Journal article
Secure Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless MEC Networks
IEEE Transactions on Communications, Vol.72(3), pp.1414-1427
2024
Abstract
This paper proposes a blockchain-secured deep reinforcement learning (BC-DRL) optimization framework for data management and resource allocation in decentralized wireless mobile edge computing (MEC) networks. In our framework, we design a low-latency reputation-based proof-of-stake (RPoS) consensus protocol to select highly reliable blockchain-enabled BSs to securely store MEC user requests and prevent data tampering attacks. We formulate the MEC resource allocation optimization as a constrained Markov decision process that balances minimum processing latency and denial-of-service (DoS) probability. We use the MEC aggregated features as the DRL input to significantly reduce the high-dimensionality input of the remaining service processing time for individual MEC requests. Our designed constrained DRL effectively attains the optimal resource allocations that are adapted to the dynamic DoS requirements. We provide extensive simulation results and analysis to validate that our BC-DRL framework achieves higher security, reliability, and resource utilization efficiency than benchmark blockchain consensus protocols and MEC resource allocation algorithms.
Details
- Title
- Secure Deep Reinforcement Learning for Dynamic Resource Allocation in Wireless MEC Networks
- Authors
- Xin Hao (Author) - University of SydneyPhee Lep Yeoh (Author) - University of the Sunshine Coast, Queensland, School of Science, Technology and EngineeringChangyang She (Corresponding Author) - University of SydneyBranka Vucetic (Author) - University of SydneyYonghui Li (Author) - University of Sydney
- Publication details
- IEEE Transactions on Communications, Vol.72(3), pp.1414-1427
- Publisher
- Institute of Electrical and Electronics Engineers
- DOI
- 10.1109/TCOMM.2023.3337376
- Grant note
- The work of P. L. Yeoh was supported in part by The University of Sydney Robinson Fellowship. The work of C. She was supported in part by DECRA under Grant DE210100415. The work of Branka Vucetic was supported in part by the ARC Laureate Fellowship grant number FL160100032. The work of Yonghui Li was supported by ARC under Grant P190101988 and DP210103410.
- Organisation Unit
- School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 99982897102621
- Output Type
- Journal article
Metrics
7 Record Views