Lyapunov-Driven Deep Reinforcement Learning for Edge Inference Empowered by Reconfigurable Intelligent Surfaces

Abstract

In this paper, we propose a novel algorithm for energy-efficient, low-latency, accurate inference at the wireless edge, in the context of 6G networks endowed with reconfigurable intelligent surfaces (RISs). We consider a scenario where new data are continuously generated/collected by a set of devices and are handled through a dynamic queueing system. Building on the marriage between Lyapunov stochastic optimization and deep reinforcement learning (DRL), we devise a dynamic learning algorithm that jointly optimizes the data compression scheme, the allocation of radio resources (i.e., power, transmission precoding), the computation resources (i.e., CPU cycles), and the RIS reflectivity parameters (i.e., phase shifts), with the aim of performing energy-efficient edge classification with end-to-end (E2E) delay and inference accuracy constraints. The proposed strategy enables dynamic control of the system and of the wireless propagation environment, performing a low-complexity optimization on a per-slot basis while dealing with time-varying radio channels and task arrivals, whose statistics are unknown. Numerical results assess the performance of the proposed RIS-empowered edge inference strategy in terms of trade-off between energy, delay, and accuracy of a classification task.

Holographic MIMO Communications: Theoretical Foundations, Enabling Technologies, and Future Directions

“…5) Other Miscellaneous Applications: Beyond the previously mentioned extensions, the emergence of HMIMO surfaces, especially the passive ones, spurs a vast range of research combinations by introducing the surfaces to various areas, including physical layer security [321]- [323], index modulation [324]- [326], non-orthogonal multiple access [327]- [329], cognitive radio [330]- [332], ambient backscattering communications [95], [333]- [335], full duplex wireless communications [336]- [341], cell-free network [342]- [344], mobile edge computing [345]- [349], federated learning [350]- [352], and machine learning aided applications [353]- [356]. It should be emphasized that these studies consider the application of HMIMO surfaces mainly as passive reflectors, incorporating in conventional communication systems, such as MIMO and mMIMO.…”