Results 1 -
8 of
8
Adaptive Dispatching of Tasks in the Cloud
"... Abstract—The increasingly wide application of Cloud Computing enables the consolidation of tens of thousands of applications in shared infrastructures. Thus, meeting the QoS requirements of so many diverse applications in such shared resource environments has become a real challenge, especially sinc ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—The increasingly wide application of Cloud Computing enables the consolidation of tens of thousands of applications in shared infrastructures. Thus, meeting the QoS requirements of so many diverse applications in such shared resource environments has become a real challenge, especially since the characteristics and workload of applications differ widely and may change over time. This paper presents an experimental system that can exploit a variety of online QoS aware adaptive task allocation schemes, and three such schemes are designed and compared. These are a measurement driven algorithm that uses reinforcement learning, secondly a “sensible ” allocation algorithm that assigns tasks to sub-systems that are observed to provide a lower response time, and then an algorithm that splits the task arrival stream into sub-streams at rates computed from the hosts ’ processing capabilities. All of these schemes are compared via measurements among themselves and with a simple round-robin scheduler, on two experimental test-beds with homogenous and heterogenous hosts having different processing capacities.
doi:10.1093/comjnl/bxt012 Guaranteeing Fault-Tolerant Requirement Load Balancing Scheme Based on VM Migration
, 2012
"... Virtualization is an important enabling technology for many large data centers and cloud computing environments, and virtual machine (VM) migration plays a key role in the load balancing among the hosts of the data center. However, the existing load balancing schemes based on VM migration have serio ..."
Abstract
- Add to MetaCart
Virtualization is an important enabling technology for many large data centers and cloud computing environments, and virtual machine (VM) migration plays a key role in the load balancing among the hosts of the data center. However, the existing load balancing schemes based on VM migration have serious influence on the fault-tolerant level of the services in the data center, and thus the reliability of the services cannot be guaranteed. In this paper, a novel guaranteeing fault-tolerant requirement load balancing scheme (GFTLBS) is proposed. GFTLBS migrates the VMs to balance the load without violating the fault-tolerant requirement of all services. The simulation results show that the scheme can guarantee the fault-tolerant requirements of all services while keeping the load balance.
Guaranteeing Fault-Tolerant Requirement Load Balancing Scheme Based on VM Migration
, 2012
"... Virtualization is an important enabling technology for many large data centers and cloud computing environments, and virtual machine (VM) migration plays a key role in the load balancing among the hosts of the data center. However, the existing load balancing schemes based on VM migration have serio ..."
Abstract
- Add to MetaCart
Virtualization is an important enabling technology for many large data centers and cloud computing environments, and virtual machine (VM) migration plays a key role in the load balancing among the hosts of the data center. However, the existing load balancing schemes based on VM migration have serious influence on the fault-tolerant level of the services in the data center, and thus the reliability of the services cannot be guaranteed. In this paper, a novel guaranteeing fault-tolerant requirement load balancing scheme (GFTLBS) is proposed. GFTLBS migrates the VMs to balance the load without violating the fault-tolerant requirement of all services. The simulation results show that the scheme can guarantee the fault-tolerant requirements of all services while keeping the load balance.
Contents lists available at SciVerse ScienceDirect
"... journal homepage: www.elsevier.com/locate/jpdc ..."
(Show Context)
Scheduling Real-Time Jobs in Distributed Systems- Simulation and Performance Analysis
, 2014
"... One of the major challenges in ultrascale systems is the effective scheduling of complex jobs within strict timing constraints. The distributed and heterogeneous system resources constitute another critical issue that must be addressed by the employed scheduling strategy. In this paper, we investiga ..."
Abstract
- Add to MetaCart
(Show Context)
One of the major challenges in ultrascale systems is the effective scheduling of complex jobs within strict timing constraints. The distributed and heterogeneous system resources constitute another critical issue that must be addressed by the employed scheduling strategy. In this paper, we investigate by simulation the performance of various policies for the scheduling of real-time directed acyclic graphs in a heterogeneous distributed environment. We apply bin packing techniques during the processor selection phase of the scheduling process, in order to utilize schedule gaps and thus enhance existing list scheduling methods. The simulation results show that the proposed policies outperform all of the other examined algorithms.
Clustering Crash Hotspots to Organize Police Dispatch Routes Using GIS
"... Abstract: Traffic crashes events are known threats to public safety. Identifying high-crash-risk road segments provides safety specialists with an insight to better understanding of crash patterns and enhancing road safety management. In this work the main aim is to identify hotspots of severe crash ..."
Abstract
- Add to MetaCart
Abstract: Traffic crashes events are known threats to public safety. Identifying high-crash-risk road segments provides safety specialists with an insight to better understanding of crash patterns and enhancing road safety management. In this work the main aim is to identify hotspots of severe crashes and reduce police dispatch time thereby reducing crash severity. In this crash monitoring and identifying approach, the objects and its positions tend to change periodically due to its dynamicity and mobility by which there should be a provision to monitor its behavior and position regularly. This will help to study the traffic flow and object behavior in the study locality. Based on the object movement in the region the position and time will be updated based on which the speed can be calculated. The frequency of speed will helps to identify the traffic situation of the region. Instead of monitoring individual node movement and speed the system will analyze the region based on multi-object speed analysis. It also defines the minimum and maximum speed and average speed flow of the object in a particular region. After a certain period of time, the object selects a new random path based on the distance and maximum speed path. In this process a novel Position-based speed updating process is proposed, in which several moving objects are recognized by the system. A dynamic segmentation is done to classify regions based on crash severity and minor clustering of hotspots is done. Finally kernel density is analyzed and frequency is calculated by which the data will be analyzed for further classification. ArcGIS was used for analyzing the data and displaying the results.
Energy-efficient and SLA-based Management of IaaS Cloud Data Centers
, 2015
"... A computação em nuvem tem vindo a ser progressivamente adoptada em diversos cenários, ofer-ecendo acesso a pedido a um ambiente de recursos distribuídos de larga escala, de forma flexível e altamente escalável, orientada ao acordo de nível de serviço. A virtualização é a tecnologia base dos sistemas ..."
Abstract
- Add to MetaCart
(Show Context)
A computação em nuvem tem vindo a ser progressivamente adoptada em diversos cenários, ofer-ecendo acesso a pedido a um ambiente de recursos distribuídos de larga escala, de forma flexível e altamente escalável, orientada ao acordo de nível de serviço. A virtualização é a tecnologia base dos sistemas de computação em nuvem, dotando-os de serviços flexíveis e escaláveis. À medida que estes sistemas distribuídos se tornam mais comuns, as empresas e fornecedores destes sistemas constrõem maiores centros de dados para lidar com a crescente procura por recursos de computação. No entanto, a quantidade de energia elétrica consumida por estes centros de dados aumenta com o poder computacional instalado. Na mesma linha, à medida que os sistemas de computação crescem em tamanho e em complexidade, eventos de falha tornam-se norma em vez de exceção, aumentando ainda mais o desperdício energético e afetando a Qualidade de Serviço do sistema percecionado pelo utilizador final. Além disso, as tecnologias de virtualização atu-ais não fornecem isolamento de desempenho, o que significa que duas aplicações executando em máquinas virtuais independentes e que partilham o mesmo servidor podem interferir na execução uma da outra, e consequentemente violando as restrições de Qualidade de Serviço. Esta tese apresenta dois mecanismos aperfeiçoados com o duplo objetivo de reduzir os custos
unknown title
"... journal homepage: www.elsevier.com/locate/jpdc Adaptive energy-efficient scheduling for real-time tasks on DVS-enabled ..."
Abstract
- Add to MetaCart
(Show Context)
journal homepage: www.elsevier.com/locate/jpdc Adaptive energy-efficient scheduling for real-time tasks on DVS-enabled
