Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
UCrea
Master thesis . 2020
License: CC BY NC ND
Data sources: UCrea
versions View all 4 versions
addClaim

Predicción con datos SCADA de series temporales

Time series forecasting for SCADA data
Authors: Martínez-Conde Salamanca, Miguel;

Predicción con datos SCADA de series temporales

Abstract

RESUMEN: El análisis de series temporales ha adquirido un gran protagonismo en el ámbito académico dadas sus implicaciones en áreas como la ingeniería, las finanzas o las ciencias sociales. El objetivo en este caso no es ahondar en dicho ámbito, sino trasladarlo a un entorno industrial con series temporales que presentan características más dispares y, en ocasiones, intermitencias. En la presente memoria se realiza una implementación de varios modelos de machine learning acerca de datos SCADA (Supervisory Control And Data Acquisition) de series temporales referidas a consumos de energía en una planta industrial con el objetivo de evaluar sus resultados para la toma de decisiones operativas en este contexto. Los modelos que se implementarán, previa aplicación de técnicas de curación y preprocesado de datos, serán máquinas de vectores soporte, modelos aditivos generalizados y modelos de ensembles en sus vertientes de bagging y boosting. Un modelo final será propuesto como una combinación de todos los anteriores adoptando de nuevo una metodología de ensembles y los modelos stacking, mediante la estimación de un meta-modelo. En última instancia, se elaborar án las predicciones para diferentes horizontes temporales que permitan obtener conclusiones sobre la viabilidad de la aplicación de estas técnicas en un ámbito centrado en la toma de decisiones operativas y que contribuya de forma aditiva a un análisis similar como el elaborado por Meneses Agudo et al. (2019).

ABSTRACT: Time series analysis has gained weight in the academic literature because of its growing penetration in areas such as engineering, finance or social sciences. The objective of the present thesis is not to research further and get a deeper look at these techniques, but rather translate their application to the industrial sector, in time series with heterogenous characteristics and, in some occasions, and intemittent behaviour. In this thesis we implement several machine learning models to time series of SCADA data (Supervisory Control and Data Acquisition) referring to energy consumption in an industrial plant, with the objective to evaluate the appropiateness of their results in order to improve the firm’s decision making. Previous to the application of these models, curation and preprocessing techniques will be applied to the data. The specific models applied are Support Vector Machines, Generalized Additive Models and Ensembles models in their bagging and boosting variations. A final model will be propposed as a combination of the mentioned models through a new ensembles methodoloy and stacking models, with the estimation of a meta-model.

Máster en Ciencia de Datos

Country
Spain
Related Organizations
Keywords

Series temporales, Time series, Machine learning, Predicción, SCADA, Forecasting

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 108
    download downloads 128
  • 108
    views
    128
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
108
128
Green