.png){kind=icon}
.png){kind=icon}
Return
Joint Resource Allocation and Multi-Part Collaborative Task Offloading in MEC Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TVT.2022.3174530.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper investigates the multi-part collaborative task offloading with multiple servers in mobile edge computing (MEC) systems by considering server overload and long-term system performance. Our goal is to achieve the optimal user experience within the range of the network operator's affordable cost. To this end, we design a two-layer computation offloading framework based on the multi-part offloading mode and the collaborations among small cell base station (SBS) servers. Furthermore, a multi-object constrained optimization problem is formulated, which jointly optimizes user association, channel allocation, and multi-part collaborative task offloading. To solve this problem, we propose a Genetic and Deep Deterministic Policy Gradient (GADDPG)-based computation offloading scheme, where the long-term system performance is considered. Numerical and simulation results demonstrate that the proposed GADDPG-based computation offloading scheme outperforms other methods in effectively solving the server overload and guarantees long-term system performances while ensuring the best user experience.
Keywords:
Task analysis
Servers
Collaboration
Resource management
Optimization
Computational modeling
System performance
Channel allocation
Genetic and Deep Deterministic Policy Gradient (GADDPG)
mobile edge computing (MEC)
multi-part collaborative task offloading
user allocation
Journal
IF:
7.1
Papers:
1.8W
Citations:
6.6W