kth.sePublications
Change search
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
AI Based Methods for Matrix Multiplication in High Resolution Simulations of Radio Access Networks
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematical Statistics.
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
AI Baserade Metoder för Matris Multiplikationer för högupplösta simuleringar av Radionätverk (Swedish)
Abstract [en]

The increasing demand for mobile data has placed significant strain on radio access networks (RANs), leading to a continuous need for increased network capacity. In keeping with that, a significant advancement in modern RANs is the ability to utilize several receivers and transmitters, to allow for beamforming. One way to increase the capacity of the network is therefore to optimize the resource allocation by preprocessing the transmitted signals, which involves several costly matrix multiplications (MMs). The aim of the project was to investigate the potential of accelerating Ericsson's RAN simulations by using AI based approximate matrix multiplication (AMM) algorithms. The main focus was on the multiply additionless (MADDNESS) algorithm, a product quantization technique that has achieved speedups of up to 100 times compared to exact MM, and 10 times faster than previous AMM methods. A complex matrix handling version of MADDNESS was implemented in Java and Python respectively, and its speed and accuracy were evaluated against Ericsson's current MM implementation. The proposed implementation did not beat the benchmark with respect to speed, instead resulting in a 4-10 times slowdown in runtime. However, this may largely be due to the fact that the used languages do not allow for complete control over memory resource allocation. As such, the implementations at hand do not incorporate all the crucial features of the algorithm. Particularly, the handicapped version does not fully leverage the vectorization potential, which is one of the key contributors to the speed of the algorithm. Consequently, further improvements are necessary before employing the techniques in an end-to-end implementation.

Abstract [sv]

Den växande efterfrågan på mobildata har ökat belastningen på dagens radionätverk (RAN) och har medfört ett behov av att utvidga dess kapacitet. En betydande innovation inom RAN är beamforming, vilket är förmågan att fokusera digitala signaler mot mottagaren och på så vis öka singalstyrkan. En metod för att öka kapaciteten i ett nätverk är att optimera både kvaliteten av och resursallokeringen mellan nätverkets digitala kanaler, vilket medför tidskrävande matrismultiplikationer. Syftet med denna studie var att utforska om AI-baserade approximativa matrismultiplikationsalgoritmer har potentialen att accelerera Ericssons digitala tvilling-simuleringar. Studien fokuserade i huvudsak på produktkvantiseringsalgoritmen MADDNESS som påvisat potentialen att accelerera exakta matrismultiplikationer med en faktor 100, samt en faktor 10 snabbare än jämförbara approximativa metoder. En modifierad version av MADDNESS, som behandlar komplexa matriser, implementerades i Java samt Python, varefter precisionen och hastigheten utvärderades. Den föreslagna implementationen resulterade i en försämring med avseende på hastigheten med en faktor 4-10 jämfört med Ericssons nuvarande algoritmer. Den föreslagna implementationen saknar effektiv minnesallokering och misslyckas följaktligen att till fullo ta tillvara på vektoriseringspotentialen i MADDNESS. Detta indikerar att det är nödvändigt för ytterligare förbättringar innan algoritmen är användbar i den givna simuleringsmiljön.

Place, publisher, year, edition, pages
2023. , p. 62
Series
TRITA-SCI-GRU ; 2023:052
Keywords [en]
Product-Quantization, MADDNESS, Radio Access Networks, Channel Estimation, MIMO, Approximate Matrix Multiplication
Keywords [sv]
Pruduktkvantisering, MADDNESS, RAN, MIMO, Approximativa matrismultiplikation
National Category
Other Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-327628OAI: oai:DiVA.org:kth-327628DiVA, id: diva2:1761894
External cooperation
Ericsson AB
Subject / course
Mathematical Statistics
Educational program
Master of Science - Applied and Computational Mathematics
Supervisors
Examiners
Available from: 2023-06-08 Created: 2023-06-02 Last updated: 2023-06-08Bibliographically approved

Open Access in DiVA

fulltext(1128 kB)641 downloads
File information
File name FULLTEXT01.pdfFile size 1128 kBChecksum SHA-512
f88517c208687520dff7bbc08c8e09ff617844e8c5b48dfd4de77715de7da8c188ce450c0b437bda3cf1c8fc6a08f5096eafc4db41b66f9297899d2b5fb140d0
Type fulltextMimetype application/pdf

By organisation
Mathematical Statistics
Other Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 641 downloads
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: 574 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