適用於高速下行封包擷取技術之乏晰Q-Learning式混合自動重傳機制

Abstract

為了在現有的第三代通訊系統下提供更高速且安全的下鏈路資料封包傳送，第三代合作夥伴計畫（3rd generation partnership project, 3GPP）提出了一種高速下行封包擷取技術（high speed downlink packet access, HSDPA）。HSDPA採用一種稱為調變編碼（adaptive modulation and coding, AMC）的技術，可以針對不同的通道情況來使用不同的調變方式和不同的編碼速率，並提供更大量的多碼（multi-code）以進行傳輸，也採取了混合自動重傳機制（hybrid automatic retransmission request, HARQ）使得傳輸機制更有效率。為了能夠適應通道的變化，HSDPA也把每個傳送時間間隔（transmission time interval, TTI）縮短為2ms，以求達成更有效率的資源分配模式。 本篇論文提出了一個適用於高速下行封包擷取技術之乏晰Q-learning式混合自動重傳機制（FQL based HARQ）。針對已被模擬成離散時間馬可夫決策過程（Markov decision process, MDP）的HARQ機制，並且期望能夠符合傳輸服務品質（quality of service, QoS），我們使用了名為乏晰Q-learning（fuzzy Q-learning）的即時加強型學習演算法來不斷地學習並決定每次傳輸的方式，以期滿足QoS並維持高速傳輸速率。由模擬結果可以看到，我們所提出的機制可以在滿足QoS的同時也維持住高速的傳輸速率，並且也維持在很低的丟棄封包之機率，確實達成了預期的目標。

In order to provide higher speed and more effective downlink packet data service in 3G, high speed downlink packet access (HSDPA) is proposed by 3rd generation partnership project (3GPP). HSDPA adopts a technique called adaptive modulation and coding (AMC) to use different modulation orders and coding rates corresponding to different channel conditions. It provides more multi-codes for transmissions, and also adopts the hybrid automatic retransmission request (HARQ) scheme to make the transmission mechanism more effective. In order to adapt the changes of channel conditions, HSDPA adopts shorter transmission time interval (TTI) as 2ms to reach more effective resource allocation. In this thesis, a fuzzy Q-learning based HARQ scheme for HSDPA is proposed. For the HARQ scheme modeled as Markov decision process (MDP), we use fuzzy Q-learning algorithm to learn the modulation and coding rates of initial transmissions. Our object is to satisfy the quality of service (QoS) and keep high data rate. The simulation results show that the proposed scheme can indeed reach the object and is feasible in different channel conditions.