臺灣博碩士論文加值系統

近幾年Google和Amazon於雲端服務崛起，但雲端服務會有網路延遲(latency)的問題，服務品質(Quality Of Service，QoS)可以解決網路延遲的問題，並有效地分配網路資源。本論文要探討的動態服務品質在實現服務導向架構(Service-Oriented Architecture，SOA)的網路服務(Web Services)中，扮演關鍵的參考依據，愈精準的QoS預測，代表各類服務得到的結果愈能符合預期。本論文提出前人使用的遺傳規劃法預測網路服務品質進行延伸研究，原方法使用單變量(Uni-variate)、一步先(One-step-ahead)服務品質時間序列預測的精準度已經能比其他時間序列預測方法好。我們則引進多變量(Multi-variate)時間序列，除了使用回應時間(Response Time)外，也加入吞吐量(Throughput)與不同地理位置使用者的回應時間，藉以提高網路服務品質預測的精準度，並使用2組真實世界QoS資料集，進行多變量、一步先遺傳規劃法預測網路的動態服務品質實驗，多變量確實比單變量提供較好的精準度。

In recent years Google and Amazon are on the rise of cloud service, but cloud service has a network latency issue. QoS can solve the issue and use network resource more efficiently. In this study, the dynamic QoS is important to implement Web Services of SOA (Service-Oriented Architecture), and the more accurate QoS predicts, the more the service gets the result as expected. Previous study shows that one-step-ahead QoS predictors using univariate (response time) base on genetic programming is better than other time series forecasting methods. However, in our proposed approach, we devise a method of using multivariate(e.g. response time, throughput, and geo-location) to improve the accuracy of the forecasting result. We experiment with two real-world QoS datasets to compare with previous study, and our approach can get better QoS predictions via multivariate.

第一章 緒論 1
1.1. 前言 1
1.2. 研究動機 4
1.3. 研究貢獻 4
1.4. 章節編排 5
第二章 相關研究 6
2.1. 單變量時間序列預測 6
2.2. 多變量時間序列預測 6
2.3. 動態網際服務品質(QoS)資料集 6
第三章 預測模型設計 8
3.1. 遺傳規劃法結構 8
3.2. 選取(selection) 8
3.3 交配(crossover) 9
3.4. 突變(mutation) 10
3.5. 遺傳規劃法演化流程 11
第四章 預測問題定義與效能量測 12
4.1. 定義QoS時間序列符號 12
4.2. 定義預測方法 13
4.3. 定義效能量測方法 14
第五章 實驗 15
5.1 實驗的QoS資料集 15
5.2 實驗的環境 16
5.3 實驗結果 18
5.4 討論 26
第六章 結論與未來工作 28
參考文獻 30

[1]Y.-Y. FanJiang and Y. Syu, "Semantic-based automatic service composition with functional and non-functional requirements in design time: A genetic algorithm approach," Inf. Softw. Technol., vol. 56, no. 3, pp. 352–373, 2014.
[2]Y. Yao and H. Chen, "QoS-aware service composition using NSGA-II," in Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human, ACM, Seoul, Korea, pp. 358–363, 2009.
[3]V. Cardellini, E. Casalicchio, V. Grassi, F.L. Presti, and R. Mirandola, "QoS-driven runtime adaptation of service oriented architectures," in Proceedings of the 7th Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering, ACM, Amsterdam, The Netherlands, pp. 131–140, 2009.
[4]Y. Yao and H. Chen, "A rule-based web service composition approach," in Proceedings of the 2010 Sixth International Conference on Autonomic and Autonomous Systems, IEEE Computer Society, pp. 150–155, 2010.
[5]Z. Li and L. O’Brien, "Towards effort estimation for web service compositions using classification matrix," International Journal on Advances in Internet Technology, vol. 3, pp. 245-260, 2010.
[6]Y.-Z. Zhang, "A Study on Missing Quality Values Prediction of Web Services by Applying Genetic Algorithm," Unpublished master’s thesis. Fu Jen Catholic University, Taiwan, 2018.
[7]Y.-Y. FanJiang, Y. Syu, and J.-Y. Kuo, " Search based approach to forecasting QoS attributes of web services using genetic programming," Inf. Softw. Technol., vol. 80, pp. 158–174, 2016.
[8]R.J. Hyndman and G. Athanasopoulos, "Forecasting: Principles and Practice," OTexts, 2014.
[9]B. Cavallo, M.D. Penta, and G. Canfora, " An empirical comparison of methods to support QoS-aware service selection," in Proceedings of the 2nd International Workshop on Principles of Engineering Service-Oriented Systems, Cape Town, South Africa, ACM, pp. 64–70, 2010.
[10]M. Godse, U. Bellur, and R. Sonar, "Automating QoS based service selection," in IEEE International Conference on Web Services, pp. 534–541, 2010.
[11]X. YunNi, D. Jian, L. Xin, and Z. QingSheng, "Dependability prediction of WS-BPEL service compositions using petri net and time series models," in 2013 IEEE 7th International Symposium on Service Oriented System Engineering, pp. 192–202, 2013.
[12]M.H. Zadeh and M.A. Seyyedi, "Qos monitoring for web services by time series forecasting," in IEEE International Conference on Computer Science and Information Technology, pp. 659–663, 2010.
[13]T. Senivongse and N. Wongsawangpanich, "Composing services of different granu- larity and varying QoS using genetic algorithm," in Lecture Notes in Engineering and Computer Science: Proceedings of The World Congress on Engineering and Computer Science, pp. 388–393, 2011.
[14]Z. Ye, S. Mistry, A. Bouguettaya, and H. Dong, "Long-term QoS-aware Cloud Service Composition using Multivariate Time Series Analysis," IEEE Transactions on Services Computing, vol. 9, pp. 382-393, 2016.
[15]P. Zhang, L. Wang, W. Li, H. Leung, and W. Song, " A Web Service QoS Forecasting Approach Based on Multivariate Time Series," in IEEE International Conference on Web Services, pp. 146–153, 2017.
[16]A. Amin, A. Colman, and L. Grunske, "An Approach to Forecasting QoS Attributes of Web Services Based on ARIMA and GARCH Models," in IEEE International Conference on Web Services, pp. 74-81, 2012.
[17]Z. Zheng, Y. Zhang, and M. R. Lyu, "Investigating QoS of Real-World Web Services," IEEE Transactions on Services Computing, vol. 7, pp. 32-39, 2012.
[18]B. Cavallo, M.D. Penta, and G. Canfora, "An empirical comparison of methods to support QoS-aware service selection," in Proceedings of the 2nd International Workshop on Principles of Engineering Service-Oriented Systems, Cape Town, South Africa, ACM, pp. 64–70, 2010.
[19]Z. Yilei, Z. Zibin, and M. R. Lyu, "WSPred: A Time-Aware Personalized QoS Prediction Framework for Web Services," in 2011 IEEE 22nd International Symposium on Software Reliability Engineering, pp. 210–219, 2011.
[20]T. Mitchell, Machine Learning, McGraw Hill, Boston, MA, 1997.
[21]R. J. Hyndman, "Another look at forecast accuracy metrics for intermittent demand," Foresight: Int. J. Appl. Forecast., no. 4, pp. 43-46, 2006.
[22]N. Wagner, Z. Michalewicz, M. Khouja, and R.R. McGregor, "Time series forecasting for dynamic environments: the DyFor genetic program model," IEEE Trans. Evolut. Comput., vol. 11, no. 4, pp. 433-452, 2007.
[23]K. Meffert, JGAP - java genetic algorithms and genetic programming package, Available at: http://jgap.sf.net .