Abstract
The explosive growth of data generated by the widespread use of IoT devices and the increasing realizations of IoT applications that require real-time responses have made it difficult for traditional cloud computing or edge computing to keep up with the tasks processing demands and/or near real-time response requirements of applications. We employ the strategy of computation offloading to nearby edge nodes to meet these requirements on time. In this research, we developed an efficient offload broker mechanism using deep reinforcement learning to perform optimal task allocation and computation offloading on this platform. Experiments show that the model learns the policies for offloading tasks to the optimal nodes appropriately. These promising results will enlighten more computation offloading issues to improve the efficiency of the model and its deployment in edge computing environment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
IDC Corporate, IoT Growth Demands Rethink of Long-Term Storage Strategies, 27 July 2020. https://www.idc.com/getdoc.jsp?containerId=prAP46737220
Cao, K., Liu, Y., Meng, G., Sun, Q.: An overview on edge computing research. IEEE Access 8, 85714–85728 (2020). https://doi.org/10.1109/ACCESS.2020.2991734
Lin, L., Liao, X., Jin, H., Li, P.: Computation offloading toward edge computing. Proc. IEEE 107, 1–24 (2019). https://doi.org/10.1109/JPROC.2019.2922285
Jiang, C., Cheng, X., Gao, H., Zhou, X., Wan, J.: Towards computation offloading in edge computing: survey. IEEE Access 7, 131543–131558 (2019). https://doi.org/10.1109/ACCESS.2019.2938660
Gao, Z., Hao, W., Han, Z., Yang, S.: Q-learning-based task offloading and resources optimization for a collaborative computing system. IEEE Access (2020). https://doi.org/10.1109/ICCC49849.2020.9238925
Sajjad Hossain, Md., Nwakanma, C.I., Lee, J.M., Kim, D.-S.: Edge computational task offloading scheme using reinforcement learning for IIoT scenario. ICT Express 6, 291–299 (2020). https://doi.org/10.1016/j.icte.2020.06.002
Awate, Y.P.: Policy-gradient based actor-critic algorithms, pp. 505–509. IEEE Xplore, May 2009. https://doi.org/10.1109/GCIS.2009.372
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: ICML 2014, vol. 32, pp. 387–395, June 2014
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR 2016, arXiv:1509.02971, Jul 2019 (latest version)
Tensorflow: The Python Deep Learning library https://www.tensorflow.org/
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ide, S., Apduhan, B.O. (2021). Development of an RL-Based Mechanism to Augment Computation Offloading in Edge Computing. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2021. ICCSA 2021. Lecture Notes in Computer Science(), vol 12954. Springer, Cham. https://doi.org/10.1007/978-3-030-86979-3_38
Download citation
DOI: https://doi.org/10.1007/978-3-030-86979-3_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86978-6
Online ISBN: 978-3-030-86979-3
eBook Packages: Computer ScienceComputer Science (R0)