Pub Date : 2014-10-01DOI: 10.1109/CCEM.2014.7015495
M. Shashidhara, C. P. Jaini
The on-demand, pay-per-use, and scalable services provided in cloud model guarantee to reduce capital as well as running expenditures for both hardware and software. In cloud environment, users can remotely store their data and access them from a shared pool of configurable computing resources, without local data storage burden. We discuss various methods related to the security and privacy capabilities in cloud paradigm especially data storage in multi cloud environment. We provide three models in form of multicloud architectures which allow categorizing the schemes and analyze them according to their security benefits. The different methods include, resource replication, split application system into tiers based on PIR methods, split both application logic and data into segments. In addition, since the integrity protection of data is a fearsome task in Cloud computing for users with limited computing resources, vulnerabilities in user data privacy are also possible in third party auditing. So we propose a safe cloud storage methodology which supports privacy-preserving third party auditing. And we study the outcomes to perform audits concurrently for multiple users in an efficient manner. Experimental results show that the third party auditing computation time is better than existing approach.
{"title":"Privacy Preserving Third Party Auditing in Multi Cloud Storage Environment","authors":"M. Shashidhara, C. P. Jaini","doi":"10.1109/CCEM.2014.7015495","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015495","url":null,"abstract":"The on-demand, pay-per-use, and scalable services provided in cloud model guarantee to reduce capital as well as running expenditures for both hardware and software. In cloud environment, users can remotely store their data and access them from a shared pool of configurable computing resources, without local data storage burden. We discuss various methods related to the security and privacy capabilities in cloud paradigm especially data storage in multi cloud environment. We provide three models in form of multicloud architectures which allow categorizing the schemes and analyze them according to their security benefits. The different methods include, resource replication, split application system into tiers based on PIR methods, split both application logic and data into segments. In addition, since the integrity protection of data is a fearsome task in Cloud computing for users with limited computing resources, vulnerabilities in user data privacy are also possible in third party auditing. So we propose a safe cloud storage methodology which supports privacy-preserving third party auditing. And we study the outcomes to perform audits concurrently for multiple users in an efficient manner. Experimental results show that the third party auditing computation time is better than existing approach.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133535593","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015489
Irene Kafeza, E. Kafeza, E. Panas
In an increasingly integrated global economy the importance as well as the growing availability of Cloud Providers has provided companies, individuals and the Governmental agencies with a variety of benefits such as significant cost reduction. As the role and number of Cloud Providers has increased a novel set of issues has emerged. These novel issues refer to a variety of legal complexities from the initial choice of the proper Cloud Provider as well as the appropriate contract for the deployment of its services. This paper is concerned with the novel issues arising of the deployment of Cloud Computing contracts. It presents the related issues and discusses ways and suggestions by which the legal framework could be demystified so that the contracts conducted in the Cloud Computing environment can be conducted efficiently and in a legal manner, for the benefit of the private as well as the public sector. It is concerned that the current legal framework cannot provide solution for effective deployment of Cloud Computing contracts and drawing on this evidence, it discusses the steps that Cloud Computing participants need to take to correctly identify their contractual rights and obligations.
{"title":"Contracts in Cloud Computing","authors":"Irene Kafeza, E. Kafeza, E. Panas","doi":"10.1109/CCEM.2014.7015489","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015489","url":null,"abstract":"In an increasingly integrated global economy the importance as well as the growing availability of Cloud Providers has provided companies, individuals and the Governmental agencies with a variety of benefits such as significant cost reduction. As the role and number of Cloud Providers has increased a novel set of issues has emerged. These novel issues refer to a variety of legal complexities from the initial choice of the proper Cloud Provider as well as the appropriate contract for the deployment of its services. This paper is concerned with the novel issues arising of the deployment of Cloud Computing contracts. It presents the related issues and discusses ways and suggestions by which the legal framework could be demystified so that the contracts conducted in the Cloud Computing environment can be conducted efficiently and in a legal manner, for the benefit of the private as well as the public sector. It is concerned that the current legal framework cannot provide solution for effective deployment of Cloud Computing contracts and drawing on this evidence, it discusses the steps that Cloud Computing participants need to take to correctly identify their contractual rights and obligations.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125612341","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015476
M. Sriram, V. Patel, D. Harishma, N. Lakshmanan
Data Outsourcing has evolved rapidly with the advent of cloud computing wherein third parties provide storage services. Insider attacks still continue to haunt cloud users as they tend to cause unprecedented damage, especially when privileged users who have access to sensitive information go rogue. Many proposals have been made to Secure the Cloud from Insider threat Attacks and most of the standard approaches have been proven to fail from time to time. In this paper, an implementation of a Hybrid protocol that uses Selective Encryption with data cleaning, Enhanced Neural Network based user profiling and decoy technology to combat the insider threat has been proposed. The proposed system gave unprecedented level of security.
{"title":"A Hybrid Protocol to Secure the Cloud from Insider Threats","authors":"M. Sriram, V. Patel, D. Harishma, N. Lakshmanan","doi":"10.1109/CCEM.2014.7015476","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015476","url":null,"abstract":"Data Outsourcing has evolved rapidly with the advent of cloud computing wherein third parties provide storage services. Insider attacks still continue to haunt cloud users as they tend to cause unprecedented damage, especially when privileged users who have access to sensitive information go rogue. Many proposals have been made to Secure the Cloud from Insider threat Attacks and most of the standard approaches have been proven to fail from time to time. In this paper, an implementation of a Hybrid protocol that uses Selective Encryption with data cleaning, Enhanced Neural Network based user profiling and decoy technology to combat the insider threat has been proposed. The proposed system gave unprecedented level of security.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132908499","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015477
T. Ashwin, Shridhar G. Domanal, R. R. Guddeti
Load Balancing plays an important role in managing the software and the hardware components of cloud. In this present scenario the load balancing algorithm should be efficient in allocating the requested resource and also in the usage of the resources so that the over/underutilization of the resources will not occur in the cloud environment. In the present work, the allocation of all the available Virtual Machines is done in an efficient manner by Particle Swarm Optimization load balancing algorithm. Further, we have used cloudsim simulator to compare and analyze the performance of our algorithm. Simulation results demonstrate that the proposed algorithm distributes the load on all the available virtual machines uniformly i.e, without any under/over utilization and also the average response time is better compared to all existing scheduling algorithms.
{"title":"A Novel Bio-Inspired Load Balancing of Virtualmachines in Cloud Environment","authors":"T. Ashwin, Shridhar G. Domanal, R. R. Guddeti","doi":"10.1109/CCEM.2014.7015477","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015477","url":null,"abstract":"Load Balancing plays an important role in managing the software and the hardware components of cloud. In this present scenario the load balancing algorithm should be efficient in allocating the requested resource and also in the usage of the resources so that the over/underutilization of the resources will not occur in the cloud environment. In the present work, the allocation of all the available Virtual Machines is done in an efficient manner by Particle Swarm Optimization load balancing algorithm. Further, we have used cloudsim simulator to compare and analyze the performance of our algorithm. Simulation results demonstrate that the proposed algorithm distributes the load on all the available virtual machines uniformly i.e, without any under/over utilization and also the average response time is better compared to all existing scheduling algorithms.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126149356","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015497
Mohammed Alrokayan, Amir Vahid Dastjerdi, R. Buyya
The stunning growth in data has immensely impacted organizations. Their infrastructure and traditional data management system could not keep up to scale of Big Data. They have to either invest heavily on their infrastructure or move their Big Data analytics to Cloud where they can benefit from both on-demand scalability and contemporary data management techniques. However, to make Cloud hosted Big Data analytics available to wider range of enterprises, we have to carefully capture their preferences in terms of budget and service level objectives. Therefore, this study aims at proposing a SLA and cost-aware resource provisioning and task scheduling approach tailored for Big Data applications in the Cloud. Current approaches assume that data is pre-stored in cluster nodes prior to deployment of Big Data applications. In addition, their focus is purely on task scheduling, and not virtual machine provisioning. We argue that in the Cloud computing context this is not applicable, because the nodes are provisioned dynamically (data cannot be pre-stored) and leaving provisioning to user may lead to under or over provisioning that can both lead to SLA or budget constraint violations. Therefore,in this study we first model the user request, which consist of Big Data analytics jobs with budget and deadline. Then, we model infrastructures as a list of data centers, virtual machines (offered in a pay-as-you-go model), data sources, and network throughputs. After that, to address the aforementioned issues, we propose and compare cost-aware and SLA-based algorithms which provision cloud resources and schedule analytics tasks.
{"title":"SLA-Aware Provisioning and Scheduling of Cloud Resources for Big Data Analytics","authors":"Mohammed Alrokayan, Amir Vahid Dastjerdi, R. Buyya","doi":"10.1109/CCEM.2014.7015497","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015497","url":null,"abstract":"The stunning growth in data has immensely impacted organizations. Their infrastructure and traditional data management system could not keep up to scale of Big Data. They have to either invest heavily on their infrastructure or move their Big Data analytics to Cloud where they can benefit from both on-demand scalability and contemporary data management techniques. However, to make Cloud hosted Big Data analytics available to wider range of enterprises, we have to carefully capture their preferences in terms of budget and service level objectives. Therefore, this study aims at proposing a SLA and cost-aware resource provisioning and task scheduling approach tailored for Big Data applications in the Cloud. Current approaches assume that data is pre-stored in cluster nodes prior to deployment of Big Data applications. In addition, their focus is purely on task scheduling, and not virtual machine provisioning. We argue that in the Cloud computing context this is not applicable, because the nodes are provisioned dynamically (data cannot be pre-stored) and leaving provisioning to user may lead to under or over provisioning that can both lead to SLA or budget constraint violations. Therefore,in this study we first model the user request, which consist of Big Data analytics jobs with budget and deadline. Then, we model infrastructures as a list of data centers, virtual machines (offered in a pay-as-you-go model), data sources, and network throughputs. After that, to address the aforementioned issues, we propose and compare cost-aware and SLA-based algorithms which provision cloud resources and schedule analytics tasks.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129171241","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015485
Naveen Shivaramu Yeshodara, Namratha S. Nagojappa, Nikhitha Kishore
This paper presents a novel idea for reducing the data storage problems in the self-driving cars. Self-driving cars is a technology that is observed by the modern word with most curiosity. However the vulnerability with the car is the growing data and the approach for handling such huge amount of data growth. This paper proposes a cloud based self-driving car which can optimize the data storage problems in such cars. The idea is to not store any data in the car, rather download everything from the cloud as per the need of the travel. This allows the car to not keep a huge amount of data and rely on a cloud infrastructure for the drive.
{"title":"Cloud Based Self Driving Cars","authors":"Naveen Shivaramu Yeshodara, Namratha S. Nagojappa, Nikhitha Kishore","doi":"10.1109/CCEM.2014.7015485","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015485","url":null,"abstract":"This paper presents a novel idea for reducing the data storage problems in the self-driving cars. Self-driving cars is a technology that is observed by the modern word with most curiosity. However the vulnerability with the car is the growing data and the approach for handling such huge amount of data growth. This paper proposes a cloud based self-driving car which can optimize the data storage problems in such cars. The idea is to not store any data in the car, rather download everything from the cloud as per the need of the travel. This allows the car to not keep a huge amount of data and rely on a cloud infrastructure for the drive.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116731111","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015494
Tiago Justino, R. Buyya
Mobile Cloud Computing enables augmenting mobile device capabilities and increasing battery lifetime through the extension of cloud services and resources, resulting in an enhanced user experience. However, the development of a mobile cloud application is challenging because it involves dealing with different cloud providers and mobile platforms. To tackle the above issues, a mobile cloud architecture is proposed to asynchronously delegate resource-intensive mobile tasks in order to alleviate the mobile device load and, consequently, extend the battery life. We demonstrate this capability by developing an interface that supports the delegation of heavy tasks from mobile apps running under the Android mobile platform to a cloud computing environment managed by the Aneka Cloud Application Platform. The Aneka Mobile Client Library encapsulates the processes of communicating to cloud is provided, thus, the effort and complexity of developing a mobile cloud application is decreased. Two different resource-intensive mobile application are presented in order to show the library effectiveness. A performance evaluation is conducted showing the feasibility of architecture through the reduction of application execution time and extension of mobile device battery life.
{"title":"Outsourcing Resource-Intensive Tasks from Mobile Apps to Clouds: Android and Aneka Integration","authors":"Tiago Justino, R. Buyya","doi":"10.1109/CCEM.2014.7015494","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015494","url":null,"abstract":"Mobile Cloud Computing enables augmenting mobile device capabilities and increasing battery lifetime through the extension of cloud services and resources, resulting in an enhanced user experience. However, the development of a mobile cloud application is challenging because it involves dealing with different cloud providers and mobile platforms. To tackle the above issues, a mobile cloud architecture is proposed to asynchronously delegate resource-intensive mobile tasks in order to alleviate the mobile device load and, consequently, extend the battery life. We demonstrate this capability by developing an interface that supports the delegation of heavy tasks from mobile apps running under the Android mobile platform to a cloud computing environment managed by the Aneka Cloud Application Platform. The Aneka Mobile Client Library encapsulates the processes of communicating to cloud is provided, thus, the effort and complexity of developing a mobile cloud application is decreased. Two different resource-intensive mobile application are presented in order to show the library effectiveness. A performance evaluation is conducted showing the feasibility of architecture through the reduction of application execution time and extension of mobile device battery life.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114623545","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015479
Devwrat More, Sanket Vaibhav Mehta, Pooja Pathak, Lokesh Walase, J. Abraham
Emergence of cloud computing has provided an efficient platform for distributed utility computing. But, the huge amount of energy consumed in cloud environment has raised many environmental concerns. To solve the issue of energy consumption in cloud environment, the design of energy efficient mechanism must start to play a major role. The paper addresses this issue by proposing Energy Manager which governs activities in cloud to attain optimal energy utilization. The Energy Manager takes into account resource utilization, CPU frequency, supply voltage and effect of all these on response time. In a novel way, it uses soft scaling as a precursor to Dynamic Voltage and Frequency Scaling (DVFS) to enhance the effectiveness of DVFS in virtualized environment. It implements DVFS, Virtual Machine (VM) migration and consolidation, soft scaling, and power state switching techniques to achieve the objective.
{"title":"Achieving Energy Efficiency by Optimal Resource Utilisation in Cloud Environment","authors":"Devwrat More, Sanket Vaibhav Mehta, Pooja Pathak, Lokesh Walase, J. Abraham","doi":"10.1109/CCEM.2014.7015479","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015479","url":null,"abstract":"Emergence of cloud computing has provided an efficient platform for distributed utility computing. But, the huge amount of energy consumed in cloud environment has raised many environmental concerns. To solve the issue of energy consumption in cloud environment, the design of energy efficient mechanism must start to play a major role. The paper addresses this issue by proposing Energy Manager which governs activities in cloud to attain optimal energy utilization. The Energy Manager takes into account resource utilization, CPU frequency, supply voltage and effect of all these on response time. In a novel way, it uses soft scaling as a precursor to Dynamic Voltage and Frequency Scaling (DVFS) to enhance the effectiveness of DVFS in virtualized environment. It implements DVFS, Virtual Machine (VM) migration and consolidation, soft scaling, and power state switching techniques to achieve the objective.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126778256","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015481
Mahesh Babu Bondada, S. M. Bhanu
Nowadays cloud computing is growing vastly as the number of companies are depending mostly on this technology due to its advantages. All the data are stored across the globe and maintained by the cloud service providers i.e., the responsibility of the data is in the hands of cloud providers. The data breach is a biggest problem in cloud as the data are shared across the globe and sensitive information of the customer is stored at some third party storage site. Security of the data is the major concern in cloud from outsiders as well as insiders. Insider attack is the most devastating threat due to the familiarity of the underlying system to the insiders. The proposed approach mitigates this threat by a host based user profiling technique where a key stroke dynamics is used for analyzing the user behavior and a retraining approach is also proposed as the imposter patterns are absent at the time of registration. Retraining boosts the overall system performance in mitigating the insider threat.
{"title":"Analyzing User Behavior Using Keystroke Dynamics to Protect Cloud from Malicious Insiders","authors":"Mahesh Babu Bondada, S. M. Bhanu","doi":"10.1109/CCEM.2014.7015481","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015481","url":null,"abstract":"Nowadays cloud computing is growing vastly as the number of companies are depending mostly on this technology due to its advantages. All the data are stored across the globe and maintained by the cloud service providers i.e., the responsibility of the data is in the hands of cloud providers. The data breach is a biggest problem in cloud as the data are shared across the globe and sensitive information of the customer is stored at some third party storage site. Security of the data is the major concern in cloud from outsiders as well as insiders. Insider attack is the most devastating threat due to the familiarity of the underlying system to the insiders. The proposed approach mitigates this threat by a host based user profiling technique where a key stroke dynamics is used for analyzing the user behavior and a retraining approach is also proposed as the imposter patterns are absent at the time of registration. Retraining boosts the overall system performance in mitigating the insider threat.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121540317","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 : 2014-10-01DOI: 10.1109/CCEM.2014.7015488
Vedsar Kushwaha, Yogesh L. Simmhan
Public Clouds offer elastic computing resources on- demand using a pay-as-you-go model. While this has opened up access to computing infrastructure, the costs for accessing Cloud resources can be a barrier to adoption in emerging markets. Spot- priced virtual machines (VMs) are offered at deep discounts for the same compute capability as fixed price on-demand VMs. But they can be reclaimed by the Cloud provider at any time, affecting reliability. This paper characterises the behaviour of spot-priced VM from Amazon Web Service for the Asia-Pacific and US East Regions, and analyses their practical impact on running jobs on spot VMs. Our simulation study using jobs of diverse sizes evaluates the trade-offs between cost savings over fixed price VMs and job resilience. Our results show that in most cases, for the workloads studied, we can achieve an effective bottom-line cost savings of 80 using spot VMs, with over 95 reliability.
公共云使用按需付费模式提供弹性计算资源。虽然这打开了对计算基础设施的访问，但访问云资源的成本可能成为新兴市场采用云计算的障碍。现货价格的虚拟机(vm)提供与固定价格的按需虚拟机相同的计算能力的大幅折扣。但是它们可以随时被云提供商回收，从而影响可靠性。本文描述了Amazon Web Service在亚太和美国东部地区的现货价格VM的行为，并分析了它们对现货VM上运行作业的实际影响。我们的模拟研究使用不同规模的工作来评估固定价格虚拟机的成本节约和工作弹性之间的权衡。我们的结果表明，在大多数情况下，对于所研究的工作负载，我们可以使用spot vm实现有效的底线成本节约80，可靠性超过95。
{"title":"Cloudy with a Spot of Opportunity: Analysis of Spot-Priced VMs for Practical Job Scheduling","authors":"Vedsar Kushwaha, Yogesh L. Simmhan","doi":"10.1109/CCEM.2014.7015488","DOIUrl":"https://doi.org/10.1109/CCEM.2014.7015488","url":null,"abstract":"Public Clouds offer elastic computing resources on- demand using a pay-as-you-go model. While this has opened up access to computing infrastructure, the costs for accessing Cloud resources can be a barrier to adoption in emerging markets. Spot- priced virtual machines (VMs) are offered at deep discounts for the same compute capability as fixed price on-demand VMs. But they can be reclaimed by the Cloud provider at any time, affecting reliability. This paper characterises the behaviour of spot-priced VM from Amazon Web Service for the Asia-Pacific and US East Regions, and analyses their practical impact on running jobs on spot VMs. Our simulation study using jobs of diverse sizes evaluates the trade-offs between cost savings over fixed price VMs and job resilience. Our results show that in most cases, for the workloads studied, we can achieve an effective bottom-line cost savings of 80 using spot VMs, with over 95 reliability.","PeriodicalId":143177,"journal":{"name":"2014 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130513040","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：