Recently, flexible networks contain various services designed and implemented by different vendors to accomplish specific tasks. Trust to security systems of such services is a significant challenge. In this paper, we propose a framework to assess trust to security systems of web services based on security policy specifications and security mechanisms running on flexible networks. The framework may be used to implement an automated system to assess trust of a specific security system protecting web services. The trust assessment process is explained with a scenario to show the applicability of the framework.
{"title":"A Framework for Trust Assessment of Security Systems on Flexible Networks","authors":"Şerif Bahtiyar, Orhan Ermis, M. Çaglayan","doi":"10.1109/FiCloud.2017.23","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.23","url":null,"abstract":"Recently, flexible networks contain various services designed and implemented by different vendors to accomplish specific tasks. Trust to security systems of such services is a significant challenge. In this paper, we propose a framework to assess trust to security systems of web services based on security policy specifications and security mechanisms running on flexible networks. The framework may be used to implement an automated system to assess trust of a specific security system protecting web services. The trust assessment process is explained with a scenario to show the applicability of the framework.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130800843","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}
Huy Trinh, D. Chemodanov, Shizeng Yao, Qing Lei, Bo Zhang, Fan Gao, P. Calyam, K. Palaniappan
New opportunities exist for applications such as disaster incident response that can benefit from the convergence of Internet of Things (IoT) and cloud computing technologies. Particularly, new paradigms such as Mobile Edge Computing (MEC) are becoming feasible to handle the data deluge occurring in the network edge to gain insights that assist in real-time decision making. In this paper, we study the potential of MEC to address application issues related to energy management on constrained IoT devices with limited power sources, while also providing low-latency processing of visual data being generated at high resolutions. Using a face recognition application that is important in disaster incident response scenarios, we analyze the tradeoffs in computing policies that offload visual data processing (i.e., to an edge cloud or a core cloud) at low-to-high workloads, and their impact on energy consumption under different visual data consumption requirements (i.e., users with thick clients or thin clients). From our empirical results obtained from experiments with our face recognition application on a realistic edge and core cloud testbed, we show how MEC can provide flexibility to users who desire energy conservation over low-latency or vice versa in the visual data processing.
{"title":"Energy-Aware Mobile Edge Computing for Low-Latency Visual Data Processing","authors":"Huy Trinh, D. Chemodanov, Shizeng Yao, Qing Lei, Bo Zhang, Fan Gao, P. Calyam, K. Palaniappan","doi":"10.1109/FiCloud.2017.13","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.13","url":null,"abstract":"New opportunities exist for applications such as disaster incident response that can benefit from the convergence of Internet of Things (IoT) and cloud computing technologies. Particularly, new paradigms such as Mobile Edge Computing (MEC) are becoming feasible to handle the data deluge occurring in the network edge to gain insights that assist in real-time decision making. In this paper, we study the potential of MEC to address application issues related to energy management on constrained IoT devices with limited power sources, while also providing low-latency processing of visual data being generated at high resolutions. Using a face recognition application that is important in disaster incident response scenarios, we analyze the tradeoffs in computing policies that offload visual data processing (i.e., to an edge cloud or a core cloud) at low-to-high workloads, and their impact on energy consumption under different visual data consumption requirements (i.e., users with thick clients or thin clients). From our empirical results obtained from experiments with our face recognition application on a realistic edge and core cloud testbed, we show how MEC can provide flexibility to users who desire energy conservation over low-latency or vice versa in the visual data processing.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134512174","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}
The purpose of the present study is to empirically investigate whether national culture has an impact on cybersecurity development. We used methods of correlation and hierarchical regression to analyse two sets of indices; the global cybersecurity index of 2015 and Hofstede cultural dimension index. The research discovered that there exist a significant correlation between cybersecurity development and the cultural dimensions as defined by Hofstede cultural theory. Five cultural dimensions were used in the study; power distance, masculinity/femininity, individualism/collectivism, uncertainty avoidance, long term/short term orientation, and the research found out that individualism and long term orientation were significantly correlated with cybersecurity development. These findings have strategic implications in helping government and decision makers fashion out relevant policies and programmes while taking into cognisance the cultural factors in the improvement of the cyberwellness profile and the development of strategic cybersecurity. Implications and recommendations for future work are further discussed.
{"title":"An Empirical Study of Cultural Dimensions and Cybersecurity Development","authors":"Aristotle Onumo, A. Cullen, I. Awan","doi":"10.1109/FiCloud.2017.41","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.41","url":null,"abstract":"The purpose of the present study is to empirically investigate whether national culture has an impact on cybersecurity development. We used methods of correlation and hierarchical regression to analyse two sets of indices; the global cybersecurity index of 2015 and Hofstede cultural dimension index. The research discovered that there exist a significant correlation between cybersecurity development and the cultural dimensions as defined by Hofstede cultural theory. Five cultural dimensions were used in the study; power distance, masculinity/femininity, individualism/collectivism, uncertainty avoidance, long term/short term orientation, and the research found out that individualism and long term orientation were significantly correlated with cybersecurity development. These findings have strategic implications in helping government and decision makers fashion out relevant policies and programmes while taking into cognisance the cultural factors in the improvement of the cyberwellness profile and the development of strategic cybersecurity. Implications and recommendations for future work are further discussed.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"59 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105078","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}
A. Galletta, Lorenzo Carnevale, A. Celesti, M. Fazio, M. Villari
Nowadays, more and more Cloud providers are appearing on the market. In this context, a typical issue is represented by the management of distributed services deployed on different federated Cloud providers. Assuming that a distributed service consists of several microservices, in this paper, we specifically focus on the setup of virtual environments and on deployment tasks required in each Federated Cloud providers In particular, we present BOSS an Orchestration Broker that starting from an ad-hoc OpenStack-based Heat Orchestration Template (HOT) service manifest produces several HOT microservice manifests including deployment instructions for involved Federated Clouds. Therefore, users can formalize advanced deployment constrains in terms of data export control, networking, and disaster recovery. Experiments prove the goodness of the proposed system in terms of performance.
{"title":"BOSS: A Multitenancy Ad-Hoc Service Orchestrator for Federated Openstack Clouds","authors":"A. Galletta, Lorenzo Carnevale, A. Celesti, M. Fazio, M. Villari","doi":"10.1109/FiCloud.2017.10","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.10","url":null,"abstract":"Nowadays, more and more Cloud providers are appearing on the market. In this context, a typical issue is represented by the management of distributed services deployed on different federated Cloud providers. Assuming that a distributed service consists of several microservices, in this paper, we specifically focus on the setup of virtual environments and on deployment tasks required in each Federated Cloud providers In particular, we present BOSS an Orchestration Broker that starting from an ad-hoc OpenStack-based Heat Orchestration Template (HOT) service manifest produces several HOT microservice manifests including deployment instructions for involved Federated Clouds. Therefore, users can formalize advanced deployment constrains in terms of data export control, networking, and disaster recovery. Experiments prove the goodness of the proposed system in terms of performance.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124664396","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}
System of Systems (SoS), are designed primarily to fill the highly increasingly complex business needs. The inherent complexity of SoS raises issues at its development, its deployment and its customization. It has been reported that the service orientation principles are beneficial to SoS engineering but they are not sufficient to support it. Cloud federation and Software as a Service (SaaS), as service oriented paradigms, are promising solutions for managing the complexity of SoS as well as its costly and complex required infrastructure. However, additional issues should be seriously considered in the construction of a SoS to tackle the dynamic nature of a federated cloud environment. Building a SoS upon existing systems deployed in a federated cloud environment may influence the overall performance of the SoS, which can raise challenges in its composition process. In this paper, we focus on how building, in flexible way, a SoS from a set of existing systems deployed on heterogeneous cloud environments. Thus, we propose a flexible composition approach of federated cloud based SoS by considering both the functional and non-functional requirements to obtain the best composition in terms of overall quality of service (QoS). We implement an agent based SoS composition simulator providing composition scenarios and their related QoS, and evaluating the different special cloud criterion that can influence the quality of SoS composition. The obtained results show that the number of cloud providers and services involved in SoS federation has a great impact on the overall SoS performance.
{"title":"Flexible Composition of System of Systems on Cloud Federation","authors":"Wided Mathlouthi, Narjès Bellamine Ben Saoud","doi":"10.1109/FiCloud.2017.18","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.18","url":null,"abstract":"System of Systems (SoS), are designed primarily to fill the highly increasingly complex business needs. The inherent complexity of SoS raises issues at its development, its deployment and its customization. It has been reported that the service orientation principles are beneficial to SoS engineering but they are not sufficient to support it. Cloud federation and Software as a Service (SaaS), as service oriented paradigms, are promising solutions for managing the complexity of SoS as well as its costly and complex required infrastructure. However, additional issues should be seriously considered in the construction of a SoS to tackle the dynamic nature of a federated cloud environment. Building a SoS upon existing systems deployed in a federated cloud environment may influence the overall performance of the SoS, which can raise challenges in its composition process. In this paper, we focus on how building, in flexible way, a SoS from a set of existing systems deployed on heterogeneous cloud environments. Thus, we propose a flexible composition approach of federated cloud based SoS by considering both the functional and non-functional requirements to obtain the best composition in terms of overall quality of service (QoS). We implement an agent based SoS composition simulator providing composition scenarios and their related QoS, and evaluating the different special cloud criterion that can influence the quality of SoS composition. The obtained results show that the number of cloud providers and services involved in SoS federation has a great impact on the overall SoS performance.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127532680","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}
The interconnection of several web services into single composite web services is known as Web Service Composition (WSC). WSC can be implemented in three different ways such as static, semi-dynamic and dynamic. In this research, the dynamic web service composition is accentuated as it is the most challenging method where it occurs during run time to fulfill the business process requirement. Too many errors may lead to the entire failure of WSC at the point whereby poor performance and unavailability take place. In such situation, healing mechanism is required to heal the faults. This research therefore emphasizes on Quality of Service (QoS) that includes availability and performance which utilizes self-healing, an autonomic act which heal the fault by itself without halting the service and human intervention. The self-healing approach that is used in this research is substitution. By substitution, the faulty web service will be automatically substituted with the next web service in the queue from a list of services. By implementing this healing method, the service malfunction is prevented and the quality of web service is improved whereby the web service will always be available with better performance.
{"title":"Self-Healing in Dynamic Web Service Composition","authors":"Venushini Rajendran, Fang-Fang Chua, Gaik-Yee Chan","doi":"10.1109/FiCloud.2017.35","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.35","url":null,"abstract":"The interconnection of several web services into single composite web services is known as Web Service Composition (WSC). WSC can be implemented in three different ways such as static, semi-dynamic and dynamic. In this research, the dynamic web service composition is accentuated as it is the most challenging method where it occurs during run time to fulfill the business process requirement. Too many errors may lead to the entire failure of WSC at the point whereby poor performance and unavailability take place. In such situation, healing mechanism is required to heal the faults. This research therefore emphasizes on Quality of Service (QoS) that includes availability and performance which utilizes self-healing, an autonomic act which heal the fault by itself without halting the service and human intervention. The self-healing approach that is used in this research is substitution. By substitution, the faulty web service will be automatically substituted with the next web service in the queue from a list of services. By implementing this healing method, the service malfunction is prevented and the quality of web service is improved whereby the web service will always be available with better performance.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129791253","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}
Suhib Bani Melhem, A. Agarwal, N. Goel, Marzia Zaman
Host load detection algorithm determines if a given host is overload or underloaded then the decision can be made to migrate VMs to achieve host/server consolidation and load balancing in cloud data centers while satisfying the QoS constraints. Presently, host load detection is a challenging problem in the cloud data center management specially with high dynamic environment for the host load. In this paper, we propose a novel Markov-based prediction algorithm to forecast the future load state of the host. The experimental results demonstrate that the proposed algorithm has better performance than the other competitive algorithms. The results for different types of PlanetLab real and random workloads show significant reduction of the SLA violation and the number of VM migrations.
{"title":"A Markov-Based Prediction Model for Host Load Detection in Live VM Migration","authors":"Suhib Bani Melhem, A. Agarwal, N. Goel, Marzia Zaman","doi":"10.1109/FiCloud.2017.37","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.37","url":null,"abstract":"Host load detection algorithm determines if a given host is overload or underloaded then the decision can be made to migrate VMs to achieve host/server consolidation and load balancing in cloud data centers while satisfying the QoS constraints. Presently, host load detection is a challenging problem in the cloud data center management specially with high dynamic environment for the host load. In this paper, we propose a novel Markov-based prediction algorithm to forecast the future load state of the host. The experimental results demonstrate that the proposed algorithm has better performance than the other competitive algorithms. The results for different types of PlanetLab real and random workloads show significant reduction of the SLA violation and the number of VM migrations.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121858358","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}
Elisabetta Farella, Manuele Rusci, B. Milosevic, A. Murphy
The Internet of Things (IoT) offers challenges that are being met by the convergence of multiple technologies, which have matured rapidly over the past decade. Broadband communication and mobile platforms enable raw data collection and its transmission to the cloud. Data science, e.g., deep learning, transforms large amounts of data from the Internet-connected sensors and personal devices in meaningful information. Nevertheless, several challenges remain open. In particular, the data deluge hinders scalability, with massive amounts of data being sent from the edge to the cloud, often unnecessarily. Simultaneously, an increasing number of smart objects must operate over extremely long time frames, necessitating sustainability. Energy efficiency is therefore a key element of the future IoT. In this paper, we identify three critical aspects for a thing-centric vision of the internet of things: sensing, processing, communication technologies. We start from the current advanced state of the art then sketch future strategies for a scalable and sustainable IoT.
{"title":"Technologies for a Thing-Centric Internet of Things","authors":"Elisabetta Farella, Manuele Rusci, B. Milosevic, A. Murphy","doi":"10.1109/FiCloud.2017.58","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.58","url":null,"abstract":"The Internet of Things (IoT) offers challenges that are being met by the convergence of multiple technologies, which have matured rapidly over the past decade. Broadband communication and mobile platforms enable raw data collection and its transmission to the cloud. Data science, e.g., deep learning, transforms large amounts of data from the Internet-connected sensors and personal devices in meaningful information. Nevertheless, several challenges remain open. In particular, the data deluge hinders scalability, with massive amounts of data being sent from the edge to the cloud, often unnecessarily. Simultaneously, an increasing number of smart objects must operate over extremely long time frames, necessitating sustainability. Energy efficiency is therefore a key element of the future IoT. In this paper, we identify three critical aspects for a thing-centric vision of the internet of things: sensing, processing, communication technologies. We start from the current advanced state of the art then sketch future strategies for a scalable and sustainable IoT.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121643163","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}
Philippe Massonet, Laurent Deru, Amel Achour, S. Dupont, Louis-Marie Croisez, A. Levin, M. Villari
Smart IoT applications require connecting multiple IoT devices and networks with multiple services running in fog and cloud computing platforms. One approach to connecting IoT devices with cloud and fog services is to create a federated virtual network. The main benefit of this approach is that IoT devices can then interact with multiple remote services using an application specific federated network where no traffic from other applications passes. This federated network spans multiple cloud platforms and IoT networks but it can be managed as a single entity. From the point of view of security, federated virtual networks can be managed centrally and be secured with a coherent global network security policy. This does not mean that the same security policy applies everywhere, but that the different security policies are specified in a single coherent security policy. In this paper we propose to extend a federated cloud networking security architecture so that it can secure IoT devices and networks. The federated network is extended to the edge of IoT networks by integrating a federation agent in an IoT gateway or network controller (Can bus, 6LowPan, Lora, ...). This allows communication between the federated cloud network and the IoT network. The security architecture is based on the concepts of network function virtualisation (NFV) and service function chaining (SFC) for composing security services. The IoT network and devices can then be protected by security virtual network functions (VNF) running at the edge of the IoT network.
{"title":"Security in Lightweight Network Function Virtualisation for Federated Cloud and IoT","authors":"Philippe Massonet, Laurent Deru, Amel Achour, S. Dupont, Louis-Marie Croisez, A. Levin, M. Villari","doi":"10.1109/FiCloud.2017.43","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.43","url":null,"abstract":"Smart IoT applications require connecting multiple IoT devices and networks with multiple services running in fog and cloud computing platforms. One approach to connecting IoT devices with cloud and fog services is to create a federated virtual network. The main benefit of this approach is that IoT devices can then interact with multiple remote services using an application specific federated network where no traffic from other applications passes. This federated network spans multiple cloud platforms and IoT networks but it can be managed as a single entity. From the point of view of security, federated virtual networks can be managed centrally and be secured with a coherent global network security policy. This does not mean that the same security policy applies everywhere, but that the different security policies are specified in a single coherent security policy. In this paper we propose to extend a federated cloud networking security architecture so that it can secure IoT devices and networks. The federated network is extended to the edge of IoT networks by integrating a federation agent in an IoT gateway or network controller (Can bus, 6LowPan, Lora, ...). This allows communication between the federated cloud network and the IoT network. The security architecture is based on the concepts of network function virtualisation (NFV) and service function chaining (SFC) for composing security services. The IoT network and devices can then be protected by security virtual network functions (VNF) running at the edge of the IoT network.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124940703","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}
In the highly competitive business environment of Software as a Service (SaaS) clouds, Quality of Service (QoS) and fair pricing are of paramount importance for differentiating between similar cloud providers. In such platforms, the workload computational demand variability may have a significant impact on the system performance and thus on the provider's Service Level Agreement (SLA) commitments. Towards this direction, in this paper we consider a SaaS cloud with a multi-tier SLA that focuses on the fair billing of the end-users, according to the provided level of QoS. The workload consists of bag-of-tasks jobs, which are scheduled on the underlying virtualized host environment. The jobs have soft deadlines and different levels of variability in their computational demands. The effect of the workload computational demand variability on the system performance, under the employed multi-tier SLA, is investigated via simulation. The experimental evaluation provides useful insights into the impact of computational demand variability on the performance of the SaaS cloud under study.
{"title":"The Effect of Workload Computational Demand Variability on the Performance of a SaaS Cloud with a Multi-tier SLA","authors":"Georgios L. Stavrinides, H. Karatza","doi":"10.1109/FiCloud.2017.26","DOIUrl":"https://doi.org/10.1109/FiCloud.2017.26","url":null,"abstract":"In the highly competitive business environment of Software as a Service (SaaS) clouds, Quality of Service (QoS) and fair pricing are of paramount importance for differentiating between similar cloud providers. In such platforms, the workload computational demand variability may have a significant impact on the system performance and thus on the provider's Service Level Agreement (SLA) commitments. Towards this direction, in this paper we consider a SaaS cloud with a multi-tier SLA that focuses on the fair billing of the end-users, according to the provided level of QoS. The workload consists of bag-of-tasks jobs, which are scheduled on the underlying virtualized host environment. The jobs have soft deadlines and different levels of variability in their computational demands. The effect of the workload computational demand variability on the system performance, under the employed multi-tier SLA, is investigated via simulation. The experimental evaluation provides useful insights into the impact of computational demand variability on the performance of the SaaS cloud under study.","PeriodicalId":115925,"journal":{"name":"2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673738","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：