基于网络流量水平等级预测的自适应随机早期检测算法

doi:10.11959/j.issn.1000-436x.2023092

Abstract

Abstract:

In view of the problem that the calculation of average queue length and maximum packet drop probability in random early detection algorithm and its variants reflect the changes of network traffic slowly, an adaptive random early detection algorithm based on network traffic level grade prediction was proposed.Based on the statistical characteristics of self-similar network traffic, the transition probability table of network traffic level grade was established, and a grade prediction method of self-similar network traffic level with low complexity and high accuracy was proposed.Furthermore, the prediction results were applied to calculate the average queue length in equal interval and adjust the maximum packet drop probability.Under the condition of fixed and variable bottleneck link capacity, it is found that regardless of the degree of self-similarity of network traffic, the proposed algorithm can improve the throughput and packet loss rate, especially when the Hurst parameter is large and the traffic is light.

Key words: active queue management, network traffic, self-similar, traffic level grade prediction

CLC Number:

TP393

Debin WEI, Chengsheng PAN, Li YANG, Zuoren YAN. Adaptive random early detection algorithm based on network traffic level grade prediction[J]. Journal on Communications, 2023, 44(6): 154-166.

Figures/Tables 18

L₁					L₂
L₁	1	2	3	4	5	6	7	8	$\bar{l}$
1	0.24	0.65	0.12	0	0	0	0	0	1.88
2	0.03	0.34	0.53	0.09	0	0	0	0	2.69
3	0	0.07	0.48	0.40	0.05	0	0	0	3.43
4	0	0	0.16	0.55	0.27	0.02	0	0	4.14
5	0	0	0.02	0.28	0.54	0.15	0	0	4.85
6	0	0	0	0.05	0.39	0.46	0.10	0	5.61
7	0	0	0	0	0.09	0.51	0.36	0.04	6.35
8	0	0	0	0	0	0.13	0.55	0.33	7.20

L₁					L₂
L₁	1	2	3	4	5	6	7	8	$\bar{l}$
1	0	0	0.25	0.44	0.25	0.06	0	0	4.13
2	0	0.04	0.22	0.42	0.26	0.07	0	0	4.12
3	0	0.03	0.18	0.40	0.30	0.09	0.01	0	4.27
4	0	0.02	0.16	0.37	0.33	0.11	0.02	0	4.39
5	0	0.01	0.13	0.33	0.35	0.15	0.03	0	4.58
6	0	0.01	0.09	0.30	0.37	0.19	0.04	0.01	4.78
7	0	0.01	0.07	0.19	0.43	0.24	0.05	0.02	5.05
8	0	0	0.06	0.14	0.33	0.41	0.06	0	5.27

References 34

[1]	JUNG S , KIM J , KIM J H . Intelligent active queue management for stabilized QoS guarantees in 5G mobile networks[J]. IEEE Systems Journal, 2021,15(3): 4293-4302.
[2]	IRAZABAL M , LOPEZ-AGUILERA E , DEMIRKOL I ,et al. Dynamic buffer sizing and pacing as enablers of 5G low-latency services[J]. IEEE Transactions on Mobile Computing, 2022,21(3): 926-939.
[3]	BARCZYK M , CHYDZINSKI A . AQM based on the queue length:a real-network study[J]. PLOS ONE, 2022,17(2): e0263407.
[4]	ZHOU K , YEUNG K L , LI V . Nonlinear RED:a simple yet efficient active queue management scheme[J]. Computer Networks, 2006,50(18): 3784-3794.
[5]	TAHILIANI M P , SHET K C , BASAVARAJU T G . CARED:cautious adaptive RED gateways for TCP/IP networks[J]. Journal of Network and Computer Applications, 2012,35(2): 857-864.
[6]	BAKLIZI M . Weight queue dynamic active queue management algorithm[J]. Symmetry, 2020,12:2077.
[7]	KUNNIYUR S S , SRIKANT R . An adaptive virtual queue (AVQ) algorithm for active queue management[J]. IEEE/ACM Transactions on Networking, 2004,12(2): 286-299.
[8]	YE J C , LEUNG K C . Adaptive and stable delay control for combating bufferbloat:theory and algorithms[J]. IEEE Systems Journal, 2020,14(1): 1285-1296.
[9]	SANTOS C , SILVA C , PEDROSO C M . Improving perceived quality of live adaptative video streaming[J]. Entropy, 2021,23(8): 948.
[10]	KIM M , JASEEMUDDIN M , ANPALAGAN A . Deep reinforcement learning based active queue management for IoT networks[J]. Journal of Network and Systems Management, 2021,29(3): 1-28.
[11]	PAN C S , ZHANG S , ZHAO C ,et al. A novel active queue management algorithm based on average queue length change rate[J]. IEEE Access, 2022,10: 75558-75570.
[12]	ABU-SHAREHA A A . Integrated random early detection for congestion control at the router buffer[J]. Computer Systems Science and Engineering, 2022,40(2): 719-733.
[13]	ABUALHAJ M M , ABU-SHAREHA A A , AL-TAHRAWI M M . FLRED:an efficient fuzzy logic based network congestion control method[J]. Neural Computing and Applications, 2018,30(3): 925-935.
[14]	LELAND W E , TAQQU M S , WILLINGER W ,et al. On the self-similar nature of Ethernet traffic[J]. IEEE/ACM Transactions on Networking, 1994,2(1): 1-15.
[15]	PARK K , KIM G , CROVELLA M . On the effect of traffic self-similarity on network performance[C]// Proceedings of the SPIE International Conference Performance and Control of Network Systems. Bellingham:SPIE Press, 1997: 168-175.
[16]	NORROS I . On the use of fractional Brownian motion in the theory of connectionless networks[J]. IEEE Journal on Selected Areas in Communications, 1995,13(6): 953-962.
[17]	XU X D , GENG C M , ZHU S R ,et al. An improved RED algorithm based on ascending semi-Cauchy distribution and EBP[C]// Proceedings of 11th IEEE Singapore International Conference on Communication Systems. Piscataway:IEEE Press, 2009: 294-298.
[18]	TAN X H , HUANG Y H . Parameters setting scheme of RED with long-range dependent traffic input[C]// Proceedings of 2009 5th International Conference on Wireless Communications,Networking and Mobile Computing. Piscataway:IEEE Press, 2009: 1-4.
[19]	王晖, 季振洲, 孙彦东 ,等. 基于时间槽的自相似流量随机早检测算法—SFRED[J]. 通信学报, 2010,31(10): 115-120.
	WANG H , JI Z Z , SUN Y D ,et al. Time slot-based RED algorithm on self-similar flows:SFRED[J. Journal on Communications, 2010,31(10): 115-120.
[20]	别玉霞, 潘成胜, 刘海燕 ,等. 基于 AOS 的 Hurst-优先级自适应RED与动态调度算法[J]. 通信学报, 2012,33(10): 160-169.
	BIE Y X , PAN C S , LIU H Y ,et al. Hurst and priority adaptive RED combined with dynamic scheduling algorithm based on AOS[J. Journal on Communications, 2012,33(10): 160-169.
[21]	MAREK D , SZYGU?A J , DOMA?SKI A ,et al. Adaptive Hurst-sensitive active queue management[J]. Entropy, 2022,24(3): 418.
[22]	DOMA?SKI A , DOMA?SKA J , CZACHóRSKI T ,et al. The influence of the traffic self-similarity on the choice of the non-integer order PIα controller parameters[C]// Proceedings of the 32nd International Symposium at the IFIP World Computer Congress. Cham:Springer, 2018: 76-83.
[23]	LIU H , YAN W . An adaptive proportional integral active queue management algorithm based on self-similar traffic rate estimation in WSN[J]. KSII Transactions on Internet and Information Systems, 2011,5(11): 1946-1958.
[24]	GAO Y , HE G H , HOU J C . On exploiting traffic predictability in active queue management[C]// Proceedings of Annual Joint Conference of the IEEE Computer and Communications Societies. Piscataway:IEEE Press, 2002: 1630-1639.
[25]	AMIN F , MIZANIAN K . Buffer management for self-similar network traffic[C]// Proceedings of the 6th International Symposium on Telecommunications. Piscataway:IEEE Press, 2013: 737-742.
[26]	温昱晖, 朱祥华, 张勇 . 自相似流量的主动队列管理算法[J]. 电子与信息学报, 2006,28(7): 1303-1307.
	WEN Y H , ZHU X H , ZHANG Y . Self-similar traffic control in active queue management[J. Journal of Electronics ＆ Information Technology, 2006,28(7): 1303-1307.
[27]	BIE Y X , LI Z H , HU Z ,et al. Queue management algorithm for satellite networks based on traffic prediction[J]. IEEE Access, 2022,10: 54313-54324.
[28]	DOMA?SKI A , DOMA?SKA J , CZACHóRSKI T ,et al. The use of a non-integer order PI controller with an active queue management mechanism[J]. International Journal of Applied Mathematics and Computer Science, 2016,26(4): 777-789.
[29]	SZYGU?A J , DOMA?SKI A , DOMA?SKA J ,et al. Supervised learning of neural networks for active queue management in the internet[J]. Sensors, 2021,21(15): 4979.
[30]	TAQQU M S , WILLINGER W , SHERMAN R . Proof of a fundamental result in self-similar traffic modeling[J]. ACM SIGCOMM Computer Communication Review, 1997,27(2): 5-23.
[31]	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.
[32]	魏德宾, 沈婷, 杨力 ,等. 基于自相似流量水平分级预测的网络队列调度算法[J]. 通信学报, 2020,41(4): 182-189
	WEI D B , SHEN T , YANG L ,et al. Network queue scheduling algorithm based on self-similar traffic level grading prediction[J. Journal on Communications, 2020,41(4): 182-189
[33]	PARK K , TUAN T . Performance evaluation of multiple time scale TCP under self-similar traffic conditions[J]. ACM Transactions on Modeling and Computer Simulation, 2000,10(2): 152-177.
[34]	FIROIU V , BORDEN M . A study of active queue management for congestion control[C]// Proceedings of the Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Piscataway:IEEE Press, 2002: 1435-1444.

Metrics

Recommended 0

No Suggested Reading articles found!

算法	丢包量/个	丢包率
CARED	33 562	3.40%
文献[21]算法	32 931	3.47%
文献[27]算法	32 895	3.40%
本文算法	32 623	3.37%

连接数目/条	CARED/ms	文献[21]算法/ms	文献[27]算法/ms	TLGP-ARED-1/ms	Imp1	Imp2	Imp3
10	45.6	45.5	45.5	45.4	0.44%	0.22%	0.22%
20	63.0	64.7	63.2	63.4	-0.63%	2.01%	-0.32%
30	62.4	65.4	62.8	64.2	-2.88%	1.83%	-2.23%
60	62.9	65.8	64.6	64.5	-2.54%	1.98%	0.15%
80	64.2	66.9	65.1	64.8	-0.94%	3.13%	0.46%
90	64.6	68.2	65.6	65.2	-0.93%	4.40%	0.61%

连接数目/条	CARED	文献[21]算法	文献[27]算法	TLGP-ARED-1	Imp1	Imp2	Imp3
10	0.189%	0.358%	0.678%	0.238%	-0.049%	0.120%	0.440%
20	0.789%	0.980%	0.834%	0.801%	-0.012%	0.179%	0.033%
30	0.874%	0.947%	0.800%	0.804%	0.070%	0.143%	-0.004%
60	0.824%	0.948%	0.814%	0.801%	0.023%	0.147%	0.013%
80	0.837%	0.948%	0.817%	0.803%	0.034%	0.145%	0.014%
90	0.859%	0.950%	0.817%	0.769%	0.090%	0.181%	0.048%

连接数目/条	CARED/(kbit·s^-1)	文献[21]算法/(kbit·s^-1)	文献[27]算法/(kbit·s^-1)	TLGP-ARED-1/(kbit·s^-1)	Imp1	Imp2	Imp3
10	1 291.44	1 329.03	1 176.30	1 333.76	3.28%	0.36%	13.39%
20	1 326.75	1 293.24	1 277.88	1 359.80	2.49%	5.15%	6.41%
30	1 347.01	1 301.95	1 364.41	1 342.28	-0.35%	3.10%	-1.62%
60	1 316.24	1 311.70	1 301.08	1 346.16	2.27%	2.63%	3.46%
80	1 321.56	1 324.33	1 316.70	1 329.85	0.63%	0.42%	1.00%
90	1 309.05	1 332.81	1 308.08	1 310.38	0.10%	-1.68%	0.18%

连接数目/条	CARED/ms	文献[21]算法/ms 文献[27]算法/ms TLGP-ARED-1	Imp1	Imp2	Imp3
10	44.66	41.9141.5243.23	3.20%	-3.15%	-4.12%
20	63.21	67.6265.0966.45	-5.13%	1.73%	-2.09%
30	64.54	68.1964.1963.43	1.72%	6.98%	1.18%
60	64.65	68.1265.2364.60	0.08%	5.17%	0.97%
80	64.74	68.1665.4364.83	-0.14%	4.89%	0.92%
90	63.21	68.1865.9864.76	-2.45%	5.02%	1.85%

Adaptive random early detection algorithm based on network traffic level grade prediction

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 18

References 34

Related Articles 15

Metrics

Recommended 0

比较项目	TLGP-ARED-1	TLGP-ARED-2	TLGP-ARED	Imp1	Imp2	Imp3
时延/ms	57.4	56.5	56.7	1.57%	1.22%	-0.35%
时延标准差/ms	4.1	3.9	3.8	4.88%	7.31%	2.56%
丢包率	1.53%	1.99%	1.84%	-0.46%	-0.31%	0.15%
吞吐量/(kbit·s^-1)	1 486.5	1 529.6	1 631.3	2.90%	9.74%	6.65%

[1]	Yifeng WANG, Yuanbo GUO, Qingli CHEN, Chen FANG, Renhao LIN, Yongliang ZHOU, Jiali MA. Method based on contrastive incremental learning for fine-grained malicious traffic classification [J]. Journal on Communications, 2023, 44(3): 1-11.
[2]	Xueyuan DUAN, Yu FU, Kun WANG, Taotao LIU, Bin LI. Network traffic anomaly detection method based on multi-scale characteristic [J]. Journal on Communications, 2022, 43(10): 65-76.
[3]	Yongjin HU,Yuanbo GUO,Jun MA,Han ZHANG,Xiuqing MAO. Method to generate cyber deception traffic based on adversarial sample [J]. Journal on Communications, 2020, 41(9): 59-70.
[4]	Debin WEI,Ting SHEN,Li YANG,Yaowen QI. Network queue scheduling algorithm based on self-similar traffic level grading prediction [J]. Journal on Communications, 2020, 41(4): 182-189.
[5]	Jie WANG,Lili YANG,Min YANG. Multitier ensemble classifiers for malicious network traffic detection [J]. Journal on Communications, 2018, 39(10): 155-165.
[6]	Yong WANG,Huiyi ZHOU,Hao FENG,Miao YE,Wenlong KE. Network traffic classification method basing on CNN [J]. Journal on Communications, 2018, 39(1): 14-23.
[7]	Cheng-long SU,Guang JIN,Xian-liang JIANG,Jun NIU. Active queue management algorithm focusing on fairness and low delay [J]. Journal on Communications, 2017, 38(5): 199-206.
[8]	Cai-xia SONG,Guo-zhen TAN,Nan DING,Jun-ling BU,Fu-xin ZHANG,Ming-jian LIU. Application oriented cross-layer multi-channel MAC protocol for VANET [J]. Journal on Communications, 2016, 37(5): 95-105.
[9]	Zhong-da TIAN,Shu-jiang LI,Yan-hong WANG,Xiang-dong WANG. Network traffic multi-step prediction based on chaos theory and improved echo state network [J]. Journal on Communications, 2016, 37(3): 55-70.
[10]	Yu-fei ZHAO,Gang XIONG,Long-tao HE,Zhou-jun LI. Approach to detecting SQL injection behaviors in network environment [J]. Journal on Communications, 2016, 37(2): 89-98.
[11]	. Abnormal network traffic detection approach based on alive entropy [J]. Journal on Communications, 2013, 34(Z2): 11-57.
[12]	Xiang-kun MU,Jin-song WANG,Yu-feng XUE,Wei HUANG. Abnormal network traffic detection approach based on alive entropy [J]. Journal on Communications, 2013, 34(Z2): 51-57.
[13]	. Self-organized CAC mechanism adopting for self-similarity service in wireless network [J]. Journal on Communications, 2013, 34(8): 4-34.
[14]	Lei FENG,Wen-jing LI,Xue-song QIU. Self-organized CAC mechanism adopting for self-similarity service in wireless network [J]. Journal on Communications, 2013, 34(8): 27-34.
[15]	Tong GUO,Ju-long LAN,Wan-wei HUANG,Zhen ZHANG. Analysis the self-similarity of network traffic in fractional Fourier transform domain [J]. Journal on Communications, 2013, 34(6): 38-48.

连接数目/条	CARED	文献[21]算法	文献[27]算法 TLGP-ARED-1	Imp1	Imp2	Imp3
10	0.092%	0.044%	0.013%0.043%	0.049%	0.001%	-0.030%
20	0.722%	1.188%	0.783%0.837%	-0.115%	0.351%	-0.054%
30	0.839%	1.321%	0.836%0.782%	0.057%	0.539%	0.054%
60	0.845%	1.215%	0.892%0.779%	0.066%	0.436%	0.113%
80	0.812%	1.238%	0.887%0.786%	0.026%	0.452%	0.101%
90	0.802%	1.242%	0.885%0.779%	0.023%	0.463%	0.106%

连接数目/条	CARED/(kbit·s^-1)	文献[21]算法/(kbit·s^-1)	文献[27]算法/(kbit·s^-1)	TLGP-ARED-1/(kbit·s^-1)	Imp1	Imp2	Imp3
10	1 250.92	1 223.45	1 234.076	1 250.27	-0.05%	2.19%	1.31%
20	1 344.93	1 306.76	1 298.643	1 311.52	-2.48%	0.36%	0.99%
30	1 290.12	1 298.02	1 366.146	1 342.76	4.08%	3.45%	-1.71%
60	1 280.69	1 278.48	1 295.14	1 308.29	2.16%	2.33%	1.02%
80	1 293.75	1 279.76	1 297.34	1 312.35	1.44%	2.55%	1.16%
90	1 305.45	1 275.52	1 275.827	1 307.82	0.18%	2.53%	2.51%