Utilizing Hybrid Machine Learning Models to Predict Quality of Service (QoS) in Multi-Channel Wireless Networks

Utilizing Hybrid Machine Learning Models to Predict Quality of Service (QoS) in Multi-Channel Wireless Networks

© 2022 by IJETT Journal
Volume-70 Issue-6
Year of Publication : 2022
Authors : Aisha M. Mashraqi
DOI : 10.14445/22315381/IJETT-V70I6P205

How to Cite?

Aisha M. Mashraqi, "Utilizing Hybrid Machine Learning Models to Predict Quality of Service (QoS) in Multi-Channel Wireless Networks," International Journal of Engineering Trends and Technology, vol. 70, no. 6, pp. 42-46, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I6P205

Understanding the behaviors of wireless networks and monitoring network flows are critical to network performance. This research combined unsupervised and supervised learning methods to develop a hybrid model for forecasting QoS in multi-channel wireless networks based on network traffic data. K-means clustering techniques were employed in the model to detect similarity in the aggregated collected data and label the dataset. The findings suggest that two is the optimal number of classes. The classified dataset was then fed into various machine learning classifiers, with the Decision Tree approach outperforming the others with a 0.971 accuracy. As a result, the Decision Tree algorithm was found to be the most effective method of forecasting QoS in multi-channel wireless networks.

Clustering, Classification, Machine Learning, Wireless Networks, QoS.

[1] J. Gubbi, R.Buyya, S.Marusic and M. Palaniswami, Internet of Things (IoT): A Vision, Architectural Elements and Future Directions, Future Generation Computer. 29(7) (2013) 1645–1660.
[2] S. Sehrawat, R. Bora, D. Harihar, Performance Analysis of QoS supported by Enhanced Distributed Channel Access (EDCA) Mechanism in IEEE 802. 11 e. IMECS. Citeseer. (2006) 943–948.
[3] I. Yeom, A. Reddy, Realizing Throughput Guarantees in a Differentiated Services Network, In Proc IEEE International Conference on Multimedia Computing and Systems, IEEE, Italy. (1999) 372–376.
[4] K. Jain, J. Padhye, V. Padmanabhan, L. Qiu, Impact of Interference on Multi-Hop Wireless Network Performance, in Proc, MobiCom '03. 11 (2005) 471–487.
[5] J. Tang, G. Xue, W Zhang, Interference-Aware Topology Control and Qos Routing in Multi-Channel Wireless Mesh Networks, in Proc, the 6th ACM International Symposium on Mobile Ad Hoc Networking and Computing. (2005) 68–77.
[6] B. Al-Kaseem, H. Al-Raweshidy, Y. Al-Dunainawi, K. Banitsas, A New Intelligent Approach for Optimizing 6 Lowpan Mac Layer Parameters, IEEE Access. 5 (2017) 16229–16240.
[7] M. Sha, R. Dor, G. Hackmann, C. Lu, T. Kim, T. Park, Self-Adapting Mac Layer for Wireless Sensor Networks, Inproc 34th Real-Time Systems Symposium, IEEE. (2013) 192–201.
[8] M. Qiao, H. Zhao, S. Wang, J. Wei, Mac Protocol Selection Based on Machine Learning in Cognitive Radio Networks, In Proc 19th International Symposium on Wireless Personal Multimedia Communications WPMC, IEEE. (2016) 453–45.
[9] S. Keerthi, S. Shevade, C. Bhattacharyya, K. Murthy, Improvements to Platt’s SMO Algorithm for SVM Classifier Design, Neural Computation. 13 (2001) 637–649.
[10] T. Liu, A. Cerpa, Foresee 4C: Wireless Link Prediction Using Link Features, in Proc the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks, IEEE. (2011) 294–330.
[11] M. Kulin, E. De Poorter, T. Kazaz, I. Moerman, Towards a Cognitive MAC Layer: Predicting the MAC-Level Performance in Dynamic WSN Using Machine Learning, In Proc. EWSN2017, the International Conference on Embedded Wireless Systems and Networks. (2017) 1–2.
[12] L. Pierucci, D. Micheli, A Neural Network for Quality of Experience Estimation in Mobile Communications, IEEE Multi Media. 23 (2017) 42–49.
[13] J. Liu, I. Matta, M. Crovella, End-to-End Inference of Loss Nature in a Hybrid Wired/Wireless Environment, WiOpt’03: Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks. (2003) 9.
[14] A. McGregor, M. Hall, P. Lorier, J. Brunskill, Flow Clustering Using Machine Learning Techniques, International Workshop on Passive and Active Network Measurement, Springer. (2004) 205–214.
[15] (2021). Network Simulator. [Online]. Available: https://www.isi.edu/nsnam/ns/Last checked on 29.10.2021.
[16] A. Jain, M. Murty, P. Flynn, Data Clustering: A Review, ACM Computing Surveys CSUR. 31 (1999) 264–323.
[17] P. Rousseeuw, Silhouettes: A Graphical Aid to the Interpretation and Validation of Cluster Analysis, Journal of Computational and Applied Mathematics. 20 (1987) 53–65.
[18] W. Mining, Data Mining: Concepts and Techniques, Morgan Kaufinann. 10 (2006) 559–569.
[19] G. Chandrashekar, F. Sahin, A Survey on Feature Selection Methods, Computers & Electrical Engineering. 40 (2014)16–28.
[20] M. Hearst, S. Dumais, E. Osuna, J. Platt, B. Scholkopf, Support Vector Machines, IEEE Intelligent Systems and their Applications. 13 (1998) 18–28.
[21] F. Yang, An Extended Idea about Decision Trees, In Proc. International Conference on Computational Science and Computational Intelligence CSCI. (2019) 349–354.
[22] G. Guo, H. Wang, D. Bell, Y. Bi, K. Greer, KNN Model-Based Approach in Classification, OTM Confederated International Conferences on the Move to Meaningful Internet Systems, Springer. (2003) 986–996.
[23] T. Kohonen, An Introduction to Neural Computing, Neural Networks. 1 (1988) 3–16.
[24] W. Peng Zhang, Statistical Inference on Recall, Precision and Average Precision under Random Selection, In Proc. 9th International Conference on Fuzzy Systems and Knowledge Discovery. (2012) 1348–1352.
[25] M. Junker, R. Hoch, A. Dengel, On the Evaluation of Document Analysis Components by Recall, Precision, and Accuracy, In Proc. the Fifth International Conference on Document Analysis and Recognition, ICDAR ’99 Cat. No.PR00318. (1999) 713–716.
[26] (2021). Anaconda, I. Anaconda Navigator. [Online]. Available: https://docs.anaconda.com/anaconda/navigator/index.html.
[27] A. Bhatnagar, R. Varshney and K. Manu, A Review: Energy Efficiency using Various Protocols in Wireless Sensor Networks, IJETT International Journal of Electronics and Communication Engineering IJETT-IJECE. 4(4) (2017) 26-29.