TRANSPORT NETWORK OPTIMIZIATION: SELF-ORGANIZATION BY GENETIC PROGRAMMING

This goal of the paper is transport network optimization. Transport networks are defined as network topologies where entities are forwarded from node to node constrained by capacity restrictions both on nodes and links. Examples include urban traffic (vehicles/signalized intersections) and IF networks (packets/routers). Optimization of such networks particularly has to provide the logic the nodes use to determine which entity to process next. Such logic can be imposed by a central authority based on global knowledge of the network state. In contrast, a self-organizing network solely relies on local decision rules to prioritize entities. At the cost of a potential loss in performance, such a decentralized network control is scalable and robust. This paper proposes genetic programming to evolve local node rules. Results indicate that the performance is similar to centrally (near-optimally) controlled systems.