RAID: Robust and Interpretable Daily Peak Load Forecasting via Multiple Deep Neural Networks and Shapley Values

Joohyun Jang, Woonyoung Jeong, Sangmin Kim, Byeongcheon Lee, Miyoung Lee and Jihoon Moon ()
Additional contact information
Joohyun Jang: Department of AI and Big Data, Soonchunhyang University, Asan 31538, Republic of Korea
Woonyoung Jeong: Department of AI and Big Data, Soonchunhyang University, Asan 31538, Republic of Korea
Sangmin Kim: Department of AI and Big Data, Soonchunhyang University, Asan 31538, Republic of Korea
Byeongcheon Lee: Department of AI and Big Data, Soonchunhyang University, Asan 31538, Republic of Korea
Miyoung Lee: Department of Software, Sejong University, Seoul 05006, Republic of Korea
Jihoon Moon: Department of AI and Big Data, Soonchunhyang University, Asan 31538, Republic of Korea

Sustainability, 2023, vol. 15, issue 8, 1-27

Abstract: Accurate daily peak load forecasting (DPLF) is crucial for informed decision-making in energy management. Deep neural networks (DNNs) are particularly apt for DPLF because they can analyze multiple factors, such as timestamps, weather conditions, and historical electric loads. Interpretability of machine learning models is essential for ensuring stakeholders understand and trust the decision-making process. We proposed the RAID (robust and interpretable DPLF) model, which enhances DPLF accuracy by recognizing daily peak load patterns and building separate DNN models for each day of the week. This approach was accessible for energy providers with limited computational resources, as the DNN models could be configured without a graphics processing unit (GPU). We utilized scikit-learn’s MLPRegressor for streamlined implementation, Optuna for hyperparameter optimization, and the Shapley additive explanations (SHAP) method to ensure interpretability. Applied to a dataset from two commercial office buildings in Richland, Washington, RAID outperformed existing methods like recurrent neural networks, Cubist, and HYTREM, achieving the lowest mean absolute percentage error values: 14.67% for Building 1 and 12.74% for Building 2. The kernel SHAP method revealed the influence of the previous day’s peak load and temperature-related variables on the prediction. The RAID model substantially improved energy management through enhanced DPLF accuracy, outperforming competing methods, providing a GPU-free configuration, and ensuring interpretable decision-making, with the potential to influence energy providers’ choices and promote overall energy system sustainability.

Keywords: daily peak load forecasting; deep neural network; hyperparameter optimization; Optuna; explainable artificial intelligence; Shapley additive explanations (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2071-1050/15/8/6951/pdf (application/pdf)
https://www.mdpi.com/2071-1050/15/8/6951/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:15:y:2023:i:8:p:6951-:d:1128502

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().