Handover Prediction in Fifth Generation Small Cell Networks with LSTM-based Deep Neural Network

Yıl 2021, , 90 - 99, 30.06.2021

Murtaza Cicioğlu

https://doi.org/10.35193/bseufbd.840927

Öz

In this study, a new model is developed that performs handover prediction in fifth generation small cell networks with Long Short Term Memory (LSTM) based deep neural networks. Firstly, the data set to be used for training in handover prediction was created with simulation scenarios designed in Riverbed Modeler. Through these scenarios, three input (RSSI, SNR and Jitter) variables and one output variable (desired value) were obtained to be used in the data set of the neural network. This data set was trained with machine learning algorithms LSTM, SVM, Tree, and Linear Regression techniques. LSTM-based deep neural network was compared with other regression algorithms and was found to have higher performance. When the test results of the trained model for LSTM are examined; R2 0.94, MAE 0.3315, MSE 0.3670, and RMSE value 0.6058 was found. It was observed that LSTM-based deep neural networks show high performance in regression processes. As a result, study shows that handover decisions can be predicted in 5G small cell networks with the proposed regression model.

Anahtar Kelimeler

5G, Small Cell, Machine Learning, LSTM

LSTM tabanlı Derin Sinir Ağı ile Beşinci Nesil Küçük Hücre Ağlarında El Değiştirme Tahmini

Öz

Bu çalışmada, Uzun Kısa-Vadeli Hafıza (LSTM) tabanlı derin sinir ağı ile beşinci nesil küçük hücre ağlarında el değiştirme (handover, HO) tahminlerini gerçekleştiren yeni bir model geliştirilmiştir. İlk olarak HO tahmininde eğitim için kullanılacak olan veri seti Riverbed Modeler benzetim yazılımında tasarlanan benzetim senaryoları ile oluşturulmuştur. Bu senaryolar aracılığıyla sinir ağının veri kümesinde kullanılacak üç adet giriş (RSSI, SNR ve Jitter) değişkeni ve bir adet çıkış (istenen değer) değişkeni elde edilmiştir. Bu veri seti makine öğrenmesi algoritmalarından LSTM, SVM, Tree ve Lineer Regresyon teknikleri ile eğitilmiştir. LSTM tabanlı derin sinir ağı diğer regresyon algoritmaları ile karşılaştırılmış ve daha yüksek başarıma sahip olduğu tespit edilmiştir. LSTM için eğitilen modelin test sonuçları incelendiğinde; R2 0.94, MAE 0.3315, MSE 0.3670 ve RMSE değeri 0.6058 olarak bulunmuştur. LSTM tabanlı derin sinir ağlarının, regresyon işlemlerinde yüksek başarım gösterdiği görülmüştür. Sonuç olarak önerilen regresyon modeli ile 5G küçük hücre ağlarında HO kararlarının tahmin edilebildiği gösterilmiştir.

Anahtar Kelimeler

5G, Küçük Hücre, Makine Öğrenmesi, LSTM

Kaynakça

• A. Çalhan and M. Cicioğlu, “Handover scheme for 5G small cell networks with non-orthogonal multiple access,” Comput. Networks, vol. 183, p. 107601, Dec. 2020, doi: 10.1016/j.comnet.2020.107601.
• M. Cicioğlu, “Performance Analysis of Handover Management in 5G Small Cells,” Comput. Stand. Interfaces, p. 103502, Dec. 2020, doi: 10.1016/j.csi.2020.103502.
• D. Muirhead, M. A. Imran, and K. Arshad, “A Survey of the Challenges, Opportunities and Use of Multiple Antennas in Current and Future 5G Small Cell Base Stations,” IEEE Access, vol. 4, pp. 2952–2964, 2016, doi: 10.1109/ACCESS.2016.2569483.
• “Ericsson Mobility Report,” Ericsson, 2020. https://www.ericsson.com/4adc87/assets/local/mobility-report/documents/2020/november-2020-ericsson-mobility-report.pdf (accessed Dec. 10, 2020).
• M. De Ree, G. Mantas, A. Radwan, S. Mumtaz, J. Rodriguez, and I. E. Otung, “Key Management for Beyond 5G Mobile Small Cells: A Survey,” IEEE Access, vol. 7, pp. 59200–59236, 2019, doi: 10.1109/ACCESS.2019.2914359.
• “Small cells - what’s the big idea? Femtocells are expanding beyond the home,” Small Cell Forum, 2014. https://scf.io/en/documents/030_-_Small_cells_big_ideas.php (accessed May 24, 2020).
• T. Bilen, B. Canberk, and K. R. Chowdhury, “Handover Management in Software-Defined Ultra-Dense 5G Networks,” IEEE Netw., vol. 31, no. 4, pp. 49–55, Jul. 2017, doi: 10.1109/MNET.2017.1600301.
• C. Çeken, S. Yarkan, and H. Arslan, “Interference aware vertical handoff decision algorithm for quality of service support in wireless heterogeneous networks,” Comput. Networks, vol. 54, no. 5, pp. 726–740, Apr. 2010, doi: 10.1016/j.comnet.2009.09.018.
• A. Çalhan and C. Çeken, “An Optimum Vertical Handoff Decision Algorithm Based on Adaptive Fuzzy Logic and Genetic Algorithm,” Wirel. Pers. Commun., vol. 64, no. 4, pp. 647–664, Jun. 2012, doi: 10.1007/s11277-010-0210-6.
• C. Fan, B. Li, C. Zhao, and Y.-C. Liang, “Regret Matching Learning Based Spectrum Reuse in Small Cell Networks,” IEEE Trans. Veh. Technol., vol. 69, no. 1, pp. 1060–1064, Jan. 2020, doi: 10.1109/TVT.2019.2947265.
• J. Xie et al., “A Survey of Machine Learning Techniques Applied to Software Defined Networking (SDN): Research Issues and Challenges,” IEEE Commun. Surv. Tutorials, vol. 21, no. 1, pp. 393–430, 2019, doi: 10.1109/COMST.2018.2866942.
• I. Alawe, A. Ksentini, Y. Hadjadj-Aoul, and P. Bertin, “Improving Traffic Forecasting for 5G Core Network Scalability: A Machine Learning Approach,” IEEE Netw., vol. 32, no. 6, pp. 42–49, Nov. 2018, doi: 10.1109/MNET.2018.1800104.
• C. Luo, J. Ji, Q. Wang, X. Chen, and P. Li, “Channel State Information Prediction for 5G Wireless Communications: A Deep Learning Approach,” IEEE Trans. Netw. Sci. Eng., vol. 7, no. 1, pp. 227–236, Jan. 2020, doi: 10.1109/TNSE.2018.2848960.
• N. Aljeri and A. Boukerche, “A two-tier machine learning-based handover management scheme for intelligent vehicular networks,” Ad Hoc Networks, vol. 94, p. 101930, Nov. 2019, doi: 10.1016/j.adhoc.2019.101930.
• E. Zeljkovic, N. Slamnik-Krijestorac, S. Latre, and J. M. Marquez-Barja, “ABRAHAM: Machine Learning Backed Proactive Handover Algorithm Using SDN,” IEEE Trans. Netw. Serv. Manag., vol. 16, no. 4, pp. 1522–1536, Dec. 2019, doi: 10.1109/TNSM.2019.2948883.
• Y. Sun et al., “Efficient Handover Mechanism for Radio Access Network Slicing by Exploiting Distributed Learning,” IEEE Trans. Netw. Serv. Manag., pp. 1–1, 2020, doi: 10.1109/TNSM.2020.3031079.
• E. Alpaydin, Introduction to Machine Learning Ethem Alpaydin. 2014.
• D. Akgün, “An Evaluation of VGG16 Binary Classifier Deep Neural Network for Noise and Blur Corrupted Images,” Sak. Univ. J. Comput. Inf. Sci., Dec. 2020, doi: 10.35377/saucis.03.03.725647.
• U. Senturk, K. Polat, and I. Yucedag, “A Novel Blood Pressure Estimation Method with the Combination of Long Short Term Memory Neural Network and Principal Component Analysis Based on PPG Signals,” in Artificial Intelligence and Applied Mathematics in Engineering Problems, 2020, pp. 868–876, doi: 10.1007/978-3-030-36178-5_75.
• M. A. Çavuşlu, C. Karakuzu, S. Şahin, and M. Yakut, “Neural network training based on FPGA with floating point number format and it’s performance,” Neural Comput. Appl., vol. 20, no. 2, pp. 195–202, Mar. 2011, doi: 10.1007/s00521-010-0423-3.
• U. Yuzgec, Y. Becerikli, and M. Turker, “Dynamic Neural-Network-Based Model-Predictive Control of an Industrial Baker’s Yeast Drying Process,” IEEE Trans. Neural Networks, vol. 19, no. 7, pp. 1231–1242, Jul. 2008, doi: 10.1109/TNN.2008.2000205.
• The Mathworks Inc., “MATLAB - MathWorks,” www.mathworks.com/products/matlab, 2016. .
• “Riverbed Modeler Software,” Riverbed Technology, 2020. https://www.riverbed.com/gb/products/steelcentral/steelcentral-riverbed-modeler.html (accessed May 24, 2020).