A Two-Game Algorithm for Device-to-Device Resource Allocation with Frequency Reuse

Abstract

Device-to-Device (D2D) communication as an extension to current mobile networks attracted a lot of attention during the last years. Along with introducing D2D communication as an underlay to cellular communication, radio frequency resources are proposed to be reused to increase spectral efficiency and system capacity. Being able to reuse frequency resources can lead to in-cell interference which must be actively mitigated. We investigate a novel joint radio resource scheduling and allocation algorithm which takes into account different user service classes and mitigates in-cell interference from frequency resource reuse. It is shown that system performance can be increased if resource allocation and reuse is done in a coordinated manner. The proposed scheduler is based on two algorithms from game theory, scales well due to its linear computational complexity and outperforms baseline schedulers in several simulated scenarios.

Reinforcement Learning for Interference Coordination Stackelberg Games in Heterogeneous Cellular Networks

“…Authors in [16] presented an artificial adjustment method of cost parameter to guarantee both sides of the reaction function the same order of magnitude, and the value of the reaction function is within a reasonable range. The cost parameters can also be determined by the channel state of the follower [17] or by the channel state of the leader [18]. In [19], an iterative strategy was proposed to improve the cost parameter, updating the global cost parameter in a fixed number of steps according to the result of the game.…”

“…Meanwhile, the RL-based distributed interference coordination methods, such as in [10], are executed by each UE, which can consume excessive computing resources. Stackelberg game-based interference coordination methods [15][16][17][18][19][20] allow distributed follower games in each UE of small cells; however, important cost parameters for follower games are not effectively optimized so far. Therefore, this paper focuses on applying reinforcement learning to the Stackelberg game model to address interference coordination problem in D2D and relay heterogeneous cellular networks.…”