A lexicographie approach to constrained MDP Admission Control

Author

Panfili, M. ; Pietrabissa, A.

Author_Institution

Dept. of Comput., Control & Manage. Eng. A. Ruberti, Univ. of Rome Sapienza, Rome, Italy

fYear

2013

fDate

25-28 June 2013

Firstpage

1428

Lastpage

1433

Abstract

This paper proposes a Reinforcement Learning-based lexicographic approach to the Call Admission Control (CAC) problem in communication networks. The CAC problem is modeled as a multi-constrained Markov Decision Problem (MDP). To overcome the problems of the standard approaches to the solution of constrained MDP, a multi-constraint lexicographic approach is defined, and an on-line implementation based on Reinforcement Learning techniques is proposed. Simulations validate the proposed approach.

Keywords

Markov processes; decision theory; learning (artificial intelligence); telecommunication congestion control; telecommunication networks; CAC; MDP; call admission control; communication network; lexicographic approach; multiconstrained Markov Decision problem; multiconstraint lexicographic approach; reinforcement learning technique; Aerospace electronics; Computational modeling; Cost function; Markov processes; Process control; Standards; Vectors; Call Admission Control; Communication networks; Markov Decision Process; Stochastic control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control & Automation (MED), 2013 21st Mediterranean Conference on

Conference_Location

Chania

Print_ISBN

978-1-4799-0995-7

Type

conf

DOI

10.1109/MED.2013.6608908

Filename

6608908