Traffic modeling and weighted fair queueing performance analysis and practice in telecommunications

CHEN Gang, XIA Li, JIANG Zhaoyu, PENG Xi, XU Huiying

Systems Engineering - Theory & Practice ›› 2024, Vol. 44 ›› Issue (4) : 1335-1348.

PDF(528 KB)
PDF(528 KB)
Systems Engineering - Theory & Practice ›› 2024, Vol. 44 ›› Issue (4) : 1335-1348. DOI: 10.12011/SETP2023-0388

Traffic modeling and weighted fair queueing performance analysis and practice in telecommunications

  • CHEN Gang1, XIA Li2, JIANG Zhaoyu3, PENG Xi4, XU Huiying5
Author information +
History +

Abstract

The internet traffic model and queueing performance evaluation are the key issues for quality of service (QoS) management and scheduling management of bandwidth.In 2019,they are also proposed by the Huawei company as one of the ten challenging problems in telecommunication area.Based on a practical project from the Huawei company,we study the traffic modeling and queueing performance evaluation in telecommunications.Unlike the classic voice flows,the high-speed traffic flows involve some statistical properties such as the correlation and burstiness.This case activates us to study the more general traffic model.In this paper,we propose a new parameter fitting approach of the batch Markov arrival process (BMAP).Based on the service mechanism of traffic flows in routers,this paper deals with a BMAP/PH/1 queueing system under weighted fair queueing (WFQ) discipline.We derive the stationary queue length distribution and performance measures (the expected queue length and delay,etc.).Finally,the performance of our proposed fitting approach is illustrated by using the teletraffic traces testing from the Huawei company.We show the effectiveness of the proposed model and the applicability of the analysis results obtained in the study via numerical and simulation experiments.

Key words

queueing theory / Markov arrival process / weighted fair queueing / network traffic modeling

Cite this article

Download Citations
CHEN Gang , XIA Li , JIANG Zhaoyu , PENG Xi , XU Huiying. Traffic modeling and weighted fair queueing performance analysis and practice in telecommunications. Systems Engineering - Theory & Practice, 2024, 44(4): 1335-1348 https://doi.org/10.12011/SETP2023-0388

References

[1] 韦烜,阮科,黄晓莹,等. IP骨干网流量的自动化预测[J].电信科学, 2020, 36(8):175-183.
Wei X, Ruan K, Huang X Y, et al. Automatic prediction for IP backbone network traffic[J]. Telecommunications Science, 2020, 36(8):175-183.
[2] 王朝静,董康银,董聪,等.信息不确定下川藏铁路防灾监测通信系统带宽资源动态配置优化研究[J].系统工程理论与实践, 2021, 41(10):2721-2732.
Wang Z J, Dong K Y, Dong C, et al. Dynamic optimization of the bandwidth allocation of disaster monitoring communication system for Sichuan-Tibet railway under information uncertainty[J]. Systems Engineering—Theory & Practice, 2021, 41(10):2721-2732.
[3] 肖军弼,魏娇娇.面向数据挖掘的网络流量分析及预测研究综述[J].计算机与数字工程, 2023, 51(2):372-379.
Xiao J B, Wei J J. Survey of data mining-oriented network traffic analysis and prediction research[J]. Computer & Digital Engineering, 2023, 51(2):372-379.
[4] 张宾,杨家海,吴建平. Internet流量模型分析与评述[J].软件学报, 2011, 22(1):115-131.
Zhang B, Yang J H, Wu J P. Survey and analysis on the internet traffic model[J]. Journal of Software, 2011, 22(1):115-131.
[5] Almousa S A D, Horváth G, Telek M. Parameter estimation of Markov modulated fluid arrival processes[J]. Performance Evaluation, 2022, 157:102316.
[6] Li C, Zheng J, Okamura H, et al. Parameter estimation of markovian arrivals with utilization data[J]. IEICE Transactions on Communications, 2022, 105(1):1-10.
[7] Telek M, Horváth G. A minimal representation of Markov arrival processes and a moments matching method[J]. Performance Evaluation, 2007, 64(9-12):1153-1168.
[8] Kim S. Minimal LST representations of MAP (n) s:Moment fittings and queueing approximations[J]. Naval Research Logistics, 2016, 63(7):549-561.
[9] Buchholz P, Panchenko A. A two-step EM algorithm for MAP fitting[C]//International Symposium on Computer and Information Sciences. Springer, Berlin, Heidelberg, 2004:217-227.
[10] Casale G, Sansottera A, Cremonesi P. Compact Markov-modulated models for multiclass trace fitting[J]. European Journal of Operational Research, 2016, 255(3):822-833.
[11] Horváth G, Telek M. BuTools 2:A rich toolbox for Markovian performance evaluation[C]//Tenth EAI International Conference on Performance Evaluation Methodologies and Tools, 2017:137-142.
[12] Casale G, Zhang E Z, Smirni E. KPC-Toolbox:Best recipes for automatic trace fitting using Markovian arrival processes[J]. Performance Evaluation, 2010, 67(9):873-896.
[13] Okamura H, Dohi T. Mapfit:An R-based tool for PH/MAP parameter estimation[C]//International Conference on Quantitative Evaluation of Systems, 2015:105-112.
[14] Klemm A, Lindemann C, Lohmann M. Modeling IP traffic using the batch Markovian arrival process[J]. Performance Evaluation, 2003, 54(2):149-173.
[15] Yera Y G, Lillo R E, Ramírez-Cobo P. Fitting procedure for the two-state batch Markov modulated Poisson process[J]. European Journal of Operational Research, 2019, 279(1):79-92.
[16] Buchholz P, Kemper P, Kriege J. Multi-class Markovian arrival processes and their parameter fitting[J]. Performance Evaluation, 2010, 67(11):1092-1106.
[17] Boussada M E H, Garcia J M, Frikha M. New fluid approaches for studying the performance of elastic traffic under class based weighed fair queuing system[J]. International Journal of Network Management, 2018, 28(6):e2037.
[18] Wang P, Jiang Z, Qi M, et al. Uncertainty-aware weighted fair queueing for routers based on deep reinforcement learning[C]//2021 IEEE 4th International Conference on Electronics and Communication Engineering, IEEE, 2021:1-7.
[19] Shortle J F, Fischer M J. Approximation for a two-class weighted fair queueing discipline[J]. Performance Evaluation, 2010, 67(10):946-958.
[20] Mahmood D A, Horváth G. A simple approximation for the response times in the two-class weighted fair queueing system[C]//International Conference on Analytical and Stochastic Modeling Techniques and Applications. Springer, Cham, 2017:125-137.
[21] Okamura H, Dohi T. Fitting phase-type distributions and Markovian arrival processes:Algorithms and tools[M]//Principles of Performance and Reliability Modeling and Evaluation. Springer, Cham, 2016:49-75.
[22] Vishnevskii V M, Dudin A N. Queueing systems with correlated arrival flows and their applications to modeling telecommunication networks[J]. Automation and Remote Control, 2017, 78(8):1361-1403.
[23] Dudin A, Klimenok V. Analysis of MAP/G/1 queue with inventory as the model of the node of wireless sensor network with energy harvesting[J]. Annals of Operations Research, 2023, 331(2):839-866.
[24] Krishnamoorthy A, Joshua A N. A BMAP/BMSP/1 queue with Markov dependent arrival and Markov dependent service batches[J]. Journal of Industrial and Management Optimization, 2021, 17(5):2925-2941.
[25] Kumar N, Gupta U C. Analysis of BMAP/MSP/1 queue with MAP generated negative customers and disasters[J]. Communications in Statistics——Theory and Methods, 2023, 52(12):4283-4309.
[26] Rodríguez J, Lillo R E, Ramírez-Cobo P. Nonidentifiability of the two-state BMAP[J]. Methodology and Computing in Applied Probability, 2016, 18(1):81-106.
[27] He Q M. Fundamentals of matrix-analytic methods[M]. New York:Springer, 2014.
[28] 张玉英,岳德权.基于服务员休假和等待销售的易逝品排队库存系统的稳态分析[J].系统工程理论与实践, 2021, 41(6):1556-1569.
Zhang Y Y, Yue D Q. Steady state analysis of perishable queueing-inventory system with server's vacation and backorder[J]. Systems Engineering—Theory & Practice, 2021, 41(6):1556-1569.
[29] Phung-Duc T, Masuyama H, Kasahara S, et al. A simple algorithm for the rate matrices of level-dependent QBD processes[C]//Proceedings of the 5th International Conference on Queueing Theory and Network Applications. 2010:46-52.

Funding

National Natural Science Foundation of China (72342006,72371253,72201072);Regional Joint Foundation of Guangdong Province (2022A1515110725)
PDF(528 KB)

368

Accesses

0

Citation

Detail

Sections
Recommended

/