Due to the fast increase of Internet traffic and the enormous bandwidth pot
ential of all-optical transport networks based on wavelength division multi
plexing, an IP-over-WDM network scenario is likely to be widespread in futu
re communication networks. At the same time, IP networks are becoming more
and more mission-critical. Hence, it is of paramount importance for IP-over
-WDM networks to be able to recover quickly from frequently occurring netwo
rk failures. This paper explains how multi-protocol label switching (both e
lectrical and optical) recovery mechanisms can be important to reach that g
oal. Moreover, a novel MPLS recovery mechanism called fast topology-driven
constrained-based rerouting is presented. Different MPLS recovery mechanism
s are compared to each other. Special attention hereby goes to the addition
al capacity that is required to recover from frequently occurring failures.