Affiliation:
1. Fraunhofer UMSICHT, Fraunhofer Institute for Environmental, Safety, and Energy Technology, Osterfelder Str.3, 46047 Oberhausen, Germany
Abstract
For load forecasting, numerous machine learning (ML) approaches have been published. Besides fully connected feedforward neural networks (FFNNs), also called multilayer perceptron, more advanced ML approaches like deep, recurrent or convolutional neural networks or ensemble methods have been applied. However, evaluating the added benefit by novel approaches is difficult. Statistical or rule-based methods constitute a too low benchmark. FFNNs need extensive tuning due to their manifold design choices. To address this issue, a structured, comprehensible five-step FFNN model creation methodology is presented, which constitutes of initial model creation, internal parameter selection, feature engineering, architecture tuning and final model creation. The methodology is then applied to forecast real world heat load data of a hospital in Germany. The forecast constitutes of 192 values (upcoming 48 h in 15 min resolution) and is composed of a multi-model univariate forecasting strategy, with three test models developed at first. As a result, the test models show great similarities which simplifies creation of the remaining models. A performance increase of up to 18% between initial and final models points out the importance of model tuning. As a conclusion, comprehensible model tuning is vital to use FFNN models as benchmark. The effort needed can be reduced by the experience gained through repeated application of the presented methodology.
Funder
Federal Ministry for Economic Affairs and Climate Action
Subject
Energy (miscellaneous),Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment,Electrical and Electronic Engineering,Control and Optimization,Engineering (miscellaneous),Building and Construction
Reference33 articles.
1. Review of low voltage load forecasting: Methods, applications, and recommendations;Haben;Appl. Energy,2021
2. Arvanitidis, A.I., Bargiotas, D., Daskalopulu, A., Laitsos, V.M., and Tsoukalas, L.H. (2021). Enhanced Short-Term Load Forecasting Using Artificial Neural Networks. Energies, 14.
3. Neural networks for short-term load forecasting: A review and evaluation;Hippert;IEEE Trans. Power Syst.,2001
4. A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models;Wang;Renew. Sustain. Energy Rev.,2017
5. A novel approach for power load forecast based on GAN data augmentation;Boicea;IOP Conf. Ser. Mater. Sci. Eng.,2022
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献