The rapid growth of energy demand by wired IP networks can be mitigated on hardware and software levels. While upgrading to more efficient transmission media still brings biggest savings, we take a look here at power-saving algorithms that combine the capability of setting networking equipment in arbitrary energy states which, combined with profound knowledge of the network traffic matrix, leads to considerable complex optimization problem formulations. Alternatively, lightweighted heuristic approaches are presented, built on much simpler network model but still capable to perform energy-efficient traffic engineering.