Predicting user performance at the base station in telecom networks is a critical task that can significantly benefit from advanced machine learning techniques. However, labeled data for user performance are scarce and costly to collect, while unlabeled data consisting of base station metrics, are more readily accessible. Self-supervised learning provides a means to leverage this unlabeled data, and has seen remarkable success in the domains of computer vision and natural language processing, with unstructured data. Recently, these methods have been adapted to structured data as well, making them particularly relevant to the telecom domain. We apply self-supervised learning to predict user performance in telecom networks. Our results demonstrate that even with simple self-supervised approaches, the percentage of variance of the target values explained by the model, in low-labeled scenarios (e.g., only 100 labeled samples) can be improved fourfold, from 15% to 60%. Moreover, to promote reproducibility and further research in the domain, we open-source a dataset creation framework and a specific dataset created from it that captures scenarios that have been deemed to be challenging for future networks.

The use of machine learning (ML) in mobile networks has surged to tackle the challenges arising from their growing complexity, dynamic behavior, and application demands.However, more support through prediction models for key performance metrics that cannot be directly observed at the base station are needed to better adapt network and application parameters to the changing network state. Moreover, the growing adoption of ML models in telecom networks brings practical challenges, like the scarcity of labeled data for training, heterogeneity of hardware, and evolving conditions, all of which pose hurdles to their seamless deployment in real-world scenarios.

In this thesis we investigate ML-driven methods to predict user performance in dynamic environments and address the practical challenges encountered over a model’s life cycle. First, we present supervised ML approaches for predicting key metrics such as round-trip time and one-way delay, using data collected from 5G mmWave testbed networks.Further, we propose a mobile edge-assisted framework for improving quality of service (QoS) and reducing backhaul load for video streaming applications, by prefetching video segments, under backhaul bandwidth and cache storage restrictions. This framework is based on ML predictions of video segment bitrates in a dynamically changing mobile network. 

Next, we address domain shifts, particularly from the arrival of new user equipment (UE) types, by applying adversarial adaptation strategies that allow models to adapt without requiring labeled samples from the new domain.Further, we apply self-supervised learning approaches to harness unlabeled data from telecom network datasets. This is shown to improve model accuracy in label-scarce scenarios. Finally, to further mitigate data-collection challenges, we introduce an open-source simulation framework for generating large-scale, customizable datasets. Overall, this thesis contributes to the careful design of ML solutions for predicting key performance metrics, and shows how they can, along with robust data generation, model adaptation, and model pretraining techniques, elevate user experience and network automation in modern telecom networks.

Användningen av maskininlärning (ML) inom mobila telekomnätverk har ökat kraftigt för att tackla utmaningar som uppstått med nätverkens växande komplexitet och applikationskrav. Mer hjälp från modeller som kan ge prognoser över viktiga prestandavärden, som inte är direkt mätbara vid basstationen behövs dock för att anpassa nätverk och applikationsparametrar till kontinuerligt skiftande nätverkstillstånd.Den växande tillämpningen av ML-modeller för telekomnätverk för med sig praktiska utmaningar, så som brist på annoterad data för träning, varierande hårdvaruarkitekturer och ständigt förändrade nätverkstillstånd. Dessa hinder försvårar driftsättning av ML i verkliga system.I denna avhandling studerar vi ML-modeller för telekomnätverk samt flera praktiska utmaningar som uppstår under en modells livscykel. Först så presenterar vi vägledda ML-metoder som förutspår viktiga mätvärden inom 5G-nätverk. Dessa metoder tränas med data insamlad  från 5G mmWave testbädds-nätverk.Vidare så utvecklar vi en ML-driven mobile edge-lösning som förbättrar videokvaliteten för videoströmningstjänster i nätverket. Vår lösning bygger på smart förhandsinladdning av videosegment, där ML används för att förutspå lämplig kvalitet på videosegmenten.

Vi studerar också hur ML-modeller påverkas när nätverk ändras till en så stor grad att ett domänskifte sker. Vi tittar speciellt på situationen som uppstår när nya typer av användarutrustnings ansluter sig till nätverk. Genom att tillämpa adaptiva strategier visar vi att ML-modeller kan anpassas utan användandet av annoterad data från den nya domänen.

Vi undersöker också hur icke-vägledda ML-modeller kan utnyttja stora mängder oannoterad data som annars inte används. Vi visar hur dessa modeller kan integreras med vägledda modeller för att förbättra prognosprestandan, speciellt när det råder brist på annoterad data.

Slutligen så introducerar vi ett ramverk, skriven i öppen källkod, för att generera stora, anpassningsbara datamängder för mobila telekomnätverk. Allt inräknat så bidrar denna avhandling med ML-lösningar för bättre användarupplevelser samt drift av moderna telekomnätverk.

From a 5G operator's perspective, accurate estimates of key User Equipments (UEs) performance metrics, especially One-Way Delay (OWD), can provide valuable information. These estimates can trigger management tasks such as reconfiguration to prevent violations of Service Level Objectives (SLOs). Moreover, such insights into UE performance can empower applications to adapt their services to end-users in a more effective manner. We use advanced machine learning over data gathered at the base stations to predict OWD from UEs and show that we are able to predict OWD with over a 2x reduction in percentage error compared to the considered baseline. We discover the close coupling between the performance of the OWD model and the type of UE, which poses a model generalization challenge. Addressing this problem, we demonstrate the shortcomings of the commonly used fine-tuning approach and develop a novel method based on domain adversarial neural networks, that can adapt to a target domain without compromising on the performance of the source domain. Our results show that we can adapt our source model to provide OWD prediction performance within 1-4 percentage points of the ideal scenario when the source and the target domains are the same. Also, our work is grounded in empirical experiments conducted within a 5G testbed, using commercially available hardware.

Dynamic Adaptive Streaming over HTTP (DASH) is a standard for delivering video in segments and adapting each segment's bitrate (quality), to adjust to changing and limited network bandwidth. We study segment prefetching, informed by machine learning predictions of bitrates of client segment requests, implemented at the network edge. We formulate this client segment request prediction problem as a supervised learning problem of predicting the bitrate of a client's next segment request, in order to prefetch it at the mobile edge, with the objective of jointly improving the video streaming experience for the users and network bandwidth utilization for the service provider. The results of extensive evaluations showed a segment request prediction accuracy of close to 90% and reduced video segment access delay with a cache hit ratio of 58%, and reduced transport network load by lowering the backhaul link utilization by 60.91%.

The inherent flexibility of 5G networks come with a high degree of configuration and management complexity. This makes the performance outcome for UEs, more than ever, dependent on intricate configurations and interplay between algorithms at various network components. In this paper, we take initial steps towards a performance exposure system at the base station using a data-driven approach for predicting performance violations in terms of RTT, as observed by the UE, in a 5G mmWave network. We present ML models to predict RTT using low-level and high-frequency base station metrics from a 5G mmWave testbed based on commercially available equipment. Predicting UE performance from a base station perspective, and exposing this knowledge, is valuable for applications to proactively address performance violations. We also compare several methods for feature reduction, which have a significant impact on monitoring load. We demonstrate our model's ability to identify RTT violations, paving the way for network providers towards an intelligent performance exposure system. 

Exploring a large area can be conveniently performed by a team of small autonomous vehicles for different applications, such as search and rescue, cleaning, or lawn mowing. The efficiency and performance of such autonomous exploration depends on the exploration algorithm implemented by the vehicles, and can be enhanced with a better communication and collaboration strategy within the team. In this paper, a new algorithm is proposed and evaluated where vehicles with a limited communication range pro-actively seek their teammates to exchange information about the explored area. Simulations show that this approach allows the vehicles to finish the exploration and return to their base station 18% faster, without consuming more energy.

We are motivated by the problem of impromptu or as-you-go deployment of wireless sensor networks. As an application example, a person, starting from a sink node, walks along a forest trail, makes link quality measurements (with the previously placed nodes) at equally spaced locations, and deploys relays at some of these locations, so as to connect a sensor placed at some a priori unknown point on the trail with the sink node. In this paper, we report our experimental experiences with some as-you-go deployment algorithms. Two algorithms are based on Markov decision process (MDP) formulations, these require a radio propagation model. We also study purely measurement based strategies: one heuristic that is motivated by our MDP formulations, one asymptotically optimal learning algorithm, and one inspired by a popular heuristic. We extract a statistical model of the propagation along a forest trail from raw measurement data, implement the algorithms experimentally in the forest, and compare them. The results provide useful insights regarding the choice of the deployment algorithm and its parameters, and also demonstrate the necessity of a proper theoretical formulation.

Predicting user performance at the base station in telecom networks is a critical task that can significantly benefit from advanced machine learning techniques. However, labeled data for user performance are scarce and costly to collect, while unlabeled data consisting of base station metrics, are more readily accessible. Self-supervised learning provides a means to leverage this unlabeled data, and has seen remarkable success in the domains of computer vision and natural language processing, with unstructured data. Recently, these methods have been adapted to structured data as well, making them particularly relevant to the telecom domain. We apply self-supervised learning to predict user performance in telecom networks. Our results demonstrate that even with simple self-supervised approaches, the percentage of variance of the target values explained by the model, in low-labeled scenarios (e.g., only 100 labeled samples) can be improved fourfold, from 15% to 60%. Moreover, to promote reproducibility and further research in the domain, we open-source a dataset creation framework and a specific dataset created from it that captures scenarios that have been deemed to be challenging for future networks.