Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning

Xianfu Chen, Zhu Han, Honggang Zhang, Guoliang Xue, Yong Xiao, Mehdi Bennis

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.

Original languageEnglish (US)
JournalIEEE Transactions on Mobile Computing
DOIs
StateAccepted/In press - Aug 22 2017

Fingerprint

Scheduling
Networks (circuits)
Controllers
Base stations
Computational complexity
Decision making

Keywords

  • Games
  • learning
  • Markov decision process
  • Mobile communication
  • Mobile computing
  • multi-user resource scheduling
  • network virtualization
  • Radio access networks
  • radio access networks
  • Scheduling
  • Software-defined networking
  • stochastic games
  • Stochastic processes
  • Wireless communication

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning. / Chen, Xianfu; Han, Zhu; Zhang, Honggang; Xue, Guoliang; Xiao, Yong; Bennis, Mehdi.

In: IEEE Transactions on Mobile Computing, 22.08.2017.

Research output: Contribution to journalArticle

@article{d31ecf61212746438c39b7fd7d39f77f,
title = "Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning",
abstract = "How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.",
keywords = "Games, learning, Markov decision process, Mobile communication, Mobile computing, multi-user resource scheduling, network virtualization, Radio access networks, radio access networks, Scheduling, Software-defined networking, stochastic games, Stochastic processes, Wireless communication",
author = "Xianfu Chen and Zhu Han and Honggang Zhang and Guoliang Xue and Yong Xiao and Mehdi Bennis",
year = "2017",
month = "8",
day = "22",
doi = "10.1109/TMC.2017.2742949",
language = "English (US)",
journal = "IEEE Transactions on Mobile Computing",
issn = "1536-1233",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Wireless Resource Scheduling in Virtualized Radio Access Networks Using Stochastic Learning

AU - Chen, Xianfu

AU - Han, Zhu

AU - Zhang, Honggang

AU - Xue, Guoliang

AU - Xiao, Yong

AU - Bennis, Mehdi

PY - 2017/8/22

Y1 - 2017/8/22

N2 - How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.

AB - How to allocate the limited wireless resource in dense radio access networks (RANs) remains challenging. By leveraging a software-defined control plane, the independent base stations (BSs) are virtualized as a centralized network controller (CNC). Such virtualization decouples the CNC from the wireless service providers (WSPs). We investigate a virtualized RAN, where the CNC auctions channels at the beginning of scheduling slots to the mobile terminals (MTs) based on bids from their subscribing WSPs. Each WSP aims at maximizing the expected long-term payoff from bidding channels to satisfy the MTs for transmitting packets. We formulate the problem as a stochastic game, where the channel auction and packet scheduling decisions of a WSP depend on the state of network and the control policies of its competitors. To approach the equilibrium solution, an abstract stochastic game is proposed with bounded regret. The decision making process of each WSP is modeled as a Markov decision process (MDP). To address the signalling overhead and computational complexity issues, we decompose the MDP into a series of single-agent MDPs with reduced state spaces, and derive an online localized algorithm to learn the state value functions. Our results show significant performance improvements in terms of per-MT average utility.

KW - Games

KW - learning

KW - Markov decision process

KW - Mobile communication

KW - Mobile computing

KW - multi-user resource scheduling

KW - network virtualization

KW - Radio access networks

KW - radio access networks

KW - Scheduling

KW - Software-defined networking

KW - stochastic games

KW - Stochastic processes

KW - Wireless communication

UR - http://www.scopus.com/inward/record.url?scp=85028500008&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028500008&partnerID=8YFLogxK

U2 - 10.1109/TMC.2017.2742949

DO - 10.1109/TMC.2017.2742949

M3 - Article

AN - SCOPUS:85028500008

JO - IEEE Transactions on Mobile Computing

JF - IEEE Transactions on Mobile Computing

SN - 1536-1233

ER -