We run experiments to collect system dynamics data under various service conditions and use statistical techniques to analyze experimental data and build activity-state-quality models. This paper presents our empirical study to establish activity-state-quality models for a voice communication service. Modeling dynamic relations of service activities, system state and service quality is required to determine if users' service requests and requirements of service quality can be satisfied by the system with limited resources and how the system and service configuration can be adapted to meet service quality requirements. On a computer and network system, competing service requests of users and associated service activities change the state of limited system resources which in turn affects the achieved service quality. Service quality of computer and network services can be measured by the performance of the service process in throughput, delay, and so on. Service quality on computer and network systems has become increasingly important as many conventional service transactions are moved online. In literature we did not find models of activity-state-quality dynamics during realistic operations of computer and network systems at a more comprehensive, system scale which account for a wide range of hardware and software resources (including CPU, memory, physical disk, caches, buffers, network interface, IP, TCP, UDP, Terminal Service, etc.), their interactions, their state changes with service activities, and their effects on the achieved service quality. on regression models of relations between varying assignments of computing, network and storage resources and application completion time, and – Sun and Ifeachor on models of relations between the playout buffer control and the quality of voice over IP. on resource usage models in a computational grid environment, – Ravindran and Hegazy on regression models between the timeliness performance of periodic tasks and external and internal load parameters such as CPU utilization, – Shivam et al. – Vazhkudai and Schopf on regression models for relations between disk load variation and file transfer time, – Kapadia et al. Performance analysis and simulation results demonstrate that the proposed replica selection strategy shows a significant performance improvement over traditional replica catalog and round-robin probing-based selection strategy. The Buyer and Seller algorithm based on VTR network and auction protocol are also described in detail. The replica response time could be estimated by VTR replica price model. Optimal data replica is defined as the replica with the smallest transfer cost. Based on these concepts and replica maintenance algorithms, a VTR-based data replica selection strategy is proposed. The topology of VTR, data replica publishing algorithm, and replica leaving algorithm in data network are presented. In this research, after surveying data replication and replica catalog techniques, it introduces a Virtual Token Ring (VTR)-based data network.
When different sites hold replicas of the same data, selecting the best replica is a significant benefit. Data replication technique reduces access latency and bandwidth consumption. Data replica management plays an important role in data grid, whose core is data replica maintenance and optimal replica selection.
0 kommentar(er)
