A Reinforcement Learning Based Joint Call Admission Control for Heterogeneous Wireless Networks

Currently, there are many wireless networks based on different radio access technologies (RATs). Despite this, new kind of networks will be developed to complement those already existing today. As there will be no RAT able to give users full service requirements with universal coverage, the next generation wireless networks will integrate multiple technologies, working jointly on a heterogeneous way. Heterogeneous networks necessitate joint radio resource management (JRRM) mechanism to enhance better resource utilization and give users better quality of service. Joint call admission controls (JCAC) are a kind of JRRM mechanisms. In this paper, we present a JCAC approach to heterogeneous wireless network management based on reinforcement learning to treat call admission and technology selection, enhancing the network’s performance. The effectiveness of this approach is assessed in terms of blocking rate results obtained by two simulation scenarios. Joint call admission control, JCAC, resource allocation, reinforcement learning, heterogeneous networks.

[1]  Jean C. Walrand,et al.  Effective bandwidths for multiclass Markov fluids and other ATM sources , 1993, TNET.

[2]  Michael J. Drevna,et al.  Introduction to Arena , 1994, Proceedings of Winter Simulation Conference.

[3]  Chih-Cheng Hung,et al.  A call admission control scheme using genetic algorithms , 2004, SAC '04.

[4]  Dimitri P. Bertsekas,et al.  Dynamic Programming: Deterministic and Stochastic Models , 1987 .

[5]  Nada Golmie,et al.  A probabilistic call admission control algorithm for WLAN in heterogeneous wireless environment , 2009, IEEE Transactions on Wireless Communications.

[6]  Joachim Sachs,et al.  Radio resource management distribution in a beyond 3G multi-radio access architecture , 2004, IEEE Global Telecommunications Conference, 2004. GLOBECOM '04..

[7]  Mohamed Hossam Ahmed,et al.  Call admission control in wireless networks: a comprehensive survey , 2005, IEEE Communications Surveys & Tutorials.

[8]  Oriol Sallent,et al.  A fuzzy-neural based approach for joint radio resource management in a beyond 3G framework , 2004, First International Conference on Quality of Service in Heterogeneous Wired/Wireless Networks.

[9]  T. V. Lakshman,et al.  Call admission control in wireless multimedia networks , 2004, IEEE Signal Processing Magazine.

[10]  G. Min,et al.  A QOS-BASED BANDWIDTH MANAGEMENT SCHEME IN HETEROGENEOUS WIRELESS NETWORKS , 2004 .

[11]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[12]  Vincenzo Suraci,et al.  A Model Based RL Admission Control Algorithm for Next Generation Networks , 2008, 2009 Eighth International Conference on Networks.

[13]  Hossam S. Hassanein,et al.  Adaptive Call Admission Control for Multimedia Wireless Networks with QoS Provisioning , 2004, ICPP Workshops.

[14]  H. Anthony Chan,et al.  Joint call admission control algorithms: Requirements, approaches, and design considerations , 2008, Comput. Commun..

[15]  Jorge D. Martinez,et al.  Optimal Admission Control Using Handover Prediction in Mobile Cellular Networks ∗ , 2004 .