Q-learning-based hybrid ARQ for high speed downlink packet access in UMTS

Chung-Ju Chang, Chia-Yuan Chang, Fang Ching Ren

研究成果: Paper

6 引文 斯高帕斯(Scopus)

摘要

In this paper, a Q-learning-based hybrid automatic repeat request (Q-HARQ) scheme is proposed to achieve efficient resource utilization for high speed downlink packet access (HSDPA) in universal mobile telecommunications system (UMTS). The Hybrid ARQ procedure is modeled as a discrete-time Markov decision process (MDP), where the transmission cost is defined in terms of the signal-to-interference-and-noise (SINR) which is based on the desired (quality-of-service) QoS parameters of transport block error rate (BLER) for enhancing spectrum utilization subject to QoS constraint. The Q-learning reinforcement algorithm is employed to accurately estimate the transmission cost to perform the most suitable decision of modulation and coding scheme for the packet initial transmission while the requirement of transport block error rate is guaranteed. Simulation results show that the QoS requirement of block error rate for Q-HARQ is nearly met around a reasonable value indeed. In addition, the system throughput of the Q-HARQ can be improved under the specific QoS constraint of BLER. It is verified finally that the Q-HARQ scheme is feasible in the practical system because of the short processing and convergence time.
原文English
頁面2610-+
DOIs
出版狀態Published - 2007
事件2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring - Dublin, Ireland
持續時間: 22 四月 200725 四月 2007

Conference

Conference2007 IEEE 65th Vehicular Technology Conference - VTC2007-Spring
國家Ireland
城市Dublin
期間22/04/0725/04/07

指紋 深入研究「Q-learning-based hybrid ARQ for high speed downlink packet access in UMTS」主題。共同形成了獨特的指紋。

引用此