MétaCan
Menu
Back to cohort
Record W7120422795

Optimal selection of energy storage system in distribution networks with distributed generation considering operation model by neural networks

2019· dissertation· pt· W7120422795 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

aboutThe title or abstract carries a Canadian signal from the geographic lexicon.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueLA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2019
Typedissertation
Languagept
FieldEngineering
TopicOptimal Power Flow Distribution
Canadian institutionsnot available
Fundersnot available
KeywordsArtificial neural networkBattery (electricity)Distributed generationGenetic algorithmRenewable energyEnergy storageFitness functionMonte Carlo methodPower (physics)
DOInot available

Abstract

fetched live from OpenAlex

This thesis presents a methodology for optimal determination of type, bar, and capacity of Battery Energy Storage Systems (BESS) in distribution systems with distributed generation (DG) where the battery optimal operation is approximated by an input/output model created with neural networks. A genetic algorithm selects the storage by a fitness function defined with the annual operation costs of the distribution system, the voltage limits, and batteries costs. The model allows to compare different types of batteries technologies, considering its technical and economical characteristics. Lifetime of the battery is based on the depth of discharge (DOD) impact to the life cycle. The database for the input/output model is obtained by a Monte Carlo simulation of the optimal daily operation of the battery for a representative sample from a yearly real data. This approach allows to consider the stochastic behavior of the distributed generation, the load and the energy prices. The daily operation of the battery is optimized by a nonlinear optimization model, considering a load flow by OpenDSS proprietary software from the Electric Power System Research Institute (EPRI). The neural network was based on the Group Method of Data Handling (GMDH). The neural network implementation allows to reduce the yearly simulation time, where the possible selection alternatives are chosen by the genetic algorithm. This methodology is tested in a distribution system of 33 nodes, and the generation, demand, and prices curves are taken from data of the Independent Electricity System Operator IESO relative to the Canadian distribution system, considering solar and wind as renewable sources. The studied case shows a good approximation of the neural network with the obtained data for the daily load flow and allows to identify the critic cases of the systems, as bar location not allowed and probability of risk of the results. The results compare the use of the batteries in the distribution network, reducing losses and operational costs along the day in the system and selecting the best type. Also, the storage systems can reduce the final energy cost of the system (limited by the proposed constraints) and the loses, with the possibility to determine the best alternative.

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.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.827
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0020.002
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 head0.012
GPT teacher head0.215
Teacher spread0.203 · 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