MétaCan
Menu
Back to cohort
Record W7118929820 · doi:10.5281/zenodo.18168106

AI-Powered Network Optimization: Application of Artificial Intelligence in Optimizing Network Performance, Including Self-Healing and Self-Optimizing Capabilities

2022· article· en· W7118929820 on OpenAlexaff
Praveen Hegde, Robin Joseph Varughese

Bibliographic record

VenueZenodo (CERN European Organization for Nuclear Research) · 2022
Typearticle
Languageen
FieldComputer Science
TopicSoftware-Defined Networks and 5G
Canadian institutionsMarriott International (Canada)
Fundersnot available
KeywordsRobustness (evolution)ScalabilityReinforcement learningQuality of serviceArtificial neural networkNetwork performanceNetwork serviceFault toleranceService provider

Abstract

fetched live from OpenAlex

The development of data traffic and the increasing complexity of telecommunication networksnecessitate a transition from manual to intelligent network management. AI has recently emergedas a disruptive solution for network performance optimization, with the capability to handle largedatasets, detect patterns, and make real-time decisions. This paper considers a range of AIapproaches to network optimization, especially those with self-healing and self-optimizingfeatures. Self-healing networks utilize machine learning algorithms to automatically detect errors,perform root cause analysis, and facilitate fault recovery without human intervention. Thisapproach enhances service availability and reduces operational expenses. Self-optimizingnetworks (SONs), however, dynamically adapt parameters such as bandwidth, power, andhandover thresholds to provide optimal system performance in response to real-time traffic anduser behavior. Incorporating AI practices (such as deep learning, reinforcement learning, andanomaly detection) into the network helps ensure that congestion, latency, and equipment failureare addressed before the problem becomes acute for a subscriber. Illustrative examples from 5Gand future networks demonstrate the performance improvements in quality of service (QoS),resource utilization, and network reliability. However, model interpretability, data privacy, anddeployment scalability still present significant challenges. This paper concludes with strategicinsights for AI-enabled network optimization deployments, discussing the robustness of datapipelines, ethical AI governance, and the benefits of cross-layer data-driven strategies.

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)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Other · Consensus signal: none
Teacher disagreement score0.003
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0030.003
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.000

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 head0.026
GPT teacher head0.240
Teacher spread0.214 · 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 designNot applicable
Domainnot available
GenreOther

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

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueZenodo (CERN European Organization for Nuclear Research)Same topicSoftware-Defined Networks and 5GFrench-language works237,207