Predicting Spectrum Occupancies Using a Non-Stationary Hidden Markov Model

被引：35

作者：

Chen, Xianfu ^{[1
]}

Zhang, Honggang ^{[2
,3
,4
]}

MacKenzie, Allen B. ^{[5
]}

Matinmikko, Marja ^{[1
]}

机构：

[1] VTT Tech Res Ctr Finland, Turku, Finland

[2] Zhejiang Univ, Dept Informat Sci & Elect Engn, Hangzhou, Peoples R China

[3] Univ Europeenne Bretagne, Bretagne, France

[4] Supelec, Paris, France

[5] Virginia Tech, Bradley Dept Elect & Comp Engn, Blacksburg, VA USA

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2014年 / 3卷 / 04期

基金：

美国国家科学基金会;

关键词：

Bayes' rule; cognitive radio; non-stationary hidden Markov model (NS-HMM); spectrum measurement; spectrum occupancy; spectrum prediction;

D O I：

10.1109/LWC.2014.2315040

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

One of the critical challenges for secondary use of licensed spectrum is the accurate modeling of primary users' (PUs') stochastic behavior. However, the conventional hidden Markov models (HMMs) assume stationary state transition probability and fail to adequately describe PUs' dwell time distributions. In this letter, we propose a non-stationary hidden Markov model (NS-HMM), in which the time-varying property of PU behavior is realized. A variant of the Baum-Welch algorithm is developed to estimate the parameters of an NS-HMM. Finally, the performance of the proposed model is evaluated through experiments using real spectrum measurement data. The results show that the NS-HMM outperforms existing HMM-based approaches.

引用

页码：333 / 336

页数：4

共 10 条

[1] STATISTICAL INFERENCE FOR PROBABILISTIC FUNCTIONS OF FINITE STATE MARKOV CHAINS [J].