簡易檢索 / 詳目顯示
| 研究生： |
陳厚邑 Chen, Hou-Yi |
|---|---|
| 論文名稱： |
利用 K-means 法則及廣義迴歸網路執行服務頻寬預測之研究 Bandwidth Allocation of a Service Based on K-means Algorithm and General Regression Neural Network |
| 指導教授： |
黃文吉
Hwang, Wen-Jyi |
| 口試委員： |
葉佐任
Yeh, Tso-Zen 董一志 Tung, Yi-Chih 黃文吉 Hwang, Wen-Jyi |
| 口試日期： | 2023/01/16 |
| 學位類別： |
碩士 Master |
| 系所名稱： |
資訊工程學系 Department of Computer Science and Information Engineering |
| 論文出版年： | 2023 |
| 畢業學年度： | 111 |
| 語文別： | 中文 |
| 論文頁數： | 48 |
| 中文關鍵詞： | 網路頻寬預測 |
| 英文關鍵詞： | GRNN, K-means |
| DOI URL： | http://doi.org/10.6345/NTNU202300220 |
| 論文種類： | 學術論文 |
| 相關次數： | 點閱：97 下載：6 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
現今社會對於網路使用越來越依賴，因此網路的頻寬分配是極度重要的，良好的頻寬分配不僅可以使網路使用不遭受卡頓，也不會造成封包傳送時的流失，但一昧的增大頻寬分配只會浪費網路資源，而在過去的研究中提出了利用GRNN 預測頻寬分配且獲得不錯的成效。
本論文提出利用 K-means 法則優化 GRNN 預測頻寬分配之系統，在先前研究中 GRNN 預測雖然有不錯的效果，但預測時所需要事先填入的頻寬數據卻沒有一個準則去選出，若原始的頻寬選擇不良則會造成預測結果不佳，而本論文利用 K-means 解決此問題，且在預測效果上穩定良好。本論文也利用此方法有效降低在先前研究中所建立的頻寬分配系統的硬體資源消耗，在降低硬體資源需求的同時，維持良好的預測結果甚至有著更佳的預測效果。
[1] Acun, F., & Gol, E. A., “Traffic Prediction on Large Scale Traffic Networks Using ARIMA and K-Means,” 2021 29th Signal Processing and Communications Applications Conference (SIU), 1-4, 2021.
[2] Amin, A., Colman, A., & Grunske, L., “An Approach to Forecasting QoS Attributes of Web Services Based on ARIMA and GARCH Models,” IEEE 19th International Conference on Web Services, 74-81, 2012.
[3] Hochreiter, S., & Schmidhuber, J., “Long Short-Term Memory,” Neural Computation, 9(8), 1735-1780, 1997.
[4] Hot, E., and Popović-Bugarin, V., “Soil data clustering by using K-means and fuzzy K-means algorithm,” 2015 23rd Telecommunications Forum Telfor (TELFOR), 890-893, 2015.
[5] Hwang, W. J., Tai, T. M., Pan, B. T., Lou, T. Y., & Jhang, Y. J., “An Intelligent QoS Algorithm for Home Networks,” IEEE Communications Letters, 23(4), 588-591, 2019.
[6] Inari, T., & Nakanishi, T., “Concentration Patterns Estimation Method in Deskwork by Using Time-series k-means,” 2022 International Electronics Symposium (IES), 576-580, 2022.
[7] Krishna, N. V., & Rao, P. M., “Modelling of large scale linear discrete time interval systems using K-means algorithm,” 2017 International Conference on Intelligent Sustainable Systems (ICISS), 556-559, 2017.
[8] Li, J., Shen, L., & Tong, Y., “Prediction of Network Flow Based on Wavelet Analysis and ARIMA Model,” 2009 International Conference on Wireless Networks and Information Systems, 217-220, 2009.
[9] MacQueen, J., “Some Methods for Classification and Analysis of Multivariate Observations,” Proceeding of the 5th Berkeley Symposium on Mathematical Statistics and Probability, 1, 281-297, 1967.
[10] Santarcangelo, J., & Zhang, X.-P., “Dynamic time-alignment k-means kernel clustering for time sequence clustering,” 2015 IEEE International Conference on Image Processing (ICIP), 2532-2536, 2015.
[11] Singh, V. K., Tiwari, N., & Garg, S., “Document Clustering Using K-Means, Heuristic K-Means and Fuzzy C-Means,” 2011 International Conference on Computational Intelligence and Communication Networks, 297-301, 2011.
[12] Specht, D.F., “A General Regression Neural Network,” IEEE Transactions on Neural Networks, 2(6), 568-576, 1991.
[13] Tung, Y.C., Law, Y.W., Hwang, W.J., Tai, T.M., Ho, C.H., & Chen, C.C., “Novel Record Replacement Algorithm and Architecture for QoS Management over Local Area Networks,” Micromachines, 13(4):594, 2022.
[14] Wang, J., Miao, F., You, L., & Fan, W., “A Deep Autoencoder Based Outlier Detection for Time Series,” 2020 IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS), 216-218, 2020.
[15] Wang, Y., Zhu, S., & Li, C., “Research on Multistep Time Series Prediction Based on LSTM,” 2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE), 1155-1159, 2019.
[16] Zhao, X., Han, X., Su, W., & Yan, Z., “Time series prediction method based on Convolutional Autoencoder and LSTM,” 2019 Chinese Automation Congress (CAC), 5790-5793, 2019.
[17] 羅玉榮,“以FPGA實現Self-aware 與Self-adaptive特性之QoS頻寬分配系統,”國立臺灣師範大學, 2021.
