Pub Date : 2013-12-01DOI: 10.1109/CloudNet.2013.6710580
H. Yamada, Takumi Sakamoto, H. Horie, K. Kono
Cloud services make use of data center resources so that hosted applications can utilize them as needed. To offer a large amount of computational resources, cloud service providers manage tens of geographically distributed data centers. Since each data center is made up of hundreds of thousands of physical machines, energy consumption is a major concern for cloud service providers. The electric cost imposes significant financial overheads on those companies and pushes up the price for the cloud users. This paper presents an energy-price-driven request dispatcher that forwards client requests to data centers in an electric-cost-saving way. In our technique, mapping nodes, which are used as authoritative DNS servers, forward client requests to data centers in which the electric price is relatively lower. We additionally develop a policy that gradually shifts client requests to electrically cheaper data centers, taking into account application latency requirements and data center loads. Our simulation-based results show that our technique can reduce electric cost by 15 % more than randomly dispatching client requests. We also implemented a prototype of the mapping node, and the experimental results show that its processing time marginally increases compared with that of legacy DNS lookups.
{"title":"Request dispatching for cheap energy prices in cloud data centers","authors":"H. Yamada, Takumi Sakamoto, H. Horie, K. Kono","doi":"10.1109/CloudNet.2013.6710580","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710580","url":null,"abstract":"Cloud services make use of data center resources so that hosted applications can utilize them as needed. To offer a large amount of computational resources, cloud service providers manage tens of geographically distributed data centers. Since each data center is made up of hundreds of thousands of physical machines, energy consumption is a major concern for cloud service providers. The electric cost imposes significant financial overheads on those companies and pushes up the price for the cloud users. This paper presents an energy-price-driven request dispatcher that forwards client requests to data centers in an electric-cost-saving way. In our technique, mapping nodes, which are used as authoritative DNS servers, forward client requests to data centers in which the electric price is relatively lower. We additionally develop a policy that gradually shifts client requests to electrically cheaper data centers, taking into account application latency requirements and data center loads. Our simulation-based results show that our technique can reduce electric cost by 15 % more than randomly dispatching client requests. We also implemented a prototype of the mapping node, and the experimental results show that its processing time marginally increases compared with that of legacy DNS lookups.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122681650","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 : 2013-11-11DOI: 10.1109/CloudNet.2013.6710555
Eric Kuada
We have over the past three years been working on the feasibility of Opportunistic Cloud Services (OCS) for enterprises. OCS is about enterprises strategically contributing and utilizing spare IT resources as cloud services. One of the major challenges that such a platform faces is data security and trust management issues. This paper presents a trust management system for OCS platforms. It models the concept of trust and applies it to OCS platforms. The trust model and the trust management system are verified through the simulation of the computation of the trust values with Infrastructure as a Service, and Software as a Service, usage scenarios.
{"title":"Trust management system for Opportunistic Cloud Services","authors":"Eric Kuada","doi":"10.1109/CloudNet.2013.6710555","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710555","url":null,"abstract":"We have over the past three years been working on the feasibility of Opportunistic Cloud Services (OCS) for enterprises. OCS is about enterprises strategically contributing and utilizing spare IT resources as cloud services. One of the major challenges that such a platform faces is data security and trust management issues. This paper presents a trust management system for OCS platforms. It models the concept of trust and applies it to OCS platforms. The trust model and the trust management system are verified through the simulation of the computation of the trust values with Infrastructure as a Service, and Software as a Service, usage scenarios.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130780381","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710577
K. Salah, J. A. Calero
These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute- and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.
{"title":"Achieving elasticity for cloud MapReduce jobs","authors":"K. Salah, J. A. Calero","doi":"10.1109/CloudNet.2013.6710577","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710577","url":null,"abstract":"These days, both the cloud computing paradigm and MapReduce programming framework have become key enablers for running big data analytics and large-scale compute- and data-intensive applications. Achieving proper elasticity for cloud MapReduce jobs is a critical research problem that has been overlooked. In this paper, we focus on how to achieve proper elasticity for MapReduce jobs when executed on cloud clusters. In particular, we present an analytical queueing model that can be used to determine at any given time and under different workload conditions the minimal number of mappers and reducers needed to satisfy the Service Level Objective (SLO) response time.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126169685","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710571
D. Allan, J. Farkas, P. Saltsidis, J. Tantsura
This paper describes how Shortest Path Bridging (SPB) and Ethernet Virtual Private Networks (EVPN) can be combined to provide a highly scalable distributed data center network fabric. It is shown how SPB can be used as the network fabric of a data center site. It is then explained how EVPN can interconnect the sites over the wide area in order provide a geographically distributed data center. The paper provides an overview for the reader to grasp the fundamentals necessary to understand how SPB and EVPN can effectively interwork. It describes the underlying algorithms and principles of operation with an examination of the design tradeoffs considered for each component. Finally it shows how multicast can be leveraged to enhance backbone network efficiency.
{"title":"Ethernet routing for large scale distributed data center fabrics","authors":"D. Allan, J. Farkas, P. Saltsidis, J. Tantsura","doi":"10.1109/CloudNet.2013.6710571","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710571","url":null,"abstract":"This paper describes how Shortest Path Bridging (SPB) and Ethernet Virtual Private Networks (EVPN) can be combined to provide a highly scalable distributed data center network fabric. It is shown how SPB can be used as the network fabric of a data center site. It is then explained how EVPN can interconnect the sites over the wide area in order provide a geographically distributed data center. The paper provides an overview for the reader to grasp the fundamentals necessary to understand how SPB and EVPN can effectively interwork. It describes the underlying algorithms and principles of operation with an examination of the design tradeoffs considered for each component. Finally it shows how multicast can be leveraged to enhance backbone network efficiency.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126852703","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710554
S. Betgé-Brezetz, Guy-Bertrand Kamga, Marie-Pascale Dupont, Aoues Guesmi
Privacy in the cloud is still a strong issue for the large adoption of cloud technologies by enterprises which fear to actually put their sensitive data in the cloud. There is indeed a need to have an efficient access control on the data stored and processed in the cloud infrastructure allowing to support the various business and country-based regulation constraints (e.g., on data location and co-location, data retention duration, data processing, node security level, tracing and audit). In this perspective, this paper presents a novel approach of end-to-end privacy policy enforcement over the cloud infrastructure and based on the sticky policy paradigm (a policy being bound to each sensitive data). In our approach the data protection is performed within the cloud nodes (e.g., within the internal file system of a VM or its attached volume) and is completely transparent for the applications (no need to modify the applications). This paper describes the concept and the proposed end-to-end architecture (from the client to the cloud nodes) as well as an implementation based on the FUSE (Filesystem in Userspace) technology. This implementation is executed on a scenario of data access and transfer control, and is also used to achieve performance evaluations. These evaluations show that, with a reasonable additional computation cost, this approach offers a flexible and transparent way to enforce various privacy constraints within the cloud infrastructure.
{"title":"End-to-end privacy policy enforcement in cloud infrastructure","authors":"S. Betgé-Brezetz, Guy-Bertrand Kamga, Marie-Pascale Dupont, Aoues Guesmi","doi":"10.1109/CloudNet.2013.6710554","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710554","url":null,"abstract":"Privacy in the cloud is still a strong issue for the large adoption of cloud technologies by enterprises which fear to actually put their sensitive data in the cloud. There is indeed a need to have an efficient access control on the data stored and processed in the cloud infrastructure allowing to support the various business and country-based regulation constraints (e.g., on data location and co-location, data retention duration, data processing, node security level, tracing and audit). In this perspective, this paper presents a novel approach of end-to-end privacy policy enforcement over the cloud infrastructure and based on the sticky policy paradigm (a policy being bound to each sensitive data). In our approach the data protection is performed within the cloud nodes (e.g., within the internal file system of a VM or its attached volume) and is completely transparent for the applications (no need to modify the applications). This paper describes the concept and the proposed end-to-end architecture (from the client to the cloud nodes) as well as an implementation based on the FUSE (Filesystem in Userspace) technology. This implementation is executed on a scenario of data access and transfer control, and is also used to achieve performance evaluations. These evaluations show that, with a reasonable additional computation cost, this approach offers a flexible and transparent way to enforce various privacy constraints within the cloud infrastructure.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131321240","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710567
Daehee Kim, Sejun Song, Baek-Young Choi
Cloud-based storages have become considerably popular in recent years, as they enable data access from anywhere and any device at any time. Many leading cloud-based storage services including Dropbox, JustCloud, and Mozy use data deduplication techniques at a source to save network bandwidth from a user to cloud servers as well as storage space, which in turn expedites the speed of data upload. Although traditional variable-size block-level deduplication techniques tend to achieve a high data reduction rate, they require a high processing overhead due to data chunking, index processing, and data fragmentation. However, a user's device can be limited in processing capability and memory space to perform an effective client side deduplication. While, a simple file-level or a large fixed-size block-level deduplication may be able to cope with the limited source device capacity, it cannot produce a high data reduction rate. In this paper, we propose a novel Structure-Aware File and Email deduplication (SAFE) scheme that achieves both fast and effective data reduction for cloud-based storage services. SAFE efficiently deduplicates redundant objects in structured files as well as emails exploiting object-level components based on their structures. Our evaluation using real data sets of structured files and emails shows that SAFE accomplishes as good of storage savings as a variable-block deduplication, while being as fast as a file-level or a large fixed-size block-level deduplication.
{"title":"SAFE: Structure-aware file and email deduplication for cloud-based storage systems","authors":"Daehee Kim, Sejun Song, Baek-Young Choi","doi":"10.1109/CloudNet.2013.6710567","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710567","url":null,"abstract":"Cloud-based storages have become considerably popular in recent years, as they enable data access from anywhere and any device at any time. Many leading cloud-based storage services including Dropbox, JustCloud, and Mozy use data deduplication techniques at a source to save network bandwidth from a user to cloud servers as well as storage space, which in turn expedites the speed of data upload. Although traditional variable-size block-level deduplication techniques tend to achieve a high data reduction rate, they require a high processing overhead due to data chunking, index processing, and data fragmentation. However, a user's device can be limited in processing capability and memory space to perform an effective client side deduplication. While, a simple file-level or a large fixed-size block-level deduplication may be able to cope with the limited source device capacity, it cannot produce a high data reduction rate. In this paper, we propose a novel Structure-Aware File and Email deduplication (SAFE) scheme that achieves both fast and effective data reduction for cloud-based storage services. SAFE efficiently deduplicates redundant objects in structured files as well as emails exploiting object-level components based on their structures. Our evaluation using real data sets of structured files and emails shows that SAFE accomplishes as good of storage savings as a variable-block deduplication, while being as fast as a file-level or a large fixed-size block-level deduplication.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124383996","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710551
J. Kempf, Ying Zhang, Ramesh Mishra, N. Beheshti
Just like computation and storage, networks in data centers require virtualization in order to provide isolation between multiple co-existing tenants. Existing data center network virtualization approaches can be roughly divided into two generations: a first generation approach using simple VLANs and MAC addresses in various ways to achieve isolation and a second generation approach using IP overlay networks. These approaches suffer drawbacks. VLAN and MAC based approaches are difficult to manage and tie VM networking directly into the physical infrastructure, reducing flexibility in VM placement and movement. IP overlay networks typically have an relatively low scalability limit in the number of tenant VMs that can participate in a virtual network and problems are difficult to debug. In addition, none of the approaches meshes easily with existing provider wide area VPN technology, which uses MPLS. In this paper, we propose a third generation approach: multiple layers of tags to achieve isolation and designate routes through the data center network. The tagging protocol can be either carrier Ethernet or MPLS, both of which support multiple layers of tags. We illustrate this approach with a scheme called Zeppelin: packet tagging using MPLS with a centralized SDN control plane implementing Openflow control of the data center switches.
{"title":"Zeppelin - A third generation data center network virtualization technology based on SDN and MPLS","authors":"J. Kempf, Ying Zhang, Ramesh Mishra, N. Beheshti","doi":"10.1109/CloudNet.2013.6710551","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710551","url":null,"abstract":"Just like computation and storage, networks in data centers require virtualization in order to provide isolation between multiple co-existing tenants. Existing data center network virtualization approaches can be roughly divided into two generations: a first generation approach using simple VLANs and MAC addresses in various ways to achieve isolation and a second generation approach using IP overlay networks. These approaches suffer drawbacks. VLAN and MAC based approaches are difficult to manage and tie VM networking directly into the physical infrastructure, reducing flexibility in VM placement and movement. IP overlay networks typically have an relatively low scalability limit in the number of tenant VMs that can participate in a virtual network and problems are difficult to debug. In addition, none of the approaches meshes easily with existing provider wide area VPN technology, which uses MPLS. In this paper, we propose a third generation approach: multiple layers of tags to achieve isolation and designate routes through the data center network. The tagging protocol can be either carrier Ethernet or MPLS, both of which support multiple layers of tags. We illustrate this approach with a scheme called Zeppelin: packet tagging using MPLS with a centralized SDN control plane implementing Openflow control of the data center switches.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"44 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131893943","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710566
Mona Nasseri, Mansoor Alam, R. Green
Mobile cloud computing is a powerful technology that integrates cloud computing with modern mobile devices. One of the realized benefits of this methodology is that various computation tasks may be temporarily offloaded to mobile devices that belong to users' who are willing to share their resources. In this process, the problem of optimally and fairly allocating compute tasks to various mobile devices must be solved while considering dynamic conditions such as battery life, response delay, and power consumption. This study presents a new solution to this problem using a combination of Markov Decision Processes (MDPs) and lookup tables in order to help guide mobile devices in accepting or rejecting such requests. To achieve a more perfect collaboration between devices requesting aid and those and providing help, an environment is considered in which persuading cooperation will be achieved through reward calculation and credit exchange.
{"title":"MDP based optimal policy for collaborative processing using mobile cloud computing","authors":"Mona Nasseri, Mansoor Alam, R. Green","doi":"10.1109/CloudNet.2013.6710566","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710566","url":null,"abstract":"Mobile cloud computing is a powerful technology that integrates cloud computing with modern mobile devices. One of the realized benefits of this methodology is that various computation tasks may be temporarily offloaded to mobile devices that belong to users' who are willing to share their resources. In this process, the problem of optimally and fairly allocating compute tasks to various mobile devices must be solved while considering dynamic conditions such as battery life, response delay, and power consumption. This study presents a new solution to this problem using a combination of Markov Decision Processes (MDPs) and lookup tables in order to help guide mobile devices in accepting or rejecting such requests. To achieve a more perfect collaboration between devices requesting aid and those and providing help, an environment is considered in which persuading cooperation will be achieved through reward calculation and credit exchange.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"335 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130718779","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710553
Bu-Sung Lee, Renuga Kanagavelu, Khin Mi Mi Aung
The use of Software-Defined Networking (SDN) with OpenFlow-enabled switches in Data Centers has received much attention from researchers and industries. One of the major issues in OpenFlow switch is the limited size of the flow table resulting in evictions of flows from the flow table. From Data Center traffic characteristics, we observe that elephant flows are very large in size (data volume) but few in numbers when compared to mice flows. Thus, Elephant flows are more likely to be evicted, due to the limited size of the switch flow table causing additional traffic to the controller. We propose a differential flow cache framework that achieves fairness and efficient cache maintenance with fast lookup and reduced cache miss ratio. The framework uses a hash-based placement and localized Least Recently Used (LRU)-based replacement mechanisms.
{"title":"An efficient flow cache algorithm with improved fairness in Software-Defined Data Center Networks","authors":"Bu-Sung Lee, Renuga Kanagavelu, Khin Mi Mi Aung","doi":"10.1109/CloudNet.2013.6710553","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710553","url":null,"abstract":"The use of Software-Defined Networking (SDN) with OpenFlow-enabled switches in Data Centers has received much attention from researchers and industries. One of the major issues in OpenFlow switch is the limited size of the flow table resulting in evictions of flows from the flow table. From Data Center traffic characteristics, we observe that elephant flows are very large in size (data volume) but few in numbers when compared to mice flows. Thus, Elephant flows are more likely to be evicted, due to the limited size of the switch flow table causing additional traffic to the controller. We propose a differential flow cache framework that achieves fairness and efficient cache maintenance with fast lookup and reduced cache miss ratio. The framework uses a hash-based placement and localized Least Recently Used (LRU)-based replacement mechanisms.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"2673 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130802454","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 : 2013-11-01DOI: 10.1109/CloudNet.2013.6710565
X. Lin, Yanzhi Wang, Massoud Pedram
The emerging mobile cloud computing (MCC) paradigm has the potential to extend the capabilities of battery-powered mobile devices. Lots of research work have been conducted for improving the performance and reducing the power consumption for the mobile devices in the MCC paradigm. Different from the previous work, we investigate the effect of the inter-charging interval (ICI) length on the mobile device control decisions, including the offloading decision of each service request and the CPU operating frequency for processing local requests. Generally, the length of an ICI is uncertain to the mobile device controller and only stochastic data are known. We first define the expected “performance sum” as the objective function, which essentially captures a desirable trade-off between performance and power consumption of the mobile device and accounts for the ICI length uncertainty. We prove that the best-suited control decisions should change as time elapses to take into account the effect of ICI length variations. We propose a dynamic programming algorithm, which can derive the optimal control policy of the mobile device to maximize the expected performance sum.
{"title":"An optimal control policy in a mobile cloud computing system based on stochastic data","authors":"X. Lin, Yanzhi Wang, Massoud Pedram","doi":"10.1109/CloudNet.2013.6710565","DOIUrl":"https://doi.org/10.1109/CloudNet.2013.6710565","url":null,"abstract":"The emerging mobile cloud computing (MCC) paradigm has the potential to extend the capabilities of battery-powered mobile devices. Lots of research work have been conducted for improving the performance and reducing the power consumption for the mobile devices in the MCC paradigm. Different from the previous work, we investigate the effect of the inter-charging interval (ICI) length on the mobile device control decisions, including the offloading decision of each service request and the CPU operating frequency for processing local requests. Generally, the length of an ICI is uncertain to the mobile device controller and only stochastic data are known. We first define the expected “performance sum” as the objective function, which essentially captures a desirable trade-off between performance and power consumption of the mobile device and accounts for the ICI length uncertainty. We prove that the best-suited control decisions should change as time elapses to take into account the effect of ICI length variations. We propose a dynamic programming algorithm, which can derive the optimal control policy of the mobile device to maximize the expected performance sum.","PeriodicalId":262262,"journal":{"name":"2013 IEEE 2nd International Conference on Cloud Networking (CloudNet)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131532931","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：