RIS-Assisted Heterogeneous Collaborative Secure Offloading for Multi-Server MEC Systems based on HATD3

Xiaojuan Bai; Ao Gao; Tianxiang Liu; Xiao Ma

doi:10.6919/ICJE.202604_12(4).0028

Authors

Xiaojuan Bai
Ao Gao
Tianxiang Liu
Xiao Ma

DOI:

https://doi.org/10.6919/ICJE.202604_12(4).0028

Keywords:

Multi-access Edge Computing; Secure Computation Offloading; Resource Allocation; Heterogeneous Multi-Agent Deep Reinforcement Learning; Physical Layer Security; Reconfigurable Intelligent Surface.

Abstract

To address physical-layer eavesdropping threats and heterogeneous hybrid decision complexity in Reconfigurable Intelligent Surface (RIS)-assisted multi-server Multi-access Edge Computing (MEC) systems, this paper proposes a heterogeneous collaborative secure offloading method based on HATD3. First, a secure offloading model involving user equipment (UE), edge servers, RIS, and an eavesdropper is established for a multi-server MEC system under communication, computation, energy consumption, and secrecy constraints. The resulting problem is then formulated as a Decentralized Partially Observable Markov Decision Process (DEC-POMDP) for heterogeneous multi-agent coordination. Then, to handle the hybrid action space composed of continuous power control, discrete server selection, and RIS resource allocation, a Heterogeneous-Agent Twin Delayed Deep Deterministic Policy Gradient (HATD3)-based heterogeneous action decoupling and mapping mechanism is developed. Simulation results demonstrate that, compared with MATD3 and the no-RIS baseline, the proposed method achieves superior secure offloading performance in complex wireless environments, maintaining the secrecy rate around 7.0 Mbps, reducing the security violation rate to below 10%, and achieving a better trade-off among latency, energy consumption, and security.

Downloads

Download data is not yet available.

References

[1] H. Guo, J. Liu, and J. Zhang, "Computation offloading for multi-access mobile edge computing in ultra-dense networks," IEEE Communications Magazine, vol. 56, no. 8, pp. 14-19, 2018.

[2] L. Qin, H. Lu, Y. Chen, et al., "Toward decentralized task offloading and resource allocation in user-centric MEC," IEEE Transactions on Mobile Computing, vol. 23, no. 12, pp. 11807-11823, 2024.

[3] Y. Xiao, Y. Jia, C. Liu, et al., "Edge computing security: State of the art and challenges," Proceedings of the IEEE, vol. 107, no. 8, pp. 1608-1631, 2019.

[4] T. Zhang, H. Wen, J. Tang, et al., "Cooperative jamming secure scheme for IWNs random mobile users aided by edge computing intelligent node selection," IEEE Transactions on Industrial Informatics, vol. 17, no. 7, pp. 4999-5009, 2020.

[5] M. Cui, G. Zhang, and R. Zhang, "Secure wireless communication via intelligent reflecting surface," IEEE Wireless Communications Letters, vol. 8, no. 5, pp. 1410-1414, 2019.

[6] Q. Wu and R. Zhang, "Intelligent reflecting surface enhanced wireless network via joint active and passive beamforming," IEEE Transactions on Wireless Communications, vol. 18, no. 11, pp. 5394-5409, 2019.

[7] Y. Zhong, J. G. Kuba, X. Feng, et al., "Heterogeneous-agent reinforcement learning," Journal of Machine Learning Research, 2024.

[8] J. Xu, A. Xu, L. Chen, et al., "Deep reinforcement learning for RIS-aided secure mobile edge computing in industrial Internet of Things," IEEE Transactions on Industrial Informatics, vol. 20, no. 2, pp. 2455-2464, 2023.

[9] Qin L, Lu H, Chen Y, et al. Towards decentralized task offloading and resource allocation in user-centric mobile edge computing[J]. arXiv preprint arXiv:2312.01499, 2023.

[10] S. Leung-Yan-Cheong and M. Hellman, "The Gaussian wire-tap channel," IEEE transactions on information theory, vol. 24, no. 4, pp. 451-456, 2003.

[11] S. Fujimoto, H. Hoof, and D. Meger, "Addressing function approximation error in actor-critic methods," in Proc. ICML, 2018, pp. 1587-1596.

[12] J. Zhang, J. Du, Y. Shen, et al., "Dynamic Computation Offloading With Energy Harvesting Devices: A Hybrid-Decision-Based Deep Reinforcement Learning Approach," IEEE Internet Things J., vol. 7, no. 10, pp. 9303-9317, 2020.