隨著無線網際網路普及化，大眾對於無線通訊技術的要求也越來越高，高速度、高頻寬、高品質…等，而最近風行的4G(4th Generation)，即是因應此種需求而產生的封包交換(Packet Switch, PS)行動通訊系統(Mobile Communication System)。4G提供高速網路存取服務，為頻寬更大、覆蓋範圍更廣的無線通訊傳輸，且主要是針對傳輸多媒體數據資料，而非單純地傳輸語音資訊，但也因此使移交(Handoff)的處理過程在4G行動通訊系統中，比傳統的無線網路更較具挑戰性，因為它需要更多的頻寬來處理與維護多媒體應用程式(Multimedia Applications)、客戶端的行動性(Client Mobility)以及其他可能被考量的因素等。
本研究主要是利用機器學習技術(Machine Learning Techniques)，根據使用者在Cellular System中移動的情形，如：速度、方向與座標位置等特性，預測使用者未來的移動趨勢，動態調整兩層式細胞架構(Two-Tier Cell Structure)的邊界所涵蓋之範圍大小，並分別利用模糊邏輯(Fuzzy Logic)、粒子族群最佳化(Particle Swarm Optimization, PSO)與支撐向量回歸(Support Vector Regression, SVR)推論出使用者即將前往的鄰近細胞(Neighboring Cells)，而後計算相鄰細胞在4G行動通訊系統中進行移交連線(Handoff Calls)時所需使用的頻寬，進而進行頻寬預留(Bandwidth Reservation)，以求降低多媒體在移交連線中斷的機率(Call Dropping Probability, CDP)，並同時整合按比例差別服務(Proportional Differentiated Services, Proportional DiffServ)，針對不同群體的網路使用者，提供不同等級的服務品質(Quality of Service, QoS)。最後透過模擬結果，可發現我們所提出的方法，比起文獻中所介紹的各種頻寬預留機制在移交連線中斷的機率(CDP)、新進連線失敗的機率(CBP)與頻寬利用率方面皆達到較好的成效。

With the development of wireless networks, excellent quality and large bandwidth of internet are strongly required for internet users. 4th Generation (4G) is a packet switch mobile wireless communication system which can provide high speed, large bandwidth and wide coverage of internet services. 4G aims to transfer not only voice information but also multimedia data. Although 4G can meet the most requirements of high quality of internet services, the process of handoff in 4G is more challenging than traditional wireless networks. This study utilizes the machine learning techniques to dynamically adjust the range of two-tier cell structure according to the user’s movement situation in cellular system such as user’s speed, direction, and coordinates etc. Besides, Fuzzy Logic, Particle Swarm Optimization (PSO), and Support Vector Regression(SVR) are used to inference the target neighboring cells which users will reach, and then count the bandwidth required which the target cells in processing handoff calls to reserve appropriate bandwidth in order to reduce the Call Dropping Probability (CDP). In the meantime, the Proportional Differentiated Services (Proportional DiffServ) is applied to provide different quality levels of services for diverse internet users. The simulation results show that the proposed schemes can achieve superior performance than the representative bandwidth-reserving schemes in the literature when performance metrics are measured in terms of the forced termination probability for handoffs, the call blocking probability for the new connections, and bandwidth utilization.

第一章 緒論……………………………………………………………………………1
1.1研究背景與動機…………………………………………………………………1
1.2研究目的…………………………………………………………………………4
1.3研究方法…………………………………………………………………………5
1.4預期成效…………………………………………………………………………6
1.5論文架構…………………………………………………………………………6
第二章 文獻探討…………………………………………………………………………7
2.1 行動通訊系統架構……………………………………………………………7
2.1.1 1G行動通訊網路…………………………………………………………7
2.1.2 2G行動通訊網路…………………………………………………………8
2.1.3 3G行動通訊網路………………………………………………………10
2.1.4 4G行動通訊網路…………………………………………………………15
2.2差別服務………………………………………………………………………21
2.2.1整合性服務(Integrated Services, IntServ)…………………………………21
2.2.2差別性服務(Differentiated Services, DiffServ)…………………………22
2.2.3 IntServ與DiffServ的比較………………………………………………23
2.2.4 按比例差別性服務(Proportional DiffServ) ……………………………24
2.3頻寬預留(Bandwidth Reservation)……………………………………………26
2.4通道配置(Channel Allocation)………………………………………………34
2.5機器學習(Machine Learning)…………………………………………………37
2.5.1灰色系統理論(Grey System Theory)……………………………………37
2.5.2模糊理論(Fuzzy Theory)………………………………………………39
2.5.2.1模糊化機構(Fuzzifier) …………………………………………44
2.5.2.2模糊規則庫(Fuzzy Rule Base) ………………………………44
2.5.2.3模糊推論引擎(Fuzzy Inference Engine) ………………………44
2.5.2.4解模糊化機構(Defuzzifier) ……………………………………46
2.5.3粒子族群最佳化(Particle Swarm Optimization, PSO)……………………47
2.5.4支撐向量回歸(Support Vector Regression, SVR)………………………48
第三章 動態調整兩層式細胞架構的邊界與適性化頻寬預留機制…………………49
3.1按比例差別性服務(Proportional DiffServ) …………………………………49
3.2動態調整兩層式細胞架構的邊界…………………………………………50
3.2.1細胞邊界值的關係式……………………………………………………50
3.3結合灰預測與模糊邏輯達到頻寬預留………………………………………51
3.3.1灰色系統理論數學模型與步驟…………………………………………51
3.3.2細胞邊界(Cellular Boundary)的調整機制………………………………55
3.3.3利用模糊邏輯預留頻寬…………………………………………………60
3.4利用粒子族群最佳化(PSO)達到頻寬預留…………………………………67
3.5利用支撐向量回歸(SVR)達到頻寬預留……………………………………69
第四章 實驗結果與分析……………………………………………………………72
4.1 模擬環境設定……………………………………………………………72
4.2 模擬結果與分析…………………………………………………………75
第五章 研究結論與展望……………………………………………………………80
5.1 研究結論……………………………………………………………………80
5.2 未來研究方向………………………………………………………………82
參考文獻………………………………………………………………………………84

[1]A. Malla, M. El-Kadi, and P. Todorova, “A Fair Resource Allocation Protocol for Multimedia Wireless Networks,” IEEE Inter. Conf. Parallel Processing, pp. 437-443, 2001.
[2]A. R. MISHRA, Fundamentals of Cellular Network Planning and Optimisation 2G /2.5G /3G...Evolution to 4G, WILEY, 2004.
[3]A. Ganz, Z. Ganz, and K. Wongthavarewat, MULTIMEDIA WIRELESS NETWORKS：Technologies Standards, and QoS, PTR, 2004.
[4]B. Scholkopf, A. Smola, R. Williamson, and P. L. Bartlett, “New support vector algorithms,” Neural Computation, vol. 12, pp. 1207-1245, 2000.
[5]C. H. Choi, M. I. Kim, T. J. Kim, and S. J. Kim, “Adaptive Bandwidth Reservation Mechanism Using Mobility Probability in Mobile Multimedia Computing Environment,” IEEE Local Computer Networks, pp. 76-85, Nov., 2000 .
[6]C. Oliveira, J. B. Kim, and T. Suda, “An Adaptive Bandwidth Reservation Scheme for High-Speed Multimedia Wireless Networks,” IEEE J. Selected Areas in Comm., vol. 16, no. 6, pp. 858-874, 1998.
[7]C. H. Choi, M. I. Kim, T. J. Kim and S. J. Kim, “A call admission control mechanism using MPP and 2-tier cell structure for mobile multimedia computing,” Tenth International Conference on Computer Communications and Networks, pp. 581-584, 2001.
[8]C. Dovrolis, D. Stiliadis, and P. Ramanathan, “Proportional differentiated services: delay differentiation and packet
scheduling,” IEEE/ACM Trans.Networking, vol. 10, no. 1, pp. 12-26, 2002.
[9]C. J. C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data Mining and Knowledge Discovery, vol. 2, no. 2, pp. 121-167, 1998.
[10]C. V. Attrock, Fuzzy Logic & NeuroFuzzy Applications Explained, New Jersey: Prentice Hall International Inc., 1997.
[11]C.-C. Li, S.-L. Tsao, M.-C. Chen, Y. Sun, and Y.-M. Huang, “Proportional delay differentiation services based on weighted fair queueing,” IEEE Inter. Conf.Computer Communications and Networks, pp. 418-423, 2000.
[12]D. J. Goodman, “Cellular packet communication,” IEEE Trans. Commun., vol.38, Aug., 1990.
[13]D. A. Levine, I. F. Akyildiz, and M. Naghshineh, “A Resource Estimation and Call Admission Algorithm for Wireless Multimedia Networks Using the Shadow Cluster Concept,” IEEE/ACM Trans. Networking, vol. 5, no. 1, pp. 1-12, 1997.
[14]D. Wisely, H. Aghvami, S. L. Gwyn, T. Zahariadis, J. Manner, V. Gazi, N.Houssos, and N. Alonistioti, “Transparent IP Radio Access for Next-Generation Mobile Networks,” IEEE Wireless Communications, pp.26-35, Aug., 2003.
[15]D. Anguita, and A. Boni, “Towards Analog and Digital Hardware for Support Vector Machines,” 2001 International Joint Conference on Neural Networks, vol. 4, pp. 2422-2426, Jul., 2001.
[16]D. Anguita, A. Boni, and S. Ridella, “Learning Algorithm for Nonlinear Support Vector Machines Suited for Digital VLSI,” Electronics Letters, vol. 35, no. 16, pp. 1349-1350, 1999.
[17]D. Anguita, A. Boni, and S. Ridella, “A VLSI Friendly Algorithm for Support Vector Machines,” 1999 International Joint Conference on Neural Networks, vol. 2, pp. 939-942, Jul., 1999.
[18]D. J. Shyy, and J. Dunyak, “Cooperative MIMO Gateways：A Promising Technique for Fast Handoff,” Wireless Telecommunications Symposium, pp.49-54, 2005.
[19]E. M. Ma, “A cost-based scheduling algorithm for differentiated service on WDM optical networks,” IEEE Communications Letters, vol. 7, no. 9, pp. 460-462, 2003.
[20]F. M. Karaliopoulos, R. Tafazolli, and B. G. Evans, “Providing differentiated service to TCP flows over bandwidth on demand geostationary satellite networks,” IEEE Journal on Selected Areas in Communications, vol. 22, no. 2, pp. 333-347, 2004.
[21]G. Schollmeier, and C. Winkler, “Providing sustainable QoS in next-generation networks,” IEEE Communications Magazine, vol. 42, no. 6, pp. 102-107, 2004.
[22]G. S. Kuo, P. C. Ko, and M. L. Kuo, “A Probabilistic Resource Estimation and Semi-Reservation Scheme for Flow-Oriented Multimedia Wireless Networks,” IEEE Communications Magazine, pp. 135-141, 2001.
[23]G. Gomez, and R. Sanchez, End-to-End Quality of Service over Cellular Networks：Data Services Performance and Optimization in 2G/3G, WILEY, 2005.
[24]H. Yang, “A Road to Future Broadband Wireless Access ：
MIMO-OFDM-Based Air Interface,” IEEE Communications Magazine, pp.
53-60, Jan., 2005.
[25]Jiang, and W. Zhuang, “Quality-of-service provisioning in future 4G CDMA cellular networks,” IEEE Wireless Communications, vol. 11, no. 2, pp. 48-54, 2004.
[26]J. M. Chung, and H. M. Soo, “A Jitter analysis of homogeneous traffic in differentiated services networks,” IEEE Communications Letters, vol. 7, no. 3, pp. 130-132, 2003.
[27]J. F. Huber, “Mobile next-generation networks,” IEEE Multimedia, vol. 11, no. 1, pp. 72-83, 2004.
[28]J. E. Padgett, C. G. Gunther, and T. Hattori, “Overview of wireless personal communications,” IEEE Commun Mag., vol. 33, Jan., 1995.
[29]J. Sarnecki, C. Vinodrai, A. Javed, P. O’Kelly, and K. Dick, “Microcell design principles, ” IEEE Commun. Mag., vol. 31, Apr., 1993.
[30]J. H. Lee, T. H. Jung, S. U. Yoon, S. K. Youm, and C. H. Kang, “An Adaptive Resource Allocation Mechanism Including Fast and Reliable Handoff in IP-Based 3G Wireless Networks,” IEEE Personal Communications, pp. 42-47, 2000.
[31]J. L. Deng, “Introduction to grey system theory,” The Journal of Grey System, vol. 1, no. l, pp. 1-24, 1989.
[32]J. Kennedy, “The behavior of particles,” 7th International Conference on Evolutionary Programming, pp. 581-589, 1998.
[33]J. Gozdecki, A. Jajszczyk, and R. Stankiewicz, “Quality of service terminology in IP networks,” IEEE Communications Magazine, vol. 41, no. 3, pp. 153-159, 2003.
[34]J. Wroclawski, “The use of RSVP with IETF integrated services,” IETF RFC 2210, Sep., 1997.
[35]J. C. CHEN, and T. ZHANG, IP-BASED NEXT-GENERATION WIRELESS
NETWORKS：Systems, Architecture, and Protocols, WILEY, 2004.
[36]J. Lilleberg, R. Prasad, and Kluwer, “Research Challenges for 3G and Paving the Way for Emerging New Generations,” Wireless Personal Communications, pp. 355-362, Jun., 2001.
[37]J. M. Gilbert, W. J. Choi, and Q. Sun, “MIMO Technology for Advanced Wireless Local Area Networks,” Design Automation Conference, pp. 13-17, Jun., 2005.
[38]K. Pahlavan, and A. H. Levesque, “Wireless data communications,” Proc. IEEE, vol. 82, Sep., 1994.
[39]K. L. Wen, J. W. Dai, T. C. Chang, and C. C. Tong, “The discussions of class ratio for AGO algorithm in grey theory,” IEEE International Conference on Systems, Man, and Cybernetics, vol. 1, pp. 7-11, 2001.
[40]L. R. Chen, C. H. Lin, R. C. Hsu, B. G. Ku, and C. S. Liu, “A study of Li-ion battery charge forecasting using Grey theory,” The 25th International Telecommunications Energy Conference, pp. 744-749, 2003.
[41]M. EI-Kadi, S. Olariu, and H. Abdel-Wahab, “Rate-Based Borrowing Scheme for QoS Provisioning in Multimedia Wireless Networks,” IEEE Trans. Parallel and Distributed Systems, vol. 13, no. 2, pp. 156-166, 2002.
[42]M. Hasegawa, G. Wu, and M. Mizuno, “Applications of Nonlinear Prediction Methods to the Internet Traffic,” The 2001 IEEE International Symposium on Circuits and Systems, vol. 2, pp. III-169-III-172, May, 2001.
[43]M. Gudmuundson, “Analysis of Handover Algorithms,” Proc. Vehcular Tech. Conf., 91, St. Louis, MO, pp.537-542, 1991.
[44]M. Ergen, S. Coleri, and P. Varaiya, “QoS Aware Adaptive Resource Allocation Techniques for Fair Scheduling in OFDMA Based Broadband Wireless Access Systems,” IEEE Transactions on Broadcasting, Vol. 40, No. 4, Dec., 2003.
[45]M. H. Dunham, DATA MINING Introductory and Advanced Topics, Pearson Education, 2003.
[46]M. Etoh, Next Generation Mobile Systems 3G and Beyond, WILEY, 2005.
[47]P. C. Ko, and P. C. Lin, “A hybrid swarm intelligence based mechanism for earning forecast,” 2nd International Conference on Information Technology for Application, pp. 193-198, 2004.
[48]P. Nicopolitidis, M. S. Obaidat, G. I. Papadimitriou, and A. S. Pomportsis, WIRELESS NETWORKS, WILEY, 2003.
[49]Q. Zhao, J. Gao, T. Wu, and L. Lu, “The grey theory and the preliminary probe into information acquisition technology,” International Conference on Information Acquisition, pp. 402-404, 2004.
[50]R. Braden, D. Clark, and S. Shenker, “Integrated Services in Internet architecture：an overview,” IETF RFC 1633, Jun., 1994.
[51]R. Braden, L. Zhang, S. Berson, S. Herzog, and S. Jamin, “Resource reservation protocol (RSVP),” IETF RFC 2005, Sep., 1997.
[52]S. Y. Hui, and K. H. Yeung, “Challenges in the migration to 4G mobile systems,” IEEE Communications Magazine, vol. 41, no. 12, pp. 54-59, 2003.
[53]S. T. Sheu and C. C. Wu, “Using grey prediction theory to reduce handoff overhead in cellular communication systems,” The 11th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, vol. 2, pp. 782-786, 2000.
[54]S. C. Chi, H. P. Chen, and C. H. Cheng, “A forecasting approach for stock index future using grey theory and neural networks,” International Joint Conference on Neural Networks, vol. 6, pp. 3850-3855, 1999.
[55]S. H. Fan, T. Y. Xiao, C. Guo, and Jie Wen, “A model of the expanded grey theory,” IEEE International Conference on Networking, Sensing and Control, vol. 1, pp. 339-342, 2004.
[56]S. I. Maniatis, E. G. Nikolouzou, and I. S. Venieris, “QoS Issues in the Converged 3G Wireless and Wired Networks,” IEEE Communications Magazine, pp. 44-53, 2002.
[57]S. Blake, D. Black, M. Carlson, E. Davies, Z. Wang, and W. Weiss, “An Architecture for Differentiated Services,” IETF RFC 2475, Dec., 1998.
[58]S. L. Su, J. Y. Chen, and J. H. Huang, “Performance Analysis of Soft Handoff in CDMA Cellular Networks,” IEEE Journal on Selected Areas in Communications, vol. 14, no. 9, December, 1996.
[59]S. C. Lee, J. C. Lui, and D. K. Yau, “A proportional-delay DiffServ-enabled Web server: admission control and dynamic adaptation,” IEEE Trans. Parallel and Distributed Systems, vol. 15, no. 5, pp. 384-400, 2004.
[60]S. Vuong, and X. Shi, “A proportional differentiation service model for the future Internet differentiated services,” IEEE Inter. Conf. Communication Technology,vol. 1, pp. 416-423, 2000.
[61]T. Zahariadis, “Trends in the path to 4G,” Communications Engineer, vol. 1, no. 1, pp. 12-15, 2003.
[62]U. Varshney, and R. Jain, “Issues in Emerging 4G Wireless Networks,” IEEE Computer, pp. 94-96, Jun., 2001.
[63]V. Vapnik, “The Nature of Statistical Learning Theory,” New York: Springer-Verlag, 1995.
[64]V. Vapnik, J. A. K. Suykens, and J. Vandewalle, “The Support Vector Method of Function Estimation in Non-linear Modeling: Advanced Black-Box Techniques,” MA: Kluwer, pp. 55-85, 1998.
[65]W. Liu, X. Chen, Y. Fang, and J. M. Shea, “Courtesy piggybacking: supporting differentiated services in multihop mobile ad hoc networks,” IEEE Transactions on Mobile Computing, vol. 3, no. 4, pp. 380-393, 2004.
[66]W. Y. Zou, and Y. Wu, “COFDM: An Overview,” IEEE Trans. Broadcasting, vol. 41, no. 1, pp 1-8, Mar., 1995.
[67]W. Hwang, and K. Kim, “Performance Analysis of OFDM on the Shadowed Multipath Channels,” IEEE Trans. Consumer Electronics, vol. 44, no. 4, pp 1323-1328, Nov., 1998.
[68]W. Mohr, and Kluwer, “Development of Mobile Communications Systems Beyond Third Generation,” Wireless Personal Communications, pp. 191-207, Jun., 2001.
[69]X. Wu, K. L. Yeung, and J. Hu, “Efficient Channel Borrowing Strategy for Real-Time Services in Multimedia Wireless Networks,” IEEE Trans. Vehicular Technology, vol. 49, no. 4, pp. 1273-1284, 2000.
[70]X. Gao, G. Wu, and T. Miki, “End-to-End QoS Provisioning in Mobile Heterogeneous Networks,” IEEE Wireless Communications, pp.24-34, Jun., 2004.
[71]Y. H. Wen, T. T. Lee, and H. J. Cho, “Hybrid models toward traffic detector data treatment and data fusion,” IEEE Networking, Sensing and Control, pp. 525-530, 2005.
[72]Y. B. Lin, and I. Chlamtac, Wireless and Mobile Network Architectures, WILEY.
[73]李允中，王小璠，蘇木春，模糊理論及其應用，全華科技圖書，民93。
[74]顏佑霖，多媒體無線網路上的分區塊頻寬預留法，國立中山大學資訊工程研
究所碩士論文，民91。
[75]蘇木春，張孝德，機器學習：類神經網路、模糊系統以及基因演算法則，全
華科技圖書，民92。