A distributed AI/ML framework for D2D Transmission Mode Selection in 5G and beyond

In this paper we build on the Distributed Artificial Intelligence (DAI) Framework, which makes use of Belief-Desire-Intention extended (BDIx) agents residing on Device-to-Device (D2D) Mobile Devices in order to establish D2D communication in an efficient, distributed, autonomous and flexible way. To demonstrate the potentials of this framework, in this work we focus on D2D Transmission Mode Selection in 5G. Specifically, we build on our previous work and develop an enhanced version of DAIS, a specific plan executed by the BDIx agents, for selecting the D2D Transmission mode that the D2D Devices will operate, aiming to offer improved Spectral Efficiency (SE) and Power Consumption (PC). To set a benchmark and allow for a fairer comparison we also enhance the Distributed Sum Rate (DSR), a distributed algorithmic approach that focuses on maximising the aggregated data rate of all the links established in the network, with similar functionality as DAIS. Furthermore, an extensive comparative evaluation of the enhanced DAIS and DSR with a number of unsupervised ML clustering approaches adapted for D2D Communication(i.e., GMEANS, Fuzzy ART, MEC, and DBSCAN) is provided. Specifically, for each approach the following have been collected and compared: QoE and QoS Fairness, SE and PC achieved, efficiency of clusters created, signalling overhead caused (i.e., volume of messages exchanged), time execution delay, D2D Effectiveness, D2D Stability and D2D Productivity. Based on the insight gained into the performance of the enhanced DAIS, DSR and the unsupervised ML techniques, we discuss performance gain trade-offs in terms of SE and PC versus signalling overhead and control delay in responding to changes.