.png){kind=icon}
.png){kind=icon}
Return
D2D and Edge Server-Enabled Computation Offloading for Resource-Constrained Wireless Networks
.png){kind=icon}
PRE
AI
DOI：10.1109/TMC.2025.3628963.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
For the computation offloading via device-to-device (D2D) terminals and edge servers in a resource-constrained wireless network (RCWN), mobile users can choose to offload their tasks to nearby D2D terminals or edge servers according to quality of service (QoS) requirements (e.g., load balancing at the network edge) by mobile edge computing. To this end, we first formulate computation offloading as a multi-user collaborative resource dynamic management optimization problem that aims to maximize user satisfaction utility function, carefully considering critical issues like the non-uniform distribution of computational resources, user’s risk awareness, and the dynamic changes between computing-intensive regions and computing-sparse regions. This is a nonlinear and nonconvex optimization problem, which is generally difficult to be solved. We then construct a resource management scheme for resource allocation of the edge server based on convex optimization. Furthermore, we propose a dynamic offloading update strategy achieving the maximum of user satisfaction utility function based on game theory. The simulation results are presented to show that our proposed method can increase the total system satisfaction utility by nearly 20% and reduce the system energy consumption by nearly 10% compared to the benchmark methods.
Keywords:
Computation offloading
mobile edge computing
edge server
resource allocation
game theory
Journal
IF:
9.2
Papers:
5.6K
Citations:
1.8W
Organization
View more organizations