金融科技Fintech是目前金融與資訊業界最熱門的話題之一，隨著這個議題的討論，IT技術中，許多網路技術為目前金融科技所需要，本論文就在研究其中的即時串流處理技術，在即時交易運算時，如何處理即時的大量資料運算，便是一個重要的議題。在本研究中將針對Fintech中的即時程式交易應該進行探討。
在即時串流運算系統這方面，Apache Storm是一個相當有名並且被許多公司所使用的一套分散式即時運算系統，像是Twitter、Yahoo、阿里巴巴、淘寶網等等，Storm的應用相當廣泛，可以應用在即時分析、線上機器學習等等。因此在本論文中，將會使用Storm作為即時串流運算系統，針對股票這種具有順序性、不可重複性、時效性這些性質的資料型態，研究如何設計Topology會有較好的效能表現，並且以定性以及定量的實驗與分析說明Storm的特性以及配置的優化，最後建立一套方便使用者監控資源以及使用的平台。

Fintech is one of the most popular topics, along with the disruptive innovation raised and more and more applications need to use real-time computing, how to real-time processing large amounts of data computing becomes a significant issues, in this study will discuss in the program trading for Fintech.
In regards of real-time computing system, Apache Storm is one of the famous distributed computing system, used by many company such as Twitter、Tahoo、Alibaba、Taobao…etc, Storm can be apply widly such as real-time analytics、online machine learning…etc. Therefore, in this paper, Storm will be used as a real-time computing system, for stocks that have sequential、non repeating、timeliness of these kinds of data type, research how to design Topology will have a better performance and experiment with qualitative research and quantitative research analysis Storm characteristics and configuration optimization, create an easy-to-use platform to monitor the resource and use.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
圖次 vii
表次 ix
第一章 序論 1
1.1 研究動機與目的 1
1.2 論文架構 2
第二章 研究背景 3
2.1 Apache Storm 3
2.1.1 Apache Storm 優勢及應用 3
2.1.2 Apache Storm基礎概念 5
2.1.3 Apache Storm機制 14
2.2 Apache Kafka 30
2.2.1 Kafka架構 30
2.2.2 Kafka特性 31
2.2.3 Kafka操作指令 32
2.3 Apache Zookeeper 33
2.4 Apache HBase 34
2.5 Apache Maven 35
2.6 Apache Ambari 38
2.7 Hortonworks 38
2.8 Linux Container（LXC） 40
2.9 Netty 42
2.10 ZeroMQ（ØMQ） 43
第三章 系統架構與實作 44
3.1 系統開發環境 44
3.1.1 主機硬體資訊 44
3.1.2 軟體與函式庫版本 45
3.2 系統架構與成果展示 46
3.2.1 使用資料型態 46
3.2.2 系統架設平台 47
3.2.3 系統架構 49
3.3 遇到的問題及解決方法 53
第四章 實驗設計與數據說明 55
4.1 實驗環境 55
4.2 實驗設計與數據說明 55
4.2.1 參數說明 55
4.2.2 實驗結果監控方式 58
4.2.3 實驗一 59
4.2.4 實驗二 62
4.2.5 實驗三 64
4.2.6 實驗四 68
4.3 Storm效能優化以及使用建議 70
第五章 結論與未來展望 71
5.1 結論 71
5.2 未來展望 71
參考文獻 73
附錄A 77

[1] History of Apache Storm and lessons learned. Available: http://nathanmarz.com/blog/history-of-apache-storm-and-lessons-learned.html. (2016, 09/02)
[2] Apache Storm. Available: http://storm.apache.org/. (2016, 4/17)
[3] A. Agopyan, E. Şener, and A. Beklen, "Financial business cloud for high-frequency trading," vol. 4, 2011.
[4] 陳敏敏, 王新春, and 黃奉线, Storm技術內幕與大數據實踐. 中國: 人民郵電出版社, 2015.
[5] 馬廷輝, Storm企業級應用: 實戰、運維和調優. 中國: 機械工業出版社, 2015.
[6] 阿里巴巴集團數據平台事業部商家數據業務部, Storm實戰: 構建大數據實時計算. 中國: 電子工業出版社, 2014.
[7] 丁維龍, 趙卓峰, and 韓燕波, Storm: 大數據流式計算及應用實踐. 中國北京 電子工業出版社。, 2015.
[8] 趙必廈 and 程麗明, Hadoop再進化：Storm流式資料即時處理引擎. 臺北: 佳魁資訊股份有限公司, 2015.
[9] M. A. U. Nasir, G. D. F. Morales, D. Garc, x00Ed, S. a, N. Kourtellis, et al., "The power of both choices: Practical load balancing for distributed stream processing engines," in 2015 IEEE 31st International Conference on Data Engineering, 2015, pp. 137-148.
[10] Transactional Topologies. Available: http://storm.apache.org/releases/current/Transactional-topologies.html. (2016, 08/31)
[11] Trident Tutorial. Available: http://storm.apache.org/releases/0.10.1/Trident-tutorial.html. (2016, 08/31)
[12] M. G. Noll. Understanding the Parallelism of a Storm Topology. Available: http://www.michael-noll.com/blog/2012/10/16/understanding-the-parallelism-of-a-storm-topology/. (2016, 6/16)
[13] J. S. v. d. Veen, B. v. d. Waaij, E. Lazovik, W. Wijbrandi, and R. J. Meijer, "Dynamically Scaling Apache Storm for the Analysis of Streaming Data," in Big Data Computing Service and Applications (BigDataService), 2015 IEEE First International Conference on, 2015, pp. 154-161.
[14] Revans2. Making Storm fly with Netty. Available: https://yahooeng.tumblr.com/post/64758709722/making-storm-fly-with-netty. (2016, 5/12)
[15] Apache Kafka. Available: http://kafka.apache.org/documentation.html. (2016, 4/17)
[16] Apache Zookeeper. Available: http://zookeeper.apache.org/. (2016, 4/17)
[17] CAP定理. Available: https://zh.wikipedia.org/wiki/CAP定理. (2016, 08/31)
[18] Apache HBase. Available: https://hbase.apache.org/. (2016, 6/18)
[19] T. O'Brien, J. Casey, B. Fox, J. Van, Z. J. Xu, T. Locher, et al., Maven by Example: Sonatype, 2010.
[20] Apache Ambari. Available: https://ambari.apache.org/. (2016, 2/18)
[21] Hortonworks. Available: http://hortonworks.com/tutorials/. (2016, 3/12)
[22] Linux Containers. Available: https://linuxcontainers.org. (2016, 6/3)
[23] Netty：Home. Available: http://netty.io/. (2016, 7/11)
[24] ØMQ - The Guide Available: http://zguide.zeromq.org/page:all. (2016, 6/3)
[25] M. M. Bersani, F. Marconi, D. A. Tamburri, P. Jamshidi, and A. Nodari, "Continuous Architecting of Stream-Based Systems," in 2016 13th Working IEEE/IFIP Conference on Software Architecture (WICSA), 2016, pp. 146-151.
[26] Hortonworks-General Guidelines. (2016, 09/04)
[27] 黃柏翰, "Building algorithmic trading and back-testing platform based on Hadoop," National Chengchi University, 2011.
[28] P. W. Tseng, "Distributed computing system and big data real-time processing structure—based on YARN, Storm and Spark," National Chengchi University, 2015.
[29] C. H. Lin, "A Future Investment Strategy Service based on Cloud Computing Architecture - Taking a High-frequency Trading System as an Example," National Chengchi University, 2013.
[30] R. Ranjan, "Streaming Big Data Processing in Datacenter Clouds," IEEE Cloud Computing, vol. 1, pp. 78-83, 2014.
[31] 戴睿, "以大量平行運算為基礎的策略挑選與期貨模擬交易平台," National Chengchi University, 2013.
[32] Storm-Kafka. Available: https://github.com/apache/storm/tree/master/external/storm-kafka. (2016, 09/01)
[33] S. Qian, G. Wu, J. Huang, and T. Das, "Benchmarking modern distributed streaming platforms," in 2016 IEEE International Conference on Industrial Technology (ICIT), 2016, pp. 592-598.
[34] GlassWire. Available: https://blog.glasswire.com/. (2016, 09/03)
[35] S. Kamburugamuve, S. Ekanayake, M. Pathirage, and G. Fox, "Towards High Performance Processing of Streaming Data in Large Data Centers," in 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2016, pp. 1637-1644.
[36] Cgroups - The Linux Kernel Archives. Available: https://www.google.com.tw/search?q=CGroup&ie=utf-8&oe=utf-8&gws_rd=cr&ei=ktPLV_unFsus0ATDsoL4DQ. (2016, 09/04)