Research Article

Mobile Soft Switch Traffic Prediction using Polynomial Neural Networks

Aliyu Ozovehe
Department of Electrical and Electronics Engineering, Abubakar Tafawa Balewa University, Bauchi, Nigeria
* Corresponding author
DOI icon 10.24018/ejeng.2018.3.7.775

Read Counter
586

Downloads
398

Citations

Share

Article Sidebar

Submitted 2018-05-31
Published 2018-07-19

Read counter = 586 times

Table of Contents

Article Main Content

This work investigates busy hour traffic demand pattern of mobile soft switch (MSS) over a period of two years and propose the application of Group Method of Data Handling (GMDH) polynomial neural network for seven-days to three-month ahead busy hour (BH) traffic forecasting for effective optimization of network resources. Busy hour call attempt (BHCA) utilization and A-interface utilization key performance indicators (KPI) are used as inputs into GMDH prediction model and BH traffic as model target. The performance of the model was evaluated based on three statistical performance indices: mean absolute percentage error (MAPE), root mean square percentage error (RMSPE) and goodness of fit (R2) values. Experimental results show that R2 value as high as 96% was achieved with the proposed model for both short-term and mid-term forecasting. The GMDH model proves an effective tool for accurate prediction of traffic demand and hence, proper optimization of GSM/GPRS MSS network resources.

Keywords: Busy Hour Traffic Busy Hour Call Attempt Utilization A-Interface Utilization and Mobile Soft Switch

References

  1. Y. Gao, G. He and J. C. Hou, “On leveraging traffic predictability in active queue management,” In Proc. IEEE, INFOCOM, June 2002.
     Google Scholar
  2. Y. Xia, C. K. Tse, W. M. Tam, C. M. L. M Francis and M Small, “Analysis of telephone network traffic based on a complex user network,” arXiv: physics/0601033v1/ [physics.soc-phy] 6 Jan 2006.
     Google Scholar
  3. I. Kennedy, “Lost call theory,” lecture notes, ELEN5007 – Teletraffic Engineering, School of Electrical and Information Engineering, University of the Witwatersrand, 2005.
     Google Scholar
  4. K. Assaleh and H. Al-Nashash, “A novel technique for the extraction of fetal ECG using polynomial networks,” IEEE Transactions on Biomedical Engineering, Vol. 52, No. 6, pp. 1148-1152, 2005.
     Google Scholar
  5. W. Campbell, K. Assaleh and C. Broun, “Speaker recognition with polynomial classifiers,” IEEE Transactions on Speech and Audio Processing, doi:10.1109/TSA.2002.1011533, Vol. 10, No. 4, pp. 205-212, 2002.
     Google Scholar
  6. K. Bon-Gil, L. Sang-Wook, K Wook and H. P. June, “Comparative study of short-term electric load forecasting,” IEEE Computer Society, Fifth International Conference on Intelligent Systems, Modeling and Simulation, 2014.
     Google Scholar
  7. A.F. Huseynov, N.A. Yusifbeyli and A.M. Hashimov, “Electrical system load forecasting with polynomial neural networks (based on combinatorial algorithm),” Modern Electric Power Systems 2010, Wroclaw, Poland, MEPS’10- paper 04.3,2010.
     Google Scholar
  8. K. Atashkari, N. Nariman-Zadeh, M. Gölcü, A. Khalkhali and A. Jamali, “Modelling and multi-objective optimization of a variable valve-timing spark-ignition engine using polynomial neural networks and evolutionary algorithms,” Energy Conversion and Management Journal 48(3) 1029-1041, 2007.
     Google Scholar
  9. Y.M. Abu-Kheil, System identification using group method of data handling, A Thesis Presented to the Faculty of the American University of Sharjah School of Engineering in Partial Fulfilment of the Requirements for the Degree Master of Science, Sharjah, UAE, January 2009.
     Google Scholar
  10. Hong C. (2010), “A GMDH-based traffic flow forecasting model,” Journal of Convergence Information Technology, Volume 5, Number 2, April 2010.
     Google Scholar
  11. V. Varahrami, “Application of genetic algorithm to neural network forecasting of short–term water demand,” International Conference on Applied Economics – ICOAE 2010, page783-787, 2010.
     Google Scholar
  12. K. Assaleh, T Shanableh. and Y. Abu Kheil, “Group method of data handling for modeling magnetorheological dampers,” Intelligent Control and Automation, 2013, 4, 70-79 http://dx.doi.org/10.4236/ica.2013.41010, http://www.scirp.org/journal/ica, 2013.
     Google Scholar
  13. M. Rădulescu and L. Banica, “Forecasting Regarding the Convergence Process of CEE Countries to the Eurozone,” Transylvanian Review of Administrative Sciences, , pp. 225-246, No. 42 E, 2014.
     Google Scholar
  14. H. Moradi, I. Joka and A. Forouzantabar, “Modelling and forecasting gold price using GMDH neural network,” Indian Journal of Fundamental and Applied Life Sciences ISSN: 2231– 6345, Vol. 5 (S1), pp. 30-4, 2015.
     Google Scholar
  15. T. Jacob, A.U. Usman, S. Bemdoo and A. A. Susan, “Short-term electrical energy consumption forecasting using GMDH-type neural network,” Journal of Electrical and Electronic Engineering, Vol. 3, No. 3, pp. 42-47. doi: 10.11648/j.jeee.20150303.14, 2015.
     Google Scholar
  16. O. Aliyu, U. O Okpo, E. C. Anene and U. U. Abraham, “Busy hour traffic congestion analysis in mobile macrocells,” Nigerian Journal of Technology (NIJOTECH) Vol. 36, No. 4, pp. 1265 – 1270, October 2017.
     Google Scholar
  17. Anonymous (2012), “Operation and maintenance centre report,” Ericsson MSS Performance Evaluation Manual,2012.
     Google Scholar
  18. Softland (2016), “GMDH Shell Forecasting Software 3.5.8” Free Trail, http://gmdh-shell-forecasting-software.soft112.com/, 2016.
     Google Scholar
  19. C. Roura, Jordi, D. Prieto, Miguel, O. Redondo, J. Antonio, G. Espinosa and Antoni, Genetic algorithm-based training of an anfis for electric energy consumption forecasting, EUROPEAN Patent Application, EP 2 551 798 A1, 2013.
     Google Scholar