A self-learning repeated game framework for optimizing packet forwarding networks

Abstract

For networks with packet forwarding, distributed control to enforce cooperation for node packet forwarding probabilities is essential to maintain the connectivity. In this paper, we propose a novel self-learning repeated game framework to optimize packet forwarding probabilities of distributed users. The framework has two major steps: first, an adaptive repeated game scheme ensures the cooperation among users for the current cooperative packet forwarding probabilities; second, a self-learning scheme tries to find better cooperation probabilities. Some special cases are analyzed to evaluate the proposed framework. From the simulation results, the proposed framework demonstrates the near optimal solutions in both symmetrical and asymmetrical networks.