Bandwidth Provisioning for 4G Mobile Network Using Hybrid ARIMA-LSTM Based Traffic Forecasting
How to Cite?
Rahmat Fuadi Syam, Abba Suganda Girsang, "Bandwidth Provisioning for 4G Mobile Network Using Hybrid ARIMA-LSTM Based Traffic Forecasting," International Journal of Engineering Trends and Technology, vol. 69, no. 5, pp. 235-241, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I5P230
Several prediction methods currently help companies improve efficiency, one of which is the prediction of bandwidth allocation. This method is expected to support a telecommunications company in carrying out cost efficiency, especially the data transfer cost from each location. Currently, the problem with telecommunication companies is the lack of management of the amount of bandwidth required. Sometimes, there is a lack or excess of bandwidth allocation in each BTS, so that this problem can reduce the profits earned by the company. From these problems, we need a system that can regulate and predict future bandwidth requirements. So in this study, we explore the prediction of bandwidth needs by utilizing the data from monitoring the bandwidth of each cell in the form of time-series data. Researchers collect the data from November 2019 to January 2020; our first step is to simulate predictions using the ARIMA method. In this study, simulations using a combined method of ARIMA and LSTM RNN. After trying several ARIMA and LSTM models, the best models are ARIMA (0.0 .6) and LSTM (windows = 100, 2 Layer, 100 Neuron), where the RMSE results obtained are 387.693019. From the results of the model, the researcher conducted an experiment using the Hybrid ARIMA LTSM model. The findings of this study indicate that predictions within 50 hours indicate an accurate level of accuracy.
Arima, Timeseries, Bandwith, Payload.
 Y. Yu, M. Song, Y. Fu, and J. Song. Traffic prediction in 3G mobile networks based on multifractal exploration, Tsinghua Sci. Technol., 18(4)(2013) 398–405.
 V. S. Kumar and A. Muthukumaravel. Seasonal forecasting of mobile data traffic in GSM networks with linear trend, 23(3)(2020) 469–474.
 H. W. Kim, J. H. Lee, Y. H. Choi, Y. U. Chung, and H. Lee. Dynamic bandwidth provisioning using ARIMA-based traffic forecasting for Mobile WiMAX, Comput. Commun., 34(1)(2011) 99–106.
 D. T. Larose and C. D. Larose. Data Mining and Predictive Analytics (Wiley Series on Methods and Applications in Data Mining), Wiley Ser., (2015) 794.
 M. Suryanegara, A. Ramadhan, A. K. Akbar, and M. Asvial. The forecasting model of 4G LTE implementation in Indonesia, ICMIT 2014 - 2014 IEEE Int. Conf. Manag. Innov. Technol., 1(2014) 461–466.
 M. Hamed, H. AI-Masaeid, and Z. Sai. SHORT-TERM PREDICTION OF TRAFFIC VOLUME IN URBAN ARTERIALS, J. Transp. Eng, I(1995) 249–254.
 H. Z. Moayedi and M. A. Masnadi-Shirazi. Arima model for network traffic prediction and anomaly detection, Proc. - Int. Symp. Inf. Technol. 2008, ITSim, 3 (2008) 6–11.
 Y. Peng, M. Lei, J. B. Li, and X. Y. Peng. A novel hybridization of echo state networks and multiplicative seasonal ARIMA model for mobile communication traffic series forecasting, Neural Comput. Appl., 24(3–4) (2014) 883–890.
 B. M. Williams and L. A. Hoel. Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results, J. Transp. Eng., 129(6) (2003) 664–672.
 A. J. SMOLA and B. SCHOLKOPF. A tutorial on support vector regression, Stat. Comput., 14(2004) 199–222..
 W. C. Hong, Y. Dong, F. Zheng, and C. Y. Lai. Forecasting urban traffic flow by SVR with continuous ACO, Appl. Math. Model., 35(3) (2011) 1282–1291.
 W. Cai, D. Yu, Z. Wu, X. Du, and T. Zhou. A hybrid ensemble learning framework for basketball outcomes prediction, Phys. A Stat. Mech. its Appl., 528(2019) 121461.
 L. Cai, Q. Chen, W. Cai, X. Xu, T. Zhou, and J. Qin. SVRGSA: A hybrid learning-based model for short-term traffic flow forecasting, IET Intell. Transp. Syst., 13(9) (2019) 1348–1355.
 W. Cai, J. Yang, Y. Yu, Y. Song, T. Zhou, and J. Qin. PSO-ELM: A Hybrid Learning Model for Short-Term Traffic Flow Forecasting, IEEE Access, 8(2020) 6505–6514.
 P. Cai, Y. Wang, G. Lu, P. Chen, C. Ding, and J. Sun. A spatiotemporal correlative K nearest-neighbor model for short-term traffic multistep forecasting, Transp. Res. Part C Emerg. Technol., 62(2016) 21–34.
 F. G. Habtemichael and M. Cetin. Short-term traffic flow rate forecasting based on identifying similar traffic patterns, Transp. Res. Part C Emerg. Technol., 66(2016) 61–78.
 L. Cai, Y. Yu, S. Zhang, Y. Song, Z. Xiong, and T. Zhou. A sample-rebalanced outlier-rejected k-Nearest neighbor regression model for short-term traffic flow forecasting, IEEE Access, 8 (2020) 22686–22696.
 E. I. Vlahogianni, M. G. Karlaftis, and J. C. Golias. Short-term traffic forecasting: Where we are and where we`re going, Transp. Res. Part C Emerg. Technol., 43(2014) 3–19.
 I. Lana, J. Del Ser, M. Velez, and E. I. Vlahogianni. Road Traffic Forecasting: Recent Advances and New Challenges, IEEE Intell. Transp. Syst. Mag., 10(2) (2018) 93–109.
 H. Liu et al. Simultaneous measurement of trace monoadenosine and diadenosine monophosphate in biomimicking prebiotic synthesis using high-performance liquid chromatography with ultraviolet detection and electrospray ionization mass spectrometry characterization, Anal. Chim. Acta, 566(1) (2006) 99–108.
 J. Z. Zhu, J. X. Cao, and Y. Zhu. Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections, Transp. Res. Part C Emerg. Technol., 47(P2) (2014) 139–154.
 S. Yang. On feature selection for traffic congestion prediction, Transp. Res. Part C Emerg. Technol., 26(2013) 160–169.
 J. Zhang, Y. Zheng, D. Qi, R. Li, and X. Yi. DNN-Based Prediction Model for Spatio-Temporal Data, 2016.
 L. Zhao et al. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction, IEEE Trans. Intell. Transp. Syst., 21(9) (2020) 3848–3858.
 J. S. Angarita-Zapata, A. D. Masegosa, and I. Triguero. A Taxonomy of Traffic Forecasting Regression Problems from a Supervised Learning Perspective, IEEE Access, 7(2019) 68185–68205.
 L. N. N. Do, N. Taherifar, and H. L. Vu. Survey of neural network-based models for short-term traffic state prediction, Wiley Interdiscip. Rev. Data Min. Knowl. Discov., 9(1)(2019) 1–24.
 A. Ermagun and D. Levinson. Spatiotemporal traffic forecasting: review and proposed directions, Transp. Rev., 38(6)(2018) 786–814.
 Z. Cui, R. Ke, and Y. Wang. Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction, (2018)1–11.
 H. Yu, Z. Wu, S. Wang, Y. Wang, and X. Ma. Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks, Sensors (Switzerland), 17(7) (2017). 1–16.
 T. Bogaerts, A. D. Masegosa, J. S. Angarita-Zapata, E. Onieva, and P. Hellinckx. A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data, Transp. Res. Part C Emerg. Technol., 112(2019) 62–77.
 I. A. S. Abu Amra and A. Y. A. Maghari. Forecasting Groundwater Production and Rain Amounts Using ARIMA-Hybrid ARIMA: Case Study of Deir El-Balah City in Gaza, Proc. - 2018 Int. Conf. Promis. Electron. Technol. ICPET 2018, (2018) 135–140.
 A. Elmasdotter. LSTM and ARIMA for sales A comparative study between LSTM and ARIMA for sales forecasting in retail, 2018.
 E. Fradinata. ANN, ARIMA and MA Timeseries Model for Forecasting in Cement Manufacturing Industry, (2014) 39–44.
 Z. Wang and Y. Lou. Hydrological time series forecast model based on wavelet de-noising and ARIMA-LSTM, Proc. 2019 IEEE 3rd Inf. Technol. Networking, Electron. Autom. Control Conf. ITNEC 2019, no. Itnec, (2019) 1697–1701.
 T. C. Fu, Y. K. Hung, and F. L. Chung. Improvement algorithms of perceptually important point identification for time series data mining, IEEE 4th Int. Conf. Soft Comput. Mach. Intell. ISCMI 2017, 2018(2018) 11–15.
 S. Jung, C. Kim, and Y. Chung. A prediction method of network traffic using time series models, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 3982 LNCS, (2006) 234–243.
 Emeka and A. Kelvin. A detailed document for ARDL, J. Stat. Econom. Methods, 5(3) (2016) 63–91.
 M. F. Zhani, H. Elbiaze, and F. Kamoun. Analysis and prediction of real network traffic, J. Networks, 4(9)(2009) 855–865.
 L. Ni, X. Chen, and Q. Huang. ARIMA model for traffic flow prediction based on wavelet analysis, 2nd Int. Conf. Inf. Sci. Eng. ICISE2010 - Proc., 0(2)(2010) 1028–1031.
 A. T. Namel, M. A. Sahib, and S. M. Hasan. Bandwidth Utilization Prediction in LAN Network Using Time Series Modeling, Iraqi J. Comput. Commun. Control Syst. Eng., (2019) 78–89.
 P. G. Zhang. Time series forecasting using a hybrid ARIMA and neural network model, Neurocomputing., 50 (2003) 159–175.
 S. Goswami. S TUDY OF E FFECTIVENESS OF T IME S ERIES M ODELING ( ARIMA ) IN F ORECASTING S TOCK, no. April 2014, 2016.
 P. Studi, S. Informasi, E. D. Wahyuni, A. A. Arifiyanti, and M. Kustyani.Exploratory Data Analysis dalam Konteks Klasifikasi Data Mining, 2019(2019) 263–269.
 S. Siami-namini and N. Tavakoli. A Comparison of ARIMA and LSTM in Forecasting Time Series, 2018 17th IEEE Int. Conf. Mach. Learn. Appl., (2018) 1394–1401.