Allocating resources for soft requests-a performance study

Yi-Bing Lin*, Yow Jian Lin, Victor Mak

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

To effectively utilize a limited number of resources shared by many users, algorithms have been proposed to manage the "dynamic resource allocation" problem. Traditionally, these algorithms only deal with rigid requests that precisely specify the desired number of resources needed. However, in applications such as storage allocation and parallel processing, or in new telecommunication services such as Switched Fractional-DS1 and adaptable-bit-rate video, a user may prefer to initiate soft requests, each of which expresses not only the desired number of resources but also the minimum number of them. In order to increase the possibility of a request being granted, the user who sends in the soft request is willing to accept a decrease in service quality by receiving fewer resources. How to decide whether to accept or deny soft requests, so that a performance objective can be met, adds a new dimension to the old resource allocation problem. This paper studies the impact of soft requests on various resource allocation algorithms. Four allocation algorithms for soft requests are studied in this paper via a simulation that is based upon an event-driven model. For the performance measures we choose (i.e., utilization, acceptance ratio, and allocation ratio), the results indicate that some algorithms can gracefully adapt to different system loads and achieve both a high acceptance ratio and a high utilization at the cost of the allocation ratio. The results also show that having soft requests is better for enhancing the acceptance ratio, and that increasing the time-out period can further improve the possibility of a soft request being accepted. However, our study indicates that making the time-out period arbitrarily large may not be cost-effective, since after the time-out period is over a threshold value, the acceptance ratio is hardly improved further.

Original languageEnglish
Pages (from-to)39-65
Number of pages27
JournalInformation sciences
Volume84
Issue number1-2
DOIs
StatePublished - May 1995

Fingerprint

Dive into the research topics of 'Allocating resources for soft requests-a performance study'. Together they form a unique fingerprint.

Cite this