Evolution of cooperation in ad hoc networks under game theoretic model

In this paper, we present a new approach to evolve a cooperative behavior in ad hoc networks. We propose an environment composed of four elements: a game theory based model of the network, trust evaluation mechanism, strategy that defines the behavior of each node and a genetic algorithm. Interaction between nodes is represented as in the Iterated Prisoner's Dilemma under the Random Pairing game. In such a game randomly chosen players receive payoffs that depend on the way they behave. Each node is using a strategy that defines when to drop or to forward packets coming from other nodes. Such strategy is based on the past behavior of the network and on the trust level in the source node of the packet. Using the genetic algorithm we show how such strategies evolve ensuring high level of cooperation in the network.