Location-Awareness for Failure Management in Cellular Networks: An Integrated Approach

Abstract

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.

Noisy Neighbour Impact Assessment and Prevention in Virtualized Mobile Networks

“…1) Prediction of KPIs: The objective of the following model is to forecast the performance of the network, based on users traffic demand conditions (given by Packet rate, Packet size, Number of UE) and the CPU consumption stats of the 5GC. In this way, and in a similar fashion to previous works dedicated to the estimation of cellular network quality of experience / key quality indicators (KQI) under different radio conditions [4,37,39], the proposed model will enable the possibility of forecasting the performance obtained by applying each of the potential solutions, in order to choose the most convenient for a specific situation.…”

“…Taking these works as a reference, several ML classification models [35,36] have been evaluated through the proposed scenario: Logistic Regression based classifier (LR), K-Nearest Neighbours (KNN) [37], RF, Decision Tree (DT), SVM with cubic polynomial kernel, and the stacking method, which considers all these algorithms as level-0, and LR for level-1. All the models are evaluated through a cross-validation with 3 folds and 10 repetitions over the entire dataset.…”

Accurate and Low-Complexity Auto-Fingerprinting for Enhanced Reliability of Indoor Localization Systems

“…However, the effect of obstacles and Non-Line-Of-Sight (NLOS) propagation [ 3 ] make GNSS essentially unavailable or very inaccurate in indoor scenarios [ 4 ]. This implies a huge barrier for the implementation of many applications of positioning, logistics [ 5 ], games and augmented reality applications [ 6 , 7 ] and even the management of cellular networks [ 8 , 9 , 10 , 11 ] indoors.…”

Location-Aware Node Management Solution for Multi-Radio Dual Connectivity Scenarios

“…However, the network operator can also use the location of the user equipments (UEs) to enhance their condition within the mobile network, improving the quality of experience (QoE) perceived in the applications they use. For example, the user location can be used to detect and manage network failures by generating new indicators about areas of interest [3] or to decrease the interference level by adjusting the transmission power [4,5]. These features can increase the overall performance obtained in the mobile network, which can lead users to perceive a better QoE because the increased network availability or the higher average Signal-to-Interference-plus-Noise Ratio (SINR).…”