Abstract
The problem discussed in this paper stems from a project of cellular network traffic prediction, the primary step of network planning striving to serve the continuously soaring network traffic best with limited resource. The traffic prediction emphasizes two aspects: (1) how to exploit the potential value of physical and electronic properties for tens of thousands of wireless stations, which may partly determine the allocation of traffic load in some intricate way; (2) the lack of sufficient and high-quality historical records, for the appropriate training of long-term predictions, further aggravated by frequent reconfigurations in daily operation. To solve this problem, we define a general framework to accommodate several variants of multi-step forecasting, via decomposing the problem into a series of single-step vector-output regression tasks. They can further be augmented by miscellaneous attributive information, in the form of boosted multiple kernels. Experiments on multiple telecom datasets show that the solution outperforms conventional time series methods on accuracy, especially for long horizons. Those attributes describing the macroscopic factors, such as the network type, topology, locations, are significantly helpful for longer horizons, whereas the immediate values in the near future are mainly determined by their recent records.
The work is partially supported by National Key R&D Program of China under Grant No. 2016YFB0200803, 2017YFB0202302, 2017YFB0202001, 2017YFB0202502, 2017YFB0202105; the National Natural Science Foundation of China under Grant No.61432018, No. 61521092, No. 61272136, No. 61402441, No. 61502450; the National High Technology Research and Development Program of China under Grant No. 2015AA011505; Key Technology Research and Development Programs of Guangdong Province under Grant No. 2015B010108006; the CAS Interdisciplinary Innovation Team of Efficient Space Weather Forecast Models; NSF of China under no. 11301420; NSF of Jiangsu province under no. BK20150373 and no. BK20171237; Suzhou science and technology program under no. SZS201613 and the XJTLU Key Programme Special Fund (KSF) under no. KSF-A-01.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cisco Visual Networking Index: Global mobile data traffic forecast update, 2016–2021 white paper. https://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/mobile-white-paper-c11-520862.html. Accessed Mar 2017
Bui, N., Cesana, M., Hosseini, S.A., Liao, Q., Malanchini, I., Widmer, J.: A survey of anticipatory mobile networking: context-based classification, prediction methodologies, and optimization techniques. IEEE Commun. Surv. Tutor. (2017)
Das, A.K., Pathak, P.H., Chuah, C.-N., Mohapatra, P.: Contextual localization through network traffic analysis. In: Proceedings of INFOCOM 2014, pp. 925–933. IEEE (2014)
Gönen, M., Alpaydın, E.: Multiple kernel learning algorithms. J. Mach. Learn. Res. 12, 2211–2268 (2011)
Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y., Wang, Y.: Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17(4), 818 (2017)
Oliveira, T.P., Barbar, J.S., Soares, A.S.: Computer network traffic prediction: a comparison between traditional and deep learning neural networks. Int. J. Big Data Intell. 3(1), 28–37 (2016)
Park, J., Raza, S.M., Thorat, P., Kim, D.S., Choo, H.: Network traffic prediction model based on training data. In: Gervasi, O., Murgante, B., Misra, S., Gavrilova, M.L., Rocha, A.M.A.C., Torre, C., Taniar, D., Apduhan, B.O. (eds.) ICCSA 2015. LNCS, vol. 9158, pp. 117–127. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21410-8_9
Taieb, S.B.: Machine learning strategies for multi-step-ahead time series forecasting. Ph.D. Thesis (2014)
Wen, Q., Zhao, Z., Li, R., Zhang, H.: Spatial-temporal compressed sensing based traffic prediction in cellular networks. In: 1st IEEE International Conference on Communications in China Workshops (ICCC), pp. 119–124. IEEE (2012)
Xia, H., Hoi, S.C.H.: MKBoost: a framework of multiple kernel boosting. IEEE Trans. Knowl. Data Eng. 25(7), 1574–1586 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zhang, D., Zhang, Y., Niu, Q., Qiu, X. (2018). Rolling Forecasting Forward by Boosting Heterogeneous Kernels. In: Phung, D., Tseng, V., Webb, G., Ho, B., Ganji, M., Rashidi, L. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2018. Lecture Notes in Computer Science(), vol 10937. Springer, Cham. https://doi.org/10.1007/978-3-319-93034-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-93034-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-93033-6
Online ISBN: 978-3-319-93034-3
eBook Packages: Computer ScienceComputer Science (R0)