Intelligent IoT for the Digital World

4Dynamic Service Provisioning Frameworks

4.1 Online Orchestration of Cross‐edge Service Function Chaining

4.1.1 Introduction

With the advancements in 5G communications and internet‐of‐things (IoT), billions of devices (e.g., mobile devices, wearable devices and sensors) are expected to be connected to the internet, which is indispensable for a wide variety of IoT applications, ranging from intelligent video surveillance and internet of vehicles (IoV) to augmented reality Taleb et al. (2017), Ananthanarayanan et al. (2017), Chen et al. (2018a), Zhou et al. (2019a), Chen et al. (2018c). As a result of the proliferation of these diverse applications, large volumes of multi‐modal data (e.g., audio and video) of physical surroundings are continuously sensed at the device side. To process such a tremendous amount of data streams, which typically requires vast computing resources and very low latency, the concept of edge computing (EC) Taleb et al. (2017) has recently been proposed. As an extension of cloud computing, EC pushes cloud resources and services from the network core to the network edges that are in closer proximity to IoT devices and data sources, leading to significant reduction of end‐to‐end latency.

Figure 4.1 An example of three service function chains (SFCs) for live video analytics. The black, blue, and red arrows represent the video streams that require the SFC ...