Performance Of Selection Algorithms Research Articles

QoS Based Cloud Service Selection to Handle Large Volume of Concurrent Requests

Background/Objectives: With the exponential growth of cloud providers and users, the possibility of arrival of large number of concurrent requests within a small interval, may reduce the performance of broker. This paper presents a cloud service selection mechanism with service grouping. The main objective of this paper to show the performance difference between the selection mechanism with grouping and without grouping. Methods/Statistical Analysis: For the concurrent services groups and sub groups are created using functional and QoS parameters. Analytical hierarchy based selection algorithm is proposed. Performance of selection algorithm with grouping is evaluated. Performance of selection algorithm with grouping is compared with algorithm without grouping and the sufficient reduction in execution time is noted. Findings: AHP based selection algorithm with grouping improves the performance by reducing the computation time and reducing the repetitive repository access. Applications/Improvements: The limitation of AHP based algorithm is the rank reversal problem. The improved AHP based algorithm can be used to eliminate the rank reversal problem.

TOWARD COMBINING AUTOMATIC RESOLUTION WITH SOCIAL MEDIATION FOR RESOLVING MULTIUSER CONFLICTS

In spite of intensive effort to resolve conflicts between multiple users of context-aware applications in a smart space, there has been no practical solution for flexibly resolving them based on the situation of the users. In this paper, we propose a mixed resolution method to combine automatic resolution with social participation for resolving multiuser conflicts. For combining the two resolution approaches, various contexts such as preferences, priority, and types of applications are used to select an appropriate resolution method for the encountered conflict. Through an evaluation, we found that the performance of selection algorithms mainly depended on the number of users and the similarity between their preferences, and we derived an appropriate threshold for determining whether users were similar or not. With a user study of 3 applications in a smart-space test-bed, we observed that the combination of automatic resolution when preferences are similar and social mediation when preferences are different effectively resolved multiuser conflict even though social pressure played an important role, and the 3 different applications had different thresholds.