Improving Small Cell Performance through Switched Multi-element Antenna Systems in Heterogeneous Networks

This paper introduces an effeffective yet simple and practical solution to improve small cell performance in heterogeneous networks. The proposed solution is based on deploying a switched multi-element antenna system capable of generating a variety of antenna patterns at small cell base stations. Then antenna patterns are assigned to user equipment in a dynamic basis. The antenna pattern selection for each user equipment is considered as a supervised machine learning classification problem, in which the small cell BS seek to find the optimal antenna pattern to serve each user equipment according to its measurement reports (i.e. UE RF fingerprint). Simulation results confirm the feasibility of the proposed approach despite potential inaccuracies in user equipment measurement reports. Compared to the existing solutions comprising a single omnidirectional antenna, the proposed approach can provide up to 72% improvement in user throughput. In addition, a technoeconomic analysis presented in this paper indicating the economic advantages of deploying the proposed scheme.