Design and implementation of utility-based radio resource optimization using CAPRI

In this paper we introduce a utility-based optimization approach for wireless communication based on developed Common Application Requirement Interface (CAPRI). The proposed system allows applications to register their utility functions to a radio resource controller at run-time and in automatic way. This enables the implementation of utility-based optimization and run-time reconfiguration of applications. Specifically, in contrast to traditional utility-based optimization approaches that usually aim at optimizing a single application deployed for the entire system, our approach aims to generalize and express the requirements of multiple applications. To validate our proposed system, we have implemented a prototype of CAPRI using Windows platform. The implementation has been made publicly available under an open source license. We show that the overhead induced by the adoption of the CAPRI framework in terms of memory and processing requirements is small, and additional latencies induced by the framework are negligible. Further, a practical case study of multi-application utility-based optimization has been addressed and the results have been analyzed.