Dynamic Advertising in VANETs using Repeated Auctions

Vehicular ad-hoc networks (VANETs) have been an active area in the research community during the last decade with focus primarily on routing protocols, security aspects and safety. Recent advances in wireless communication and the inherent dynamic nature of VANETs provide excellent opportunity for advertisement dissemination. In this paper, we address the problem of dynamic advertising in VANETs. We consider a city divided into a grid, where the blocks have different vehicular densities that vary over time. Several advertising companies compete for the blocks to broadcast their advertisements in the network. The content dissemination in the network is controlled by a data management unit that receives requests from advertising companies for each block. To solve the problem of block allocation, we adapt the repeated auction scheme for the dynamic setting. Two new metrics are defined to better represent the real-world scenario and fairness in repeated auctions. We propose an algorithm which is a combination of adaptive linear prediction and nonparametric Bayesian belief update, enabling smart bidding and improving the utilities of the competing advertising companies significantly in the long-run. Through simulations, we show that the proposed algorithm achieves better performance than two baselines approaches.