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.