IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v353y2024ipas0306261923014435.html
   My bibliography  Save this article

Harnessing eXplainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of Grad-CAM and SHAP

Author

Listed:
  • van Zyl, Corne
  • Ye, Xianming
  • Naidoo, Raj

Abstract

This study investigates the efficacy of Explainable Artificial Intelligence (XAI) methods, specifically Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP), in the feature selection process for national demand forecasting. Utilising a multi-headed Convolutional Neural Network (CNN), both XAI methods exhibit capabilities in enhancing forecasting accuracy and model efficiency by identifying and eliminating irrelevant features. Comparative analysis revealed Grad-CAM’s exceptional computational efficiency in high-dimensional applications and SHAP’s superior ability in revealing features that degrade forecast accuracy. However, limitations are found in both methods, with Grad-CAM including features that decrease model stability, and SHAP inaccurately ranking significant features. Future research should focus on refining these XAI methods to overcome these limitations and further probe into other XAI methods’ applicability within the time-series forecasting domain. This study underscores the potential of XAI in improving load forecasting, which can contribute significantly to the development of more interpretative, accurate and efficient forecasting models.

Suggested Citation

  • van Zyl, Corne & Ye, Xianming & Naidoo, Raj, 2024. "Harnessing eXplainable artificial intelligence for feature selection in time series energy forecasting: A comparative analysis of Grad-CAM and SHAP," Applied Energy, Elsevier, vol. 353(PA).
    • Handle: RePEc:eee:appene:v:353:y:2024:i:pa:s0306261923014435
    DOI: 10.1016/j.apenergy.2023.122079
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261923014435
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2023.122079?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Ghadimi, Noradin & Akbarimajd, Adel & Shayeghi, Hossein & Abedinia, Oveis, 2018. "Two stage forecast engine with feature selection technique and improved meta-heuristic algorithm for electricity load forecasting," Energy, Elsevier, vol. 161(C), pages 130-142.
    2. Aslam, Sheraz & Herodotou, Herodotos & Mohsin, Syed Muhammad & Javaid, Nadeem & Ashraf, Nouman & Aslam, Shahzad, 2021. "A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids," Renewable and Sustainable Energy Reviews, Elsevier, vol. 144(C).
    3. Kazmi, Hussain & Tao, Zhenmin, 2022. "How good are TSO load and renewable generation forecasts: Learning curves, challenges, and the road ahead," Applied Energy, Elsevier, vol. 323(C).
    4. Bommert, Andrea & Sun, Xudong & Bischl, Bernd & Rahnenführer, Jörg & Lang, Michel, 2020. "Benchmark for filter methods for feature selection in high-dimensional classification data," Computational Statistics & Data Analysis, Elsevier, vol. 143(C).
    5. Kim, Tae-Young & Cho, Sung-Bae, 2019. "Predicting residential energy consumption using CNN-LSTM neural networks," Energy, Elsevier, vol. 182(C), pages 72-81.
    6. Li, Wei & Becker, Denis Mike, 2021. "Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling," Energy, Elsevier, vol. 237(C).
    7. Mitrentsis, Georgios & Lens, Hendrik, 2022. "An interpretable probabilistic model for short-term solar power forecasting using natural gradient boosting," Applied Energy, Elsevier, vol. 309(C).
    8. Hugh Chen & Scott M. Lundberg & Su-In Lee, 2022. "Explaining a series of models by propagating Shapley values," Nature Communications, Nature, vol. 13(1), pages 1-15, December.
    9. Tao Hong & Pierre Pinson & Yi Wang & Rafal Weron & Dazhi Yang & Hamidreza Zareipour, 2020. "Energy forecasting: A review and outlook," WORking papers in Management Science (WORMS) WORMS/20/08, Department of Operations Research and Business Intelligence, Wroclaw University of Science and Technology.
    10. Lim, Bryan & Arık, Sercan Ö. & Loeff, Nicolas & Pfister, Tomas, 2021. "Temporal Fusion Transformers for interpretable multi-horizon time series forecasting," International Journal of Forecasting, Elsevier, vol. 37(4), pages 1748-1764.
    11. Dai, Yeming & Zhao, Pei, 2020. "A hybrid load forecasting model based on support vector machine with intelligent methods for feature selection and parameter optimization," Applied Energy, Elsevier, vol. 279(C).
    12. Tschora, Léonard & Pierre, Erwan & Plantevit, Marc & Robardet, Céline, 2022. "Electricity price forecasting on the day-ahead market using machine learning," Applied Energy, Elsevier, vol. 313(C).
    13. Białek, Jakub & Bujalski, Wojciech & Wojdan, Konrad & Guzek, Michał & Kurek, Teresa, 2022. "Dataset level explanation of heat demand forecasting ANN with SHAP," Energy, Elsevier, vol. 261(PA).
    14. Chakraborty, Debaditya & Alam, Arafat & Chaudhuri, Saptarshi & Başağaoğlu, Hakan & Sulbaran, Tulio & Langar, Sandeep, 2021. "Scenario-based prediction of climate change impacts on building cooling energy consumption with explainable artificial intelligence," Applied Energy, Elsevier, vol. 291(C).
    15. Léonard Tschora & Erwan Pierre & Marc Plantevit & Céline Robardet, 2022. "Electricity price forecasting on the day-ahead market using machine learning," Post-Print hal-03621974, HAL.
    16. Wei Li & Denis Mike Becker, 2021. "Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling," Papers 2101.05249, arXiv.org, revised Jul 2021.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Neubauer, Alexander & Brandt, Stefan & Kriegel, Martin, 2024. "Relationship between feature importance and building characteristics for heating load predictions," Applied Energy, Elsevier, vol. 359(C).
    2. Chen, Yong & Lu, Zhiyuan & Liu, Heng & Wang, Hu & Zheng, Zunqing & Wang, Changhui & Sun, Xingyu & Xu, Linxun & Yao, Mingfa, 2024. "Machine learning-based design of target property-oriented fuels using explainable artificial intelligence," Energy, Elsevier, vol. 300(C).
    3. Eskandari, Hamidreza & Saadatmand, Hassan & Ramzan, Muhammad & Mousapour, Mobina, 2024. "Innovative framework for accurate and transparent forecasting of energy consumption: A fusion of feature selection and interpretable machine learning," Applied Energy, Elsevier, vol. 366(C).

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Madadkhani, Shiva & Ikonnikova, Svetlana, 2024. "Toward high-resolution projection of electricity prices: A machine learning approach to quantifying the effects of high fuel and CO2 prices," Energy Economics, Elsevier, vol. 129(C).
    2. Deniz Kenan Kılıç & Peter Nielsen & Amila Thibbotuwawa, 2024. "Intraday Electricity Price Forecasting via LSTM and Trading Strategy for the Power Market: A Case Study of the West Denmark DK1 Grid Region," Energies, MDPI, vol. 17(12), pages 1-15, June.
    3. Adela Bâra & Simona-Vasilica Oprea & Bogdan George Tudorică, 2024. "From the East-European Regional Day-Ahead Markets to a Global Electricity Market," Computational Economics, Springer;Society for Computational Economics, vol. 63(6), pages 2525-2557, June.
    4. Daniel Manfre Jaimes & Manuel Zamudio López & Hamidreza Zareipour & Mike Quashie, 2023. "A Hybrid Model for Multi-Day-Ahead Electricity Price Forecasting considering Price Spikes," Forecasting, MDPI, vol. 5(3), pages 1-23, July.
    5. Gonçalves, Rui & Ribeiro, Vitor Miguel & Pereira, Fernando Lobo, 2023. "Variable Split Convolutional Attention: A novel Deep Learning model applied to the household electric power consumption," Energy, Elsevier, vol. 274(C).
    6. Tovar Rosas, Mario A. & Pérez, Miguel Robles & Martínez Pérez, E. Rafael, 2022. "Itineraries for charging and discharging a BESS using energy predictions based on a CNN-LSTM neural network model in BCS, Mexico," Renewable Energy, Elsevier, vol. 188(C), pages 1141-1165.
    7. Xu, Gaoyuan & Shi, Jian & Wu, Jiaman & Lu, Chenbei & Wu, Chenye & Wang, Dan & Han, Zhu, 2024. "An optimal solutions-guided deep reinforcement learning approach for online energy storage control," Applied Energy, Elsevier, vol. 361(C).
    8. Karol Pilot & Alicja Ganczarek-Gamrot & Krzysztof Kania, 2024. "Dealing with Anomalies in Day-Ahead Market Prediction Using Machine Learning Hybrid Model," Energies, MDPI, vol. 17(17), pages 1-20, September.
    9. Pesantez, Jorge E. & Li, Binbin & Lee, Christopher & Zhao, Zhizhen & Butala, Mark & Stillwell, Ashlynn S., 2023. "A Comparison Study of Predictive Models for Electricity Demand in a Diverse Urban Environment," Energy, Elsevier, vol. 283(C).
    10. Dounia El Bourakadi & Hiba Ramadan & Ali Yahyaouy & Jaouad Boumhidi, 2023. "A robust energy management approach in two-steps ahead using deep learning BiLSTM prediction model and type-2 fuzzy decision-making controller," Fuzzy Optimization and Decision Making, Springer, vol. 22(4), pages 645-667, December.
    11. Yao, Qiuxiang & Wang, Linyang & Ma, Mingming & Ma, Li & He, Lei & Ma, Duo & Sun, Ming, 2024. "A quantitative investigation on pyrolysis behaviors of metal ion-exchanged coal macerals by interpretable machine learning algorithms," Energy, Elsevier, vol. 300(C).
    12. Hasnain Iftikhar & Josue E. Turpo-Chaparro & Paulo Canas Rodrigues & Javier Linkolk López-Gonzales, 2023. "Forecasting Day-Ahead Electricity Prices for the Italian Electricity Market Using a New Decomposition—Combination Technique," Energies, MDPI, vol. 16(18), pages 1-23, September.
    13. Sharma, Abhishek & Jain, Sachin Kumar, 2022. "A novel seasonal segmentation approach for day-ahead load forecasting," Energy, Elsevier, vol. 257(C).
    14. Kılıç Depren, Serpil & Kartal, Mustafa Tevfik & Ertuğrul, Hasan Murat & Depren, Özer, 2022. "The role of data frequency and method selection in electricity price estimation: Comparative evidence from Turkey in pre-pandemic and pandemic periods," Renewable Energy, Elsevier, vol. 186(C), pages 217-225.
    15. Ghimire, Sujan & Deo, Ravinesh C. & Casillas-Pérez, David & Salcedo-Sanz, Sancho, 2024. "Two-step deep learning framework with error compensation technique for short-term, half-hourly electricity price forecasting," Applied Energy, Elsevier, vol. 353(PA).
    16. Wei Li & Wolfgang Karl Hardle & Stefan Lessmann, 2022. "A Data-driven Case-based Reasoning in Bankruptcy Prediction," Papers 2211.00921, arXiv.org.
    17. Houben, Nikolaus & Cosic, Armin & Stadler, Michael & Mansoor, Muhammad & Zellinger, Michael & Auer, Hans & Ajanovic, Amela & Haas, Reinhard, 2023. "Optimal dispatch of a multi-energy system microgrid under uncertainty: A renewable energy community in Austria," Applied Energy, Elsevier, vol. 337(C).
    18. Shiyu Liu & Ou Liu & Junyang Chen, 2023. "A Review on Business Analytics: Definitions, Techniques, Applications and Challenges," Mathematics, MDPI, vol. 11(4), pages 1-20, February.
    19. Sheybanivaziri, Samaneh & Le Dréau, Jérôme & Kazmi, Hussain, 2024. "Forecasting price spikes in day-ahead electricity markets: techniques, challenges, and the road ahead," Discussion Papers 2024/1, Norwegian School of Economics, Department of Business and Management Science.
    20. Wang, Jianzhou & Xing, Qianyi & Zeng, Bo & Zhao, Weigang, 2022. "An ensemble forecasting system for short-term power load based on multi-objective optimizer and fuzzy granulation," Applied Energy, Elsevier, vol. 327(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:appene:v:353:y:2024:i:pa:s0306261923014435. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/description#description .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.