臺灣博碩士論文加值系統

傳統路由通常是藉由當下所獲取各路段的車流資訊作為路徑決策的傳遞依據，但車流量和道路狀況卻會隨時間不斷變動，這也讓傳統最佳路徑的決策帶來失準的情形。因此未來短期時間內各路段流量之預測將是封包延遲估算之重要參考，據此再計算出最佳之傳遞路徑。本論文提出一封包動態路段延遲預測方法和即時動態最佳路徑演算法，首先利用歷史資料來進行車流量的預測，進而估算出封包路段延遲，降低預測誤差，再根據估算出之封包路段延遲動態找出最佳路徑。實驗模擬針對日期屬性類別(假日及非假日)和時段類別(尖峰、離峰以及凌晨)與延遲平均預測方法進行效能分析比較，最後比較演算法所找出之最佳路徑的總時間延遲花費，實驗模擬結果顯示出本論文所提出之動態路段延遲預測在各時段的預測誤差皆小於延遲平均預測，且整體平均而言，即時動態最佳路徑演算法所找之最佳路徑的平均總延遲花費時間少於最短時間演算法。

Most of traditional routing protocols determine the transmission paths according to current traffic information of each road segment. However, the determine paths are not precise enough due to the ongoing change of traffic flow and road conditions. Therefore, predictions of following traffic conditions will be the important reference for computing the delay estimation of packets as well as finding the best packets transmission path. This thesis aims to propose a packets routing algorithm for the dynamic traffic conditions on roads. The historical data of previous traffic conditions are used to predict traffic flow, in order to compute estimating packets delays of road segment and to reduce the prediction error. Then, the packets routing path based on these estimating delays would be determined. The simulated experiment analyzes the efficiency of the average packets routing delays prediction. The simulations also compared the efficiency of the proposed packets routing algorithm against the traditional algorithm on the total traveling time. The experiment results show that the proposed prediction method outperforms the prediction of average delays in terms of prediction error. And the proposed algorithm also can determine a shorter routing path than the compared algorithm.

致 謝 i
摘 要 ii
Abstract iii
目 錄 iv
圖 次 v
表 次 vii

第一章 緒論 1

第二章 文獻探討 4
第一節 VANET路由方法 4
第二節 容錯網路 6
第三節 預測相關方法 8
第四節 車流量預測與路段封包傳遞延遲估算方法 10

第三章 問題描述與方法架構 15

第四章 效能評估 24
第一節 實驗模擬環境與參數設定 24
第二節 模擬結果與分析 26

第五章 結論 34

參考文獻 35

[1]R.A. Santos and R.M. Edwards, "Cluster-Based Location Routing Algorithm for Vehicle to Vehicle Communication", in Proceeding of the Radio and Wireless Conference, pp.39-42, 2004.
[2]M.R. Jabbarpour, H. Malakooti, M. Taheri, and R. M. Noor, "The Comparative Analysis of Velocity and Density in VANET Using Prediction-Based Intelligent Routing Algorithms", in Proceeding of the Future Generation Communication Technology (FGCT), pp.54-58, 2013.
[3]W. Qiwu, L. Qingzi, Z. Long, and Z. Zhiming, "A Trusted Routing Protocol Based on GeoDTN+Nav in VANET", China Communications, Vol. 11(14), pp.166-174, 2014.
[4]M. Ayaida, M. Barhoumi, H. Fouchal, Y.G. Doudane, and L. Afilal, "PHRHLS: A Movement-Prediction-Based Joint Routing and Hierarchical Location Service for VANETs", Communications (ICC), pp.1424-1428, 2013.
[5]X. Li, W. Sun, X. Li, and J. Liu, "GRTR: A Geocasting Routing Based Target Region for VANET", Intelligent Networking and Collaborative Systems (INCoS), pp.215-219, 2013.
[6]W.H. Hsieh, S.R. Yang, and G.L. Chiou, "TGMD: A Trajectory-Based Group Message Delivery Protocol for Vehicular Ad Hoc Networks", Communications (ICC), pp.703-707, 2012.
[7]M.J. Khabbaz, C.M. Assi, and W.F. Fawaz, "Disruption-Tolerant Networking: A Comprehensive Survey on Recent Developments and Persisting Challenges", IEEE Communications Surveys & Tutorials, Vol. 14(2), pp.607–640, 2012.
[8]M.K. Nasir, S.A.A. Shah, M.A. Qureshi, M. Oche, and R.M. Noor, "Aapting Geographical DTN Routing for Enhanced Connectivity in Partitioned VANETs on Highways", Region 10 Symposium, pp.105-110, 2014.
[9]S. Jain, K. Fall and R. Patra, "Routing in a Delay Tolerant Network", Proc. ACM SIGCOMM, pp.1–13, January 2004.
[10]H. Kang and D. Kim, "Vector Routing for Delay Tolerant Networks", IEEE Vehicular Technology Conference, pp.1-5, September 2008.
[11]C. Liu and J. Wu, "An Optimal Probabilistic Forwarding Protocol in Delay Tolerant Networks", Proc. ACM MobiHoc, May 2009.
[12]G. Yu, J. Hu, C. Zhang, L. Zhuang, and J. Song, "Short-Term Traffic Flow Forecasting Based on Markov Chain Model", Intelligent Vehicles Symposium, pp.208-212, 2003.
[13]M.S. Dougherty and M.R. Cobbett., "Short-Term Inter-Urban Traffic Forecasts Using Neural Networks", International journal of forecasting, Vol. 13(1), pp.21-31, 1997.
[14]Y. Hongbin, S.C. Wong, J. Xu, and C.K. Wong, "Urban Traffic Flow Prediction Using a Fuzzy-Neural Approach", Transportation Research Part C: Emerging Technologies, Vol. 10(2), pp.85-98, 2002.
[15]H. Dia, "An Object-Oriented Neural Network Approach to Short-Term Traffic Forecasting", European Journal of Operational Research, Vol. 131(2), pp.253-261, 2001.
[16]T. Thomas, W. Weijermars, and E.V. Berkum, "Predictions of Urban Volumes in Single Time Series", IEEE Transactions on Intelligent Transportation Systems, Vol. 11(1), pp.71–80, 2010.
[17]J. Jeong, S. Guo, Y. Gu, T. He, and D.H.C. Du, "Trajectory-Based Data Forwarding for Light-Traffic Vehicular Ad Hoc Networks", IEEE Transactions on Parallel and Distributed Systems, Vol. 22(5), pp.743-757, 2011.
[18]孫敏哲，「在車載網路中以隨機模型估算郊區環境之封包傳遞延遲」，國立屏東大學，碩士論文，民國105年6月。
[19]N.S. Nafi, R.H. Khan, J.Y. Khan, and M. Gregory, "A Predictive Road Traffic Management System Based on Vehicular Ad-Hoc Network", Telecommunication Networks and Applications Conference (ATNAC), pp.135-140, 2014.
[20]X. Jiang and D.H.C. Du, "BUS-VANET: A BUS Vehicular Network Integrated with Traffic Infrastructure", IEEE Intelligent Transportation Systems Magazine, Vol. 7(2), pp.47-57, 2015.