TU Darmstadt / ULB / TUbiblio

Very Short-Term Load Forecasting on Factory Level — A Machine Learning Approach

Walther, Jessica and Spanier, Dario and Panten, Niklas and Abele, Eberhard (2019):
Very Short-Term Load Forecasting on Factory Level — A Machine Learning Approach.
In: Procedia CIRP, 26th CIRP Conference on Life Cycle Engineering Purdue University, West Lafayette, IN (USA), Elsevier B.V., pp. 705-710, 80, DOI: 10.1016/j.procir.2019.01.060,
[Article]

Abstract

In the context of energy transition in Germany, precise load forecasting enables reducing the impact of increased volatility in power generation induced by renewable energies. This paper presents a machine learning approach to generate a 15 minutes forecasting model of the electric load for the ETA research factory at TU Darmstadt on a factory level. In the first iteration, a feature selection process was conducted to select significant features for machine learning datasets. The raw data contained 1,554 features from machine tools, technical building equipment, the building itself and external factors like the weather. The second iteration examined the forecasting capabilities of six hyperparameter tuned algorithms on the feature selected datasets. In the third iteration, feature engineering and hyperparameter tuning led to an optimized Gradient Boosting Regression Trees (GBRT) algorithm. The results indicate that the utilized machine learning approach is feasible and creates a precise very short term load forecasting model, depending on the use case of the load forecast.

Item Type: Article
Erschienen: 2019
Creators: Walther, Jessica and Spanier, Dario and Panten, Niklas and Abele, Eberhard
Title: Very Short-Term Load Forecasting on Factory Level — A Machine Learning Approach
Language: English
Abstract:

In the context of energy transition in Germany, precise load forecasting enables reducing the impact of increased volatility in power generation induced by renewable energies. This paper presents a machine learning approach to generate a 15 minutes forecasting model of the electric load for the ETA research factory at TU Darmstadt on a factory level. In the first iteration, a feature selection process was conducted to select significant features for machine learning datasets. The raw data contained 1,554 features from machine tools, technical building equipment, the building itself and external factors like the weather. The second iteration examined the forecasting capabilities of six hyperparameter tuned algorithms on the feature selected datasets. In the third iteration, feature engineering and hyperparameter tuning led to an optimized Gradient Boosting Regression Trees (GBRT) algorithm. The results indicate that the utilized machine learning approach is feasible and creates a precise very short term load forecasting model, depending on the use case of the load forecast.

Journal or Publication Title: Procedia CIRP, 26th CIRP Conference on Life Cycle Engineering Purdue University, West Lafayette, IN (USA)
Volume: 80
Publisher: Elsevier B.V.
Uncontrolled Keywords: Load forecasting, machine learning, feature selection, feature engineering, Gradient Boosting Regression Trees
Divisions: 16 Department of Mechanical Engineering
16 Department of Mechanical Engineering > Institute of Production Management, Technology and Machine Tools (PTW)
16 Department of Mechanical Engineering > Institute of Production Management, Technology and Machine Tools (PTW) > ETA Energy Technologies and Applications in Production
Date Deposited: 09 Jul 2019 05:47
DOI: 10.1016/j.procir.2019.01.060
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item