Blaise O. Yenke; Diane C. M. Tala; Jean Louis E. K. Fendji

Extended Probabilistic Cost Model (EPCM): A Framework for Cost Estimation of Wireless Network Deployment in Rural Areas

Full Text (PDF, 726KB), PP.1-9

Views: 0 Downloads: 0

Author(s)

Blaise O. Yenke ^1,* Diane C. M. Tala ¹ Jean Louis E. K. Fendji ¹

1. Department of Computer Engineering,University of Ngaoundéré, Ngaoundéré, Cameroon

* Corresponding author.

DOI: https://doi.org/10.5815/ijieeb.2017.01.01

Received: 20 Oct. 2016 / Revised: 2 Nov. 2016 / Accepted: 3 Dec. 2016 / Published: 8 Jan. 2017

Index Terms

Model, contingency, wireless networks, cost estimation, rural areas

Abstract

This paper tackles a critical issue emerging when planning the deployment of a wireless network in rural regions: the cost estimation. Wireless Networks have usually been presented as a cost-effective solution to bridge the digital divide between rural and urban regions. But this assertion is too general and does not give an insight about the real estimation of the deployment cost of such an infrastructure. Providing such a cost estimation framework may help to avoid underestimation or overestimation of required resources since the budget is almost always limited in rural regions. This work extends the Probabilistic Cost Model (PCM) that has been proposed. This model does not take into account the difference in the costs of unexpected events. To extend the PCMfirst, a list of unexpected events that can occur when deploying Wireless Networks has been established. This list is based on data from past projects and a set of unexpected events that can occur. Afterwards, the standard deviation and the average have been computed for each unexpected event. The Poisson process has been therefore used to predict the number of unexpected events that may occur during the network deployment. This approach led to the proposal of a model that gives an estimation of the total cost of contingencies, which takes into account the probability that the total cost of unexpected events does not exceed a given contingency. The evaluation of the proposed model on a given dataset provided a good accuracy in the prediction of the cost induced by unexpected events.

Cite This Paper

Blaise O. Yenke, Diane C. M. Tala, Jean Louis E. K. Fendji, "Extended Probabilistic Cost Model (EPCM): A Framework for Cost Estimation of Wireless Network Deployment in Rural Areas", International Journal of Information Engineering and Electronic Business(IJIEEB), Vol.9, No.1, pp.1-9, 2017. DOI:10.5815/ijieeb.2017.01.01

Reference

[1]Benjamin J. R. and Cornell C. A., Probability, statistics, and decision for civil engineers. McGraw-Hill, New York, 1970.
[2]Kolakez E., Observatoire des projets stratégiques. Research report, pp.16-18, 2011.
[3]Littlefield B. And Hanselman D., Matlab user guide. MathworksInc, Natick, Mass, 1999.
[4]Khoshgoftaar T.,Idri A., Abran A., Fuzzy analogy: A new approach for software cost estimation. Proceedings of the 11th International Workshop on Software Measurements, Montréal, pp.93-101, 2001.
[5]Yeung D.Y. and Kwok T.Y., Constructive algorithms for structure learning in feed forward neural networks for regression problems. IEEE Trans. Neural Networks, 8(3), pp. 630-645, 1997.
[6]Jay L.D., Probability and statistics for engineering and sciences, 8th ed. Michelle Julet, Boston, MA, pp.105-230, 2010.
[7]Narendra K.S. and Levin A.U., Control of nonlinear dynamical systems using neural networks - part ii: Observability, identification, and control. IEEE Trans. Neural Networks ,vol. 7, no.1, 1996.
[8]Haykin S., Neural networks: A comprehensive foundation. 2nd ed Prentice Hall, 1998.
[9]Khulumani S.,Muyingi H.N. and Mabanza, Building wireless Community Networks with 802.16 Standards. Broadcom, Third International Conference on Broadband Communications, Information Technology and Biomedical Applications, ISSBN: 978-0-7695-3453-4, pp.384-388, 2008.
[10]Khulumani S. and Nsung-Nza H.M., networks: Emerging topics in Computer Science. BookChapter, Chapter3, Paperback, March 16, 2013.
[11]Aditya P.S. and Pradeep T., Web Service Component Reusability Evaluation: A Fuzzy Multi-Criteria Approach. International Journal of Information Technology and Computer Science, vol. 1, pp.40-47, 2016.
[12]Navjot K. and Amerdeep S., Analysis of Vascular Pattern Recognition Using Neural Network. International Journal of Mathematical Sciences and Computing, vol. 3,pp.9-19,2015.
[13]Deepa B.P. and Yashwant V.D., A Fuzzy Approach For Text Mining, vol. 4, pp.34-43, 2015.
[14]Katsinis C. and Volz A., A Network traffic shaping technique based on waiting time. International Journal of Computer and Application, vol. 21, pp.44-49, 1996.
[15]Idri A. and Abran A., Towards A Fuzzy Logic Based Measures For Software Project Similarity. Sixth Maghebian Conference on Computer Science, pp.9-18, 2000.
[16]Touran A., Probabilistic model for cost contingency. Journal of Construction Engineering and Management, vol. 129, issue 3, pp.280-284, 2003.
[17]Anupama K., Soni A.K. and Rachna S., A Simple Neural Network Approach to Software Estimation. Global Journal of Computer Science and Technology Neural and Artificial Intelligence, vol.13, issue 1, version 1.0, 2013.
[18]Malathi S. and Sridhar S., A Classical Fuzzy Approach for Software Effort Estimation on Machine Learning Technique. International of Computer Sciences Issues, vol.8, issue 6, no.1, November 2011.

International Journal of Information Engineering and Electronic Business (IJIEEB)