Artificial Intelligence Meets Autonomy in Wireless Networks: A Distributed Learning Approach

Abstract

Future wireless networks entail autonomous controls of mobile devices in a variety of applications, such as internet of things and mobile edge computing. A distributed nature of wireless networks poses a fundamental challenge in decentralized management of separate devices. In particular, the coordination among devices possessing heterogeneous levels of cooperation policy and computation power emerges as a critical implementation issue for practical wireless networks. This challenge turns out to handle dynamic link topologies with node interconnections prone to arbitrary configurations and random changes. This article presents a structural learning solution called Platform for Learning Autonomy in Distributed Optimization (PLAyDO), with an objective of modeling dynamic interactions among wireless devices through a mesh of deep neural networks (NNs). This framework identifies distributed mechanisms among autonomous devices, such as decentralized computations and communication protocols, to handle arbitrary interaction topologies. The autonomous cooperation involves the design of a novel NN architecture that learns network-wide cooperation policies. To this end, device interaction mechanisms are classified according to interaction levels. NN unit groups called interaction slices are dedicated to configure heterogeneous cooperation abilities so that a multi-hop coordination of individual NN-empowered devices collectively characterizes a self-organizing management of the network. The feasibility and effectiveness of this NN-oriented formalism are investigated for decentralized power management of wireless ad-hoc networks.