Edge Server Scheduling

Edge server scheduling optimizes the allocation of computational resources to incoming tasks, aiming to minimize latency and maximize resource utilization in edge computing environments. Current research heavily focuses on developing efficient scheduling algorithms, employing techniques like reinforcement learning, evolutionary computing, and graph neural networks to address the complexities of diverse task types and dynamic network conditions. These advancements are crucial for enabling real-time applications like augmented reality and federated learning, improving performance and efficiency in resource-constrained edge networks. The ultimate goal is to create robust and adaptable scheduling frameworks that guarantee low latency and high reliability for a wide range of edge services.

Papers

September 4, 2024

TS-EoH: An Edge Server Task Scheduling Algorithm Based on Evolution of Heuristic
Wang Yatong, Pei Yuchen, Zhao Yuqi
Edge Computing Specie Evolution Evolutionary Computation Task Scheduling Scheduling Policy Cognitive Heuristic Edge Server Scheduling

August 30, 2024

SafeTail: Efficient Tail Latency Optimization in Edge Service Scheduling via Computational Redundancy Management
Jyoti Shokhanda, Utkarsh Pal, Aman Kumar, Soumi Chattopadhyay, Arani Bhattacharya
Edge Computing Near Optimal Redundancy Aware Latency Critical Edge Server Scheduling Safe Deep

November 3, 2023

Client Orchestration and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning
Bibo Wu, Fang Fang, Xianbin Wang, Donghong Cai, Shu Fu, Zhiguo Ding
Joint Optimization Hierarchical Federated Learning Non Orthogonal Multiple Access Convergence Orchestration Edge Server Scheduling

August 28, 2023

Edge Generation Scheduling for DAG Tasks Using Deep Reinforcement Learning
Binqi Sun, Mirco Theile, Ziyuan Qin, Daniele Bernardini, Debayan Roy, Andrea Bastoni, Marco Caccamo
Deep Reinforcement Learning Directed Acyclic Graph Mobile Edge Edge Server Scheduling

April 10, 2023

RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs
Jiaqi Yin, Yingjie Li, Daniel Robinson, Cunxi Yu
Reinforcement Learning Deep Neural Network Optimal Scheduling Edge TPU Edge Server Scheduling Multi DNN Scheduling

February 1, 2023

Task Placement and Resource Allocation for Edge Machine Learning: A GNN-based Multi-Agent Reinforcement Learning Paradigm
Yihong Li, Xiaoxi Zhang, Tianyu Zeng, Jingpu Duan, Chuan Wu, Di Wu, Xu Chen
Machine Learning Multi Agent Reinforcement Learning Resource Allocation Edge Computing Global Placement Edge Server Scheduling

August 2, 2022

Digital Twin-Assisted Efficient Reinforcement Learning for Edge Task Scheduling
Xiucheng Wang, Longfei Ma, Haocheng Li, Zhisheng Yin, Tom. Luan, Nan Cheng
Reinforcement Learning Digital Twin Q Learning Task Scheduling Asynchronous Q Learning Edge Server Scheduling

Edge Server Scheduling

Papers

TS-EoH: An Edge Server Task Scheduling Algorithm Based on Evolution of Heuristic

SafeTail: Efficient Tail Latency Optimization in Edge Service Scheduling via Computational Redundancy Management

Client Orchestration and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning

Edge Generation Scheduling for DAG Tasks Using Deep Reinforcement Learning

RESPECT: Reinforcement Learning based Edge Scheduling on Pipelined Coral Edge TPUs

Task Placement and Resource Allocation for Edge Machine Learning: A GNN-based Multi-Agent Reinforcement Learning Paradigm

Digital Twin-Assisted Efficient Reinforcement Learning for Edge Task Scheduling