臺灣博碩士論文加值系統

無線網路與行動通訊的快速發展完成隨處可以存取充足的網際網路資源，形成一個IP-based的環境，大量的IP資料封包透過TCP連接來傳送。一個典型的all IP網路由不同的無線網路所構成，例如IEEE 802.11 WLANs和3G/HSDPA/HSUPA 系統,並且構成一個異質無線網路 。傳統的TCP/IP網路，TCP的擁塞控制的運作在於有線網路表現很好，但在異質無線網路中TCP要決定精確的congestion window是困難的。主要的原因是TCP連線不只受到網路擁塞的影響還受到了無線 連線錯誤地影響。因此我們提出個以cross layer-based的擁塞控制，那 就是Cross Layer Logarithmic Increase Adaptive Decrease，CL-LIAD為 了TCP的擁塞控制在於異質無線網路。CL-LIAD有三個重要的貢獻，第一我們提出新的cross layer機制賦予receiver的TCP協定有攜帶MAC層無線狀況的資訊給sender利用ACK option。第二提出一個動態的頻寬預測演算法來預測可利用頻寬，因此能精確的決定congestion window。第三在Congestion Avoidance state，我們提出對數增加cwnd在發生三次duplicate ACKs事件後所收到的每個ACK。另外我們分析穩態時congestion window和throughput在不同loss rate時。數據結果證明提出的CL-LIAD 勝過其他的方法在goodput 、 fairness 、和friendliness在不同的異質無線網路拓撲。尤其，我們所提出的方法在10％packet loss rate的無線環境與LogWestwood+和Newreno相較之
下，goodput分別能提昇111% 和225%。

Rapid advances in wireless networks and mobile communications achieve ubiquitous access to the plentiful resources in the Internet and construct an all IP-based environment, in which most IP data packets transmitted through the TCP connections. A typical all IP network may consist of different wireless networks, e.g., the IEEE 802.11 WLANs and 3G/HSDPA/HSUPA cellular systems, and then form a heterogeneous wireless network. In TCP/IP transmissions, the TCP congestion control operates well in the wired network, but it is difficult to determine an accurate congestion window in a heterogeneous wireless network. The primary reason is that TCP connections are affected not only by networks congestion but also by wireless error links. Thus, this paper proposes a cross layer-based adaptive window congestion control, namely Cross Layer Logarithmic Increase Adaptive Decrease, CL-LIAD, for TCP congestion control in the heterogeneous wireless networks. CL-LIAD deploys three significant contributions. First, we propose a novel cross layer mechanism that enables the receiver’s TCP protocol to carry the MAC-layer wireless state information to the sender through the ACK option. Second, an adaptive bandwidth expectation algorithm is proposed to predict available bandwidth, and thus accurately determine the
congestion window. Third, in the Congestion Avoidance (CA) phase, we propose a Logarithmic Increase algorithm to increase cwnd while receiving each ACK after causing three duplicate ACKs. In addition, we analyze the congestion window and throughput under different packet loss rate by determining a closed-form expression. Furthermore, the state transition diagram of CL-LIAD is detailed. Numerical results demonstrate that the proposed CL-LIAD outperforms other approaches in goodput, fairness, and friendliness under diverse topologies of the heterogeneous wireless network. Especially, in the case of 10% packet loss rate in wireless links, the proposed approach increases goodput up to 111% and 225% as compared with LogWestwood+ and NewReno, respectively.

摘要 I
Abstract III
誌謝 V
Content VI
List of Figures VIII
Chapter 1 Introduction 1
Chapter 2 Related works 4
2.1. The type with help from intermediate nodes 4
2.2. The type without any help from intermediate nodes 5
2.2.1. The sliding window-based Additive Increase Multiplicative Decrease (AIMD) TCP 6
2.2.2. The Available Bandwidth Estimation (ABE) TCP 7
2.3. The loss-based and delay-based types TCP for long-distance networks 9
Chapter 3 Network Model 11
Chapter 4 The Cross Layer-based Logarithmic Increase Adaptive Decrease TCP Approach 15
4.1. The CL mechanism for determining adaptive network bandwidth 17
4.1.1. The CL mechanism 17
4.1.2. The CL-based TCP receiver 18
4.1.3. The CL-based TCP sender 21
4.2. In the increasing cwnd phase while the expected network bandwidth is enough 23
4.2.1. The algorithm of determining the optimal congestion window ( ) 23
4.2.2. The algorithm of determining the ideal ssthresh for the initial Slow Start state 24
4.2.3. The determination of adaptive network bandwidth and network ssthresh 26
4.3. In the decrease cwnd phase while the expected network bandwidth is insufficient 31
Chapter 5 Analysis of The CL-LIAD’s Grow Function in CA 35
Chapter 6 State Transition Diagram of The Proposed Approach 41
6.1. The Slow Start state 41
6.2. The Congestion Avoidance state 42
6.3. The Fast Retransmit state 42
6.4. The Fast Recovery state 42
Chapter 7 Numerical Results 44
7.1. Scenario 1: N TCP connections in a wired network 44
7.2. Scenario 2: one TCP connection in a wireless network 45
7.3. Scenario 3: N TCP connections in a wired network with a single wireless link 48
7.4. Scenario 4: N TCP connections in a wired network with two wireless links 50
Chapter 8 Conclusions and Future works 54
References 56

Fig. 1. An example of a cross layer-based TCP connections in heterogeneous wireless networks 12
Fig. 2. The conceptual ideas of CL-LIAD and related approaches 17
Fig. 3. Message flow in the cross layer CL-LIAD mechanism 18
Fig. 4. RTS/CTS and NAV in IEEE 802.11 19
Fig. 5. The cross layer-based TCP ACK’s option structure 20
Fig. 6. The state transition diagram of the CL TCP receiver 21
Fig. 7. The estimated and actual bandwidth 22
Fig. 8. Data and acknowledgement transmissions of a TCP connection 24
Fig. 9. The algorithm of controlling congestion window while receiving ACKs at sender 29
Fig. 10. The cwnd variations of CL-LIAD, NewReno, LogWestwood+, BIC, and CUBIC. 31
Fig. 11. The algorithm of shrinking congestion window while receiving three duplicate ACKs 34
Fig. 12. CL-LIAD’s grow function in the CA phase 35
Fig. 13. Response functions of all approaches under different packet loss rates 39
Fig. 14. Analyses of static throughput of all approaches under different packet loss rates 40
Fig. 15. The state transition diagram of CL-LIAD 43
Fig. 16. Scenario 1: a wired network with a single bottleneck link 45
Fig. 17. Friendliness of CL-LIAD and NewReno 45
Fig. 18. Scenario 2: one TCP connection in a wired network with a single wireless link 46
Fig. 19. Goodput of all compared approaches under different packet loss rates (Wireless network) 47
Fig. 20. The cwnd variations of NewReno, CL-LIAD, and LogWestwood+ under 1% and 10% wireless packet loss rates (One connection operated with a single wireless network) 48
Fig. 21. Scenario 3: 20 TCP connections in a wired network with a single wireless link 49
Fig. 22. Goodput of all compared approaches (with a single wireless network) 50
Fig. 23. Fairness of all compared approaches (with a single wireless network) 50
Fig. 24. Scenario 4: 10 TCP connections in a wired network with two wireless links 51
Fig. 25. Goodput of compared approaches (with two wireless networks) 52
Fig. 26. Fairness of compared approaches (with two wireless networks) 52

[1] IEEE 802.11 WG, “Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications,” IEEE std. 802.11, 1999.
[2] “IEEE Standard for Local and Metropolitan Area Networks Part 16: Air Interface for Fixed Broadband Wireless Access Systems,” IEEE Std. 802.16, Oct. 2004.
[3] http://www.3gpp.org
[4]K.R. Santhi, V.K. Srivastava, G. SenthilKumaran, and A. Butare, “Goals of true broad band''s wireless next wave (4G-5G),” IEEE VTC 2003-Fall, Vol. 4, pp. 2317-2321, Oct. 2003.
[5] “Transmission Control Protocol,” IETF RFC 793, 1981.
[6] “Internet Protocol,” IETF RFC 791, 1981.
[7] L. Scalia, F. Soldo, and M. Gerla, “PiggyCode: A MAC Layer Network Coding Scheme to Improve TCP Performance over Wireless Networks,” IEEE Globecom 2007, Vol.10, No.3, pp.3672–3677, Nov. 2007.
[8] O. Shagdar, M.N. Shirazi, and Bing Zhang, “Improving ECN-based TCP Performance over Wireless Networks Using a Homogeneous Implementation of EWLN,” ICT 2003, pp.812–817, Mar. 2003.
[9] R. Chaudhary, and L. Jacob, “ECN based TCP-friendly rate control for wireless multimedia streaming,” ICCCN 2003, pp.599–602, Oct. 2003.
[10] F. Paganini, Z. Wang, S. Low, and J. Doyle, “A New TCP/AQM for Stable Operation in Fast Networks,” IEEE INFOCOM 2003, Vol. 1, pp. 96-105, April 2003.
[11] A. Misra, and T. Ott, “Performance Sensitivity and Fairness of ECN-aware Modified TCP,” Performance Evaluation, Vol. 53, Issue 3-4, pp. 255-272, Aug. 2003.
[12] S. Kopparty, S. Krishnamurthy, M. Faloutsos, and S. Tripathi, “Split-TCP for Mobile Ad-Hoc Networks”, IEEE Globecom2002, Vol.1, pp. 138-142, Nov. 2002.
[13] H. Balakrishnan, S. Seshan, and R. H. Katz, “Improving reliable transport and handoff performance in cellular wireless networks,” Wireless Networks, Vol. 1, Issue 4, pp. 469–481, Dec. 1995.
[14] M. Garcıa, J. Choque, L. Sanchez, and L. Munoz, “An experimental study of Snoop TCP performance over the IEEE 802.11b WLAN,” International Symposium on Wireless Personal Multimedia Communications 2002, Vol. 3, pp. 1068–1072, Oct. 2002.
[15] M. Garcia, R. Aguero, L. Munoz, and J. A. Irastorza, “Stabilizing TCP Performance over Bursty Wireless Links through the Combined Use of Link-Layer Techniques,” IEEE Communications Letters, Vol.10, No.3, pp.153–155, Mar. 2006.
[16] H. Jung, N. Choi, Y. Seok, T. Kwon, and Yanghee Choi, “Augmented Split-TCP over Wireless LANs,” IEEE ICC2006, Vol. 12, pp.5420–5425, June 2006.
[17] H. Jung, N. Choi, Y. Seok, T. Kwon, and Yanghee Choi, “Augmented Split-TCP over Wireless LANs,” IEEE ICC2006, Vol. 12, pp.5420–5425, June 2006.
[18] “Transmission Control Protocol,” IETF RFC 2581, 1999.
[19] “The Newreno Modification to TCP’s Fast Recovery Algorithm,” IETF RFC 2582, 1999.
[20] “The Newreno Modification to TCP’s Fast Recovery Algorithm,” IETF RFC 3782, 2004.
[21] Janey C. Hoe, “Improving the start-up behavior of a congestion control scheme for TCP,” ACM SIGCOMM 1996, pp. 270-280, Aug. 1996.
[22] D. Chiu, and R. Jain, “Analysis of the increase/decrease algorithms for congestion avoidance in computer networks,” Journal of Computer Networks and ISDN systems, Vol.17, No. 1, pp. 1-14, June 1989.
[23] V. Jacobson, “Congestion avoidance and control,” ACM SIGCOMM 1988, pp. 314-329, Aug. 1988.
[24] W. Stevens, “TCP slow start, congestion avoidance, fast retransmit and fast recovery algorithms,” IETF RFC 2001, 1997.
[25] C. Casetti, M. Gerla, S. Mascolo, M.Y. Sanadidi, and R. Wang, “TCP Westwood: Bandwidth estimation for enhanced transport over wireless links,” ACM Mobicom 2001, pp. 287-297, July 2001.
[26] X. Kai, T. Ye, and N. Ansari, “TCP-Jersey for wireless IP communications,” IEEE Journal on Selected Areas in Communications, Vol. 22, Issue 4, pp. 747-756, May 2004.
[27] R. Wang, M. Valla, M.Y. Sanadidi, B.K.F. Ng, and M. Gerla, “Efficiency/friendliness tradeoffs in TCP Westwood,” IEEE ISCC 2002, pp. 304-311, July 2002.
[28] L.A. Grieco, and S. Mascolo, “Performance evaluation of Westwood+ TCP over WLANs with local error control,” IEEE International Conference on Local Computer Networks, pp. 440-448, Oct. 2003.
[29] Lawrence S. Brakmo, Sean W. O''Malley, and Larry L. Peterson, “TCP Vegas: new techniques for congestion detection and avoidance,” ACM SIGCOMM, pp. 24-35, 1994.
[30] http://193.204.59.68/mascolo/tcp westwood/homeW.htm
[31] J. Mo, R.J. La, V. Anantharam, and J. Walrand, “Analysis and comparison of TCP Reno and Vegas,” IEEE INFOCOM ''99, Vol. 3, pp. 1556-1563, Mar. 1999.
[32] C. Villamizar, and C. Song, “High Performance TCP in the ANSNET,” ACM SIGCOMM Computer Communication Review, Vol. 24, No. 5, pp.45–60, Nov. 1994.
[33] Y. R. Yang and S. S. Lam, “General AIMD Congestion Control,” ICNP 2000, pp. 187–198, Nov. 2000.
[34] S. Floyd, “HighSpeed TCP for large congestion windows,” RFC 3649, Dec. 2003.
[35] T. Kelly, “Scalable TCP: improving performance in highspeed wide area networks,” ACM Comp. Comm. Rev., Vol. 33, pp. 83 – 91, Apr. 2003.
[36] Cheng Jin, D.X. Wei, and S.H. Low, “FAST TCP: motivation, architecture, algorithms, performance,” IEEE Infocom 2004, Vol. 4, pp. 2490–2501, Mar. 2004.
[37] L. Xu, K. Harfoush, and I. Rhee, “Binary Increase Congestion Control for Fast, Long Distance Networks,” IEEE Infocom 2004, Vol. 4, pp. 2514 – 2524, Mar. 2004.
[38] I. Rhee, and L. Xu, “CUBIC: A New TCP-Friendly High-Speed TCP Variants,” International Workshop on Protocols for Fast Long-Distance Networks 2005, Feb. 2005.
[39] D. Kliazovich, F. Granelli, and D. Miorandi, “TCP Westwood+ Enhancement in High-Speed Long-Distance Networks,” IEEE ICC 2006, Vol. 2, pp. 710 – 715, June 2006.
[40] K. Tan, J. Song, Q. Zhang, and M. Sridharan, “A Compound TCP Approach for High-Speed and Long Distance Networks,” IEEE Infocom 2006, pp. 1 – 12, Apr. 2006.
[41] B.-J. Chang, S.-Y. Lin, and Y.-H. Liang, “TCP-Taichung: A RTT-based Predictive Bandwidth Based with Optimal Shrink Factor for TCP Congestion Control in Heterogeneous Wired and Wireless Networks,” IFIP Lecture Note in Computer Science Proceeding of International Conference on Embedded and Ubiquitous Computing 2007, Vol. 4808, pp. 367-378, Dec. 2007.
[42] V. Tsaoussidis, and C. Zhang, “The Dynamics of Responsiveness and Smoothness in Heterogeneous Networks,” IEEE JSAC, Vol. 23, No. 6, pp.1178–1189, June 2005.
[43] R. M. Corless, G. H. Gonnet, D. E. G. Hare, D. J. Jeffrey, and D. E. Knuth, “On the LambertW Function,” Advances in Computational Mathematics, Vol.5, No. 4, pp.329-359, Dec. 1996.
[44] The Network Simulator ns-2, http://www.isi.edu/nsnam/ns/