Joint Millimeter Wave and Microwave Resources Allocation in Cellular Networks With Dual-Mode Base Stations

The use of dual-mode base stations that can jointly exploit millimeter wave (mmW) and microwave (<inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula>) resources is a promising solution for overcoming the uncertainty of the mmW environment. In this paper, a novel dual-mode scheduling framework is proposed that jointly performs user applications (UAs) selection and scheduling over <inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula> and mmW bands. The proposed scheduling framework allows multiple UAs to run simultaneously on each user equipment (UE) and utilizes a set of <italic>context information</italic>, including the channel state information per UE, the delay tolerance and required load per UA, and the uncertainty of mmW channels, to maximize the quality-of-service (QoS) per UA. The dual-mode scheduling problem is then formulated as an optimization problem with minimum unsatisfied relations problem, which is shown to be challenging to solve. Consequently, a long-term scheduling framework, consisting of two stages, is proposed. Within this framework, first, the joint UA selection and scheduling over the <inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula> band is formulated as a one-to-many matching game between the <inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula> resources and UAs. To solve this problem, a novel scheduling algorithm is proposed and shown to yield a two-sided stable resource allocation. Second, over the mmW band, the joint context-aware UA selection and scheduling problem is formulated as a 0-1 Knapsack problem and a novel algorithm that builds on the Q-learning algorithm is proposed to find a suitable mmW scheduling policy while adaptively learning the UEs’ line-of-sight probabilities. Furthermore, it is shown that the proposed scheduling framework can find an effective scheduling solution, over both <inline-formula> <tex-math notation="LaTeX">$\mu \text{W}$ </tex-math></inline-formula> and mmW, in polynomial time. Simulation results show that, compared with conventional scheduling schemes, the proposed approach significantly increases the number of satisfied UAs while improving the statistics of QoS violations and enhancing the overall users’ quality-of-experience.