基于LSTM流量预测的路由规划和切换

doi:10.11959/j.issn.1000-0801.2022172

Abstract

Abstract:

With the continuous development and evolution of network technology in recent years, the user’s demand for network resources is becoming larger and larger, and the content is becoming more and more complex.The traditional network architecture is difficult to meet the current flexible network needs.The revolutionary technology of SDN endows the network with programm ability and evolvability, and realizes more flexible management of network resources.In order to improve the utilization of network resources, a traffic prediction agent based on LSTM model was proposed, which provides a theoretical basis for routing planning.By predicting the network traffic in advance, we can take defensive measures before the traffic surge to ensure the security and stability of the network.The function of route planning and lossless path switching based on traffic prediction was realized.

Key words: software defined network, traffic prediction, routing planning, paths witching, LSTM model

CLC Number:

TP393

Bin ZHUGE, Linchao WANG, Yang SONG, Yu SHAO, Ligang DONG, Xian JIANG. Routing planning and handoff based on LSTM traffic prediction[J]. Telecommunications Science, 2022, 38(8): 86-100.

Figures/Tables 21

References 10

[1]	张朝昆, 崔勇, 唐翯翯 ,等. 软件定义网络(SDN)研究进展[J]. 软件学报, 2015,26(1): 62-81.
	ZHANG C K , CUI Y , ANGH H . State-of-the-art survey on software-defined networking(SDN)[J]. Journal of Software, 2015,26(1): 62-81.
[2]	UHLIG S , QUOITIN B , LEPROPRE J ,et al. Providing public intradomain traffic matrices to the research community[J]. ACM SIGCOMM Computer Communication Review, 2006,36(1): 83-86.
[3]	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997,9(8): 1735-1780.
[4]	BENGIO Y , COURVILLE A , VINCENT P . Representation learning:a review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(8): 1798-1828.
[5]	贺小伟, 徐靖杰, 王宾 ,等. 基于GRU-LSTM组合模型的云计算资源负载预测研究[J]. 计算机工程, 2022,48(5): 11-17,34.
	HE X W , XU J J , WANG B ,et al. Research on cloud computing resource load forecasting based on GRU-LSTM combination model[J]. Computer Engineering, 2022,48(5): 11-17,34.
[6]	杜秀丽, 陶帆, 范志宇 ,等. 面向骨干网流量的非线性组合预测方法[J]. 小型微型计算机系统, 2021(4): 1-7.
	DU X L , TAO F , FAN Z Y ,et al. Nonlinear Combined Prediction Method for Backbone Network Traffic[J]. Small Microcomputer System, 2021(4): 1-7.
[7]	刘振鹏, 张庆文, 李明 ,等. 基于蚁群优化算法的 SDN 路由策略[J]. 昆明理工大学学报(自然科学版), 2022,47(3): 60-66.
	LIU Z P , ZHANG Q W , LI M ,et al. SDN routing strategy based on ant colony optimization algorithm[J]. Journal of Kunming University of science and Technology (Natural Science edition), 2022,47(3): 60-66.
[8]	宋永辉 . 认知无线网络中基于人工智能算法的流量预测和数据传输机制研究[D]. 重庆:重庆邮电大学, 2017.
	SONG Y H . Research on mechanism of traffic prediction and data transmission based on artificial intelligence algorithm in cognitive wireless network[D]. Chongqing:Chongqing University of Posts and Telecommunications, 2017.
[9]	汪尧, 黄宁, 武润升 ,等. 基于改进自回归差分移动平均模型的网络流量预测[J]. 通信技术, 2021,54(12): 2626-2631.
	WANG Y , HUANG N , WU R S ,et al. An improved autoregressive integrated moving average model for network traffic prediction[J]. Communications Technology, 2021,54(12): 2626-2631.
[10]	刘庆杰, 王小英, 王茂发 . 基于BP算法和ACO算法的故障诊断推理研究[J]. 计算机测量与控制, 2012,20(6): 1460-1462,1466.
	LIU Q J , WANG X Y , WANG M F . Research on reasoning for fault diagnosis based on BP and ACO algorisms[J]. Computer Measurement ＆ Control, 2012,20(6): 1460-1462,1466.

Metrics

Recommended 0

No Suggested Reading articles found!

统计编号	线路1流通量	统计编号	线路1流通量
1	67 746.500 0	11	60 187.555 6
2	66 788.506 7	12	53 070.968 9
3	59 951.386 7	13	53 844.088 9
4	147 980.524 4	14	58 859.048 9
5	142 226.871 1	15	121 630.168 9
6	170 772.764 4	16	130 752.986 7
7	174 522.826 7	17	134 375.217 8
8	115 441.662 2	18	143 795.431 1
9	107 204.693 3	19	155 778.044 4
10	92 442.328 9	20	166 465.457 8

姓名	MAPE	MAE	MSE	RMSE	R2
BL-LSTM	22.361 037%	0.044 330	0.003 890	0.062 366	0.679 550
GRU	43.088 212%	0.088 303	0.015 412	0.124 145	0.26 975
SAE	35.915 936%	0.073 148	0.009 76	0.098 79	0.195 930

评价指数			发送速率
评价指数	100 Mbit/s	200 Mbit/s	300 Mbit/s	400 Mbit/s	500 Mbit/s
收到的数据包	8 550	18 542	25 825	34 882	45 852
丢失的数据包	0	0	0	0	0
丢包率	0%	0%	0%	0%	0%
数据包记录	0	1	5	14	24
重新排序率	0%	0.005 39%	0.019%	0.040%	0.052%

评价指数			发送速率
评价指数	800 Mbit/s	900 Mbit/s	1 000 Mbit/s	1 100 Mbit/s	1 200 Mbit/s
收到的数据包	64 589	75 628	85 421	88 642	108 541
丢失的数据包	0	0	0	0	0
丢包率	0%	0%	0%	0%	0%
数据包记录	25	24	22	41	45
重新排序率	0.039%	0.032%	0.026%	0.046%	0.041%

SR				ATS
SR	0.525 Gbit/s	0.685 Gbit/s	0.728 Gbit/s	0.846 Gbit/s	0.985 Gbit/s	1.258 Gbit/s	1.532 Gbit/s
NR	15	14	14	14	15	14	15
TTR/s	70.87	72.51	70.87	70.53	71.87	72.17	71.10
NTT/s	70.85	72.41	70.73	70.28	71.52	71.76	70.58
TDIR/s	0.02	0.10	0.14	0.25	0.35	0.41	0.52
ADIER/s	0.001 3	0.007 1	0.010	0.018	0.023	0.029	0.034

Routing planning and handoff based on LSTM traffic prediction

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 21

References 10

Related Articles 15

Metrics

Recommended 0

缩写	全称
ATS	average transmission rate
SR	simulation result
NR	number of reconfiguration
NTT	normal transmission time
TTR	transmission time with reconfiguration
TDIR	total delay increased by reconfiguration
ADIER	average delay increased by each reconfiguration

[1]	Xinxin TANG, Xuewen ZENG, Zhiyuan LING, Lei SONG. Overview of programmable data plane technology [J]. Telecommunications Science, 2023, 39(4): 1-16.
[2]	Wei ZHAO, Bei LI, Ning MENG, Tingwei WANG, Junfan LIN, Le CHEN, Yuhua HU, Hanyuan YANG. Design and implementation of AI-based all-scenario intelligent base station power-saving system [J]. Telecommunications Science, 2022, 38(8): 163-170.
[3]	Miaomiao ZHANG, Hao ZHAO, Yan ZHOU, Yang ZHANG, Li YU, Yanping LIANG, Chunjie FENG. A long-time ＆ short-time prediction based 5G base station energy-saving policy [J]. Telecommunications Science, 2022, 38(11): 153-162.
[4]	Shuo YUAN, Yijing REN, Zeyu WANG, Yaohua SUN, Mugen PENG. Software defined intelligent satellite-terrestrial integrated wireless network [J]. Telecommunications Science, 2021, 37(6): 66-77.
[5]	Hongyi ZHU, Xiaoyuan LU, Yi LI. Management technologies of cyberspace endogenous safety and security test site [J]. Telecommunications Science, 2021, 37(3): 66-74.
[6]	Xuliang WANG, Shuo QUAN, Zengyi LIU, Jun ZHANG. Research on architecture of novel programmable networks for 6G [J]. Telecommunications Science, 2021, 37(12): 84-92.
[7]	Qian HU, Guoyong ZHAO, Xiaoli HUO, Junjie LI, Ruiquan JING, Fei YAN, Xiaofeng WU. Application and research of SDN-based management and control technology for optical transport grey-box devices [J]. Telecommunications Science, 2021, 37(12): 93-100.
[8]	Tianjiao CHEN,Jiang LIU,Tao HUANG. Application of artificial intelligence in network orchestration system [J]. Telecommunications Science, 2019, 35(5): 9-16.
[9]	Li XIAO,Zhilin YUAN,Chengpeng FU,Weidong MA. Intelligent metro optical networks and key optical components [J]. Telecommunications Science, 2019, 35(4): 33-40.
[10]	Dongshan WANG,Yue MA,Yan LI,Jian GAO,Zhibin YIN. Coordinated and unified control technology of IP and optical transport network for power services [J]. Telecommunications Science, 2019, 35(3): 116-121.
[11]	Jiang ZHOU,Hewu LI. A general way to assign IPv6 trusted address under portal authentication [J]. Telecommunications Science, 2019, 35(12): 8-14.
[12]	Fengchao FU,Peng WANG,Yu MAO,Yongmei HUANG,Xiaobing GAO,Aihua ZHANG,Guoqiang LIN. Realization of vOLT and development trend [J]. Telecommunications Science, 2018, 34(7): 157-161.
[13]	Yuan ZHANG. Architecture and key technologies of network on demand for small and medium enterprises [J]. Telecommunications Science, 2018, 34(7): 7-14.
[14]	Cui ZHONG,Lei WANG,Xing LUO. SDN solutions for cloud data center [J]. Telecommunications Science, 2018, 34(7): 15-22.
[15]	Bin ZHUGE,Yihang QI,Hanwen FU,Weiming WANG. Network resource pricing strategy based on SDN framework [J]. Telecommunications Science, 2018, 34(7): 49-61.