			Home About us Contact

Server System (server + system)

Distribution by Scientific Domains

Information Science and Computing	100%

Selected Abstracts

An optimal multimedia object allocation solution in multi-powermode storage systems

CONCURRENCY AND COMPUTATION: PRACTICE & EXPERIENCE, Issue 13 2010
Yingwei Jin
Abstract Given a set of multimedia objects R={o1, o2, ,, ok} each of which has a set of multiple versions oi.v={Ai.0, Ai.1, ,, Ai.m}, i=1, 2, ,, k, there is a problem of distributing these objects in a server system so that user requests for accessing specified multimedia objects can be fulfilled with the minimum energy consumption and without significant degrading of the system performance. This paper considers the allocation problem of multimedia objects in multi-powermode storage systems, where the objects are distributed among multi-powermode storages based on the access pattern to the objects. We design an underlying infrastructure of storage system and propose a dynamic multimedia object allocation policy based on the designed infrastructure, which integrate and prove the optimality of the proposed policy. Copyright © 2010 John Wiley & Sons, Ltd. [source]

Fuzzy scheduling strategy for generalized switched server systems and its robustness over system heterogeneity

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS, Issue 3 2009
Xingxuan Wang
Generalized switched server system, a discretely controlled continuous-time system, in which N tanks are used to represent N parallel entities, respectively, can be employed to address a class of load-balancing problems. A tank-pair model is a system that consists of two tanks and a single input single output controller, which regulates the inflows of the two tanks to acquire the two uniform levels under the specified inflow constraints. According to a quantized observation of the N tank levels, some discrete events are generated, and based on certain event feedback strategy, switching the location of the tank-pair can control all the N tanks in a time-sharing manner to acquire the N levels uniformity. Different from some existing scheduling strategies, this study proposes a fuzzy scheduling strategy (FSS) for such generalized switched server systems. Special measures are taken to reduce the N -inputs two-outputs fuzzy inference to a two-inputs one-output one, which greatly facilitates fuzzy scheduler design. Simulation results show that the proposed FSS strategy outperforms over the three existing scheduling strategies as a whole, and they also show that the proposed FSS strategy demonstrates high robustness over system heterogeneity. © 2009 Wiley Periodicals, Inc. [source]