We consider a cellular network where mobile transceiver devices that areowned by self-interested users are incentivized to cooperate with each otherusing tokens, which they exchange electronically to "buy" and "sell" downlinkrelay services, thereby increasing the network's capacity compared to a networkthat only supports base station-to-device (B2D) communications. We investigatehow an individual device in the network can learn its optimal cooperationpolicy online, which it uses to decide whether or not to provide downlink relayservices for other devices in exchange for tokens. We propose a supervisedlearning algorithm that devices can deploy to learn their optimal cooperationstrategies online given their experienced network environment. We thensystematically evaluate the learning algorithm in various deployment scenarios.Our simulation results suggest that devices have the greatest incentive tocooperate when the network contains (i) many devices with high energy budgetsfor relaying, (ii) many highly mobile users (e.g., users in motor vehicles),and (iii) neither too few nor too many tokens. Additionally, within the tokensystem, self-interested devices can effectively learn to cooperate online, andachieve over 20% higher throughput on average than with B2D communicationsalone, all while selfishly maximizing their own utilities.
展开▼
