Pattern-Identified Online Task Scheduling in Multitier Edge Computing for Industrial IoT Services

Abstract

In smart manufacturing, production machinery and auxiliary devices, referred to as industrial Internet of things (IIoT), are connected to a unified networking infrastructure for management and command deliveries in a precise production process. However, providing autonomous, reliable, and real-time offloaded services for such a production is an open challenge since these IIoT devices are assumed lightweight embedded platforms with limited computing performance. In this paper, we propose a pattern-identified online task scheduling (PIOTS) mechanism for the networking infrastructure, where multitier edge computing is provided, in order to handle the offloaded tasks in real time. First, historical IIoT task patterns in every timeslot are used to train a self-organizing map (SOM), which represents the features of the task patterns within defined dimensions. Consequently, offline task scheduling among edge computing-enabled entities is performed on the set of all SOM neurons using the Hungarian method to determine the expected optimal task assignments. In real-time context, whenever a task arrives at the infrastructure, the expected optimal assignment for the task is scheduled to the appropriate edge computing-enabled entity. Numerical simulation results show that the proposed PIOTS mechanism overcomes existing solutions in terms of computation performance and service capability.

Joint energy and latency optimization for upstream IoT offloading services in fog radio access networks

“…With the diversity of IoT services such as sensor reading, motion detection, and video surveillance, each IoT device requires a transmission data rate varying in the range of [512, 2048] kbps with computational complexities of {10, 50, 100, 500, 1000} computing cycles/bit. 16 The task execution deadline to satisfy the IoT service requirement is assumed in the range of [0.1, 1] second. Note that the proposed scheme is performed by the orchestrator with an algorithmic execution threshold of 5 ms. For convenience, the threshold is included into the task execution deadline.…”

“…In order to demonstrate the performance of the proposed JELO scheme, we compare our scheme with three task assignment schemes including the pattern-identified online task scheduling (PIOTS), 16 offline Hungarian task assignment (OHTA), 38 and online greedy task assignment (OGTA) 39 algorithms. In the PIOTS scheme, offline task scheduling among the FNs is performed on the set of all self-organizing maps (ie, task patterns) using the Hungarian method to obtain the expected optimal task assignments while minimizing the latency.…”

“…There is a significant number of researchers tackling this problem. [14][15][16] Unfortunately, there have been few proposals to resolve the joint optimization between the energy efficiency and the offload latency. 12,13 As mentioned in Section 1, our taxonomy consists of two main categories, ie, intrinsic and extrinsic approaches.…”

Task scheduling in Internet of Things cloud environment using a robust particle swarm optimization

“…Indeed, there are some studies that outperformed with Ω(log ) approximation algorithm. 30 Thus, running list scheduling algorithms in terms of earliest time of starting of computation requires a stronger lower and upper boundaries to provide a relationship between the number of VMs and total number of tasks to be scheduled. Finally, we conclude that ECT, EST, EDeadLine, and EDuedate show a significant performance which can guarantee a reasonable approximation (2 − 1 )-speed algorithms for preemptively minimizing average flow time as depicted in Figures 8B and 8C as compared with traditional list scheduling, which provides some theoretical justification of applying CPSO.…”

Energy-Efficient Learning System Using Web-Based Panoramic Virtual Photoreality for Interactive Construction Safety Education

“…These issues are severe, particularly on mobile device applications, where the equipped battery has capacity constraints [22]. As described in [23], the operation of an application results in the generation of multiple workloads. We let A denote the workload set of the application.…”