Statistical Learning in Automated Troubleshooting: Application to LTE Interference Mitigation

This paper presents a method for automated healing as part of offline automated troubleshooting. The method combines statistical learning with constraint optimization. The automated healing aims at locally optimizing the radio-resource management (RRM) or system parameters of cells with poor performance in an iterative manner. The statistical learning processes the data using logistic regression (LR) to extract closed-form (functional) relations between key performance indicators (KPIs) and RRM parameters. These functional relations are then processed by an optimization engine that proposes new parameter values. The advantage of the proposed formulation is the small number of iterations required by the automated healing method to converge, making it suitable for offline implementation. The proposed method is applied to heal an intercell-interference-coordination (ICIC) process in a third-generation (3G) long-term evolution (LTE) network, which is based on the soft-frequency reuse scheme. Numerical simulations illustrate the benefits of the proposed approach.

[1]  Z. Altman,et al.  Steered optimization strategy for automatic cell planning of UMTS networks , 2005, 2005 IEEE 61st Vehicular Technology Conference.

[2]  Volker Wille,et al.  System for automated diagnosis in cellular networks based on performance indicators , 2005, Eur. Trans. Telecommun..

[3]  Gábor Fodor.  Performance Analysis of a Reuse Partitioning Technique for OFDM Based Evolved UTRA , 2006, 200614th IEEE International Workshop on Quality of Service.

[4]  Nikolaos Koutsouris,et al.  A Management Framework for Ambient Systems Operating in Wireless B3G Environments , 2008, Mob. Networks Appl..

[5]  Tung-Sang Ng,et al.  An analytic discrete-time model for a fading dispersive WSSUS channel , 1994, Proceedings of IEEE Vehicular Technology Conference (VTC).

[6]  Alan Agresti,et al.  Introduction to Generalized Linear Models , 2003 .

[7]  James L. Massey,et al.  Proper complex random processes with applications to information theory , 1993, IEEE Trans. Inf. Theory.

[8]  Tung-Sang Ng,et al.  Karhunen-Loève Expansion of the WSSUS Channel Output and Its Applications to Efficient Simulation , 1997, IEEE J. Sel. Areas Commun..

[9]  Zwi Altman,et al.  Handover Adaptation for Dynamic Load Balancing in 3GPP Long Term Evolution Systems , 2007, MoMM.

[10]  Werner Kozek,et al.  On the transfer function calculus for underspread LTV channels , 1997, IEEE Trans. Signal Process..

[11]  Sagar Patel,et al.  Automated troubleshooting of a mobile communication network using Bayesian networks , 2002, 4th International Workshop on Mobile and Wireless Communications Network.

[12]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[13]  C.-C. Jay Kuo,et al.  Multicell OFDMA Downlink Resource Allocation Using a Graphic Framework , 2009, IEEE Transactions on Vehicular Technology.

[14]  A. Dobson.  An Introduction to Generalized Linear Models, Second Edition , 2001 .

[15]  Peter Adam Hoeher,et al.  A statistical discrete-time model for the WSSUS multipath channel , 1992 .

[16]  Tung-Sang Ng,et al.  Efficient simulation of digital transmission over WSSUS channels , 1995, IEEE Trans. Commun..

[17]  Jan Mietzner,et al.  A rigorous analysis of the statistical properties of the discrete-time triply-selective mimo rayleigh fading channel model , 2007, IEEE Transactions on Wireless Communications.