Annual Industrial and Commercial Heat Load Profiles: Modeling Based on k-Means Clustering and Regression Analysis

Jesper, Mateo; Pag, Felix; Vajen, Klaus; Jordan, Ulrike

doi:10.1016/j.ecmx.2021.100085

Cited by 12 publications

(19 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, both types of load profiles, natural gas, and electricity, are available for only a few companies. This explains the significantly lower number of load profiles compared to the authors' earlier work [26], in which 797 natural gas load profiles were examined. For data protection reasons the load profiles cannot be published.…”

Section: Implications From Literature and Objectivementioning

confidence: 82%

“…Studies that analyze a broad database of industrial heat load profiles are also not available. As far as the authors are aware, they have presented the only studies that analyze at least a high three-digit number of load profiles of large industrial consumers [26][27][28]. The authors recently presented a comprehensive cluster and regression analysis of 797 industrial and commercial natural gas load profiles [26].…”

Section: Load Profile Prediction For Individual Consumers In Recent L...mentioning

confidence: 99%

“…As far as the authors are aware, they have presented the only studies that analyze at least a high three-digit number of load profiles of large industrial consumers [26][27][28]. The authors recently presented a comprehensive cluster and regression analysis of 797 industrial and commercial natural gas load profiles [26]. Linear regressions have been developed that reflect the relationship between outdoor temperature and heat demand with a high degree of accuracy.…”

Section: Load Profile Prediction For Individual Consumers In Recent L...mentioning

confidence: 99%

“…Natural gas load profiles are normalized to the mean daily consumption on days with a mean daily ambient temperature of 8°C. This method corresponds to the SLP methodology [6] and it is explained in detail in the authors' previous publication [26]. The electricity load profiles are normalized to the maximum daily electricity consumption.…”

Section: Pre-processingmentioning

confidence: 99%

“…Due to the normalization, the gas boiler efficiency has not to be considered. A detailed discussion of this assumption can be found in the authors' previous work [26].…”

Section: Pre-processingmentioning

confidence: 99%

See 4 more Smart Citations

Heat Load Profiles in Industry and the Tertiary Sector: Correlation with Electricity Consumption and Ex Post Modelling

Jesper¹,

Pag²,

Vajen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The accurate prediction of heat load profiles with a daily resolution is required for a broad range of applications such as potential studies, design, or predictive operation of heating systems. If the heat demand of a consumer is mainly caused by (production) processes independent of the ambient temperature, existing load profile prediction methods fail. To close this gap, this study develops two ex post machine learning models for the prediction of the heat demand with a daily resolution. The selected input features are commonly available to each consumer connected to public natural gas and electricity grids or operating an energy monitoring system: Ambient temperature, weekday, electricity consumption, and heat consumption of the last seven days directly before the predicted day. The study’s database covers electricity and natural gas consumption load profiles from 82 German consumers over a period of two years. Electricity and heat consumption correlate strongly with individual patterns for many consumers. Both, shallow and deep learning algorithms are evaluated. The highest accuracy is achieved by a Long Short Term Memory (LSTM) model with a median of R² of 0.94. The ex post model architecture makes the model suitable for automated anomaly detection in energy monitoring systems.

show abstract

Section: Implications From Literature and Objectivementioning

confidence: 82%

Section: Load Profile Prediction For Individual Consumers In Recent L...mentioning

confidence: 99%

Section: Load Profile Prediction For Individual Consumers In Recent L...mentioning

confidence: 99%

Section: Pre-processingmentioning

confidence: 99%

“…Due to the normalization, the gas boiler efficiency has not to be considered. A detailed discussion of this assumption can be found in the authors' previous work [26].…”

Section: Pre-processingmentioning

confidence: 99%

See 3 more Smart Citations