Learning and Control in Stochastic Networks

  in Special Issue   Posted on September 28, 2020

Information for the Special Issue

Submission Deadline: Sat 31 Oct 2020
Journal Impact Factor : 1.114
Journal Name : Queueing Systems
Journal Publisher:
Website for the Special Issue: https://www.springer.com/journal/11134/updates/17587628
Journal & Submission Website: https://www.springer.com/journal/11134

Special Issue Call for Papers:

Queueing Systems: Theory and Applications is seeking submissions to a forthcoming Special Issue on Learning and Control in Stochastic Networks

Background and Scope
The theory of stochastic networks and their control is undergoing a phase of exciting collaborative growth with modern machine learning and artificial intelligence techniques, fueled by several new applications. 

On the one hand, recent years have seen a surge of interest in the application of machine learning techniques to the control of stochastic networks arising in modern communications applications like data centers, the goal being to design agile control mechanisms that operate under minimal informational assumptions and that adapt to changes in system characteristics over time. 

On the other hand, stochastic networks have emerged as a powerful modeling paradigm for addressing operational questions of matching demand and supply in modern platforms and marketplaces. Examples include ride-sharing platforms, labor platforms, energy markets, etc. A key value proposition of these platforms is the ability to learn from the tremendous amount of transactional data being generated to predict and mitigate supply-demand imbalances, and to recommend and make higher value matches than would otherwise be possible without centralized recommendations and/or matchmaking. Realizing this value proposition requires network control mechanisms that seamlessly assimilate information from data while being robust to strategic concerns. 

These developments have led to a growing body of literature on control of stochastic networks with novel architectures and at the interface of these control mechanisms with machine learning and strategic behavior. The special issue invites papers addressing novel technical challenges in this domain with direct applications to practice.

Submission Process 
We request that manuscripts be submitted through the Queueing Systems web portal (link below). Please choose ‘S.I.: Learning and Control in Stochastic Networks’ to ensure that the manuscripts are directed towards the guest editors for handling the review process.

Submission Portal

Author Instructions

Guest Editors: 
Rahul Jain,
University of Southern California
Vijay Kamble, University of Illinois at Chicago
Sanjay Shakkottai, University of Texas at Austin
Jiaming Xu, Duke University

Important Dates: 
Submission deadline: October 31, 2020 
First reviews sent: April 30, 2021
Revision deadline: July 31, 2021 
Final decisions: November 30, 2021 
Publication: December 2021.

Closed Special Issues