Optimal Policy for LSP Control in MPLS Networks

  • G. Lauks Riga Technical University
  • J. Jeļinskis Riga Technical University

Abstract

In present time there is a very active research in the field of multiprotocol label switching (MPLS), and lots of networks are supporting MPLS. A possibility of a new LSP setup policy algorithm, which uses optimization procedure based on multi-objective model with Pareto ranking and Genetic Algorithm, is verified. Adaptation to variable and bursty traffic is achieved by using Neural Network learning capabilities, and decision making under uncertainty is made up with Fuzzy Logical approach. This algorithm functions in two phases – learning and operating, which are accomplished consecutive. Algorithm is described and depicted. Experimental data is depicted and future research subjects are pointed. Ill. 4, bibl. 11 (in English, summary in English, Russian and Lithuanian).

Published
2015-03-19
Section
T 121 SIGNAL TECHNOLOGY