Wireless backhaul network’s capacity optimization using time series forecasting approach


The extensive technological participation in our daily life and business world has transformed the technology model predominantly from last decade and it has created many directions for further research and development. In previous generations of technology, the major development was hardware side but now it is shifting to the smart and intelligent solutions based on AI. The new challenges have provoked and complexity is increasing for resource orchestration because of the nonstop increasing network and its applications. In cellular architecture, the backhaul network (intermediate network) is used to connect the radio and core network. The key technology is the point to point fixed links that is used in the wireless backhaul network. More than 60% radio base station are connected using this technology. Currently, the static approach is used for planning and optimization of the network which is now becoming very difficult as the network is increasing continuously and becoming more complex. The dynamic resource allocation method is proposed for the future capacity forecasting system which is founded on the factual employment of point to point links. Capacity is a crucial factor in wireless backhaul network so best capacity optimization can lead to a good frequency reuse and optimal use of other network resources. The development is based on three different models namely (1) Autoregressive (AR), (2) Seasonal Autoregressive Integrated Moving Average (SARIMA) and (3) Multi-Layer Perceptron (MLP) neural network. Root Means Squared Error (RMSE) and Means Absolute Percentage Error (MAPE) are performance criterion that are used to evaluate the models. When we compare the models' performance, the MLP results are most credible but it takes more time to converge than AR and SARIMA. By using the proposed estimation method, the static optimization will positively move to the dynamic (forecasted) optimization and the distribution of capacity utilization will be right skewed. Hence, the proposed system is efficient and has the ability to optimize the network according to the actual network’s capacity utilization. It will assist the network planner to perform more efficiently, resource distribution will be more balanced and the wastage of resources can be reduced.

This is a preview of subscription content, access via your institution.

Fig. 1

Source: Cisco VNI Global IP Traffic Forecast, 2017–2022)

Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10


  1. Abdullah I, Daw DAA, Seman K (2015) Traffic forecasting and planning of wimax under multiple priority using fuzzy time series analysis. J Appl Math Phys 3(4):68–74

    Article  Google Scholar 

  2. Alfred R, Asri A, Ibrahim A (2015) A performance comparison of statistical and machine learning techniques in learning time series data. Adv Sci Lett 21(10):3037–3041

    Article  Google Scholar 

  3. Benet CH, Kassler A, Zola E (2016) Predicting expected TCP throughput using genetic algorithm. Comput Netw 108:307–322

    Article  Google Scholar 

  4. Biernacki A (2017) Analysis and modelling of traffic produced by adaptive HTTP-based video. Multimed Tools Appl 76(10):12347–12368

    Article  Google Scholar 

  5. Box GE, Jenkins GM, Reinsel GC, Ljung GM (2015) Time series analysis: forecasting and control. Wiley

  6. Chen A, Leung MT, Hazem D (2003) Application of neural networks to an emerging financial market: forecasting and trading the Taiwan Stock Index. Comput Oper Res 30:901–923

    Article  Google Scholar 

  7. Chong C-Y, Kumar SP (2003) Sensor networks: evolution, opportunities, and challenges. Proc IEEE 91(8):1247–1256

    Article  Google Scholar 

  8. Cortez P, Rio M, Rocha M, Sousa P (2012) Multi-scale internet traffic forecasting using neural networks and time series methods. Expert Syst 29(2):143–155

    Google Scholar 

  9. Dengen HN (2016) Comparison of SARIMA, NARX and BPNN models in forecasting time series data of network traffic. In: the 2nd International Conference on Science in Information Technology (ICSITech), pp. 264–269.

  10. Fadlullah ZM, Tang F, Mao B, Kato N, Akashi O, Inoue T, Mizutani K (2017a) State of the art deep learning: evolving machine intelligence toward tomorrow’s intelligent network traffic control systems. IEEE Commun Surv Tutor 19(4):2432–2455

    Article  Google Scholar 

  11. Fadlullah ZM, Tang F, Mao B, Kato N, Akashi O, Inoue T, Mizutani K (2017) State-of the-art deep learning: evolving machine intelligence toward tomorrow’s intelligent network traffic control systems. IEEE Commun Surv Tutor 19(4):2432–2455

    Article  Google Scholar 

  12. Fang L, Member S, Cheng X, Member S, Wang H, Yang L (2018) Mobile demand forecasting via deep modelling in cellular networks. IEEE Internet Things J 5(4):3091–3101

    Article  Google Scholar 

  13. Gowrishankar S, Satyanarayana PS (2009) A time series modelling and prediction of wireless network traffic. Int J Interact Mob Technol 3(1):53–62

    Article  Google Scholar 

  14. Guo J, Peng Y, Peng XY, Chen Q, Yu J, Dai YF (2009) Traffic forecasting for mobile networks with multiplicative seasonal ARIMA models. In: the Proceedings of the 9th International Conference on Electronic Measurement and Instruments—ICEMI2009, pp. 3377–3380.

  15. Haviluddin H, Alfred R (2014a) Comparison of ANN Back propagation techniques in modelling network traffic activities. In: the 1st Proceeding of the International Conference on Science and Technology for Sustainability, pp. 224–231.

  16. Haviluddin H, Alfred R (2014) Forecasting network activities using ARIMA method. J Adv Comput Netw 2:173–179

    Article  Google Scholar 

  17. Javed F, Afzal MK, Sharif M, Kim B-S (2018) Internet of things (IoT) operating systems support, networking technologies, applications, and challenges: a comparative review. IEEE Commun Surv Tutor 20(3):2062–2100

    Article  Google Scholar 

  18. Jia Y, Wan B, Liang L, Zhao Q, Zhang Y, Tan L (2015) A new method for traffic prediction in emerging mobile networks. J Commun 10(12):947–954

    Google Scholar 

  19. Katris C, Daskalaki S (2015) Comparing forecasting approaches for Internet traffic. Expert Syst Appl 42(21):8172–8183

    Article  Google Scholar 

  20. Kim S (2011) Forecasting internet traffic by using seasonal GARCH models. J Commun Netw 13(6):621–624

    Article  Google Scholar 

  21. Le LV, Sinh D, Tung LP, Lin BSP (2018) A practical model for traffic forecasting based on big data, machine-learning, and network KPIs. In the Proceedings of the 15th IEEE Consumer Communications & Networking Conference (CCNC), pp 1–4.

  22. Lehpamer H (2010) Microwave Transmission Net. 2E. Tata McGraw-Hill Education

  23. Little S (2009) Is microwave backhaul up to the 4G task? IEEE Microwave Mag 10(5):67–74

    Article  Google Scholar 

  24. Mishra AR (2018) Fundamentals of Network Planning and Optimization 2G/3G/4G: Evolution to 5G. Wiley

  25. Montgomery DC, Johnson LA, Gardiner JS (1990) Forecasting and time series analysis, 5th edn. Wiley, Hoboken

    Google Scholar 

  26. Moysen J, Giupponi L (2018) From 4G to 5G: Self-organized network management meets machine learning. Comput Commun 129:248–268

    Article  Google Scholar 

  27. Nokia (2015). Looking ahead to 5G, White Paper, Accessed Online at: https://www.5gamericas.org/files/3614/3898/6583/Nokia_White_Paper_-_Looking_ahead_to_5G.pdf. Accessed 2018

  28. Ntalampiras S, Fiore M (2018) Forecasting mobile service demands for anticipatory MEC. In: IEEE 19th International Symposium on “A World of Wireless, Mobile and Multimedia Networks” (WoWMoM), pp. 14–19.

  29. Nuhung PB, Haviluddin H (2016) Comparing performance of Backpropagation and RBF neural network models for predicting daily network traffic. In: the Proceedings of the Makassar International Conference on Electrical Engineering and Informatics (MICEEI), pp. 1–4.

  30. Oliveira TP, Barbar JS, Soares AS (2016) Computer network traffic prediction: a comparison between traditional and deep learning neural network. Int J Big Data Intell 3(1):28–37

    Article  Google Scholar 

  31. Otoshi T, Ohsita Y, Murata M, Takahashi Y, Ishibashi K, Shiomoto K (2015) Traffic prediction for dynamic traffic engineering. Comput Netw 85:36–50

    Article  Google Scholar 

  32. Pilka F, Oravec M (2011) Multi-step ahead prediction using neural networks. In: Proceedings of the 53rd International Symposium ELMAR-2011, 14–16 September, Zadar, Croatia.

  33. Rutka G (2008) Network traffic prediction using arima and neural networks models. Electron Electron Eng 4(4):47–52

    Google Scholar 

  34. Rutka G (2009) Some aspects of traffic analysis used for internet traffic prediction. Electron Electron Eng Elektronika ir Elektrotechnika 93(5):7–10

    Google Scholar 

  35. Sahrani MN, Zan MM, Yassin IM, Zabidi A (2017) Artificial Neural network non-linear auto regressive moving average (narma) model for internet traffic prediction. J Telecommun Electron Comput Eng 9(1):145–149

    Google Scholar 

  36. Szmit M, Szmit A, Adamus S, Bugała S (2012) Usage of holt-winters model and multilayer perceptron in network traffic modelling and anomaly detection. Informatica 36(4):359–368

    Google Scholar 

  37. Tahyudin I (2015) Time series prediction using radial basis function neural network. Int J Elect Comput Eng 5(4):765–771

    Google Scholar 

  38. Tikunov D, Nishimura T (2007) Traffic prediction for mobile network using Holt-Winter’s exponential smoothing. In: the Proceedings of the 15th International Conference on Software, Telecommunications and Computer Networks, pp. 1–5.

  39. Wang C, Zhang X, Yan H, Zheng L (2008) An internet traffic forecasting model adopting radical based on function neural network optimized by genetic algorithm. In: the Proceedings of the 1st International Workshop on Knowledge Discovery and Data Mining, pp. 367–370.

  40. Wang C-X, Haider F, Gao X, You X-H, Yang Y, Yuan D, Aggoune HD, Haas H, Fletcher S, Hepsaydir E (2014) Cellular architecture and key technologies for 5G wireless communication networks. IEEE Commun Mag 52(2):122–130

    Article  Google Scholar 

  41. Xue J, Yan F, Birke R, Chen LY, Scherer T, Smirni E (2015) PRACTISE: robust prediction of data center time series. In: the Proceedings of the 11th International Conference on Network and Service Management (CNSM), pp. 126–134.

  42. Yu Y, Song M, Fu Y, Song J (2013) Traffic prediction in 3G mobile networks based on multifractal exploration. Tsinghua Sci Technol 18(4):398–405

    Article  Google Scholar 

  43. Zhang C, Patras P (2018) Long-term mobile traffic forecasting using deep spatio-temporal neural networks. In: the Proceedings of the 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing, pp. 231–240.

  44. Zhang GP, Qi GM (2005) Neural network forecasting for seasonal and trend time series. Eur J Oper Res 160:501–514

    Article  Google Scholar 

  45. Zhani MF, Elbiaze H (2009) Analysis and prediction of real network traffic. J Netw 4(9):855–865

    Google Scholar 

  46. Zhou B, He D, Sun Z, Ng W (2005) Network traffic modeling and prediction with ARIMA/GARCH, pp. 1–10. Accessed Online at: https://pdfs.semanticscholar.org/8b69/2869bc2e55f4d14f34f83e8e8e08427e8b5c.pdf. Accessed 2019

  47. Zhuang Z, Ramachandra H, Tran C, Subramaniam S, Botev C, Xiong C, Sridharan B (2015) Capacity planning and headroom analysis for taming database replication latency: experiences with linkedin internet traffic. In: Proceedings of the 6th ACM/SPEC International Conference on Performance Engineering, pp. 39–50.

Download references


This work has been done under the Grant BK032-2018 by University of Malaya.

Author information



Corresponding author

Correspondence to Saaidal Razalli Azzuhri.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Mahmood, A., Kiah, M.L.M., Azzuhri, S.R. et al. Wireless backhaul network’s capacity optimization using time series forecasting approach. J Ambient Intell Human Comput 12, 1407–1418 (2021). https://doi.org/10.1007/s12652-020-02209-2

Download citation