Long Short-Term Memory Recurrent Neural Network based Mobility Prediction in MANET


  • J. Manimaran Annamalai University
  • Dr. T.Suresh






ARIMA, LSTM, MANET, Mobility Prediction.


A Mobile Ad hoc NETwork (MANET) is formed by a gathering of wireless nodes without any infrastructure and the wireless nodes are not static but dynamic in nature. The mobile nodes can be connected together dynamically to route data packets from other mobile node present in the network. The mobility of the nodes is a significant feature in the MANET. The nodes follow one of the different mobility patterns which affect the connectivity among the other nodes. The dynamic changes in the connectivity decides the performance of the routing protocol and hence the performance of the overall network. When considering these characteristics of the MANET it becomes essential to predict the mobility of the nodes in both service-oriented and as well as application-oriented aspects of the dynamic         networking. At the network level the mobility prediction is useful in pre-configuring services, provisioning of QoS and reservation of net-work resources and whereas in application level the end user can be provisioned with route guidance, information on network traffic and broadcasting important information to users. The mobility prediction will lead to the estimation of the stability of the routing paths and the distances between the neighboring nodes. This helps to improve the overall performance of the network by reducing the frequent link failures and increasing packet delivery ratio. In this paper, a novel mobility prediction method is developed using the historical time and positioning data. Auto Regressive Integrated Moving Average (ARIMA) and Long Short Term Memory (LSTM) with Recurrent Neural Network (RNN) are utilized for mobility prediction based on the sequence of time series data.




[1] R. Suraj, S. Tapaswi, S. Yousef, K. Pattanaik, and M. Cole.: Mobility prediction in mobile ad hoc networks using a lightweight genetic algorithm. Wireless Networks, 22(6), 1797–1806, 2016.https://doi.org/10.1007/s11276-015-1059-0.

[2] A. Pamanik, B. Choudhury, T.S Arif and W Mehedi.: Simulative study of random waypoint mobility model for mobile ad hoc networks. Proceedings of 2015 Global Conference on Communication Technologies (GCCT), p 112-16, 2015.https://doi.org/10.1109/GCCT.2015.7342634.

[3] V. K. Jain, and B. Sharma.: A Survey on mobility Models and Its Applications. International Journal of Recent Trends in Engineering and Research. 2(3), 35-41, 2016.

[4] GBox, G.M Jenkins, and G.C Reinsel.: Time Series Analysis: Forecasting and Control. 4th edn. Wiley, Chichester, 2008.https://doi.org/10.1002/9781118619193.

[5] K. Namuduri, S. Devaraj, M. Srinivasan, and R. Pendse.: Analytical estimation of path duration in mobile ad hoc networks. IEEE SensorsJ. 12(6), 1828–1835, 2011.https://doi.org/10.1109/JSEN.2011.2176927.

[6] Wenjing Yang, Xinyu Yang, Shusen Yang, Yage Gong.: Improving Route Stability in Mobile Ad Hoc Networks Based on Link Lifetime. Journal of Communications, 6(3), 205–214, 2011.https://doi.org/10.4304/jcm.6.3.205-214.

[7] M.Khashei,M.Bijari.: A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl.SoftComput.11 (2), 2664–2675, 2011.https://doi.org/10.1016/j.asoc.2010.10.015.

[8] X Ma, Z Tao, and Y Wang.: Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transport.Res. Part C: Emerg. Technol. 54, 187–197, 2015.https://doi.org/10.1016/j.trc.2015.03.014.

[9] Kulkarni, S.B., Yuvaraju, B.N.: Node connectivity, energy and bandwidth aware clustering routing algorithm for real-time traffic multicasting in MANET. In: Proceedings of the Advance Computing Conference (IACC), IEEE International, pp. 760–763, 2015.https://doi.org/10.1109/IADCC.2015.7154809.

[10] Ashbrook, D., Starner, T.: Learning significant locations and predicting user movement with gps, In: Wearable Computers, (ISWC 2002) Sixth International Symposium, pp. 101 – 108, 2002.

[11] Creixell, W., Sezaki, K.: Mobility prediction algorithm for mobile ad hoc network using pedestrian trajectory data. In: Proceedings of the TENCON 2004. 2004 IEEE Region 10 Conference, pp. 668–671, 2004.

[12] Zaidi, Z.R., Mark, B.L.: Mobility estimation for wireless networks based on an autoregressive model. In: Proceedings of IEEE GLOBECOM, Dallas, Texas, USA, Nov–Dec 2004.

[13] Basarkod, P.I., Manvi, S.S., Albur, D.S.: Mobility based estimation of node stability in MANETs. In: Proceedings of the International Conference on Emerging Trends in Computing, Communication and Nanotechnology (ICE-CCN), pp 126–130, 2013.https://doi.org/10.1109/ICE-CCN.2013.6528477.

[14] Park, R., Kim, W., Jang, S.: Improved AOMDV to increase path stability by utilizing the node mobility information in MANET. In: Proceedings of the International Conference on Information Networking (ICOIN), pp 417–422, 2013.

[15] Mohsin, R.J., Woods, J., Shawkat, M.Q.: Density and mobility impact on MANET routing protocols in a maritime environment. In: Proceedings of the Science and Information Conference (SAI), pp. 1046–1051, 2015.https://doi.org/10.1109/SAI.2015.7237271.

[16] Palani, U., Alamelumangai, V., Nachiappan, A.: Hybrid routing and load balancing protocol for wireless sensor network. Wirel. Netw. (8), 2659–2666, 2016.https://doi.org/10.1007/s11276-015-1110-1.

[17] Rajalakshmi, C.: Mobility prediction in MANET using neural learning methods. Artif. Intell. Syst. Mach. Learn. 9(2), 39–42, 2017.

[18] Nagwani, R., Singh Tomar, D. Mobility Prediction based Routing in Mobile Adhoc Network using Hidden Markov Model. International Journal of Computer Applications. 59(1), 39–44, 2012.https://doi.org/10.5120/9516-3919.

[19] Ghouti L, Sheltami TR, Alutaibi KS. Mobility prediction in mobile ad hoc networks using extreme learning machines. Procedia Computer Science. 19, 305–312, 2013.https://doi.org/10.1016/j.procs.2013.06.043.

View Full Article: