MétaCan
Menu
Back to cohort

Solver-Free Data Generation for Training Neural Networks with Applications in Power Flow Analysis

2025· article· W4416341619 on OpenAlexaff
Fuat Can Beylunioğlu, Mehrdad Pirnia, P. Robert Duimering

Bibliographic record

Venuenot available
Typearticle
Language
FieldPhysics and Astronomy
TopicModel Reduction and Neural Networks
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsArtificial neural networkBounded functionOptimization problemRelation (database)Function (biology)Test dataConstruct (python library)Function approximation

Abstract

fetched live from OpenAlex

As universal function approximators, Neural Networks (NN) can approximate any function with less than a desired error anywhere within a bounded domain. However, existing studies that train NNs to solve optimization problems based on solver-generated datasets, cannot yet produce predictions with desired accuracy. Motivated by the Universal Approximation Theorem (UAT), this paper examines the accuracy of NN prediction in relation to dataset size, problem size, and the construction of training data. Our study shows that a sufficiently large NN can produce accurate predictions when trained with very large datasets, but even so its performance is limited by the quality of the training dataset, which is traditionally obtained by the solution of optimization problems for any given input. A novel data generation approach is proposed for training NN to solve optimization problems, particularly the power flow (PF) problem. The method bypasses the need for solvers to construct datasets by directly utilizing the PF equations. Applications to IEEE test systems show that the proposed approach outperforms solver-based NNs and different optimization algorithms by a wide margin.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.974
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.002
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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 head0.050
GPT teacher head0.297
Teacher spread0.247 · 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 teacher head, not a consensus.

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicModel Reduction and Neural NetworksFrench-language works237,207