Admission Control

Admission control, the process of selectively accepting or rejecting incoming requests for resources, is a critical problem across diverse systems, aiming to optimize resource utilization and performance while meeting quality-of-service requirements. Current research heavily utilizes reinforcement learning, particularly deep reinforcement learning and contextual bandit algorithms, often coupled with techniques like graph neural networks and digital twins to improve model training and efficiency, especially in complex scenarios such as network slicing and queueing systems. These advancements are significant for improving resource allocation in areas like network virtualization, wireless communication (including URLLC), and even robotic control, leading to more efficient and reliable systems.

Papers

June 25, 2024

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
Tianfu Wang, Li Shen, Qilin Fan, Tong Xu, Tongliang Liu, Hui Xiong
Proximal Policy Optimization Resource Allocation Virtual Network REinforcement Learning Network Virtualization Admission Control Multi Objective Reward

June 7, 2024

Reinforcement Learning and Regret Bounds for Admission Control
Lucas Weber, Ana Bušić, Jiamin Zhu
Reinforcement Learning Markov Decision Process Reinforcement Learning Algorithm Regret Bound Low Regret Admission Control Customer Side Queue

March 28, 2024

Adaptive Preload Control of Cable-Driven Parallel Robots for Handling Task
Thomas Reichenbach, Johannes Clar, Andreas Pott, Alexander Verl
Related Task Force Control Cable Driven Optimal Stiffness Toughness Trade Offs Moving Platform Admission Control Position Control

January 5, 2024

Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach
Omid Semiari, Hosein Nikopour, Shilpa Talwar
Mobility Management Quality of Service Neural Contextual Bandit Ultra Reliable Low Latency Communication Admission Control

October 7, 2023

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network
Zhenyu Tao, Wei Xu, Xiaohu You
Deep Reinforcement Learning Markov Decision Process Digital Twin Deep Q Network Slice Admission Control

August 4, 2023

Learning Optimal Admission Control in Partially Observable Queueing Networks
Jonatha Anselmi, Bruno Gaujal, Louis-Sébastien Rebuffi
Reinforcement Learning Markov Decision Process Efficient Reinforcement Learning Admission Control

May 9, 2022

AdaCap: Adaptive Capacity control for Feed-Forward Neural Networks
Katia Meziani, Karim Lounici, Benjamin Riu
Neural Network Machine Learning Model Operator Learning Admission Control

April 14, 2022

Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach
Simon Lindståhl, Alexandre Proutiere, Andreas Johnsson
Best Arm Identification Dataflow Architecture Network Slice Measurement Operator Admission Control

March 14, 2022

Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction
Marc Rigter, Danial Dervovic, Parisa Hassanzadeh, Jason Long, Parisa Zehtabi, Daniele Magazzeni
Markov Decision Process Discrete Time State Abstraction Optimal Value Function Admission Control

Admission Control

Papers

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

Reinforcement Learning and Regret Bounds for Admission Control

Adaptive Preload Control of Cable-Driven Parallel Robots for Handling Task

Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach

Digital Twin Assisted Deep Reinforcement Learning for Online Admission Control in Sliced Network

Learning Optimal Admission Control in Partially Observable Queueing Networks

AdaCap: Adaptive Capacity control for Feed-Forward Neural Networks

Measurement-based Admission Control in Sliced Networks: A Best Arm Identification Approach

Optimal Admission Control for Multiclass Queues with Time-Varying Arrival Rates via State Abstraction