An Adaptive Immune System Applied to Task Scheduling on NOC

DOI

10.2991/eeic-13.2013.22How to use a DOI?

Keywords

component; AIS; Dependent Task Scheduling; Network on Chip; Population Diversification; Adaptive

Abstract

In this paper, an ADaptive Immune Algorithm (ADIA) based on the artificial immune system (AIS) is proposed for the dependent task scheduling on Network on Chip (NoC). We increase the diversity of population of AIS in two ways, and improve the output result of scheduling. On one hand, new calculation method of the number of clones and the probability of mutation are proposed to enlarge the search space appropriately. On the other hand, our algorithm adopts an adaptive strategy to enable the local search to drive the population evolution when evolution speed is low after many iterative processes. Moreover, the influences of different factors in the proposed algorithm are studied. The comparative simulation results show that our algorithm always outperforms the tradition algorithms.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Wei Gao
AU  - Yubai Li
AU  - Song Chai
AU  - Jian Wang
PY  - 2013/12
DA  - 2013/12
TI  - An Adaptive Immune System Applied to Task Scheduling on NOC
BT  - Proceedings of the 3rd International Conference on Electric and Electronics
PB  - Atlantis Press
SP  - 95
EP  - 99
SN  - 1951-6851
UR  - https://doi.org/10.2991/eeic-13.2013.22
DO  - 10.2991/eeic-13.2013.22
ID  - Gao2013/12
ER  -