Resource allocation for blockchain-enabled fog computing with deep reinforcement learning

Document Type

Conference Proceeding

Publication Title

ICCNS '22: Proceedings of the 2022 12th International Conference on Communication and Network Security

Publisher

Association for Computing Machinery

School

School of Engineering

Funders

Beijing Natural Science Foundation / Natural Science Foundation of China / China Ministry of Education - China Mobile Scientific Research Foundation / China Postdoctoral Science Foundation / Beijing Municipal Commission of Education Foundation

Comments

Zhang, Y., Tu, S., Waqas, M., Yang, Y., Wu, A., & Bai, X. (2022). Resource allocation for blockchain-enabled fog computing with deep reinforcement learning. In ICCNS '22: Proceedings of the 2022 12th International Conference on Communication and Network Security (pp. 211-218). Association for Computing Machinery. https://doi.org/10.1145/3586102.3586134

Abstract

With the developments of the Internet of Things, the demands of low latency, high bandwidth and high-performance computing has increased higher. Therefore, the distributed computing named Fog Computing has proposed to solve the problem above. Fog computing can provide lower transmission latency, faster response time and less network congestion. However, the fog devices are unable to guarantee the security and privacy of data transmission, due to they are vulnerable to attack. Blockchain technology works as a decentralized public ledger to store and share transactions. Blockchain can improve security and protect data privacy of Fog Computing. Moreover, there are still issues in the blockchain-enabled Fog Computing, the two main issues are the energy consumption and computing efficiency. Thus, in this paper, we propose an optimization framework for blockchain-enabled Fog Computing systems to optimize resource allocation. Besides, we adopt the dueling deep reinforcement learning to obtain the optimal resource allocation strategy, with dynamically selecting the fog server, offloading decision, block size. Simulation results show that the proposed framework can reduce the energy consumption and computation overhead of the system, as well as can improve the computing efficiency. © 2022 ACM.

DOI

10.1145/3586102.3586134

Access Rights

subscription content

Link to Full Text

Share

 
COinS