Towards Efficient Medium Access for Millimeter-Wave Networks

Abstract

The need of highly directional communications at mmWave frequencies introduces high overhead for beam training and alignment, which makes the medium access control (MAC) a grand challenge. To harvest the gain for high performance transmissions in mmWave networks, we propose an efficient and integrated MAC design with the concurrent support of three closely interactive components: 1) an accurate and low-cost beam training methodology with a) multiuser, multi-level, bi-directional coarse training for fast user association and beam alignment and b) adaptive fine beam training with compressed channel measurement and multi-resolution block-sparse channel estimation in response to the channel condition and the learning from past measurements; 2) an elastic virtual resource scheduling scheme that jointly considers beam training, beam tracking and data transmissions while enabling burst data transmissions with the concurrent allocation of transmission rate and duration; and 3) a flexible and efficient beam tracking strategy to enable stable beam alignment with beamwidth adaptation and mobility estimation. Compared with literature studies, our performance results demonstrate that our design can effectively reduce the training overhead and thus significantly improve the throughput. Compared to 802.11ad, the training overhead can be reduced more than 60%, and the throughput can be more than 75% higher. In low SNR case, the throughput gain can be more than 90%. Our scheme can also achieve about 50% higher throughput in the presence of user mobility.