Near-optimal packet allocation algorithm for content uploading to media cloud via collaborative wireless network

This paper investigates the problem of uploading user-generated content files (e.g., video captured on mobile devices) to a media cloud via a cooperative wireless network. The multi-path uploading capability of the cooperative network provides new opportunities by optimally allocating the packets into multiple paths to reduce end-to-end file uploading delay, thus improve the end user experience. In this paper, we formulate the delay minimization problem as an optimization task which is then studied using evolutionary algorithm (EA). Particularly, we perform a comprehensive investigation on two EA methods, namely, a simple mutation-based method and then the covariance matrix adaptation evolution strategy (CMA-ES) for minimizing the uploading delay. Extensive numerical simulations demonstrate their near-optimal performance, where the CMA-ES is shown to generate more efficient and robust results. The insights from this paper serves to provide some guidelines in future platform and application development.