Article details

Title: Efficient Recovery from Cascade Failures Using Q-learning
Author(s): George Leu   Akira Namatame            

Abstract: In the latest years, our society tends to become more and more dependent on large scale (global) infrastructure networks. Sometimes, attacks on a few important nodes of the network may generate cascade failures which lead to global failure of the system. This paper describes a mechanism for efficient recovery from cascade failures. An agent based method using reinforcement learning is provided, in order to reroute the traffic and to prevent failures to propagate over the entire network.

Keywords: large scale infrastructure networks, attacks (or failures), efficient recovery from cascade failures, agent based method.