Modern heuristic techniques for combinatorial problems
MPLS and the evolving Internet architecture
IEEE Communications Magazine
MPLS advantages for traffic engineering
IEEE Communications Magazine
| Hi-index | 0.00 |
This paper presents a procedure for MPLS network dimensioning that allows for multi-hour dimensioning of networks supporting simultaneously peer-to-peer and client-server services. The dimensioning model is able to take into account several LSP attributes: degree of survivability (link disjoint and node disjoint cases), maximum hop count, usable colours and preferred routes. The dimensioning problem is a combined capacity design and routing problem where the LSP sets are calculated in order to minimise the network operational costs. This problem is formulated as an integer programming problem, which is solved through an heuristic based on Lagrangean relaxation with sub-gradient optimisation. Results show that the procedure can design networks with realistic size in seconds using a standard PC platform.