IDEAS home Printed from https://ideas.repec.org/a/eee/appene/v378y2025ipas0306261924021469.html
   My bibliography  Save this article

Explainable deeply-fused nets electricity demand prediction model: Factoring climate predictors for accuracy and deeper insights with probabilistic confidence interval and point-based forecasts

Author

Listed:
  • Ghimire, Sujan
  • AL-Musaylh, Mohanad S.
  • Nguyen-Huy, Thong
  • Deo, Ravinesh C.
  • Acharya, Rajendra
  • Casillas-Pérez, David
  • Yaseen, Zaher Mundher
  • Salcedo-Sanz, Sancho

Abstract

Electricity consumption has stochastic variabilities driven by the energy market volatility. The capability to predict electricity demand that captures stochastic variances and uncertainties is significantly important in the planning, operation and regulation of national electricity markets. This study has proposed an explainable deeply-fused nets electricity demand prediction model that factors in the climate-based predictors for enhanced accuracy and energy market insight analysis, generating point-based and confidence interval predictions of daily electricity demand. The proposed hybrid approach is built using Deeply Fused Nets (FNET) that comprises of Convolutional Neural Network (CNN) and Bidirectional Long-Short Term Memory (BILSTM) Network with residual connection. The study then contributes to a new deep fusion model that integrates intermediate representations of the base networks (fused output being the input of the remaining part of each base network) to perform these combinations deeply over several intermediate representations to enhance the demand predictions. The results are evaluated with statistical metrics and graphical representations of predicted and observed electricity demand, benchmarked with standalone models i.e., BILSTM, LSTMCNN, deep neural network, multi-layer perceptron, multivariate adaptive regression spline, kernel ridge regression and Gaussian process of regression. The end part of the proposed FNET model applies residual bootstrapping where final residuals are computed from predicted and observed demand to generate the 95% prediction intervals, analysed using probabilistic metrics to quantify the uncertainty associated with FNETS objective model. To enhance the FNET model’s transparency, the SHapley Additive explanation (SHAP) method has been applied to elucidate the relationships between electricity demand and climate-based predictor variables. The suggested model analysis reveals that the preceding hour’s electricity demand and evapotranspiration were the most influential factors that positively impacting current electricity demand. These findings underscore the FNET model’s capacity to yield accurate and insightful predictions, advocating its utility in predicting electricity demand and analysis of energy markets for decision-making.

Suggested Citation

  • Ghimire, Sujan & AL-Musaylh, Mohanad S. & Nguyen-Huy, Thong & Deo, Ravinesh C. & Acharya, Rajendra & Casillas-Pérez, David & Yaseen, Zaher Mundher & Salcedo-Sanz, Sancho, 2025. "Explainable deeply-fused nets electricity demand prediction model: Factoring climate predictors for accuracy and deeper insights with probabilistic confidence interval and point-based forecasts," Applied Energy, Elsevier, vol. 378(PA).
    • Handle: RePEc:eee:appene:v:378:y:2025:i:pa:s0306261924021469
    DOI: 10.1016/j.apenergy.2024.124763
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0306261924021469
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.apenergy.2024.124763?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. AL-Musaylh, Mohanad S. & Deo, Ravinesh C. & Adamowski, Jan F. & Li, Yan, 2019. "Short-term electricity demand forecasting using machine learning methods enriched with ground-based climate and ECMWF Reanalysis atmospheric predictors in southeast Queensland, Australia," Renewable and Sustainable Energy Reviews, Elsevier, vol. 113(C), pages 1-1.
    2. Mariano, Roberto S. & Preve, Daniel, 2012. "Statistical tests for multiple forecast comparison," Journal of Econometrics, Elsevier, vol. 169(1), pages 123-130.
    3. Shufan Zhang & Minda Ma & Nan Zhou & Jinyue Yan & Wei Feng & Ran Yan & Kairui You & Jingjing Zhang & Jing Ke, 2024. "Estimation of Global Building Stocks by 2070: Unlocking Renovation Potential," Papers 2406.04074, arXiv.org.
    4. Yanqiao Deng & Minda Ma & Nan Zhou & Zhili Ma & Ran Yan & Xin Ma, 2024. "China's plug-in hybrid electric vehicle transition: an operational carbon perspective," Papers 2405.07308, arXiv.org, revised Aug 2024.
    5. Alejandro J. del Real & Fernando Dorado & Jaime Durán, 2020. "Energy Demand Forecasting Using Deep Learning: Applications for the French Grid," Energies, MDPI, vol. 13(9), pages 1-15, May.
    6. Ghimire, Sujan & Deo, Ravinesh C. & Casillas-Pérez, David & Salcedo-Sanz, Sancho, 2022. "Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Deep Residual model for short-term multi-step solar radiation prediction," Renewable Energy, Elsevier, vol. 190(C), pages 408-424.
    7. Rohani, Abbas & Taki, Morteza & Abdollahpour, Masoumeh, 2018. "A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I)," Renewable Energy, Elsevier, vol. 115(C), pages 411-422.
    8. Hafeez, Ghulam & Alimgeer, Khurram Saleem & Khan, Imran, 2020. "Electric load forecasting based on deep learning and optimized by heuristic algorithm in smart grid," Applied Energy, Elsevier, vol. 269(C).
    9. Despotovic, Milan & Nedic, Vladimir & Despotovic, Danijela & Cvetanovic, Slobodan, 2015. "Review and statistical analysis of different global solar radiation sunshine models," Renewable and Sustainable Energy Reviews, Elsevier, vol. 52(C), pages 1869-1880.
    10. Ghimire, Sujan & Nguyen-Huy, Thong & AL-Musaylh, Mohanad S. & Deo, Ravinesh C. & Casillas-Pérez, David & Salcedo-Sanz, Sancho, 2023. "A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction," Energy, Elsevier, vol. 275(C).
    11. Zhang, Jinliang & Wei, Yi-Ming & Li, Dezhi & Tan, Zhongfu & Zhou, Jianhua, 2018. "Short term electricity load forecasting using a hybrid model," Energy, Elsevier, vol. 158(C), pages 774-781.
    12. Marsaglia, George & Tsang, Wai Wan & Wang, Jingbo, 2003. "Evaluating Kolmogorov's Distribution," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 8(i18).
    13. Shao, Zhen & Chao, Fu & Yang, Shan-Lin & Zhou, Kai-Le, 2017. "A review of the decomposition methodology for extracting and identifying the fluctuation characteristics in electricity demand forecasting," Renewable and Sustainable Energy Reviews, Elsevier, vol. 75(C), pages 123-136.
    14. Gueymard, Christian A., 2014. "A review of validation methodologies and statistical performance indicators for modeled solar radiation data: Towards a better bankability of solar projects," Renewable and Sustainable Energy Reviews, Elsevier, vol. 39(C), pages 1024-1034.
    15. Ghimire, Sujan & Deo, Ravinesh C. & Casillas-Pérez, David & Salcedo-Sanz, Sancho, 2022. "Boosting solar radiation predictions with global climate models, observational predictors and hybrid deep-machine learning algorithms," Applied Energy, Elsevier, vol. 316(C).
    16. Qu, Jiaqi & Qian, Zheng & Pei, Yan, 2021. "Day-ahead hourly photovoltaic power forecasting using attention-based CNN-LSTM neural network embedded with multiple relevant and target variables prediction pattern," Energy, Elsevier, vol. 232(C).
    17. Yuan, Hong & Ma, Minda & Zhou, Nan & Xie, Hui & Ma, Zhili & Xiang, Xiwang & Ma, Xin, 2024. "Battery electric vehicle charging in China: Energy demand and emissions trends in the 2020s," Applied Energy, Elsevier, vol. 365(C).
    18. Sujan Ghimire & Ravinesh C. Deo & Hua Wang & Mohanad S. Al-Musaylh & David Casillas-Pérez & Sancho Salcedo-Sanz, 2022. "Stacked LSTM Sequence-to-Sequence Autoencoder with Feature Selection for Daily Solar Radiation Prediction: A Review and New Modeling Results," Energies, MDPI, vol. 15(3), pages 1-39, January.
    19. Wang, Kejun & Qi, Xiaoxia & Liu, Hongda, 2019. "Photovoltaic power forecasting based LSTM-Convolutional Network," Energy, Elsevier, vol. 189(C).
    20. Yan, Ran & Ma, Minda & Zhou, Nan & Feng, Wei & Xiang, Xiwang & Mao, Chao, 2023. "Towards COP27: Decarbonization patterns of residential building in China and India," Applied Energy, Elsevier, vol. 352(C).
    21. Hwang, Eunju, 2022. "Prediction intervals of the COVID-19 cases by HAR models with growth rates and vaccination rates in top eight affected countries: Bootstrap improvement," Chaos, Solitons & Fractals, Elsevier, vol. 155(C).
    22. Mohanad S. Al-Musaylh & Ravinesh C. Deo & Yan Li, 2020. "Electrical Energy Demand Forecasting Model Development and Evaluation with Maximum Overlap Discrete Wavelet Transform-Online Sequential Extreme Learning Machines Algorithms," Energies, MDPI, vol. 13(9), pages 1-19, May.
    23. Debora Maia-Silva & Rohini Kumar & Roshanak Nateghi, 2020. "The critical role of humidity in modeling summer electricity demand across the United States," Nature Communications, Nature, vol. 11(1), pages 1-8, December.
    Full references (including those not matched with items on IDEAS)

    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. Ghimire, Sujan & Nguyen-Huy, Thong & AL-Musaylh, Mohanad S. & Deo, Ravinesh C. & Casillas-Pérez, David & Salcedo-Sanz, Sancho, 2023. "A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction," Energy, Elsevier, vol. 275(C).
    2. Ghimire, Sujan & Deo, Ravinesh C. & Casillas-Pérez, David & Sharma, Ekta & Salcedo-Sanz, Sancho & Barua, Prabal Datta & Rajendra Acharya, U., 2024. "Half-hourly electricity price prediction with a hybrid convolution neural network-random vector functional link deep learning approach," Applied Energy, Elsevier, vol. 374(C).
    3. 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).
    4. Saima Akhtar & Sulman Shahzad & Asad Zaheer & Hafiz Sami Ullah & Heybet Kilic & Radomir Gono & Michał Jasiński & Zbigniew Leonowicz, 2023. "Short-Term Load Forecasting Models: A Review of Challenges, Progress, and the Road Ahead," Energies, MDPI, vol. 16(10), pages 1-29, May.
    5. Zhigao Liao & Yufeng Bai & Kerong Jian & Wongvanichtawee Chalermkiat, 2024. "The Spatial Spillover Effect and Mechanism of Carbon Emission Trading Policy on Pollution Reduction and Carbon Reduction: Evidence from the Pearl River–West River Economic Belt in China," Sustainability, MDPI, vol. 16(23), pages 1-25, November.
    6. Zhao, Zhenyu & Zhang, Yao & Yang, Yujia & Yuan, Shuguang, 2022. "Load forecasting via Grey Model-Least Squares Support Vector Machine model and spatial-temporal distribution of electric consumption intensity," Energy, Elsevier, vol. 255(C).
    7. Hu, Yusha & Man, Yi, 2023. "Energy consumption and carbon emissions forecasting for industrial processes: Status, challenges and perspectives," Renewable and Sustainable Energy Reviews, Elsevier, vol. 182(C).
    8. Zhineng Hu & Jing Ma & Liangwei Yang & Liming Yao & Meng Pang, 2019. "Monthly electricity demand forecasting using empirical mode decomposition-based state space model," Energy & Environment, , vol. 30(7), pages 1236-1254, November.
    9. Tang, Yugui & Yang, Kuo & Zhang, Shujing & Zhang, Zhen, 2022. "Photovoltaic power forecasting: A hybrid deep learning model incorporating transfer learning strategy," Renewable and Sustainable Energy Reviews, Elsevier, vol. 162(C).
    10. Hao, Jianhua & Liu, Fangai & Zhang, Weiwei, 2024. "Multi-scale RWKV with 2-dimensional temporal convolutional network for short-term photovoltaic power forecasting," Energy, Elsevier, vol. 309(C).
    11. Hany Habbak & Mohamed Mahmoud & Khaled Metwally & Mostafa M. Fouda & Mohamed I. Ibrahem, 2023. "Load Forecasting Techniques and Their Applications in Smart Grids," Energies, MDPI, vol. 16(3), pages 1-33, February.
    12. Khan, Zulfiqar Ahmad & Hussain, Tanveer & Baik, Sung Wook, 2023. "Dual stream network with attention mechanism for photovoltaic power forecasting," Applied Energy, Elsevier, vol. 338(C).
    13. Zhong, Wenli & Liu, Yang & Dong, Kangyin & Ni, Guohua, 2024. "Assessing the synergistic effects of artificial intelligence on pollutant and carbon emission mitigation in China," Energy Economics, Elsevier, vol. 138(C).
    14. Li, Yiyan & Zhang, Si & Hu, Rongxing & Lu, Ning, 2021. "A meta-learning based distribution system load forecasting model selection framework," Applied Energy, Elsevier, vol. 294(C).
    15. Khan, Taimoor & Choi, Chang, 2025. "Attention enhanced dual stream network with advanced feature selection for power forecasting," Applied Energy, Elsevier, vol. 377(PC).
    16. Xie, Yiwei & Hu, Pingfang & Zhu, Na & Lei, Fei & Xing, Lu & Xu, Linghong & Sun, Qiming, 2020. "A hybrid short-term load forecasting model and its application in ground source heat pump with cooling storage system," Renewable Energy, Elsevier, vol. 161(C), pages 1244-1259.
    17. Hugo Gaspar Hernandez-Palma & Jonny Rafael Plaza Alvarado & Jesús Enrique García Guiliany & Guilherme Luiz Dotto & Claudete Gindri Ramos, 2024. "Implications of Machine Learning in the Generation of Renewable Energies in Latin America from a Globalized Vision: A Systematic Review," International Journal of Energy Economics and Policy, Econjournals, vol. 14(2), pages 1-10, March.
    18. Msefula, Griffin & Hou, Tony Chieh-Tse & Lemesi, Tina, 2024. "Dynamics of legal structure and geopolitical influence on carbon tax in response to green transportation," Applied Energy, Elsevier, vol. 371(C).
    19. 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).
    20. Zhineng Hu & Jing Ma & Liangwei Yang & Xiaoping Li & Meng Pang, 2019. "Decomposition-Based Dynamic Adaptive Combination Forecasting for Monthly Electricity Demand," Sustainability, MDPI, vol. 11(5), pages 1-25, February.

    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:378:y:2025:i:pa:s0306261924021469. 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.