Pub Date : 2014-12-15DOI: 10.1109/CloudCom.2014.111
Brandon Amos, David Tompkins
This paper shares our experiences building and benchmarking Spindle as an open source Spark-based web analytics platform. Spindle's design has been motivated by real-world queries and data requiring concurrent, low latency query execution. We identify a search space of Spark tuning options and study their impact on Spark's performance. Results from a self-hosted six node cluster with one week of analytics data (13.1GB) indicate tuning options such as proper partitioning can cause a 5x performance improvement.
{"title":"Performance Study of Spindle, A Web Analytics Query Engine Implemented in Spark","authors":"Brandon Amos, David Tompkins","doi":"10.1109/CloudCom.2014.111","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.111","url":null,"abstract":"This paper shares our experiences building and benchmarking Spindle as an open source Spark-based web analytics platform. Spindle's design has been motivated by real-world queries and data requiring concurrent, low latency query execution. We identify a search space of Spark tuning options and study their impact on Spark's performance. Results from a self-hosted six node cluster with one week of analytics data (13.1GB) indicate tuning options such as proper partitioning can cause a 5x performance improvement.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114449634","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.62
Per-Olov Östberg, Henning Groenda, S. Wesner, James Byrne, Dimitrios S. Nikolopoulos, Craig Sheridan, Jakub Krzywda, A. Ali-Eldin, Johan Tordsson, E. Elmroth, Christian Stier, K. Krogmann, Jörg Domaschka, Christopher B. Hauser, P. J. Byrne, Sergej Svorobej, B. McCollum, Zafeirios C. Papazachos, D. Whigham, S. Ruth, Dragana Paurevic
Recent advances in hardware development coupled with the rapid adoption and broad applicability of cloud computing have introduced widespread heterogeneity in data centers, significantly complicating the management of cloud applications and data center resources. This paper presents the CACTOS approach to cloud infrastructure automation and optimization, which addresses heterogeneity through a combination of in-depth analysis of application behavior with insights from commercial cloud providers. The aim of the approach is threefold: to model applications and data center resources, to simulate applications and resources for planning and operation, and to optimize application deployment and resource use in an autonomic manner. The approach is based on case studies from the areas of business analytics, enterprise applications, and scientific computing.
{"title":"The CACTOS Vision of Context-Aware Cloud Topology Optimization and Simulation","authors":"Per-Olov Östberg, Henning Groenda, S. Wesner, James Byrne, Dimitrios S. Nikolopoulos, Craig Sheridan, Jakub Krzywda, A. Ali-Eldin, Johan Tordsson, E. Elmroth, Christian Stier, K. Krogmann, Jörg Domaschka, Christopher B. Hauser, P. J. Byrne, Sergej Svorobej, B. McCollum, Zafeirios C. Papazachos, D. Whigham, S. Ruth, Dragana Paurevic","doi":"10.1109/CloudCom.2014.62","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.62","url":null,"abstract":"Recent advances in hardware development coupled with the rapid adoption and broad applicability of cloud computing have introduced widespread heterogeneity in data centers, significantly complicating the management of cloud applications and data center resources. This paper presents the CACTOS approach to cloud infrastructure automation and optimization, which addresses heterogeneity through a combination of in-depth analysis of application behavior with insights from commercial cloud providers. The aim of the approach is threefold: to model applications and data center resources, to simulate applications and resources for planning and operation, and to optimize application deployment and resource use in an autonomic manner. The approach is based on case studies from the areas of business analytics, enterprise applications, and scientific computing.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127526270","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 : 2014-12-15DOI: 10.1109/CLOUDCOM.2014.108
Brian Schmidt, D. Kountanis, Ala Al-Fuqaha
Internet traffic classification has been researched extensively in the last 10 years, with a few different algorithms applied to it. Internet traffic classification has also become more relevant because of its potential applications in the business world. Having information about network traffic has many benefits in network design, security, management, and accounting. The classification of network traffic is most easily achieved by Machine Learning algorithms, which can automatically build a model from training data, without much input from humans. Artificial Immune System classification algorithms have been used previously to classify network connections in network security systems [1]. They have proven to be very versatile, as well as having low sensitivity to input parameters. Because of this we are encouraged to explore the value of AIS algorithms to the Internet traffic classification problem. In this research, we propose an AIS-inspired algorithm for flow-based traffic classification, where each network flow is classified into an application class. We measure the algorithm's performance with and without the use of kernel functions, using a publicly available data set. We also compare the algorithm's performance with SVM and Naive Bayes classifiers. The algorithm generalizes well and gives high accuracy even with a small training set when compared to other algorithms, although the training and classification times were higher. The algorithm is also insensitive to the use of kernels, which makes it attractive for embedded and IoT applications.
{"title":"Artificial Immune System Inspired Algorithm for Flow-Based Internet Traffic Classification","authors":"Brian Schmidt, D. Kountanis, Ala Al-Fuqaha","doi":"10.1109/CLOUDCOM.2014.108","DOIUrl":"https://doi.org/10.1109/CLOUDCOM.2014.108","url":null,"abstract":"Internet traffic classification has been researched extensively in the last 10 years, with a few different algorithms applied to it. Internet traffic classification has also become more relevant because of its potential applications in the business world. Having information about network traffic has many benefits in network design, security, management, and accounting. The classification of network traffic is most easily achieved by Machine Learning algorithms, which can automatically build a model from training data, without much input from humans. Artificial Immune System classification algorithms have been used previously to classify network connections in network security systems [1]. They have proven to be very versatile, as well as having low sensitivity to input parameters. Because of this we are encouraged to explore the value of AIS algorithms to the Internet traffic classification problem. In this research, we propose an AIS-inspired algorithm for flow-based traffic classification, where each network flow is classified into an application class. We measure the algorithm's performance with and without the use of kernel functions, using a publicly available data set. We also compare the algorithm's performance with SVM and Naive Bayes classifiers. The algorithm generalizes well and gives high accuracy even with a small training set when compared to other algorithms, although the training and classification times were higher. The algorithm is also insensitive to the use of kernels, which makes it attractive for embedded and IoT applications.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127570490","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.152
Fatma Masmoudi, M. Loulou, A. Kacem
Software as a Service (SaaS) is a delivery model in which software resources are accessed remotely by users. Multi-tenancy is one of key properties of SaaS to achieve higher profit margin by leveraging the economies of scale. This feature empowered by virtualization comes several new complexities introduced related to the area of accountability. For this purpose, we tackle the problem of integrating multi-tenancy in cloud services accountability and determine crucial issues that can be solved. To do this, we propose a multitenant services monitoring approach that keeps monitoring service execution at runtime and detecting privacy violations. This approach is based on multitenant accountability patterns for integrating multi-tenancy architecture and expressing rules that are enforced using AOP. Furthermore, we propose a middleware layer for implementing our approach into conventional cloud architecture. The performed evaluation proves the flexibility and the efficiency of our approach for services based applications in the cloud computing.
{"title":"Multi-tenant Services Monitoring for Accountability in Cloud Computing","authors":"Fatma Masmoudi, M. Loulou, A. Kacem","doi":"10.1109/CloudCom.2014.152","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.152","url":null,"abstract":"Software as a Service (SaaS) is a delivery model in which software resources are accessed remotely by users. Multi-tenancy is one of key properties of SaaS to achieve higher profit margin by leveraging the economies of scale. This feature empowered by virtualization comes several new complexities introduced related to the area of accountability. For this purpose, we tackle the problem of integrating multi-tenancy in cloud services accountability and determine crucial issues that can be solved. To do this, we propose a multitenant services monitoring approach that keeps monitoring service execution at runtime and detecting privacy violations. This approach is based on multitenant accountability patterns for integrating multi-tenancy architecture and expressing rules that are enforced using AOP. Furthermore, we propose a middleware layer for implementing our approach into conventional cloud architecture. The performed evaluation proves the flexibility and the efficiency of our approach for services based applications in the cloud computing.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"210 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121717950","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.41
Ansuman Dash, A. Banerjee
Making mobile applications energy efficient immensely builds user satisfaction. Apart from the fact that there are not many efficient techniques for evaluating energy consumption for applications on mobile devices, the methods used are static in nature. Static techniques assume that during the running of an application, no other process can run concurrently, and the concerned application has the entire CPU at its disposal. In this paper, we propose a novel idea of measuring the energy consumption of an application running on a mobile device considering the fact that not always the entire CPU is available. This is because the application may sometimes run in the foreground when the mobile is idle and therefore, use the maximum CPU available, at other times, there maybe other tasks being run (apart from the routine background tasks) by the user for which this application is forced to run in the background. The major highlight of this paper is in considering the concept of variable CPU availability in energy analysis. We have also suggested to model the energy consumption problem of a mobile phone as a finite state automaton, where our aim is to find if a state can be reached where the entire battery of the mobile phone is exhausted.
{"title":"When to Schedule an Application? An Energy-Aware Decision","authors":"Ansuman Dash, A. Banerjee","doi":"10.1109/CloudCom.2014.41","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.41","url":null,"abstract":"Making mobile applications energy efficient immensely builds user satisfaction. Apart from the fact that there are not many efficient techniques for evaluating energy consumption for applications on mobile devices, the methods used are static in nature. Static techniques assume that during the running of an application, no other process can run concurrently, and the concerned application has the entire CPU at its disposal. In this paper, we propose a novel idea of measuring the energy consumption of an application running on a mobile device considering the fact that not always the entire CPU is available. This is because the application may sometimes run in the foreground when the mobile is idle and therefore, use the maximum CPU available, at other times, there maybe other tasks being run (apart from the routine background tasks) by the user for which this application is forced to run in the background. The major highlight of this paper is in considering the concept of variable CPU availability in energy analysis. We have also suggested to model the energy consumption problem of a mobile phone as a finite state automaton, where our aim is to find if a state can be reached where the entire battery of the mobile phone is exhausted.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125032749","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.117
Aissan Dalvandi, G. Mohan, K. Chua
Power efficiency and predictable performance have become major concerns for cloud service providers as they significantly affect cloud adoption and tenancy cost. Providing guaranteed resources for predictable performance in data centers drives the need for a request model which abstracts the traffic characteristics as well as the resource requirements of tenant applications. In this paper, we propose a novel Sliding Scheduled Tenant (SST) request model which enables tenants to request their resources for an estimated required time duration which can slide within a certain time-window. We investigate the power-efficient resource-guaranteed Virtual Machine (VM) -placement and routing problem for dynamically arriving SST requests. The problem requires provisioning of the specified resources in a data center for the required duration of requests by choosing an appropriate start- and end-time within their specified time-window, so as to maximize the number of accepted requests while consuming as low power as possible. We develop a mixed integer linear programming (MILP) optimization problem formulation based on the multi-component utilization-based power model. Since this problem which is a combination of VMplacement, scheduling and routing problems, is computationally rohibitive, we develop a fast and scalable heuristic algorithm. We demonstrate the effectiveness of the proposed algorithm and SST request model in terms of power saving and acceptance ratio through comprehensive simulation results.
{"title":"Power-Efficient and Predictable Data Centers with Sliding Scheduled Tenant Requests","authors":"Aissan Dalvandi, G. Mohan, K. Chua","doi":"10.1109/CloudCom.2014.117","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.117","url":null,"abstract":"Power efficiency and predictable performance have become major concerns for cloud service providers as they significantly affect cloud adoption and tenancy cost. Providing guaranteed resources for predictable performance in data centers drives the need for a request model which abstracts the traffic characteristics as well as the resource requirements of tenant applications. In this paper, we propose a novel Sliding Scheduled Tenant (SST) request model which enables tenants to request their resources for an estimated required time duration which can slide within a certain time-window. We investigate the power-efficient resource-guaranteed Virtual Machine (VM) -placement and routing problem for dynamically arriving SST requests. The problem requires provisioning of the specified resources in a data center for the required duration of requests by choosing an appropriate start- and end-time within their specified time-window, so as to maximize the number of accepted requests while consuming as low power as possible. We develop a mixed integer linear programming (MILP) optimization problem formulation based on the multi-component utilization-based power model. Since this problem which is a combination of VMplacement, scheduling and routing problems, is computationally rohibitive, we develop a fast and scalable heuristic algorithm. We demonstrate the effectiveness of the proposed algorithm and SST request model in terms of power saving and acceptance ratio through comprehensive simulation results.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131495227","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.58
Rubing Duan, R. Prodan
We address the problem of scheduling a class of large-scale applications inspired from real-world on hybrid Clouds, characterized by a large number of homogeneous and concurrent tasks that are the main sources of bottlenecks but open great potential for optimization. We formulate the scheduling problem as a new sequential cooperative game and propose a communication- and storage-aware multi-objective algorithm that optimizes two user objectives (execution time and economic cost) while fulfilling two constraints (network bandwidth and storage requirements). We present comprehensive experiments using both simulation and real-world applications that demonstrate the efficiency and effectiveness of our approach in terms of algorithm complexity, make span, cost, system-level efficiency, fairness, and other aspects compared with other related algorithms.
{"title":"Cooperative Scheduling of Bag-of-Tasks Workflows on Hybrid Clouds","authors":"Rubing Duan, R. Prodan","doi":"10.1109/CloudCom.2014.58","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.58","url":null,"abstract":"We address the problem of scheduling a class of large-scale applications inspired from real-world on hybrid Clouds, characterized by a large number of homogeneous and concurrent tasks that are the main sources of bottlenecks but open great potential for optimization. We formulate the scheduling problem as a new sequential cooperative game and propose a communication- and storage-aware multi-objective algorithm that optimizes two user objectives (execution time and economic cost) while fulfilling two constraints (network bandwidth and storage requirements). We present comprehensive experiments using both simulation and real-world applications that demonstrate the efficiency and effectiveness of our approach in terms of algorithm complexity, make span, cost, system-level efficiency, fairness, and other aspects compared with other related algorithms.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131160705","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.107
Lifeng Wang, Zhengping Wu
Cloud computing provides many benefits for individuals and enterprises by offering a range of computing services. The service dynamism, elasticity, economy and choices are too attractive to ignore. At the meantime, cloud computing has opened up a new frontier of challenges by introducing trust scenario. The Trustworthiness Evaluation of cloud Services is a paramount concern. In this paper, we present a framework to quantitatively measure and rank the trustworthiness of cloud services. In particular, we address the fundamental understanding of trustworthiness, quantitative trustworthiness metrics, unified scale of trust factors, trust factors categorization, trust coordinate and multi-criteria analysis for trustworthiness decision making. Our comprehensive framework of trustworthiness evaluation contains five basic building blocks. The preprocessing block query and calculate the existent trustworthiness record. Then the trust factors are collected, if there was no match record found. The trust factor management block categorize the trust factors and convert them by using unified scale. The trust factor processing block is for weighting and positioning of trust factors. The trustworthiness decision making block provide calculation of cloud service trustworthiness, and the results are recorded in our trustworthiness record block. The proposed trustworthiness measurement framework is employed in several experiments by using existing trust dataset. The analysis based on the experiment result indicates our trustworthiness evaluation is accurate and flexible.
{"title":"A Trustworthiness Evaluation Framework in Cloud Computing for Service Selection","authors":"Lifeng Wang, Zhengping Wu","doi":"10.1109/CloudCom.2014.107","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.107","url":null,"abstract":"Cloud computing provides many benefits for individuals and enterprises by offering a range of computing services. The service dynamism, elasticity, economy and choices are too attractive to ignore. At the meantime, cloud computing has opened up a new frontier of challenges by introducing trust scenario. The Trustworthiness Evaluation of cloud Services is a paramount concern. In this paper, we present a framework to quantitatively measure and rank the trustworthiness of cloud services. In particular, we address the fundamental understanding of trustworthiness, quantitative trustworthiness metrics, unified scale of trust factors, trust factors categorization, trust coordinate and multi-criteria analysis for trustworthiness decision making. Our comprehensive framework of trustworthiness evaluation contains five basic building blocks. The preprocessing block query and calculate the existent trustworthiness record. Then the trust factors are collected, if there was no match record found. The trust factor management block categorize the trust factors and convert them by using unified scale. The trust factor processing block is for weighting and positioning of trust factors. The trustworthiness decision making block provide calculation of cloud service trustworthiness, and the results are recorded in our trustworthiness record block. The proposed trustworthiness measurement framework is employed in several experiments by using existing trust dataset. The analysis based on the experiment result indicates our trustworthiness evaluation is accurate and flexible.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132123318","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.50
David Nuñez, Isaac Agudo, Javier López
Among Big Data technologies, Hadoop stands out for its capacity to store and process large-scale datasets. However, although Hadoop was not designed with security in mind, it is widely used by plenty of organizations, some of which have strong data protection requirements. Traditional access control solutions are not enough, and cryptographic solutions must be put in place to protect sensitive information. In this paper, we describe a cryptographically-enforced access control system for Hadoop, based on proxy re-encryption. Our proposed solution fits in well with the outsourcing of Big Data processing to the cloud, since information can be stored in encrypted form in external servers in the cloud and processed only if access has been delegated. Experimental results show that the overhead produced by our solution is manageable, which makes it suitable for some applications.
{"title":"Delegated Access for Hadoop Clusters in the Cloud","authors":"David Nuñez, Isaac Agudo, Javier López","doi":"10.1109/CloudCom.2014.50","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.50","url":null,"abstract":"Among Big Data technologies, Hadoop stands out for its capacity to store and process large-scale datasets. However, although Hadoop was not designed with security in mind, it is widely used by plenty of organizations, some of which have strong data protection requirements. Traditional access control solutions are not enough, and cryptographic solutions must be put in place to protect sensitive information. In this paper, we describe a cryptographically-enforced access control system for Hadoop, based on proxy re-encryption. Our proposed solution fits in well with the outsourcing of Big Data processing to the cloud, since information can be stored in encrypted form in external servers in the cloud and processed only if access has been delegated. Experimental results show that the overhead produced by our solution is manageable, which makes it suitable for some applications.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114611207","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 : 2014-12-15DOI: 10.1109/CloudCom.2014.34
Raksha Srinivas, S. Hegde, D. Divakaran, G. Mohan
With ever increasing traffic demands, data enter networks are envisioned to be a hybrid of both optical and electrical networks. In this context, we consider the recently proposed dynamic wavelength grouping (DWG) architecture for the optical network. This architecture can dynamically group wavelengths from different ports onto a single fiber carrying fixed number of wavelength groups. We focus on the joint problem of VM-placement and bandwidth allocation in such a hybrid optical-electrical data enter network with DWG capability. There are multiple challenges: (i) the number of edge-switches that can be simultaneously reached using optical paths from an edge-switch is limited by cost, and (ii) wavelength-group continuity constraint. Abstracting the requests of tenants as virtual networks, we study the novel problem of embedding virtual networks on this hybrid datacenter, which translates to the joint problem of bandwidth allocation and placement such that the requirements of virtual networks are satisfied. We develop and analyse two algorithms for embedding dynamically arriving virtual network demands on a hybrid datacenter with DWG capability. The performance studies demonstrate the effectiveness of exploiting existing optical paths as well as using electrical links in the face of multiple constraints to accept higher number of requests.
{"title":"Virtual Network Embedding in Hybrid Datacenters with Dynamic Wavelength Grouping","authors":"Raksha Srinivas, S. Hegde, D. Divakaran, G. Mohan","doi":"10.1109/CloudCom.2014.34","DOIUrl":"https://doi.org/10.1109/CloudCom.2014.34","url":null,"abstract":"With ever increasing traffic demands, data enter networks are envisioned to be a hybrid of both optical and electrical networks. In this context, we consider the recently proposed dynamic wavelength grouping (DWG) architecture for the optical network. This architecture can dynamically group wavelengths from different ports onto a single fiber carrying fixed number of wavelength groups. We focus on the joint problem of VM-placement and bandwidth allocation in such a hybrid optical-electrical data enter network with DWG capability. There are multiple challenges: (i) the number of edge-switches that can be simultaneously reached using optical paths from an edge-switch is limited by cost, and (ii) wavelength-group continuity constraint. Abstracting the requests of tenants as virtual networks, we study the novel problem of embedding virtual networks on this hybrid datacenter, which translates to the joint problem of bandwidth allocation and placement such that the requirements of virtual networks are satisfied. We develop and analyse two algorithms for embedding dynamically arriving virtual network demands on a hybrid datacenter with DWG capability. The performance studies demonstrate the effectiveness of exploiting existing optical paths as well as using electrical links in the face of multiple constraints to accept higher number of requests.","PeriodicalId":249306,"journal":{"name":"2014 IEEE 6th International Conference on Cloud Computing Technology and Science","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114794126","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：