RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Generalizable Representation for Wireless Networks Optimization through Native Graph Topology
KTH, Skolan för elektroteknik och datavetenskap (EECS), Datavetenskap, Teoretisk datalogi, TCS. Ericsson Research.ORCID-id: 0000-0002-0866-8342
2025 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Graph representation learning has become a powerful paradigm for modeling structured data, enabling machine learning systems to reason over relationships, spatial dependencies, and topological patterns. However, its potential in wireless networks remains underexplored, particularly in learning native representations of complex and dynamic wireless environments. This thesis addresses the challenge of applying graph representation learning (such as graph neural networks and transformer architectures) to wireless systems, where topology, domain heuristics, and physical constraints critically impact optimization performance and generalization.

The core problem investigated is how to construct and exploit graph representations that faithfully encode the native structure of wireless networks to enable scalable, topology-aware optimization. This includes coverage relations, interference patterns, and environment-specific propagation effects. Existing solutions in wireless machine learning often overlook these structural priors, resulting in brittle models that generalize poorly across different network deployments.

This thesis introduces a graph-centric methodology to bridge this gap. By representing wireless elements—such as base stations, links, and coverage zones as nodes and their interactions as graph edges, we develop learning architectures that integrate attention mechanisms, domain-aware features, and physics-inspired constraints. Four studies demonstrate the approach across key tasks: routing latency prediction, antenna tilt optimization, real-time radio coverage estimation, and neural ray tracing for link-level modeling.

Our results suggest that these graph-based models significantly outperform traditional baselines, achieving near-simulator accuracy with improved generalization across unseen topologies and user scenarios. They also uncover a correspondence between engineering practices and graph spectral properties, offering a new lens for understanding network design. The proposed methods reduce supervision needs and support scalable deployment across variable network configurations.

Overall, this thesis establishes graph representation learning as a foundational tool for wireless intelligence, enabling structure-informed, optimization-driven modeling across diverse network conditions. These advances pave the way towards future wireless foundation models capable of supporting a wide range of optimization, sensing, and decision-making tasks with minimal retraining.

Abstract [sv]

Inlärning av grafrepresentation har blivit ett kraftfullt paradigm för modellering av strukturerad data, vilket gör det möjligt för maskininlärningssystem att resonera kring relationer, rumsliga beroenden och topologiska mönster. Dess potential inom trådlösa nätverk är dock fortfarande underutforskad, särskilt när det gäller att lära sig nativa representationer av komplexa och dynamiska trådlösa miljöer. Denna avhandling tar upp utmaningen att tillämpa inlärning av grafrepresentation – såsom grafiska neurala nätverk och transformatorarkitekturer – på trådlösa system, där topologi, domänheuristik och fysiska begränsningar kritiskt påverkar optimeringsprestanda och generalisering.

Det centrala problemet som undersöks är hur man konstruerar och utnyttjar grafrepresentationer som troget kodar den nativa strukturen i trådlösa nätverk för att möjliggöra skalbar, topologimedveten optimering. Detta inkluderar optimering av täckningsrelationer, interferensmönster och miljöspecifika utbredningseffekter. Befintliga lösningar inom trådlös maskininlärning förbiser ofta dessa strukturella förutsättningar, vilket resulterar i sköra modeller som generaliserar dåligt över implementeringar och erbjuder begränsad återanvändbarhet.

Denna avhandling introducerar en grafcentrerad metod för att överbrygga detta gap. Genom att representera trådlösa element – såsom basstationer, länkar och täckningszoner – som noder, och deras interaktioner som grafkanter, utvecklar vi inlärningsarkitekturer som integrerar uppmärksamhetsmekanismer, domänmedvetna funktioner och fysikinspirerade begränsningar. Fyra studier demonstrerar denna metod för viktiga trådlösa optimeringsuppgifter: förutsägelse av routinglatens, antennlutningskonfiguration, realtidsuppskattning av radiotäckning och neural strålspårning för modellering på länknivå.

Våra resultat visar att dessa grafbaserade modeller avsevärt överträffar traditionella baslinjer och uppnår nästan simulatornoggrannhet med förbättrad generalisering över osynliga topologier och användarscenarier. De avslöjar också korrespondenser mellan tekniska designmönster och grafspektralegenskaper, vilket erbjuder en ny lins för att förstå och optimera nätverksbeteende. De föreslagna metoderna minskar övervakningsbehovet och stöder skalbar distribution över variabla nätverkskonfigurationer.

Sammantaget etablerar denna avhandling grafrepresentationsinlärning som ett grundläggande verktyg för trådlös intelligens – vilket möjliggör strukturinformerad, optimeringsdriven modellering över olika nätverksförhållanden. Dessa framsteg banar väg för framtida trådlösa grundmodeller som kan stödja ett brett spektrum av uppgifter inom optimering, avkänning och beslutsfattande med minimal omskolning.

sted, utgiver, år, opplag, sider
Stockholm: KTH Royal Institute of Technology, 2025. , s. 58
Serie
TRITA-EECS-AVL ; 2025:88
Emneord [en]
Graph neural network, Wireless network, Representation learning, 5G & B5G, Digital twins
Emneord [sv]
Grafiskt neuralt nätverk, Trådlöst nätverk, Representationsinlärning, 5G & B5G, Digitala tvillingar
HSV kategori
Forskningsprogram
Datalogi; Elektro- och systemteknik
Identifikatorer
URN: urn:nbn:se:kth:diva-372589ISBN: 978-91-8106-418-6 (digital)OAI: oai:DiVA.org:kth-372589DiVA, id: diva2:2012871
Disputas
2025-12-16, Kollegiesalen, Brinellvägen 8, Stockholm, 13:15 (engelsk)
Opponent
Veileder
Merknad

QC 20251111

Tilgjengelig fra: 2025-11-11 Laget: 2025-11-10 Sist oppdatert: 2025-12-02bibliografisk kontrollert
Delarbeid
1. A Graph Attention Learning Approach to Antenna Tilt Optimization
Åpne denne publikasjonen i ny fane eller vindu >>A Graph Attention Learning Approach to Antenna Tilt Optimization
Vise andre…
2022 (engelsk)Inngår i: 2022 1St International Conference On 6G Networking (6GNET), Institute of Electrical and Electronics Engineers (IEEE) , 2022Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

6G will move mobile networks towards increasing levels of complexity. To deal with this complexity, optimization of network parameters is key to ensure high performance and timely adaptivity to dynamic network environments. The optimization of the antenna tilt provides a practical and cost-efficient method to improve coverage and capacity in the network. Previous methods based on Reinforcement Learning (RL) have shown effectiveness for tilt optimization by learning adaptive policies outperforming traditional tilt optimization methods. However, most existing RL methods are based on single-cell features representation, which fails to fully characterize the agent state, resulting in suboptimal performance. Also, most of such methods lack scalability and generalization ability due to state-action explosion. In this paper, we propose a Graph Attention Q-learning (GAQ) algorithm for tilt optimization. GAQ relies on a graph attention mechanism to select relevant neighbors information, improving the agent state representation, and updates the tilt control policy based on a history of observations using a Deep Q-Network (DQN). We show that GAQ efficiently captures important network information and outperforms baselines with local information by a large margin. In addition, we demonstrate its ability to generalize to network deployments of different sizes and density.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2022
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-320297 (URN)10.1109/6GNet54646.2022.9830258 (DOI)000860313400009 ()2-s2.0-85136105973 (Scopus ID)
Konferanse
1st International Conference on 6G Networking (6GNet), JUL 06-08, 2022, Orange, Paris, FRANCE
Merknad

Part of proceedings: ISBN 978-1-6654-6763-6

QC 20221024

Tilgjengelig fra: 2022-10-24 Laget: 2022-10-24 Sist oppdatert: 2025-11-10bibliografisk kontrollert
2. SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate
Åpne denne publikasjonen i ny fane eller vindu >>SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate
Vise andre…
2025 (engelsk)Inngår i: 2025 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025, Institute of Electrical and Electronics Engineers (IEEE) , 2025Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time interaction with radio environment during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, solved with the proposed Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH) approach. The SANDWICH approach leverages a decision transformer to jointly learn the optical, physical, and signal properties within each designated environment in a fully differentiable approach, which can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, and outperforms the baseline by 4e<sup>-2</sup> rad in RT accuracy. Furthermore, channel gain estimation w.r.t predicted trajectory only fades 0.5 dB away from using ground truth wireless RT result for channel gain estimation.<sup>2</sup>

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2025
Emneord
Channel Generation, Channel Modeling, RF Sensing, Wireless Raytracing
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-371723 (URN)10.1109/ICMLCN64995.2025.11139897 (DOI)2-s2.0-105016789661 (Scopus ID)
Konferanse
2nd IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025, Barcelona, Spain, May 26 2025 - May 29 2025
Merknad

Part of ISBN 979-8-3315-2042-7

QC 20251022

Tilgjengelig fra: 2025-10-22 Laget: 2025-10-22 Sist oppdatert: 2025-11-10bibliografisk kontrollert
3. Learning Cellular Coverage from Real Network Configurations using GNNs
Åpne denne publikasjonen i ny fane eller vindu >>Learning Cellular Coverage from Real Network Configurations using GNNs
2023 (engelsk)Inngår i: 2023 IEEE 97th Vehicular Technology Conference, VTC 2023-Spring - Proceedings, Institute of Electrical and Electronics Engineers (IEEE) , 2023Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Cellular coverage quality estimation has been a critical task for self-organized networks. In real-world scenarios, deep-learning-powered coverage quality estimation methods cannot scale up to large areas due to little ground truth can be provided during network design & optimization. In addition, they fall short in producing expressive embeddings to adequately capture the variations of the cells' configurations. To deal with this challenge, we formulate the task in a graph representation and so that we can apply state-of-the-art graph neural networks, that show exemplary performance. We propose a novel training framework that can both produce quality cell configuration embeddings for estimating multiple KPIs, while we show it is capable of generalising to large (area-wide) scenarios given very few labeled cells. We show that our framework yields comparable accuracy with models that have been trained using massively labeled samples.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2023
Emneord
Cellular Coverage Estimation, Few-shot Learning, Graph Neural Network, Self-supervised Learning
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-336725 (URN)10.1109/VTC2023-Spring57618.2023.10199469 (DOI)001054797200081 ()2-s2.0-85169786270 (Scopus ID)
Konferanse
97th IEEE Vehicular Technology Conference, VTC 2023-Spring, Florence, Italy, Jun 20 2023 - Jun 23 2023
Merknad

Part of ISBN 9798350311143

QC 20230919

Tilgjengelig fra: 2023-09-19 Laget: 2023-09-19 Sist oppdatert: 2025-12-08bibliografisk kontrollert
4. Open World Learning Graph Convolution for Latency Estimation in Routing Networks
Åpne denne publikasjonen i ny fane eller vindu >>Open World Learning Graph Convolution for Latency Estimation in Routing Networks
2022 (engelsk)Inngår i: 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), Institute of Electrical and Electronics Engineers (IEEE) , 2022Konferansepaper, Oral presentation with published abstract (Fagfellevurdert)
Abstract [en]

Accurate routing network status estimation is a key component in Software Defined Networking. However, existing deep-learning-based methods for modeling network routing are not able to extrapolate towards unseen feature distributions. Nor are they able to handle scaled and drifted network attributes in test sets that include open-world inputs. To deal with these challenges, we propose a novel approach for modeling network routing, using Graph Neural Networks. Our method can also be used for network-latency estimation. Supported by a domainknowledge-assisted graph formulation, our model shares a stable performance across different network sizes and configurations of routing networks, while at the same time being able to extrapolate towards unseen sizes, configurations, and user behavior. We show that our model outperforms most conventional deep-learningbased models, in terms of prediction accuracy, computational resources, inference speed, as well as ability to generalize towards open-world input.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2022
Serie
IEEE International Joint Conference on Neural Networks (IJCNN), ISSN 2161-4393
Emneord
Graph Convolution, Software Define Networks, Open World Learning
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-322283 (URN)10.1109/IJCNN55064.2022.9892952 (DOI)000867070908062 ()2-s2.0-85140761415 (Scopus ID)
Konferanse
IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC), JUL 18-23, 2022, Padua, ITALY
Merknad

Part of proceedings: ISBN 978-1-7281-8671-9

QC 20221219

Tilgjengelig fra: 2022-12-08 Laget: 2022-12-08 Sist oppdatert: 2025-11-10bibliografisk kontrollert

Open Access i DiVA

Kappa(1269 kB)173 nedlastinger
Filinformasjon
Fil FULLTEXT06.pdfFilstørrelse 1269 kBChecksum SHA-512
4a09326299baa62812226deaee783f50f39bc963e27e1d9a80da2ed5b2bd58d7472c41840d6af98d79bf2cc137f4e19967013e08bd8996b8aec99e2d6d8e7984
Type fulltextMimetype application/pdf

Søk i DiVA

Av forfatter/redaktør
Yifei, Jin
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 192 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 2028 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf