Abstract
Edge computing (EC) has recently emerged as a promising paradigm that supports resource-hungry Internet of Things (IoT) applications with low latency services at the network edge. However, the limited capacity of computing resources at the edge server poses great challenges for scheduling application tasks. In this paper, a task scheduling problem is studied in the EC scenario, and multiple tasks are scheduled to virtual machines (VMs) configured at the edge server by maximizing the long-term task satisfaction degree (LTSD). The problem is formulated as a Markov decision process (MDP) for which the state, action, state transition, and reward are designed. We leverage deep reinforcement learning (DRL) to solve both time scheduling (i.e., the task execution order) and resource allocation (i.e., which VM the task is assigned to), considering the diversity of the tasks and the heterogeneity of available resources. A policy-based REINFORCE algorithm is proposed for the task scheduling problem, and a fully-connected neural network (FCN) is utilized to extract the features. Simulation results show that the proposed DRL-based task scheduling algorithm outperforms the existing methods in the literature in terms of the average task satisfaction degree and success ratio.
Highlights
Accepted: 24 February 2021Technology advancements in sensing, communications, and computing directly accelerate the recent development of the Internet of Things (IoT), leading to diverse IoT uses [1,2]
We focus on the heterogeneous virtual machines (VMs) resources for the task scheduling to maximize the long-term value of the quality of experience (QoE) by considering the expected delay requirement
A new mechanism is designed in the Markov decision process (MDP) formulation, where the scheduling time step is decoupled from the real time step
Summary
Technology advancements in sensing, communications, and computing directly accelerate the recent development of the Internet of Things (IoT), leading to diverse IoT uses [1,2]. In [25], the task scheduling and dispatching of networking and computing resources were investigated to maximize the number of completed tasks These methods are based on an ideal mathematical model and optimized by a mixed-integer non-linear programming (MINLP) or heuristic algorithms. In [35], a DRL-based approach was proposed to address the task scheduling and offloading problems in vehicular edge computing, while the latency demands were not considered. We focus on the heterogeneous VM resources for the task scheduling to maximize the long-term value of the QoE by considering the expected delay requirement In achieving this goal, the DRL algorithm is applied, and the task satisfaction degree is determined as the reward.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
