移动通信中WWW业务建模及调度算法研究
|
摘要
随着计算机性能和仿真技术的提高,计算机仿真技术得到越来越广泛的运用。OPNET是一种具有高可靠度的网络建模、设计、仿真和分析工具。本文首先介绍了基于OPNET建立的UMTS仿真平台,并基于该平台研究了UMTS网络典型业务端到端的关键性能参数,以及根据业务服务质量的需求提供不同等级服务的可行性。仿真结果表明,该系统级仿真平台对UMTS系统的性能分析是有效的,为网络的规划设计提供客观、可靠的定量依据。
计算机仿真系统的性能分析总是建立在某些假设前提基础上的,例如信道模型、信源模型等等。业务源模型极大地影响到系统性能评估结果的准确程度,因此,建立正确的业务分布模型就成为系统仿真模型中重要的组成部分。本文第三章通过对ON/OFF模型和WWW业务流的分析得到一个与实际无线网络更吻合的三层业务模型,并且利用第二章知识在OPNET上完成UMTS单蜂窝仿真平台的搭建。最后通过OPNET仿真平台上的仿真,证明了三层业务模型比ON/OFF模型更加精确,是一种理想的业务模型。此模型的应用有利于提高无线网络规划与优化的质量和效率。
UMTS中要求能为不同的用户提供多种的通信业务,同时满足不同业务的服务质量要求。在充分利用无线系统资源的基础上,并尽可能地保证用户数据的传输质量,需要对无线资源进行合理的管理与分配。调度算法的研究是无线资源管理的关键部分,本文第四章在WCDMA系统混合业务下研究调度算法,WCDMA系统混合业务下设计调度算法要考虑信道条件,要区分业务保证用户的QoS要求,避免用户“饥饿”现象,同时也要尽可能提高整个系统的吞吐量和调度的公平性。由此,在比例公平调度算法(PFS)基础上基于C/I、QoS、饥饿权重提出区分业务类型的比例公平分组调度算法(CQSSD-PFS),同时引入实时业务和系统容量补偿模型。在第二章建立的UMTS仿真平台上根据第三章的业务模型配置业务,最后对算法进行仿真,仿真结果表明CQSSD-PFS算法可有效确保各类业务之间的短期、长期公平性和较高的系统吞吐量。
总之,本文研究工作为多业务UMTS系统的网络建模、业务建模和无线资源优化管理提供了理论依据。
With the improvement of capability of computer and simulating technology, the use of computer simulation is more and more widely. OPNET is a high trustiness network model, design, simulation and analysis tool. First, This paper main introduce UMTS simulation platform which base on OPNET, and study type traffic point-to-point key performance of the UMTS network,as well as the feasibility base on traffic service QoS’s demand provide vary class service. The simulation results indicate this system simulation platform is effective for UMTS system’s performance analysis, and afford objective, reliable ration warranty for network programming and designing.
The analysis of the performance of computer simulating system are always based on some hypothetic preconditions, for example, channel model、source model, etc. since the traffic model has a great influence on the veracity of the system capability evaluating result, the establish of a correct traffic distributing model becomes an very important part in system simulation model. In part three proposes a three-layer traffic model from analyzing the ON/OFF model and the WWW traffic stream that fit actual wireless traffic better, and build a single cell UMTS simulation plat. Stimulating on the OPNET model proves that three-layer traffic model is more precise than ON/ OFF modeling. It is a kind of ideal traffic model. Applying this model benefit improving quality and efficiency of the wireless network programming and optimizing.
UMTS ask different kinds of service for different users. At the same time, it also requires a high service quality for all kinds of different business. Based on the full use of the wireless resources system, and also make sure the transmitted quality of the users’data, it is necessary to make a reasonable management and admeasure of the wireless resources. The research of the Scheduling Algorithm is the key point of the management of the wireless resources. In the fourth chapter of this paper, based on the mix traffic for WCDMA system, the author will do a research on the Scheduling Algorithm. Designing Scheduling Algorithm in multi-traffic WCDMA System must take channel condition into account, and differentiate the service to guarantee the demand of QoS, avoid the user’s starvation,meanwhile try to improve the throughput and the fairness of the scheduling in the system as much as possible. Therefore, on the basis of PFS, we proposed a service differentiated proportional fairness scheduling algorithm (CQSSD-PFS) based on C/I, QoS, and starvation weight. It also introduced real time service and system capacitance compensate model. Simulation results showed that effectively insured all kinds of service’s short-term and long-term fairness and the throughput of the system.
In a word, the article provides a theory gist for the mix-traffic UMTS system’s network modeling, traffic modeling and wireless source management
计算机仿真系统的性能分析总是建立在某些假设前提基础上的,例如信道模型、信源模型等等。业务源模型极大地影响到系统性能评估结果的准确程度,因此,建立正确的业务分布模型就成为系统仿真模型中重要的组成部分。本文第三章通过对ON/OFF模型和WWW业务流的分析得到一个与实际无线网络更吻合的三层业务模型,并且利用第二章知识在OPNET上完成UMTS单蜂窝仿真平台的搭建。最后通过OPNET仿真平台上的仿真,证明了三层业务模型比ON/OFF模型更加精确,是一种理想的业务模型。此模型的应用有利于提高无线网络规划与优化的质量和效率。
UMTS中要求能为不同的用户提供多种的通信业务,同时满足不同业务的服务质量要求。在充分利用无线系统资源的基础上,并尽可能地保证用户数据的传输质量,需要对无线资源进行合理的管理与分配。调度算法的研究是无线资源管理的关键部分,本文第四章在WCDMA系统混合业务下研究调度算法,WCDMA系统混合业务下设计调度算法要考虑信道条件,要区分业务保证用户的QoS要求,避免用户“饥饿”现象,同时也要尽可能提高整个系统的吞吐量和调度的公平性。由此,在比例公平调度算法(PFS)基础上基于C/I、QoS、饥饿权重提出区分业务类型的比例公平分组调度算法(CQSSD-PFS),同时引入实时业务和系统容量补偿模型。在第二章建立的UMTS仿真平台上根据第三章的业务模型配置业务,最后对算法进行仿真,仿真结果表明CQSSD-PFS算法可有效确保各类业务之间的短期、长期公平性和较高的系统吞吐量。
总之,本文研究工作为多业务UMTS系统的网络建模、业务建模和无线资源优化管理提供了理论依据。
With the improvement of capability of computer and simulating technology, the use of computer simulation is more and more widely. OPNET is a high trustiness network model, design, simulation and analysis tool. First, This paper main introduce UMTS simulation platform which base on OPNET, and study type traffic point-to-point key performance of the UMTS network,as well as the feasibility base on traffic service QoS’s demand provide vary class service. The simulation results indicate this system simulation platform is effective for UMTS system’s performance analysis, and afford objective, reliable ration warranty for network programming and designing.
The analysis of the performance of computer simulating system are always based on some hypothetic preconditions, for example, channel model、source model, etc. since the traffic model has a great influence on the veracity of the system capability evaluating result, the establish of a correct traffic distributing model becomes an very important part in system simulation model. In part three proposes a three-layer traffic model from analyzing the ON/OFF model and the WWW traffic stream that fit actual wireless traffic better, and build a single cell UMTS simulation plat. Stimulating on the OPNET model proves that three-layer traffic model is more precise than ON/ OFF modeling. It is a kind of ideal traffic model. Applying this model benefit improving quality and efficiency of the wireless network programming and optimizing.
UMTS ask different kinds of service for different users. At the same time, it also requires a high service quality for all kinds of different business. Based on the full use of the wireless resources system, and also make sure the transmitted quality of the users’data, it is necessary to make a reasonable management and admeasure of the wireless resources. The research of the Scheduling Algorithm is the key point of the management of the wireless resources. In the fourth chapter of this paper, based on the mix traffic for WCDMA system, the author will do a research on the Scheduling Algorithm. Designing Scheduling Algorithm in multi-traffic WCDMA System must take channel condition into account, and differentiate the service to guarantee the demand of QoS, avoid the user’s starvation,meanwhile try to improve the throughput and the fairness of the scheduling in the system as much as possible. Therefore, on the basis of PFS, we proposed a service differentiated proportional fairness scheduling algorithm (CQSSD-PFS) based on C/I, QoS, and starvation weight. It also introduced real time service and system capacitance compensate model. Simulation results showed that effectively insured all kinds of service’s short-term and long-term fairness and the throughput of the system.
In a word, the article provides a theory gist for the mix-traffic UMTS system’s network modeling, traffic modeling and wireless source management
引文
[1] Susan Spagnola Rutherford, Steven P. Gordon. Using OPNET to simulate an IP network. Proceedings of the 36th conference on Winter simulation, Dec. 2004 .
[2]裴廷睿,周胜,刘晓宇,吴伟陵.基于BONeS的WCDMA性能分析仿真平台.计算机仿真,2005,22(6):205-209.
[3] Qiang Li , Hongzi Zhu , Meng Zhang , Jiubin Ju. Simulating and Improving Probabilistic Packet Marking Schemes Using Ns2. Sixth International Conference on Parallel and Distributed Computing Applications and Technologies (PDCAT'05), December.2005
[4] B-ISDN ATM Adaptation Layer AAL-1 Specification, ITU-T Recommendation I.363.1, Aug. 1996.
[5] B-ISDN ATM Adaptation Layer AAL 3/4 Specification, ITU-T Recommendation I.363.3/4, Aug. 1996.
[6] B-ISDN ATM Adaptation Layer AAL-5 Specification, ITU-T Recommendation I.363.5, Aug. 1996.
[7] B-ISDN ATM Adaptation Layer Type-2 Specification, ITU-T Recommendation I.363.2, Aug. 1997.
[8] AAL Type2 Signalling Protocol (Capability Set 1), Draft new ITU-T Recommendation Q.aal2, Jan. 1999
[9] Transport Control Signalling Requirements– Signalling Requirements for AAL Type 2 Link Control Capability Set 1, ITU-T Technical Report TRQ.2400, Nov. 1998.
[10] ETSI Mobile Competence Centre. Overview of 3GPP Release 99. Summary of all Release 99 Features 2004.
[11] D. Staehle, K. Leibnitz, and P. Tran-Gia. Source Traffic Modeling of Wireless Applications.Report No.261,University Würzburg. June 2000.
[12] A. Klemm, C. Lindemann, M. Lohmann. Traffic modeling and characterization for UMTS networks.Proceedings of the IEEE Globecom 2001, San Antonio Texas, November 2001
[13] 3GPP, Technical Specification TS22.105-520 V3.10.0. Services and Service Capabilities 2001.
[14] R. van de Meent,M. Mandjes. Evaluation of‘user-oriented’and‘black-box’traffic models for link provisioning. in Proceedings of the1st EuroNGI Conference on Next Generation Internet Networks Traffic Engineering, (Rome, Italy), April 2005
[15] M. Mandjes,R. van de Meent. Inferring traffic characteristics by observing the buffer content distribution. in Proceedings of the 4th International IFIP-TC6 Networking Conference (NETWORKING 2005) (R. B. et al., ed.), no. 3462 in Lecture Notes in Computer Science (LNCS), (Waterloo, Canada), May 2005:303～315
[16] S. Deng. Empirical model of WWW document arrivals at access link. in Proceedings of ICC’96,vol. 3, June 1996:1797～1802
[17] B.Mah.“An empirical model of HTTP network traffic”,in Proceedings of IEEEINFOCOM’97,Kobe, Japan, April 1997:592～600
[18] H .Choi,. J .Limb. A behavioral model of web traffic. International Conference of Networking Protocol 99’(ICNP 99’),Sep 1999
[19] Barford P, Crovella M. Generating representative workloads for network and server performance evaluation. Proceedings of ACM SIGMETRICS 98, June 1998:151～160
[20] D. Staehle, K. Leibnitz, and P. Tran-Gia. Source Traffic Modeling of Wireless Applications”.Report No.261, University Würzburg. June 2000
[21] A. Klemm, C. Lindemann, M. Lohmann. Traffic modeling and characterization for UMTS networks. Proceedings of the IEEE Globecom 2001, San Antonio Texas, November 2001
[22] Michael Jiang, Milan Nikolic,Stephen Hardy, Ljiljana Trajkovic. IMPACT OF SELF-SIMILARITY ON WIRELESS DATA NETWORK PERFORMANCE. In:Proc ICC2001,Finland,June,2001:477～481
[23] W. Willinger, M. S. Taqqu, W. E. Leland, and D. V. Wilson,“Self-Similarity in High-Speed Packet Traffic: Analysis and Modeling of Ethernet Traffic Measurements,”Statist. Sci., vol. 10, no. 1, 1995, pp. 67-85.
[24] J. Beran,“Statistical Methods for Data with Long-Range Dependence,”Statist. Sci., vol. 7, 1992, pp. 404-427.
[25] E. Hurst,“Long-Term Storage Capacity of Reservoirs,”Trans. Amer. Soc. Civil Engineers, vol. 116, 1951, pp. 770-799.
[26] B. B. Mandelbrot and J. R. Wallis,“Some Long-Run Properties of Geophysical Rcords,”Water Resource Research, vol. 5, 1969. pp. 321-340.
[27] E.Hahne,Round Robin.Scheduling for Fair Flow Control in Data Communication Networks. Ph.D.thesis, Dept.Elect.Eng.And Comput.Sci.M.I.T.Dec.1986
[28] S.Lu,V.Bharghavan,R.Srikant.Fair scheduling in Wireless Packet Networks.ACM,1997,8
[29] Yaxin Cao.Scheduling algorithems in broadband wireless networks.Proceedings of the IEEE, 2001, 89(1): 76-87
[30] Daeyoung Park Seo, H. Hojoong Kwon ,Byeong Gi Lee . Wireless packet scheduling based on the cumulative distribution function of user transmission rates. IEEE Transactions on Communications, 2005, 53(11):1919-1929
[31] Lee, B G. QoS Support by Using CDF-Based Wireless Packet Scheduling in Fading Channels. IEEE Transactions on Communications. 2006, 54(5): 955-955.
[32] Fei, X. Marshall, A. Luo, J. DO-WF/sup 2/Q: delay-optimised WF/sup 2/Q packet scheduling. IEEE Proceedings-Communications,2005,152(5):655-660
[33] Ericsson,N.S. Adaptive modulation and scheduling of IP traffic over fading channels.IEEE VTS 50th, vol.2: 849-853
[34] Jalali. Data throughput of CDMA-HDR a high efficiency-high data rate personal communication wireless system.VTC 2000-spring Tokyo, vol.3:1854-1858
[35] Peng Tao,Peng Mugen. Effect of H-ARQ on Pcket Throughput in UTRA TDD HSDPA.CIC2002:1978– 1983
[36] P.Mogensen. High speed downlink packet access(HSDPA)-the path 3.5G.IEEE Workshop onSignal Processing syetem,2001
[37] Yongboon Choi,Youngnam Han. A channel-based scheduling algorithm for CDMA2000 1xEV-DO system. Wireless personal Multimedia Communication,2002,Volume2:621-625
[38] 3GPP TS25.101,UE Radio Transmission and Reception.2001.
[2]裴廷睿,周胜,刘晓宇,吴伟陵.基于BONeS的WCDMA性能分析仿真平台.计算机仿真,2005,22(6):205-209.
[3] Qiang Li , Hongzi Zhu , Meng Zhang , Jiubin Ju. Simulating and Improving Probabilistic Packet Marking Schemes Using Ns2. Sixth International Conference on Parallel and Distributed Computing Applications and Technologies (PDCAT'05), December.2005
[4] B-ISDN ATM Adaptation Layer AAL-1 Specification, ITU-T Recommendation I.363.1, Aug. 1996.
[5] B-ISDN ATM Adaptation Layer AAL 3/4 Specification, ITU-T Recommendation I.363.3/4, Aug. 1996.
[6] B-ISDN ATM Adaptation Layer AAL-5 Specification, ITU-T Recommendation I.363.5, Aug. 1996.
[7] B-ISDN ATM Adaptation Layer Type-2 Specification, ITU-T Recommendation I.363.2, Aug. 1997.
[8] AAL Type2 Signalling Protocol (Capability Set 1), Draft new ITU-T Recommendation Q.aal2, Jan. 1999
[9] Transport Control Signalling Requirements– Signalling Requirements for AAL Type 2 Link Control Capability Set 1, ITU-T Technical Report TRQ.2400, Nov. 1998.
[10] ETSI Mobile Competence Centre. Overview of 3GPP Release 99. Summary of all Release 99 Features 2004.
[11] D. Staehle, K. Leibnitz, and P. Tran-Gia. Source Traffic Modeling of Wireless Applications.Report No.261,University Würzburg. June 2000.
[12] A. Klemm, C. Lindemann, M. Lohmann. Traffic modeling and characterization for UMTS networks.Proceedings of the IEEE Globecom 2001, San Antonio Texas, November 2001
[13] 3GPP, Technical Specification TS22.105-520 V3.10.0. Services and Service Capabilities 2001.
[14] R. van de Meent,M. Mandjes. Evaluation of‘user-oriented’and‘black-box’traffic models for link provisioning. in Proceedings of the1st EuroNGI Conference on Next Generation Internet Networks Traffic Engineering, (Rome, Italy), April 2005
[15] M. Mandjes,R. van de Meent. Inferring traffic characteristics by observing the buffer content distribution. in Proceedings of the 4th International IFIP-TC6 Networking Conference (NETWORKING 2005) (R. B. et al., ed.), no. 3462 in Lecture Notes in Computer Science (LNCS), (Waterloo, Canada), May 2005:303～315
[16] S. Deng. Empirical model of WWW document arrivals at access link. in Proceedings of ICC’96,vol. 3, June 1996:1797～1802
[17] B.Mah.“An empirical model of HTTP network traffic”,in Proceedings of IEEEINFOCOM’97,Kobe, Japan, April 1997:592～600
[18] H .Choi,. J .Limb. A behavioral model of web traffic. International Conference of Networking Protocol 99’(ICNP 99’),Sep 1999
[19] Barford P, Crovella M. Generating representative workloads for network and server performance evaluation. Proceedings of ACM SIGMETRICS 98, June 1998:151～160
[20] D. Staehle, K. Leibnitz, and P. Tran-Gia. Source Traffic Modeling of Wireless Applications”.Report No.261, University Würzburg. June 2000
[21] A. Klemm, C. Lindemann, M. Lohmann. Traffic modeling and characterization for UMTS networks. Proceedings of the IEEE Globecom 2001, San Antonio Texas, November 2001
[22] Michael Jiang, Milan Nikolic,Stephen Hardy, Ljiljana Trajkovic. IMPACT OF SELF-SIMILARITY ON WIRELESS DATA NETWORK PERFORMANCE. In:Proc ICC2001,Finland,June,2001:477～481
[23] W. Willinger, M. S. Taqqu, W. E. Leland, and D. V. Wilson,“Self-Similarity in High-Speed Packet Traffic: Analysis and Modeling of Ethernet Traffic Measurements,”Statist. Sci., vol. 10, no. 1, 1995, pp. 67-85.
[24] J. Beran,“Statistical Methods for Data with Long-Range Dependence,”Statist. Sci., vol. 7, 1992, pp. 404-427.
[25] E. Hurst,“Long-Term Storage Capacity of Reservoirs,”Trans. Amer. Soc. Civil Engineers, vol. 116, 1951, pp. 770-799.
[26] B. B. Mandelbrot and J. R. Wallis,“Some Long-Run Properties of Geophysical Rcords,”Water Resource Research, vol. 5, 1969. pp. 321-340.
[27] E.Hahne,Round Robin.Scheduling for Fair Flow Control in Data Communication Networks. Ph.D.thesis, Dept.Elect.Eng.And Comput.Sci.M.I.T.Dec.1986
[28] S.Lu,V.Bharghavan,R.Srikant.Fair scheduling in Wireless Packet Networks.ACM,1997,8
[29] Yaxin Cao.Scheduling algorithems in broadband wireless networks.Proceedings of the IEEE, 2001, 89(1): 76-87
[30] Daeyoung Park Seo, H. Hojoong Kwon ,Byeong Gi Lee . Wireless packet scheduling based on the cumulative distribution function of user transmission rates. IEEE Transactions on Communications, 2005, 53(11):1919-1929
[31] Lee, B G. QoS Support by Using CDF-Based Wireless Packet Scheduling in Fading Channels. IEEE Transactions on Communications. 2006, 54(5): 955-955.
[32] Fei, X. Marshall, A. Luo, J. DO-WF/sup 2/Q: delay-optimised WF/sup 2/Q packet scheduling. IEEE Proceedings-Communications,2005,152(5):655-660
[33] Ericsson,N.S. Adaptive modulation and scheduling of IP traffic over fading channels.IEEE VTS 50th, vol.2: 849-853
[34] Jalali. Data throughput of CDMA-HDR a high efficiency-high data rate personal communication wireless system.VTC 2000-spring Tokyo, vol.3:1854-1858
[35] Peng Tao,Peng Mugen. Effect of H-ARQ on Pcket Throughput in UTRA TDD HSDPA.CIC2002:1978– 1983
[36] P.Mogensen. High speed downlink packet access(HSDPA)-the path 3.5G.IEEE Workshop onSignal Processing syetem,2001
[37] Yongboon Choi,Youngnam Han. A channel-based scheduling algorithm for CDMA2000 1xEV-DO system. Wireless personal Multimedia Communication,2002,Volume2:621-625
[38] 3GPP TS25.101,UE Radio Transmission and Reception.2001.