Welcome to the InfoSci Platform
Reference Hub2
Cost-Based Topology Optimization of Embedded Ethernet Networks

Cost-Based Topology Optimization of Embedded Ethernet Networks

Jörg Sommer, Elias A. Doumith, Andreas Reifert
Copyright: © 2011 |Volume: 2 |Issue: 1 |Pages: 22
ISSN: 1947-3176|EISSN: 1947-3184|EISBN13: 9781613506899|DOI: 10.4018/jertcs.2011010101
Cite Article Cite Article

MLA

Sommer, Jörg, et al. "Cost-Based Topology Optimization of Embedded Ethernet Networks." IJERTCS vol.2, no.1 2011: pp.1-22. http://doi.org/10.4018/jertcs.2011010101

APA

Sommer, J., Doumith, E. A., & Reifert, A. (2011). Cost-Based Topology Optimization of Embedded Ethernet Networks. International Journal of Embedded and Real-Time Communication Systems (IJERTCS), 2(1), 1-22. http://doi.org/10.4018/jertcs.2011010101

Chicago

Sommer, Jörg, Elias A. Doumith, and Andreas Reifert. "Cost-Based Topology Optimization of Embedded Ethernet Networks," International Journal of Embedded and Real-Time Communication Systems (IJERTCS) 2, no.1: 1-22. http://doi.org/10.4018/jertcs.2011010101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

During past decades, Ethernet progressively became the most widely used Local Area Network (LAN) technology. Apart from LAN installations, Ethernet also became attractive for other application areas such as industrial control, automotive, and avionics. In traditional LAN design, the objective is to minimize the network deployment cost. However, in embedded networks, additional constraints and ambient conditions add to the complexity of the problem. In this paper, the authors propose a Simulated Annealing (SA) algorithm to optimize the physical topology of an embedded Ethernet network. The various constraints and ambient conditions are modeled by a cost map. For networks with small number of nodes and/or switches, the authors were able to find the optimal solutions using adapted algorithms. These solutions will serve as a lower bound for the solutions obtained via the SA algorithm. However, the adapted algorithms are time consuming and application specific. The paper shows that the SA algorithm can be applied in all cases and finds (near-) optimal solutions.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.