.png){kind=icon}
.png){kind=icon}
Return
Secure mobile edge computing with dual UAVs jointly assisting task offloading
.png){kind=icon}
PRE
AI
DOI：10.1016/j.phycom.2026.103096.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The integration of re-configurable intelligent surfaces (RIS) onto unmanned aerial vehicles (UAVs) presents a viable solution to the constraints associated with fixed RIS, thereby enhancing the overall efficacy of the system. Furthermore, the synergy between RIS and mobile edge computing (MEC) has the potential to broaden traditional signal models. In this paper, we propose a novel model for secure mobile edge computing (SMEC). Specifically, we consider a wireless communication scenario where user equipments (UEs) first offloads computing tasks to a UAV integrated with an edge server. Then, another UAV equipped with a reconfigurable intelligent surface (RIS) assists in forwarding the remaining unprocessed tasks to an access point (AP) for further computation, while an eavesdropper (EVE) is present in the system. In the proposed model, to ensure the secure transmission of UE's computing resources and maximize the system's secrecy computing energy efficiency, we leverage the flexibility of dual UAVs to jointly optimize time-slot allocation, resource allocation, UAV flight trajectories, and RIS phase shifts. The problem is formulated as a hybrid convex optimization challenge, and we employ a double deep Qnetwork (DDQN) algorithm to facilitate real-time environmental interaction, thereby deriving the optimal online solution. Simulation results indicate that the proposed algorithm significantly enhances the energy efficiency of the dual UAVs-assisted SMEC system while ensuring secure signal transmission.
Keywords:
Double deep Q-network
Secure mobile edge computing
Mobile edge computing
Secrecy computing energy efficiency
Journal
IF:
2.2
Papers:
360
Citations:
2.6K
Organization
No organization information available