.png){kind=icon}
返回
Multi-Objective Deep Reinforcement Learning for Function Offloading in Serverless Edge Computing
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2024.3489443.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Function offloading problems play a crucial role in optimizing the performance of applications in serverless edge computing (SEC). Existing research has extensively explored function offloading strategies based on optimizing a single objective. However, a significant challenge arises when users expect to optimize multiple objectives according to the relative importance of these objectives. This challenge becomes particularly pronounced when the relative importance of the objectives dynamically shifts. Consequently, there is an urgent need for research into multi-objective function offloading methods. In this paper, we redefine the SEC function offloading problem as a dynamic multi-objective optimization issue and propose a novel approach based on Multi-objective Reinforcement Learning (MORL) called MOSEC. MOSEC can coordinately optimize three objectives, i.e., application completion time, User Device (UD) energy consumption, and user cost. To reduce the impact of extrapolation errors, MOSEC integrates a Near-on Experience Replay (NER) strategy during the model training. Furthermore, MOSEC adopts our proposed Earliest First (EF) scheme to maintain the policies learned previously, which can efficiently mitigate the catastrophic policy forgetting problem. Extensive experiments conducted on various generated applications demonstrate the superiority of MOSEC over state-of-the-art multi-objective optimization algorithms.
Keyword:
Servers
Optimization
Energy consumption
Costs
Edge computing
Heuristic algorithms
Vectors
Serverless computing
Computational modeling
Wireless communication
Serverless edge computing
function offloading
multi-objective optimization
deep reinforcement learning
期刊
IF:
5.8
论文数:
2.2K
被引数:
6.5K
机构
引用论文
Offloading dependent tasks in multi-access edge computing: A multi-objective reinforcement learning approach多接入边缘计算中的依赖任务分流: 一种多目标强化学习方法
.png){kind=icon}
PREAI
分享收藏When Serverless Computing Meets Edge Computing: Architecture, Challenges, and Open Issues当无服务器计算遇到边缘计算时: 架构、挑战和开放问题
PREAI
分享收藏Workflow Scheduling in Serverless Edge Computing for the Industrial Internet of Things: A Learning Approach工业物联网无服务器边缘计算中的工作流调度: 一种学习方法
PREAI
分享收藏Performance optimization of serverless edge computing function offloading based on deep reinforcement learning基于深度强化学习的无服务器边缘计算功能卸载性能优化
PREAI
分享收藏
查看更多内容