Several upcoming 5G and 6G services will rely on unmanned aerial vehicles (UAV) sending live information to remote terminals. Thus, understanding the traffic flows that might influence end-user experience in these services is key for cellular network operators. One of these UAV-based services is first person view (FPV) drone control, consisting on the remote control of the UAV in Beyond Visual Line of Sight scenarios using only the live video visualized in a ground control station. This work focuses on the networking aspects of this service by presenting the assembly, integration and evaluation methodology of an UAV quadrotor teleoperated via FPV through a Long Term Evolution (LTE) network or WiFi radio access link. To assess system performance, three different connectivity schemes between UAV and ground control station are tested, namely server-based connection via LTE, direct LTE, and peer-to-peer WiFi connection. Then, several experiments are carried out in the testbed to characterize telemetry, control and video traffic for FPV service in the above schemes. Later, a methodology is defined to estimate Quality of Experience (QoE) for FPV service based on image quality and video latency measurements collected at network and application level. Results show that the QoE model for live video introduced in this work can be the basis of more sophisticated models for cellular FPV services.

Cellular networks are constantly evolving, driven by changes in user behavior and device capabilities. To ensure that networks adapt to these changes, it is of vital importance for mobile operators to have a good understanding of how well their network meets subscriber needs. For this purpose, the Minimization of Drive Test (MDT) feature has been standardized, allowing operators the cost-effective provision of geolocated network performance statistics and radio events. However, in practice, positioning errors severely limit the potential of MDT measurements. In this paper, an in-depth analysis of a large MDT dataset taken from a commercial Long-Term Evolution (LTE) network shows for the first time several sources of positioning errors in MDT measurements not previously reported in the literature. To address these, a novel heuristic filtering algorithm is proposed to discard samples with inaccurate location data. Method assessment is done by checking the impact of filtering on the coverage map built with a real MDT dataset. Results show that the proposed filtering method significantly improves the accuracy of coverage maps by eliminating unreliable measurements.

In 5G systems, Network Slicing (NS) feature allows to deploy several logical networks customized for specific verticals over a common physical infrastructure. To make the most of this feature, cellular operators need models reflecting cell and slice performance for re-dimensioning the Radio Access Network (RAN). For enhanced Mobility BroadBand (eMBB) services, throughput is regarded as a key performance metric since it strongly influences user experience. This work presents the first comprehensive analysis tackling cell and slice throughput estimation in the downlink of RAN-sliced networks through Supervised Learning (SL), based on information collected in the operations support system. Different well-known SL algorithms are tested in two NS scenarios with single-service or multi-service slices serving eMBB users. To this end, several synthetic datasets are generated with a system-level simulator emulating the activity of a sliced RAN. Results show that NS alters the correlation between network performance indicators and cell throughput compared to legacy RANs, thus being required a separate analysis for NS scenarios. Moreover, the best model to estimate throughput at cell/slice level may depend on the scenario (single-service vs multi-service slices). In all cases, the best models have shown an estimation error below 10 %.

Due to the diversity of mobile services and rising user expectations, mobile network management has changed its focus from Quality of Service (QoS) to Quality of Experience (QoE). As a consequence, classical network optimization procedures must be updated accordingly. One of these optimization procedures is Mobility Robustness Optimization (MRO), whose aim is to improve HandOver (HO) performance by reducing HO failures. In this work, a novel QoE-aware MRO algorithm is proposed considering a multi-service scenario. Unlike previous approaches, whose aim is to increase successful handover rates, the optimization aim in this work is two-folded: to improve cell edge QoE while improving successful handover rates in the whole network. For this purpose, the handover trigger point, defined by the pair of HO control parameters HO margin and Time to Trigger, are tuned on a per-adjacency basis according to QoE and HO failure measurements. Method assessment is based on a dynamic system-level simulator implementing a realistic LTE scenario with multiple services. Results show that the proposed QoE-aware MRO algorithm improves cell edge QoE throughout the network while increasing the percentage of successful handovers compared to traditional approaches.

Network dimensioning is a critical task for cellular operators to avoid degraded user experience and unnecessary upgrades of network resources with changing mobile traffic patterns. For this purpose, smart network planning tools require accurate cell and user capacity estimates. In these tools, throughput is often used as a capacity metric due to its close relationship with user satisfaction. In this work, a comprehensive analysis is carried out to compare different well-known Supervised Learning (SL) algorithms for estimating cell and user throughput in the DownLink in busy hours from radio measurements collected on a cell basis in the Operation Support System (OSS). The considered SL approaches include random forest, shallow multi-layer perceptron, support vector regression and k-nearest neighbors. Such algorithms are compared with classical multiple linear regression and deep learning approaches considered in previous works. All these algorithms are tested in two radio access technologies: High Speed DownLink Packet Access (HSDPA) and Long Term Evolution (LTE). To this end, two datasets with the most relevant performance indicators per technology are collected from live cellular networks. Results show that non-deep SL algorithms are the most appropriate option for applications with storage constraints, such as network planning tools, since they provide a higher accuracy with reduced datasets.