MétaCan
Menu
Back to cohort
Record W7006478797

Two-Stage Stochastic Optimization for Peak Load Reduction in Smart District Microgrid

2022· other· fr· W7006478797 on OpenAlexaboutno aff

Bibliographic record

VenuePolyPublie (École Polytechnique de Montréal) · 2022
Typeother
Languagefr
FieldMedicine
TopicBiological and pharmacological studies of plants
Canadian institutionsnot available
Fundersnot available
KeywordsWork (physics)LimitingField (mathematics)Context (archaeology)
DOInot available

Abstract

fetched live from OpenAlex

RÉSUMÉ: Les microréseaux offrent une diversité de ressources énergétiques distribuées pour fournir de l'électricité aux propriétaires de bâtiments, et ainsi contribuer à la réduction de la facture énergétique et les émissions de gaz à effet de serre. En effet, les sources d'énergies renouvelables sont propres et peu coûteuses, mais elles ont la particularité d'avoir un caractère intermittent. Pour la clientèle de grande puissance, les microréseaux peuvent également contribuer à l'écrêtage de la demande de pointe locale. Cependant, définir le dimensionnement et l'opération optimaux d'un microréseau compte tenu des incertitudes liées à la génération et à la consommation est un grand défi. Ces incertitudes doivent être adéquatement modélisées pour la gestion optimale d'un microréseau. L'optimisation stochastique offre un cadre approprié pour l'ople dimensionnement et l'opération du microréseau dans un contexte incertain. Ce-pendant, il existe un besoin accru pour le développement d'approches de génération et de réduction de scenarios pour limiter le temps de calcul de tels problèmes. Dans cette étude, un problème d'optimisation stochastique en deux étapes comprenant le dimensionnement et le fonctionnement d'un microréseau pour la réduction de la charge de pointe est proposé. Un réseau antagoniste génératif (GAN) a été proposé pour générer des scénarios de profils de puissance PV et de demande électrique. En raison d'un grand nombre de scénarios, la technique de réduction de scénarios K-medoids a été appliqué. Les résultats du cas d'étude d'un campus canadien ont démontré que la méthode proposée réduisait les coûts ainsi que la demande de pointe en utilisant des systèmes de production d'énergie PV et du stockage sur batterie. ABSTRACT: Microgrids offer a diversity of distributed energy resources to supply electricity to building owners, and thus contribute to the reduction of energy bills and greenhouse gas emissions. Indeed, renewable energy sources are clean and inexpensive, but they have the particularity of being intermittent. For large-power customers, microgrids can also contribute to local peak-shaving. However, defining the optimal sizing and operation of a microgrid considering generation and consumption uncertainties is a big challenge. These uncertainties must be adequately modeled for the optimal management of a microgrid. Stochastic optimization provides an appropriate framework for microgrid sizing and operation under uncertainty. However, there is an increased need for the development of scenarios generation and reduction approaches to limit the computation time of such problems. In this study, a two-stage stochastic optimization problem including sizing and operation of a MG and peak load reduction has been solved. A generative Adversarial Network (GAN) was proposed to generate PV power and electrical load demand scenarios. Due to a large number of scenarios, the K-medoids scenario reduction technique has been applied. The results of the case study of a Canadian university campus, showed that the proposed method decreased costs and properly shaved peak loads using PV power generation and battery storage systems.

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: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.012
Threshold uncertainty score0.024

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.000

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 head0.019
GPT teacher head0.267
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
GenreEmpirical

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 venuePolyPublie (École Polytechnique de Montréal)Same topicBiological and pharmacological studies of plantsFrench-language works237,207