A general framework for analyzing the optimal call admission control in DS-CDMA cellular network

Authors:
Wen Chen;Feiyu Lei;Weinong Wang
Affiliations:
Network Information Center, Computer Science and Engineering Dept., Shanghai Jiao Tong University, Shanghai, China;Network Information Center, Computer Science and Engineering Dept., Shanghai Jiao Tong University, Shanghai, China;Network Information Center, Computer Science and Engineering Dept., Shanghai Jiao Tong University, Shanghai, China
Venue:
ICCSA'05 Proceedings of the 2005 international conference on Computational Science and Its Applications - Volume Part II
Year:
2005

Citing 8
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Channel Occupancy Times and Handoff Rate for Mobile Computing and PCS Networks

IEEE Transactions on Computers
Call admission control in cellular networks: a reinforcement learning solution

International Journal of Network Management
Adaptive call admission control for QoS/revenue optimization in CDMA cellular networks

Wireless Networks
Integrated voice/data call admission control for wireless DS-CDMAsystems

IEEE Transactions on Signal Processing
Call admission control for CDMA mobile communications systems supporting multimedia services

IEEE Transactions on Wireless Communications
Adaptive call admission control under quality of service constraints: a reinforcement learning solution

IEEE Journal on Selected Areas in Communications
Call admission control for voice/data integrated cellular networks: performance analysis and comparative study

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with the optimal Call Admission Control (CAC) problem in DS-CDMA cellular network supporting multiple traffic types with different Quality of Service (QoS) requirements. We present a general analysis framework to solve the problem, that is, Generalized semi-Markov Decision Process (GSMDP). It discards any restrictive unrealistic assumptions and therefore can be applied to any complex cases including non-Markovian environment. Besides, incorporating a weighted linear function of new call and handoff call blocking probabilities for each service type, we attain the goal of maximizing network revenue while minimizing the blocking probabilities. Finally, through a form of reinforcement learning algorithm known as Q-learning, the optimal policy is worked out with requiring neither explicit state transition probabilities nor any assumptions behind the network model.