The self-traffic-engineering network

This paper characterizes several techniques for the distributed, dynamic management of telecommunications network transmission facilities. Several methods are presented for changing trunk-group sizes in order to respond to extraordinary network loads. These methods are given the generic title of self-traffic-engineering (STE), because the network effectively reengineers itself to adapt to unforeseen circumstances. Self-traffic-engineering is a new network management application for telecommunications facilities networks. One of these methods is based on a new interpretation of network reliability, which is embodied in a metric called connectability. Connectability can be used as the basis of a distributed, isolated strategy that is competitive with a centralized linear programming scheme. (This is surprising, because the distributed strategy uses only data which are locally available, whereas the centralized scheme has a global picture of the network.) Connectability can also be used to compare the performance of network rearrangement techniques. Finally, this paper reports the results of a simulation study in which self-traffic-engineering is used to enable the Telecom Canada network to adapt to a focused overload. These results are based on the assumption that the spare capacity normally used to protect the network from failure can be temporarily reassigned to help the network adapt to an extreme traffic load. Self-traffic-engineering is a new physical-layer technique that can be applied in a variety of settings (e.g., private networks, virtual private networks). It can be applied in a controlled fashion, ranging from very aggressively to very cautiously.