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
Towards Learning for System Behavior
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Traditional network management typically relies on clever heuristics to capture thecharacteristics of environments, workloads in order to derive an accurate model.While such methodology has served us well in early days, it is challenged by thegrowing intricacies of modern network design from various dimensions: the rocketingtraffic volumn, proliferation of software applications and varied hardware, higheruser-specific Quality of Experience (QoE) requirements with respect to bandwidthand latencies, overwhelming number of knobs and configurations and so forth. Allthese surging complexity and dynamics pose greater difficulty on us to understandand derive management rules to reach global optimum with heuristics that fits thedynamic context. Driven by the pulls of the challenges and encouraged by the successin machine learning techniques, this work elaborates on augmenting adaptive systemsbehaviors with learning approaches. This thesis specifically investigates the use caseof the packet scheduling. The work explores the opportunity to augment systemsto learn existing behaviors and explore custom behaviors with Deep ReinforcementLearning (DRL). We show the possibility to approximate the existing canonicalbehaviors with a generic representation, meanwhile, the agent is able to explorecustomized policy that are comparable to the state-of-art approaches. The resultsdemonstrate the potentials of learning based approaches as an alternative to canonicalscheduling approaches.

Abstract [sv]

Traditionell nätverkshantering bygger vanligtvis på smart heuristik för att fångaegenskaper hos miljöer, arbetsbelastning för att få en exakt modell. Medan sådan metodik har fungerat bra i början av dagen, utmanas den av växande intricacies av modern nätverksdesign från olika dimensioner: rocketing Traumatiska volymer, spridning av programvaror och varierad hårdvara, högre Krav på användarspecifik kvalitet av erfarenhet (QoE) med avseende på bandbredd och latenser, överväldigande antal knoppar och konurationer och så vidare. allt Dessa växande komplexitet och dynamik gör oss mer engagerade i förståelsen och härleda ledningsregler för att nå global optimalt med heuristik som ts dynamiskt sammanhang. Drivs av utmaningarna och uppmuntras av framgången I maskininlärningsteknik utarbetar detta arbete på att öka adaptiva system beteenden med inlärningsmetoder. Denna avhandling anger användningsfallet eller paketplaneringen. Arbetet undersöker möjligheten attöka systemen att lära sig befintliga beteenden och utforska anpassade beteenden med Deep Reinforcement Lärande (DRL). Vi visar möjligheten att approximera den befintliga canonicalen Beteende med en generisk representation, under tiden kan agenten utforska anpassade policyer som är jämförbara med state-of-the-art-metoder. Resultaten visa potentialen att lära sig baserade metoder som ett alternativ tillcanonical planeringsmetoder.

Place, publisher, year, edition, pages
2019. , p. 52
Series
TRITA-EECS-EX ; 2019:61
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-253203OAI: oai:DiVA.org:kth-253203DiVA, id: diva2:1324226
Educational program
Master of Science - Wireless Systems
Examiners
Available from: 2019-06-13 Created: 2019-06-13 Last updated: 2019-06-13Bibliographically approved

Open Access in DiVA

fulltext(4342 kB)59 downloads
File information
File name FULLTEXT01.pdfFile size 4342 kBChecksum SHA-512
3cf66016298bd5679c5464abe9a2b667ea510caca2f64c520c5333d9252d375ddfbc664a90f83ba78839bcd989310d8791b6a465acba1bec93bd42b75a374fd3
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 59 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: 272 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