Dynamics of a Localized Reputation-Based Network Protocol

We consider a type of game theoretic dynamics in a network model where all nodes act selfishly and will forward packets only if it is to their benefit. The model we present assumes that each node receives utility from successfully sending its own flow to its destination(s) and from receiving flow, while it pays a cost (e.g., battery energy) for its transmissions. Each node has to decide whether to relay flow as an intermediate node from other sources, as relaying incurs only costs. To induce nodes into acting as intermediaries, the model implements a reputation-based mechanism which punishes non-cooperative nodes by cutting off links to them, a decision that is made in a very local fashion. In our setting, the nodes know only the state of the network in their local neighborhood, and can only decide on the amount of the flow on their outgoing edges, unlike the previously considered models where users have full knowledge of the network and can also decide the routing of flow originating from them. Given the opportunistic nature of the nodes and their very limited knowledge of the network, our simulations show the rather surprising fact that a non-negligible amount of non-trivial flow (flow over at least two hops) is successfully transmitted.