Abstract
Bandwidth demand forecasting is the basis and foundation of the power communication network planning. In view of the traditional neural network learning speed is slow, the number of iterations is large, and the local optimal problem, an adaptive extreme learning machine model based on the theory of extreme learning machine and K nearest neighbor theory is proposed to predict the bandwidth of electric power communication. The adaptive metrics of inputs can solve the problems of amplitude changing and trend determination, and reduce the effect of the overfitting of networks. The proposed algorithms are validated using real data of a province in China. The results show that this method is better than the traditional neural network, auto regressive model, self organization model, and single extreme learning machine model. It can be used in electric power communication bandwidth prediction.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jain, M., Dovrolis, C.: End-to-end estimation of the available bandwidth variation range. ACM Sigmetrics Perform. Eval. Rev. 33(1), 265–276 (2005)
Dovrolis, C., Ramanathan, P., Moore, D.: Packet-dispersion techniques and a capacity-estimation methodology. IEEE/ACM Trans. Netw. 12(6), 963–977 (2004)
Liu, X., Ravindran, K., Loguinov, D.: A stochastic foundation of available bandwidth estimation: multi-hop analysis. IEEE/ACM Trans. Netw. 16(1), 130–143 (2008)
Nam, S.Y., Kim, S., Kim, J., et al.: Probing-based estimation of end-to-end available bandwidth. IEEE Commun. Lett. 8(6), 400–402 (2004)
Park, K.J., Lim, H., Choi, C.H.: Stochastic analysis of packet-pair probing for network bandwidth estimation. Comput. Netw. Int. J. Comput. Telecommun. Netw. 50(12), 1901–1915 (2006)
Zhang, M., Luo, C., Li, J.: Estimating available bandwidth using multiple overloading streams. Int. Conf. IEEE 2, 495–502 (2006)
Liu, J., Zhang, D.: Toward accurate and efficient available bandwidth measurement. Telecommun. Syst. 41(3), 211–227 (2009)
Li, M., Chang, C.R.: A two-way available bandwidth estimation scheme for multimedia streaming networks adopting scalable video coding. IEEE Sarnoff Symp. 1, 1–6 (2009)
Guerrero, C.D., Labrador, M.A.: Traceband: “A fast, low overhead and accurate tool for available bandwidth estimation and monitoring”. Comput. Netw. 54(6), 977–990 (2010)
Guerrero, C.D., Labrador, M.A.: On the applicability of available bandwidth estimation techniques and tools. Comput. Commun. 33(1), 11–22 (2010)
Dolama, M.V., Rahbar, A.G.: Modified smallest available report first: new dynamic bandwidth allocation schemes in QoS-capable EPONs. Opt. Fiber Technol. 17(1), 7–16 (2011)
Huang, S.C.: Online option price forecasting by using unscented kalman filters and support vector machines. Expert Syst. Appl. 43(4), 2819–2825 (2008)
Funahashi, K.I.: On the approximate realization of continuous mappings by neural networks. Neural Netw. 2(3), 183–192 (1989)
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Control Sig. Syst. 2(4), 303–314 (1989)
Huang, G.B.: Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans. Neural Netw. 14(2), 274–281 (2003)
Huang, G.B., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Netw. 17(4), 879–892 (2006)
Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)
Zhu, Q.Y., Qin, A.K., Suganthan, P.N., et al.: Evolutionary extreme learning machine. Pattern Recogn. 38(10), 1759–1763 (2005)
Bartlett, P.L.: For valid generalization, the size of the weights is more important than the size. Adv. Neural Inf. Process. Syst. (NIPS) 9, 134 (1997)
Wong, W.K., Xia, M., Chu, W.C.: Adaptive neural network model for time-series forecasting. Eur. J. Oper. Res. 207(1), 807–816 (2010)
Acknowledgments
This work is supported in part by, the National Natural Science Foundation of PR China (61105115), Six Talent Peaks Program of Jiangsu Province (2014-XXRJ-007), Natural Science Foundation of Jiangsu Province (BK20161533), Perspective Research Foundation of Production Study and Research Alliance of Jiangsu Province (BY2015007-01), and Laboratory open project of Nuist.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Zheng, Z., Di, L., Wang, S., Xia, M., Hu, K., Zhang, R. (2016). Bandwidth Forecasting for Power Communication Using Adaptive Extreme Learning Machine. In: Sun, X., Liu, A., Chao, HC., Bertino, E. (eds) Cloud Computing and Security. ICCCS 2016. Lecture Notes in Computer Science(), vol 10040. Springer, Cham. https://doi.org/10.1007/978-3-319-48674-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-48674-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48673-4
Online ISBN: 978-3-319-48674-1
eBook Packages: Computer ScienceComputer Science (R0)