Machine Learning in Real-Time Internet of Things (IoT) Systems: A Survey

Over the last decade, machine learning (ML) and deep learning (DL) algorithms have significantly evolved and been employed in diverse applications, such as computer vision, natural language processing, automated speech recognition, etc. Real-time safety-critical embedded and Internet of Things (IoT) systems, such as autonomous driving systems, UAVs, drones, security robots, etc., heavily rely on ML/DL-based technologies, accelerated with the improvement of hardware technologies. The cost of a deadline (required time constraint) missed by ML/DL algorithms would be catastrophic in these safety-critical systems. However, ML/DL algorithm-based applications have more concerns about accuracy than strict time requirements. Accordingly, researchers from the real-time systems (RTSs) community address the strict timing requirements of ML/DL technologies to include in RTSs. This article will rigorously explore the state-of-the-art results emphasizing the strengths and weaknesses in ML/DL-based scheduling techniques, accuracy versus execution time tradeoff policies of ML algorithms, and security and privacy of learning-based algorithms in real-time IoT systems.

I. Introduction

Real-time systems (RTSs) design must have both functional and temporal correctness [1], [2]. Thus, RTSs are traditionally designed with temporally predictable and deterministic algorithms. For instance, before implementing an online scheduler, the regular real-time scheduling algorithms have to perform (exact or sufficient only) deterministic (finite time) offline feasibility (also known as schedulability) tests [1]. However, the feasibility test of the scheduling algorithms becomes highly complicated (in most cases intractable) with the underlying system heterogeneity and inter- and intra-dependent tasks [3]. Hence, until recently, RTS was restricted to only safety- and mission-critical systems, such as avionics, spacecraft, etc., with dedicated proprietary hardware platforms and simple task models.