開發類神經網路非線性分類器及降低其複雜度之方法並應用於高速光傳輸系統

Developing Artificial Neural Network based Non-linear Classifiers with Complexity Reduction Methods for High Speed Optical Transmission Systems

劉禮郡(Li-Chun Liu)

指導教授 ： 陳智弘

國立交通大學/電機學院/光電工程系所/碩士(2019年)

摘要

為了要因應網路資訊量以及需求量成爆炸性成長的雲端服務與物聯網應用，最新制定的400G Ethernet提供了傳輸距離為兩公里以及十公里的標準。然而，對於數據中心之間的連接以及其他十公里以上傳輸距離的應用上很明顯是不夠的。因此，IEEE 802 LMSC執行委員會成立的研究組織正在研討如何制定200 Gb/s以及400 Gb/s Ethernet於十公里以上應用的標準。數位訊號處理被認為是能夠增加可使用頻寬且成本最低的方法。現今人工智慧類神經網路的發展逐漸開始朝向應用於光通訊領域，目前各大研究機構皆在研究和開發出能夠補償傳輸時的失真及非線性效應的類神經網路非線性補償器。另外，為了要應用於數位訊號處理的晶片上，模型複雜度及其計算量是需要被降低的，以利減少功率損耗。
本研究以波長1293奈米的電致吸收調變雷射搭配單模光纖為基礎之光連接系統，以四階脈衝振幅調制傳輸80Gb/s的訊號長達40公里的距離，並成功的利用開發出的類神經網路非線性分類器做非線性失真的補償。另外，也利用剪裁方式大幅的降低非線性分類器的複雜度以及運用八位元量化計算來減少計算量。

關鍵字

類神經網路非線性分類器 ； 高速光傳輸系統 ； 降低複雜度方法

並列摘要

In order to satisfy the Internet data traffic and explosive growth of cloud computing and Internet of Things (IoT). The latest IEEE 802.3bs 400G Ethernet standard has been announced to support 2-km and 10-km transmission. However, it is obvious that the requirements for inter-data center applications or other beyond 10-km applications are insufficient. Therefore, the IEEE 802 LMSC Executive Committee has chartered a Study Group under the IEEE 802.3 Ethernet Working Group to develop the 200-Gb/s and 400-Gb/s Ethernet standard for beyond 10-km optical PHYs. Digital signal processing (DSP) is considered for expanding available bandwidth and capacity and cost-effective solution in the next generation network. Nowadays, artificial neural networks have already been used for optical transmission systems. Organizations in this field are developing and researching the artificial neural network based non-linear equalizers to compensated distorted signals caused by the non-linear effect. In addition, in order to apply in DSP ICs, it is necessary to reduce model complexity and computational complexity since the power consumption is critical.
In this work, we establish an 80-Gb/s PAM-4 1293-nm EML-based optical link over 40-km transmission and successfully use artificial neural network based non-linear classifiers (ANN-based NLCs) to compensate distorted signals. Furthermore, we adopt the pruning method to reduce model complexity and use 8-bit quantization to decrease computational complexity.

並列關鍵字

Artificial neural network Nonlinear classifier ； High-speed optical transmission system ； Complexity reduction method

參考文獻

[1] Cisco white paper, “The Zettabyte Era: Trends and Analysis”, 2017. [Online]. Available: https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/vni-hyperconnectivity-wp.html

[2] Futurewei, Subsidiary of Huawei, “CFI Consensus - Beyond 10km Optical PHYs”, 2017. [Online]: http://www.ieee802.org/3/cfi/0717_1/CFI_01_0717.pdf

[3] IEEE P802.3bs 200 Gb/s and 400 Gb/s Ethernet Task Force. [Online]. Available: http://www.ieee802.org/3/bs/

[4] IEEE P802.3bs Baseline Summary. July 18, 2015. [Online]. Available: http://www.ieee802.org/3/bs/baseline_3bs_0715.pdf

[5] C. Chen et al., “C-band Single Wavelength 100-Gb/s IM-DD Transmission over 80-km SMF without CD compensation using SSB-DMT”, OFC, paper Th4A.5, 2015.