Traffic Prediction Method for GEO Satellites Combining ARIMA Model and Grey Model

doi:10.1007/s12204-019-2152-9

Abstract

Abstract: An accurate traffic prediction on various service is of great importance to the channel resource man- agement of geostationary earth orbit (GEO) satellites. Therefore, a traffic prediction method for GEO satellites combining autoregressive integrated moving average (ARIMA) model and grey model is proposed. First, the traffic prediction methods based on ARIMA model and grey model are introduced respectively. Second, a combined model is given, in which according to the results of the historical prediction of ARIMA model and grey model, those two models are combined with di?erent weights. Third, the combined model is applied to a multi-service access and the access probability of each kind of service is calculated based on the prediction results. Finally, the simulation experiments indicate that the combined model has better prediction stability and higher average prediction accuracy than either of the separated models. Moreover, the proposed access strategy based on the combined model performs better than other similar strategies.

Key words: traffic prediction| ARIMA model| grey model| access| GEO satellites

摘要： An accurate traffic prediction on various service is of great importance to the channel resource man- agement of geostationary earth orbit (GEO) satellites. Therefore, a traffic prediction method for GEO satellites combining autoregressive integrated moving average (ARIMA) model and grey model is proposed. First, the traffic prediction methods based on ARIMA model and grey model are introduced respectively. Second, a combined model is given, in which according to the results of the historical prediction of ARIMA model and grey model, those two models are combined with di?erent weights. Third, the combined model is applied to a multi-service access and the access probability of each kind of service is calculated based on the prediction results. Finally, the simulation experiments indicate that the combined model has better prediction stability and higher average prediction accuracy than either of the separated models. Moreover, the proposed access strategy based on the combined model performs better than other similar strategies.

关键词: traffic prediction| ARIMA model| grey model| access| GEO satellites

CLC Number:

TP 393

ZHOU Jian (周剑), YANG Qidong (杨启东), ZHANG Xiaofei (张小飞), HAN Chong (韩崇), SUN Lijuan (孙力娟). Traffic Prediction Method for GEO Satellites Combining ARIMA Model and Grey Model[J]. Journal of Shanghai Jiao Tong University (Science), 2020, 25(1): 65-69.

References 19

[1]	PARK K, WILLINGER W. Self-similar network traffic and performance evaluation [M]. New York, John Wiley & Sons, 2000.
[2]	TIAN Z D, GAO X W, LI S J, et al. Prediction method for network traffic based on genetic algorithm optimized echo state network [J]. Journal of Computer Research & Development, 2015, 52(5): 1137-1145 (in Chinese).
[3]	JIANG M, WU C M, ZHANG M, et al. Research on the comparison of time series models for network traffic prediction [J]. Acta Electronica Sinica, 2009, 37(11):2353-2358 (in Chinese).
[4]	TANG Z J, PENG T,WANGWB. A local least square support vector machine prediction algorithm of small scale network tra±c based on correlation analysis [J].Acta Physica Sinica, 2014, 63(13): 130504 (in Chinese).
[5]	WEI D B, PAN C S, HAN R. Self-similarity analysis of satellite network traffic [J]. Computer Science, 2013,40(5): 67-69 (in Chinese).
[6]	QIN H X, YANG F. A new traffic flow prediction algorithm for satellite communication network [J].Telecommunication Engineering, 2013, 53(7): 835-839(in Chinese).
[7]	WEI W, ZHANG G X, L?U J, et al. Tra±c prediction method for satellite network [J]. Communications Technology, 2015, 48(11): 1285-1289 (in Chinese).
[8]	CHITI F, FANTACCI R, TARCHI D, et al. QoS provisioning in GEO satellite with onboard processing using predictor algorithms [J]. IEEE Wireless Communications, 2005, 12(5): 21-27.
[9]	YAN D, WANG L Y. TPDR: Traffic prediction based dynamic routing for LEO&GEO satellite networks[C]//5th International Conference on Electronics Information and Emergency Communication. Beijing,China: IEEE, 2015: 104-107.
[10]	DANG X C, YAN L. Network tra±c forecast based on short related ARIMA model [J]. Computer Engineering, 2012, 38(13): 71-74 (in Chinese).
[11]	BARTHOLOMEW D J. Reviewed work: Time series analysis forecasting and control [J]. Operational Research Quarterly (1970-1977), 1971, 22(2): 199-201.
[12]	DENG J L. Control problems of grey systems [J]. Systems & Control Letters, 1982, 1(5): 288-294.
[13]	DING S, LI Y Q, WU D S, et al. Time-aware cloud service recommendation using similarity-enhanced collaborative ˉltering and ARIMA model [J]. Decision Support Systems, 2018, 107: 103-115.
[14]	BIERNACKI A. Improving quality of adaptive video by tra±c prediction with (F) ARIMA models [J]. Journal of Communications and Networks, 2017, 19(5):521-530.
[15]	YASEEN Z M, FU M L, WANG C, et al. Application of the hybrid artificial neural network coupled with rolling mechanism and grey model algorithms for stream°ow forecasting over multiple time horizons[J]. Water Resources Management, 2018, 32(5): 1883-1899.
[16]	SHAIKH F, JI Q, SHAIKH P H, et al. Forecasting China's natural gas demand based on optimised nonlinear grey models [J]. Energy, 2017, 140: 941-951.
[17]	NIE Q P, ZHANG X D. The analysis of united test of F statistics in ADF unit root test [J]. Statistical Research, 2007, 24(2): 73-80 (in Chinese).
[18]	BURNHAM K P, ANDERSON D R. Multimodel inference: Understanding AIC and BIC in model selection [J]. Sociological Methods & Research, 2004, 33(2):261-304.
[19]	ZHOU J, SUN L J, HAN C, et al. Channel resources management strategy for multi-layer satellite network[J]. Systems Engineering and Electronics, 2017, 39(8):1857-1863 (in Chinese).