MétaCan
Menu
Back to cohort
Record W2907894052 · doi:10.22215/etd/2015-11198

Lightweight Robust Optimizer for Distributed Application Deployment in Multi-Clouds

2015· dissertation· en· W2907894052 on OpenAlexaff
Ravneet Kaur

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldEngineering
TopicVLSI and FPGA Design Techniques
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer scienceSoftware deploymentCloud computingDistributed computingSimulated annealingGraphPower consumptionEnhanced Data Rates for GSM EvolutionGraph partitionBin packing problemBinParallel computingMathematical optimizationTheoretical computer scienceAlgorithmPower (physics)MathematicsArtificial intelligence

Abstract

fetched live from OpenAlex

Cloud computing refers to the applications and services that run on a distributed network using virtualized resources and accessed by common Internet protocols and networking standards.In cloud computing, an edge cloud is close to some of the end users, to give faster service for very demanding applications.Transactions that require heavy processing capacity and longer processing times are better carried out at the core cloud.To deploy applications with many tasks across a cloud infrastructure, many goals must be satisfied, which poses a large and complex optimization problem.Meeting latency constraints is an important requirement in future cloud applications and is critical in task deployment.This thesis creates a new approach for task assignment in an edge-core multicloud architecture to reduce power consumption in service centers using multilevel graph partitioning technique.Multilevel graph partitioning has three phases of coarsening, refinement and uncoarsening.For the refinement phase, a new algorithm based on a modified Kernighan-Lin algorithm is proposed which takes into account multiple constraints, and that mitigates the problem of stopping at a local minimum.Once tasks are assigned to the edge and core, multidimensional bin-packing is used to deploy tasks to individual hosts so that power consumption can be calculated.The approach is validated by comparing it to extended simulated annealing and an extended modified Kernighan-Lin algorithm.The experiments show that our approach is fast and produces better results.It is also less prone to failure in finding a feasible deployment for given constraints.me grow and mature as a serious graduate researcher and made this thesis an enjoyable experience.I thank members of SAVI group for their valuable comments and ideas, which were indispensable in producing this thesis.I would like to acknowledge and thank my colleagues Adnan Faisal, Farhana Islam and Derek Hawker for their friendly, often philosophical, discussions which made me laugh and kept me engaged.I would also like to express my gratitude to the professors, staff and students at the department of Systems and Computer Engineering for making my work an enjoyable experience.I would like to thank the most supportive, affectionate and

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.003
Threshold uncertainty score0.008

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.028
GPT teacher head0.276
Teacher spread0.248 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2015
Admission routes1
Has abstractyes

Explore more

Same topicVLSI and FPGA Design TechniquesFrench-language works237,207