Simulation on Task Scheduling for Multiprocessors Based on Improved Neural Network

Xiao Fang Li

doi:10.4028/www.scientific.net/AMM.513-517.2293

Paper Titles

Secure Message Transmission Method of MMS Telecontrol Communication Based on AES-CCM
p.2277

Study of an Improved Hadoop Speculative Execution Algorithm
p.2281

The Application of an Improved Integration Algorithm of Support Vector Machine to the Prediction of Network Security Situation
p.2285

Invulnerability Analysis of Large Logistics Supply Chain Network in Complex Environment Based on the Internet of Things
p.2289

Simulation on Task Scheduling for Multiprocessors Based on Improved Neural Network
p.2293

Convergence Proof for Unsteady Classification Model with Data Fluctuations
p.2297

Employing Generalized Bezier Tube to Smoothly Blending Tubes Whose Axes are Non-Coplanar
p.2301

Analysis on Three-Dimensional Virtual Simulation for Rationality of Large-Scale Commercial and Residential Space
p.2307

The Analysis of the Specific Network Content Search Model in Public Policy Formulation
p.2311

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 513-517Simulation on Task Scheduling for Multiprocessors...

Simulation on Task Scheduling for Multiprocessors Based on Improved Neural Network

Abstract:

This paper mainly discusses task scheduling for multiprocessors. Application requires higher performance of the multiprocessors task scheduling systems. The traditional algorithms majorly consider the accuracy and neglect the real-time performance. In order to improve the real-time performance while maintaining the accuracy, the paper proposes a task scheduling algorithm (GA-ACO) for multiprocessors based on improved neural network. It first builds mathematical models for task scheduling of multiprocessor systems, and then introduces genetic algorithms to quickly find feasible solutions. The simulation results show that the improved neural network algorithm not only has the global optimization ability of genetic algorithm, but also has both local search and the positive feedback capabilities of neural networks; compared with single optimization algorithm, it can quickly find the task scheduling solutions to meet real-time requirements, accelerate the speed of execution of the task, furthermore achieve reasonable, effective task allocation and scheduling for multi-processor.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

2293-2296

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.2293

Citation:

Cite this paper

Online since:

February 2014

Authors:

Xiao Fang Li*

Keywords:

Genetic Algorithm (GA), Multiprocessor, Neural Network (NN), Task Scheduling

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Kwok Yu-Kwong, Ahmad Ishfaq On multiprocessor task scheduling using efficient state space search approaches [J]. Journal of Parallel and Distributed Computing, 2005, 65(12): 1515-1532.

DOI: 10.1016/j.jpdc.2005.05.028

Google Scholar

[2] Wu Yonggang, Xu Xiangxin, Liu Mei, Zhao Long, The optimal route to explore the city garbage removal based on genetic algorithm [J]. Computer Simulation, 2012. 29(4): 259-263.

Google Scholar

[3] LIU YI, ZHANG XIN, LI HE, et al. Allocating tasks in multi-core processor based parallel system[C]. Proceedings of the IFIP International Conference on Network and Parallel Computing Workshops. Washington DC: IEEE Computer Society, 2007: 748-753.

DOI: 10.1109/npc.2007.26

Google Scholar

[4] M. Kistler, M. Perrone, and F. Petrini, CELL Multiprocessor Communication Network: Built for Speed [J], IEEE Micro, 2006, 26(3): 10-23.

DOI: 10.1109/mm.2006.49

Google Scholar

[5] Wang Yasen, Liu Houquan, Simulation on multi-level dynamic information extraction based on ant colony algorithm [J]. Computer Simulation, 2012. 29(5): 133-135.

Google Scholar