A novel Distributed AI framework with ML for D2D communication in 5G/6G networks

Abstract

Inspired by the adoption of Artificial Intelligence (AI) and Machine Learning (ML) approaches in 5G and 6G networks, in this paper we propose a novel ML based Distributed AI (DAI) framework able to attain the ambitious goals set for emerging 5G/6G networks. The novelty of the DAI framework is that it is implemented in an autonomous, dynamic and flexible fashion, utilising Belief Desire Intention (BDI) agents, extended with ML capabilities, which reside on the mobile devices (User Equipment). We refer to these as BDIx agents. This provides a component-based framework (likened to LEGO-based building blocks), which can build on and utilise execution plans, by composing and arranging ML techniques in flexible ways within the framework, in order to achieve the desired goals. More specifically, we form a modular BDIx agent at a multi-agent system (MAS), integrated with Fuzzy Logic for the perception/cognitive part of the agents. By exploiting the capabilities of the BDIx agents in our DAI framework, we allow mobile devices to intercommunicate and cooperate in an autonomous manner, thus offering a number of attractive features, including improved performance in terms of network control execution time and message exchange, fast response in handling dynamic aspects in the network, self-organising network functionalities, and a framework that can act as the glue platform in employing one or more intelligent approaches to tackle the diverse 5G/6G technical requirements. To demonstrate the potential of the DAI framework we focus on Device to Device (D2D) communication and illustrate its flexibility in addressing diverse D2D challenges. Through example Plan Libraries and enhanced metrics, we outline DAI implementation specifics to achieve a number of identified 5G/6G D2D requirements. To embed the concept further, the specific problem of D2D transmission mode selection is expanded upon, from problem description to solution approach (DAIS) and implementation specifics, and hence comparatively evaluate over other approaches (i.e., Unsupervised learning ML techniques, centralised control techniques, random techniques). The results demonstrated that DAIS provides, among other performance metrics, improved mobile network Spectral Efficiency (SE) and Power Consumption (PC), better and more efficient cluster formation and reduced control decision delay.