kth.sePublications KTH
Operational message
There are currently operational disruptions. Troubleshooting is in progress.
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Meta-Learning-Based Fronthaul Compression for Cloud Radio Access Networks
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2025 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This work explores the application of a GRU-based meta-learning method to improve fronthaul compression efficiency in Cloud Radio Access Networks (C-RAN), a critical component of 5G. The goal is to accelerate the optimization of transformation matrices used for compressing and decompressing high-dimensional signals between remote radio heads (RRHs) and the central processor, by reducing convergence time and signaling overhead. The system sum rate is the optimization objective. The method, proposed by Ruihua Qiao, Tao Jiang, and Wei Yu at the University of Toronto, is divided into two stages: first, fully connected neural networks generate initial suboptimal matrices from local CSI at each RRH; second, GRU-blocks iteratively refine these matrices based on current and historical gradient information. By applying meta-learning with a low-dimensional gradient signaling scheme, the number of signaling rounds is significantly reduced compared to traditional gradient descent and naive global CSI transmissions. Simulations show that communication overhead is reduced while maintaining system sum rate performance.

Abstract [sv]

Detta arbete utforskar en GRU-baserad meta-lärningsmetod för att förbättra effektiviteten av fronthaul-kompression i ett användarcentrerat Cloud Radio Access Networks (C-RAN), en kritisk komponent i 5G. Målet är att påskynda optimeringen av transformationsmatriserna som används för att komprimera och dekomprimera högdimensionella signaler mellan fjärrradioenheterna (RRHs) och den centrala processorn, genom att minska konvergenstiden och signaling overhead. Systemets end-to-end sum-rate är optimeringsmålet. Metoden föreslogs av Ruihua Qiao, Tao Jiang och Wei Yu vid University of Toronto, och är uppdelad i två steg. Först genererar helt anslutna neurala nätverk initiala, suboptimala transformationsmatriser baserat på lokal CSI vid varje RRH. Därefter förfinas dessa matriser iterativt med GRU-block som uppdaterar dem utifrån aktuell och historisk gradientinformation. Genom att tillämpa meta-lärning och ett föreslaget lågdimensionellt gradient signaling scheme minskas antalet signaleringsrundor jämfört med traditionell gradientnedstigning och direkta globala CSI-överföringar. Simuleringar visar att communication overhead minskar avsevärt, samtidigt som systemets sum-rate bibehålls.

Place, publisher, year, edition, pages
2025. , p. 445-451
Series
TRITA-EECS-EX ; 2025:143
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-376165OAI: oai:DiVA.org:kth-376165DiVA, id: diva2:2034525
Supervisors
Examiners
Projects
Kandidatexamensarbete i Elektroteknik 2025, EECS, KTHAvailable from: 2026-02-02 Created: 2026-02-02

Open Access in DiVA

fulltext(80627 kB)9 downloads
File information
File name FULLTEXT01.pdfFile size 80627 kBChecksum SHA-512
35ce0a386dafe4649eb99cbe0efdfed651a3c9044e3339612422234d17a7e8ec21d4fd4aa201500c3c7a8f57194994b78b3e0cfbd5319ecd49f18a5d8a7ff775
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 4084 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf