Apprenticeship Learning Based Spectrum Decision in Multi-Channel Wireless Mesh Networks with Multi-Beam Antennas

We propose a novel spectrum decision scheme (i.e., channel selection and handoff) for wireless mesh networks (WMN) which use multiple channels and nodes equipped with multi-beam directional antennas. Our scheme has the following features: (i) It performs spectrum decision by considering various WMN parameters, including the channel quality, beam orientation, antenna-caused deafness and capture effects, and application priority level. (ii) It uses the reinforcement learning (RL)-based spectrum decision process to achieve the optimal quality of multimedia transmission in the long term. However, a newly-joined WMN node could take a long time to make a correct spectrum decision due to the difficult choice of initial RL parameters. Therefore, our scheme uses the apprenticeship learning in conjunction with the RL model, to speed up the spectrum decision process by choosing a suitable neighboring node (called “expert”) to teach a newly-joined node (called “apprentice”). Our experiments demonstrate that the proposed spectrum decision scheme improves the network performance and multimedia transmission quality.

1 Introduction

The performance of wireless mesh networks (WMN) degrades when their size and number of hops increase. The use of multiple channels can significantly improve WMN throughput due to the reduction in the contending transmissions in the frequency domain [1], [2]. The use of directional antennas can further improve the WMN capacity by enhancing the transmission range and spatial reuse. Lately, the use of multi-beam smart antennas (MBSAs) has been investigated in the literature [3], [4]. However, most schemes select channels simply based on the non-interference principle between neighboring links, without considering other important factors (such as the link quality, antenna deafness, and node capture effect); these factors can considerably degrade the network performance.