Fuzzy-Q-learning-based autonomic management of macro-diversity algorithm in UMTS networks

Third generationUmts network has come with significant high-quality services that considerably increase the complexity of its management. Autonomic management has been introduced to alleviate these complex lengthy tasks. In this paper, we propose an autonomic management of macro-diversity algorithm inUmts networks. The new approach allows to dynamically adapt macro-diversity parameters to varying network situations. The online adaptation of these parameters is made by an intelligent controller calledfuzzy-Q-Learning. The combination of Fuzzy Inference System (Fis) and Q-learning algorithm allows to determine the best on-line parameterization of base stations and to deal with large number of continuous states and actions. The proposed scheme improves the system capacity up to 30% compared to a classical network with fixed parameters, balances the load between base stations and minimizes human interventions in the network management. However, the reactivity of the controller should be chosen with a special care since it impacts the frequency of active set updates and hence signalling messages in the radio interface as well as in the core network.RésuméLes réseaux mobilesUmts de troisième génération offrent un haut niveau de qualité de service qui complique de plus en plus le management des ressources radios. L’introduction du processus de management autonome dans ces réseaux permet de réduire considérablement cette complexité. Dans cet article, nous proposons une nouvelle méthode pour le réglage autonome des paramètres de macro-diversité d’un réseauUmts. Cette nouvelle approche permet d’adapter dynamiquement les paramètres en fonction de la situation du réseau en termes de fluctuations de trafic et de types de mobilité. Le réglage automatique et autonome de ces paramètres est réalisé par un contrôleur de typefuzzy-Q-Learning. Ce contrôleur combine un système d’inférence floue (Sif) et un algorithme d’apprentissage par renforcement. Cette combinaison permet au contrôleur de trouver dynamiquement le meilleur paramétrage pour chaque station de base et de traiter des états et des actions continus. Cette méthode augmente la capacité du système jusqu ’à 30 % par rapport à un réseau classique, permet d’équilibrer la charge entre les stations de base et diminue l’intervention humaine dans la tache de management du réseau. Cependant, La réactivité du contrôleur doit être prudemment choisie car elle influe la fréquence des mises à jour de l’active set du mobile qui se traduit par une augmentation des messages de signalisation au niveau de l’interface radio ainsi que du réseau cœur.

[1]  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.

[2]  Guy Pujolle,et al.  Call admission control in cellular networks: A reinforcement learning solution , 2004, Int. J. Netw. Manag..

[3]  Chung-Ju Chang,et al.  A Q-learning-based multi-rate transmission control scheme for RRC in WCDMA systems , 2002, The 13th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications.

[4]  Victor C. M. Leung,et al.  A new QoS provisioning method for adaptive multimedia in cellular wireless networks , 2004, IEEE INFOCOM 2004.

[5]  P. Stuckmann,et al.  The EUREKA Gandalf project: monitoring and self-tuning techniques for heterogeneous radio access networks , 2005, 2005 IEEE 61st Vehicular Technology Conference.

[6]  Watit Benjapolakul,et al.  QoS-controlling soft handoff based on simple step control and a fuzzy inference system with the gradient descent method , 2004, IEEE Transactions on Vehicular Technology.

[7]  Hamid R. Berenji,et al.  Learning and tuning fuzzy logic controllers through reinforcements , 1992, IEEE Trans. Neural Networks.

[8]  John M. Graybeal,et al.  The new paradigm for wireless network optimization: a synergy of automated processes and human intervention , 2005, IEEE Communications Magazine.

[9]  Antti Toskala,et al.  WCDMA for UMTS: Radio Access for Third Generation Mobile Communications , 2000 .

[10]  Paolo Dini,et al.  A call admission control strategy based on fuzzy logic for WCDMA systems , 2004, 2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577).

[11]  Xuemin Shen,et al.  Call Admission Control in Wideband CDMA Cellular Networks by Using Fuzzy Logic , 2005, IEEE Trans. Mob. Comput..

[12]  J. M. Picard,et al.  Auto‐tuning of RRM Parameters in UMTS Networks , 2006 .

[13]  George Edwards,et al.  Microcellular handoff using fuzzy techniques , 1998, Wirel. Networks.

[14]  Oriol Sallent,et al.  Radio Resource Management Strategies in UMTS , 2005 .

[15]  Donal O'Mahony,et al.  Secure routing for mobile ad hoc networks , 2005, IEEE Communications Surveys & Tutorials.

[16]  M. Clerc,et al.  Particle swarm optimization of fuzzy logic controller for high quality RRM auto-tuning of UMTS networks , 2005, 2005 IEEE 61st Vehicular Technology Conference.

[17]  Sana Ben Jemaa,et al.  Manual and Automatic Design for UMTS Networks , 2004, Mob. Networks Appl..

[18]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[19]  Wenhui Zhang,et al.  Handover decision using fuzzy MADM in heterogeneous networks , 2004, 2004 IEEE Wireless Communications and Networking Conference (IEEE Cat. No.04TH8733).

[20]  Fotini-Niovi Pavlidou,et al.  Broadband communications via high-altitude platforms: a survey , 2005, IEEE Communications Surveys & Tutorials.

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

[22]  Symeon Papavassiliou,et al.  Admission Control in Wireless Networks , 2003 .

[23]  Lionel Jouffe,et al.  Fuzzy inference system learning by reinforcement methods , 1998, IEEE Trans. Syst. Man Cybern. Part C.

[24]  Victor C. M. Leung,et al.  Efficient QoS Provisioning for Adaptive Multimedia in Mobile Communication Networks by Reinforcement Learning , 2004, BROADNETS.

[25]  Tomás̆ Novosad,et al.  Radio Network Planning and Optimisation for Umts , 2006 .