.png){kind=icon}
返回
HAT: Task Offloading and Resource Allocation in RIS-Assisted Collaborative Edge Computing
.png){kind=icon}
PRE
AI
DOI：10.1109/TNSE.2024.3432893.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The problem of joint offloading decisions, resource allocation, and Reconfigurable Intelligent Surface (RIS) beamforming matrices for RIS-Assisted Edge Computing is a challenging issue. In this paper, user tasks can be either executed locally, or offloaded to a collaborative device or edge server with the assistance of the RIS, where RIS elements are grouped and assigned to all users to enable parallel services. The objective is formulated as a mixed integer nonlinear programming (MINLP) problem, where collaborative offloading decisions, RIS beamforming matrices, transmission power allocation, and computation resource allocation are jointly optimized to minimize the energy consumption. To address this problem, we propose a discrete-continuous Hybrid Action adapted Twin Delayed Deep Deterministic policy gradient (TD3) algorithm based on Deep Reinforcement Learning, named HAT. HAT constructs a latent representation space for the original discrete-continuous hybrid actions, fully considering the relations among highly coupled hybrid optimization variables. Experimental results demonstrate that HAT achieves significant performance gains over existing work (e.g., MELO, DDPG, PADDPG) and other benchmark schemes.
Keyword:
Array signal processing
Collaboration
Reconfigurable intelligent surfaces
Performance gain
Benchmark testing
Hybrid power systems
Resource management
Collaborative edge computing
deep reinforcement learning
reconfigurable intelligent surface
resource allocation
task offloading
期刊
I
IF:
7.9
论文数:
2.6K
被引数:
10.0K
机构
引用论文
.png){kind=icon}
Energy-Efficient Collaborative Multi-Access Edge Computing via Deep Reinforcement Learning通过深度强化学习实现高能效的协作式多访问边缘计算
PREAI
分享收藏分享收藏Imaging of the Spatial Density Distribution on the Capsule of the Lens with Scheimpflug Photography
PREAI
分享收藏Joint C-V2X Based Offloading and Resource Allocation in Multi-Tier Vehicular Edge Computing System
PREAI
分享收藏
查看更多内容