in some scenarios, resulting in 97% less keys and objects in the network).
{"title":"A scalable approach for managing access control in Information Centric Networks","authors":"Rafael Hansen da Silva, Weverton Cordeiro, L. Gaspary","doi":"10.23919/INM.2017.7987268","DOIUrl":"https://doi.org/10.23919/INM.2017.7987268","url":null,"abstract":"One of the main challenges in Information Centric Networks (ICN) is providing access control to content publication and retrieval. Most of the existing approaches often consider a single user acting as publisher within a group. When dealing with multiple publishers, they may lead to a combinatorial explosion of cryptographic keys. Approaches that focus on multiple publishers, on the other hand, rely on specific network architectures and/or changes to operate. In this paper we propose a novel solution, supported by attribute-based encryption, for managing content access control. In our solution, we introduce secure content distribution groups, in which any member user can publish to and retrieve from. Unlike previous work, our solution keeps the number of cryptographic keys proportional to the number of group members, and may even be adopted gradually in any ICN architecture. The proposed solution is evaluated with respect to the overhead it imposes, number of required keys, and efficiency of content dissemination. In contrast to existing approaches, it offers higher access control flexibility, while reducing key management process complexity (in some scenarios, resulting in 97% less keys and objects in the network).","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129365762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987464
Mohit Taneja, A. Davy
With the evolving IoT scenario, computing has spread to the most minuscule everyday activities, leading to a momentous shift in the way applications are developed and deployed. With the volume of impact increasing exponentially, a coherent approach of deploying these applications is critical for an efficient utilization of the network infrastructure. A typical IoT application consists of various modules running together with active interdependencies; traditionally running on the Cloud hosted in global data centres. In this paper, we present a Module Mapping Algorithm for efficient utilization of resources in the network infrastructure by efficiently deploying Application Modules in Fog-Cloud Infrastructure for IoT based applications. With Fog computing into picture, computation is dynamically distributed across the Fog and Cloud layer, and the modules of an application can thus be deployed closer to the source on devices in the Fog layer. The result of this work can serve as a Micro-benchmark in studies/research related with IoT and Fog Computing, and can be used for Quality of Service (QoS) and Service Level Objective benchmarking for IoT applications. The approach is generic, and applies to a wide range of standardized IoT applications over varied network topologies irrespective of load.
{"title":"Resource aware placement of IoT application modules in Fog-Cloud Computing Paradigm","authors":"Mohit Taneja, A. Davy","doi":"10.23919/INM.2017.7987464","DOIUrl":"https://doi.org/10.23919/INM.2017.7987464","url":null,"abstract":"With the evolving IoT scenario, computing has spread to the most minuscule everyday activities, leading to a momentous shift in the way applications are developed and deployed. With the volume of impact increasing exponentially, a coherent approach of deploying these applications is critical for an efficient utilization of the network infrastructure. A typical IoT application consists of various modules running together with active interdependencies; traditionally running on the Cloud hosted in global data centres. In this paper, we present a Module Mapping Algorithm for efficient utilization of resources in the network infrastructure by efficiently deploying Application Modules in Fog-Cloud Infrastructure for IoT based applications. With Fog computing into picture, computation is dynamically distributed across the Fog and Cloud layer, and the modules of an application can thus be deployed closer to the source on devices in the Fog layer. The result of this work can serve as a Micro-benchmark in studies/research related with IoT and Fog Computing, and can be used for Quality of Service (QoS) and Service Level Objective benchmarking for IoT applications. The approach is generic, and applies to a wide range of standardized IoT applications over varied network topologies irrespective of load.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130000569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-05-01DOI: 10.23919/INM.2017.7987404
Tom De Schepper, Patrick Bosch, Ensar Zeljković, Koen De Schepper, Chris Hawinkel, Steven Latré, J. Famaey
The current local area networks (LANs) are occupied by a large variety of heterogeneous consumer devices, equipped with the ability to connect to the Internet using a variety of different network technologies (e.g., Ethernet, 2.4 and 5GHz Wi-Fi). Nevertheless, devices generally opt to statically connect using a single technology, based on predefined priorities. This static behaviour does not allow the network to unlock its full potential, which becomes increasingly more important as the requirements of services, in terms of latency and throughput, grow. In this paper we present a real-life SDN-based implementation of our previously proposed algorithm that addresses this problem.
{"title":"SDN-based transparent flow scheduling for heterogeneous wireless LANs","authors":"Tom De Schepper, Patrick Bosch, Ensar Zeljković, Koen De Schepper, Chris Hawinkel, Steven Latré, J. Famaey","doi":"10.23919/INM.2017.7987404","DOIUrl":"https://doi.org/10.23919/INM.2017.7987404","url":null,"abstract":"The current local area networks (LANs) are occupied by a large variety of heterogeneous consumer devices, equipped with the ability to connect to the Internet using a variety of different network technologies (e.g., Ethernet, 2.4 and 5GHz Wi-Fi). Nevertheless, devices generally opt to statically connect using a single technology, based on predefined priorities. This static behaviour does not allow the network to unlock its full potential, which becomes increasingly more important as the requirements of services, in terms of latency and throughput, grow. In this paper we present a real-life SDN-based implementation of our previously proposed algorithm that addresses this problem.","PeriodicalId":119633,"journal":{"name":"2017 IFIP/IEEE Symposium on Integrated Network and Service Management (IM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129146690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：