This paper considers the problem of logical topology selection in an IP-over-WDM network, with the objective to minimize the total power consumption used to support the traffic demands. While there are several power consuming devices in a backbone WDM network, it is assumed that major power consumption occurs at IP router ports, which are termination points of optical connections or lightpaths. The logical topology selection problem is first formulated as an integer linear programming (ILP) problem that is computationally difficult to solve. To focus on minimizing the power consumption, it is assumed that the network is not limited by available link capacities. Two systematic approaches to obtain a lower bound on the power consumption are considered, namely linear programming (LP) relaxation and Lagrangian relaxation. It is shown that both methods result in the same lower bound that corresponds to shortest path routing of traffic. A heuristic based on shortest path routing and pruning of unnecessary lightpaths is then evaluated using simulation results obtained from the heuristic in comparison to the baseline case in which the logical topology is taken to be the same as the physical topology.