請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72200
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 鐘嘉德 | |
dc.contributor.author | Fang-Ying Liao | en |
dc.contributor.author | 廖芳瑩 | zh_TW |
dc.date.accessioned | 2021-06-17T06:28:32Z | - |
dc.date.available | 2028-12-31 | |
dc.date.copyright | 2018-08-20 | |
dc.date.issued | 2018 | |
dc.date.submitted | 2018-08-17 | |
dc.identifier.citation | [1] S. Sen, C. Joe-Wong, S. Ha, and M. Chiang. Smart data pricing (sdp): Economic solutions to network congestion. In Recent Advances in Networking, ACM SIGCOMM, pages 221–274, 01 2013.
[2] Soumya Sen, Carlee Joe-Wong, Sangtae Ha, and Mung Chiang. A survey of smart data pricing: Past proposals, current plans, and future trends. ACM Computing Surveys,46(2):15:1–15:37, November 2013. [3] Liang Zhang, Weijie Wu, and Dan Wang. Time-dependent pricing in wireless data networks: Flat-rate vs. usage-based schemes. In Proc. of IEEE INFOCOM, 2014. [4] Chia-Husan Chang, Phone Lin, Junshan Zhang, and Jeu-Yih Jeng. Time dependent adaptive pricing for mobile internet access. In Computer Commun. Workshops (INFOCOM WKSHPS), page 540–545, 4 2014. [5] Hung-Wen Lin, Meng-Ju Lu, Phone Lin, Po-Heng Chou, Jeu-Yih Jeng, and Char-Dir Chung. Location-based time-dependent smart data pricing by sdn. In Proc. IEEE Global Commun. Conf., pages 1–6, 12 2016. [6] National Taiwan University. Ntu campus network. http://ws5.cc.ntu.edu.tw/ntucc/. [7] Li Deng. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Transactions on Signal and Information Processing, 2014. [8] LeCun Yann and Bengio Yoshua. Convolutional networks for images, speech, and time series. In Michael A. Arbib, editor, The Handbook of Brain Theory and Neural Networks, pages 255–258. MIT Press, Cambridge, MA, USA, 1998. [9] Harris Drucker, Chris J. C. Burges, Linda Kaufman, Alex J. Smola, and Vladimir Vapnik. Support vector regression machines. Advances in Neural Information Processing Systems, 9:155–161, 1997. [10] D. P. Solomatine and D. L. Shrestha. Adaboost.rt: a boosting algorithm for regression problems. In 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541), volume 2, pages 1163–1168, July 2004. [11] Leo Breiman. Random forests. Machine Learning, 45(1):5–32, 2001. [12] Pierre Geurts, Damien Ernst, and Louis Wehenkel. Extremely randomized trees. Machine Learning, 63:3–42, 4 2006. [13] Alexey Natekin and Alois Knoll. Gradient boosting machines, a tutorial. Front. Neurorobots, 7:21, 2013. [14] Thomas G. Dietterich. Ensemble methods in machine learning. In Multiple Classifier Systems, pages 1–15, Berlin, Heidelberg, 2000. Springer Berlin Heidelberg. [15] Franc¸ois Chollet et al. Keras. https://keras.io, 2015. [16] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011. [17] James Bergstra, R. Bardenet, Yoshua Bengio, and Bal´azs K´egl. Algorithms for hyperparameter optimization. In J. Shawe-Taylor, R.S. Zemel, P. Bartlett, F. Pereira, and K.Q. Weinberger, editors, 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), volume 24 of Advances in Neural Information Processing Systems, Granada, Spain, December 2011. Neural Information Processing Systems Foundation. [18] Christoph Bergmeir and Jos´e M. Ben´ıtez. On the use of cross-validation for time series predictor evaluation. Information Sciences: an International Journal, pages 192–213, 2012. [19] 3GPP. Lte radio access network enhancements for diverse data applications. TR 36.822, 3rd Generation Partnership Project (3GPP), September 2012. [20] Huawei. Mobile video report. Technical Report A Huawei Mobile Video Insight Report Series, September 2017. [21] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: A simple way to prevent neural networks from overfitting.J. Mach. Learn. Res., 15(1):1929–1958, January 2014. [22] Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR, abs/1502.03167, 2015. [23] Vinod Nair and Geoffrey E. Hinton. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML’10, pages 807–814, USA, 2010. Omnipress. [24] Yann LeCun, L´eon Bottou, Genevieve B. Orr, and Klaus-Robert M¨uller. Efficient backprop. In Neural Networks: Tricks of the Trade, This Book is an Outgrowth of a 1996 NIPS Workshop, pages 9–50, London, UK, 1998. Springer-Verlag. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/72200 | - |
dc.description.abstract | 為了舒緩網路壅塞,網路營運商利用時間相依智慧計價,去刺激用戶在離峰時間使用網路。在時間相依智慧計價中,網路的計費是根據當時段網路壅塞狀況決定。
然而,在過去的文獻中,藉由假設用戶的網路使用行為,影響未來的網路使用量。並假設任何應用程式的使用,都可以因價錢而延後使用時間。在實際狀況中,即時的應用程式不能被延遲,非即時的應用程式可以被延遲。因此,本篇論文中,我們提出基於預測的時間相依智慧計價。結合預測機制以及計價機制,預測即時性應用程式的網路使用量,並帶入時間相依計價,為非即時性應用程式的網路使用量制定價格,藉以刺激用戶轉移時段使用網路。考慮到價錢變動造成的適應性問題,本研究的應用,我們提出排程機制,根據價格及用戶可等待的時間,為用戶安排在較便宜的時段使用網路,用戶藉此可以付較少的費用在非即時的應用程式上。 | zh_TW |
dc.description.abstract | Internet Service Providers (ISPs) adopt Time-Dependent SDP (TDP) to motivate users to change their Internet access behavior from peak hours to off-peak hours. In previous work, future network status was affected by assuming user's Internet access behavior. They assume that any behavior can be postponed due to prices. In the real situation, real-time applications cannot be delayed, and non real-time applications can be delayed. Therefore, we propose prediction-based TDP which is the combination of the prediction mechanism and TDP. We predict real-time Internet usage in the future, and apply TDP to decide prices for non real-time Internet based on predicted values. Considering the adaptation issue for users, we propose a scheduling application. According to prices and user's waiting time, the application provides users with suggestions about when to access Internet, so that users can pay less for non real-time Internet usage. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T06:28:32Z (GMT). No. of bitstreams: 1 ntu-107-R05942065-1.pdf: 3202300 bytes, checksum: fcc9720080badc333f02a6064c570285 (MD5) Previous issue date: 2018 | en |
dc.description.tableofcontents | 誌謝i
中文摘要ii Abstract iii Contents iv 1 Introduction 1 2 Data Collection 4 3 Network Traffic Prediction 7 3.1 Training Phase . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.1 Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.2 Model Construction . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.2 Prediction Phase . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2.1 Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.2.2 Model Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 4 Pricing 14 5 Scheduling 15 5.1 System Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 5.2 Simulation Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 6 Numerical Results 19 6.1 Prediction Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 6.1.1 Performance Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . 19 6.1.2 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 6.2 Scheduling Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 6.2.1 Performance Metrics . . . . . . . . . . . . . . . . . . . . . . . . . . 24 6.2.2 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 7 Conclusion 26 Appendix A Algorithms and Parameters 27 A.1 Learning Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27 A.1.1 Deep Learning Algorithms . . . . . . . . . . . . . . . . . . . . . . . 27 A.1.2 Machine Learning Algorithms . . . . . . . . . . . . . . . . . . . . . 29 A.2 Best Combinations of Parameters . . . . . . . . . . . . . . . . . . . . . . . . 34 A.2.1 Deep Learning Algorithms . . . . . . . . . . . . . . . . . . . . . . . 34 A.2.2 Machine Learning Algorithms . . . . . . . . . . . . . . . . . . . . . 35 | |
dc.language.iso | en | |
dc.title | 基於預測機制的時間相依智慧定價及於價錢導向排程應用 | zh_TW |
dc.title | Prediction-Based Time-Dependent Smart Data Pricing and its Application to Price-Oriented Scheduling | en |
dc.type | Thesis | |
dc.date.schoolyear | 106-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 林風 | |
dc.contributor.oralexamcommittee | 李宏毅,鄭枸澺,林一平 | |
dc.subject.keyword | 時間相依智慧計價,網路流量預測,台大校園網路流量, | zh_TW |
dc.subject.keyword | Time-Dependent Pricing,Network Traffic Prediction,NTU Campus Traffic, | en |
dc.relation.page | 39 | |
dc.identifier.doi | 10.6342/NTU201801525 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2018-08-17 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-1.pdf 目前未授權公開取用 | 3.13 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。