In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of autoencoders (AE) for cell outage detection. First, we briefly introduce deep learning (DL) and also shed light on why it is a promising technique to make self organizing networks intelligent, cognitive, and intuitive so that they behave as fully self-configured, self-optimized, and self-healed cellular networks. The concept of SON is then explained with applications of intrusion detection and mobility load balancing. Our empirical study presents a framework for cell outage detection based on an autoencoder using simulated data obtained from a SON simulator. Finally, we provide a comparative analysis of the proposed framework with the existing frameworks.

Recent years have seen the proliferation of different techniques for outdoor and, especially, indoor positioning. Still being a field in development, localization is expected to be fully pervasive in the next few years. Although the development of such techniques is driven by the commercialization of location-based services (e.g., navigation), its application to support cellular management is considered to be a key approach for improving its resilience and performance. When different approaches have been defined for integrating location information into the failure management activities, they commonly ignore the increase in the dimensionality of the data as well as their integration into the complete flow of networks failure management. Taking this into account, the present work proposes a complete integrated approach for location-aware failure management, covering the gathering of network and positioning data, the generation of metrics, the reduction in the dimensionality of such data, and the application of inference mechanisms. The proposed scheme is then evaluated by system-level simulation in ultra-dense scenarios, showing the capabilities of the approach to increase the reliability of the supported diagnosis process as well as reducing its computational cost.