Hybrid edge-cloud collaborator resource scheduling approach based on deep reinforcement learning and multiobjective optimization
Document Type
Journal Article
Publication Title
IEEE Transactions on Computers
Volume
73
Issue
1
First Page
192
Last Page
205
Publisher
IEEE
School
School of Engineering
RAS ID
62435
Funders
National Key Research and Development Project of China / National Natural Science Foundation of China / King Khalid University
Abstract
—Collaborative resource scheduling between edge terminals and cloud centers is regarded as a promising means of effectively completing computing tasks and enhancing quality of service. In this paper, to further improve the achievable performance, the edge cloud resource scheduling (ECRS) problem is transformed into a multi-objective Markov decision process based on task dependency and features extraction. A multi-objective ECRS model is proposed by considering the task completion time, cost, energy consumption and system reliability as the four objectives. Furthermore, a hybrid approach based on deep reinforcement learning (DRL) and multi-objective optimization are employed in our work. Specifically, DRL preprocesses the workflow, and a multi-objective optimization method strives to find the Pareto-optimal workflow scheduling decision. Various experiments are performed on three real data sets with different numbers of tasks. The results obtained demonstrate that the proposed hybrid DRL and multi-objective optimization design outperforms existing design approaches.
DOI
10.1109/TC.2023.3326977
Access Rights
subscription content
Comments
Zhang, J., Ning, Z., Waqas, M., Alasmary, H., Tu, S., & Chen, S. (2024). Hybrid edge-cloud collaborator resource scheduling approach based on deep reinforcement learning and multiobjective optimization. IEEE Transactions on Computers, 73(1), 192-205. https://doi.org/10.1109/TC.2023.3326977