Cognitive Network Management with Reinforcement Learning for Wireless Mesh Networks

We present a framework of cognitive network management by means of an autonomic reconfiguration scheme. We propose a network architecture that enables intelligent services to meet QoS requirements, by adding autonomous intelligence, based on reinforcement learning, to the network management agents. The management system is shown to be better able to reconfigure its policy strategy around areas of interest and adapt to changes. We present preliminary simulation results showing our autonomous reconfiguration approach successfully improves the performance of the original AODV protocol in a heterogeneous network environment.

[1]  Carl Wijting,et al.  Mesh WLAN networks: concept and system design , 2006, IEEE Wireless Communications.

[2]  Brian Haberman,et al.  Key Challenges of Military Tactical Networking and the Elusive Promise of MANET Technology , 2006, IEEE Communications Magazine.

[3]  Ting Wang,et al.  Adaptive Routing for Sensor Networks using Reinforcement Learning , 2006, The Sixth IEEE International Conference on Computer and Information Technology (CIT'06).

[4]  Hari Balakrishnan,et al.  Quality-Aware Routing Metrics for Time-Varying Wireless Mesh Networks , 2006, IEEE Journal on Selected Areas in Communications.

[5]  G. Dimitrakopoulos,et al.  Introducing reconfigurability and cognitive networks concepts in the wireless world , 2006, IEEE Vehicular Technology Magazine.

[6]  Marco Conti,et al.  Cross-layering in mobile ad hoc network design , 2004, Computer.

[7]  Marco Conti,et al.  MobileMAN: Design, Integration, and Experimentation of Cross-Layer Mobile Multihop Ad Hoc Networks , 2006 .

[8]  Allen B. MacKenzie,et al.  Cognitive networks: adaptation and learning to achieve end-to-end performance objectives , 2006, IEEE Communications Magazine.

[9]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[10]  Philippe Jacquet,et al.  Optimized Link State Routing Protocol (OLSR) , 2003, RFC.

[11]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[12]  Zygmunt J. Haas,et al.  The zone routing protocol (zrp) for ad hoc networks" intemet draft , 2002 .

[13]  David A. Maltz,et al.  Dynamic Source Routing in Ad Hoc Wireless Networks , 1994, Mobidata.

[14]  Stefano Basagni,et al.  Distributed clustering for ad hoc networks , 1999, Proceedings Fourth International Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN'99).

[15]  Michael L. Littman,et al.  Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach , 1993, NIPS.

[16]  Charles E. Perkins,et al.  Ad hoc On-Demand Distance Vector (AODV) Routing , 2001, RFC.

[17]  Donal O'Mahony,et al.  Ad hoc innovation: distributed decision making in ad hoc networks , 2006, IEEE Communications Magazine.

[18]  Weihua Zhuang,et al.  Cross-layer design for resource allocation in 3G wireless networks and beyond , 2005, IEEE Communications Magazine.

[19]  M. Motani,et al.  Cross-layer design: a survey and the road ahead , 2005, IEEE Communications Magazine.

[20]  David Andre,et al.  Model based Bayesian Exploration , 1999, UAI.