A scalable network resource allocation mechanism with bounded efficiency loss

The design of pricing mechanisms for network resource allocation has two important objectives: 1) a simple and scalable end-to-end implementation and 2) efficiency of the resulting equilibria. Both objectives are met by certain recently proposed mechanisms when users are price taking, but not when users can anticipate the effects of their actions on the resulting prices. In this paper, we partially close this gap, by demonstrating an alternative resource allocation mechanism which is scalable and guarantees a fully efficient allocation when users are price taking. In addition, when links have affine marginal cost, this mechanism has efficiency loss bounded by 1/3 when users are price anticipating. These results are derived by studying Cournot games, and in the process we derive the first nontrivial constant factor bounds on efficiency loss in these well-studied economic models.