Short-Term Power Load Forecasting for Industrial Parks Using CNN-BiLSTM Network with Kernel Density Estimation-based Interval Prediction Method
DOI:
https://doi.org/10.4108/ew.12681Keywords:
load forecasting, neural network, kernel density function, probabilistic prediction intervalAbstract
Predicting electrical power loads in industrial parks is challenging due to the uncertainty and variance in model construction. This paper proposes an interval forecasting approach based on a residual-form CNN-BiLSTM, which effectively captures spatial patterns and bidirectional temporal dependencies in time series data. To handle uncertainty, a kernel density estimation (KDE)-based method is employed to generate probabilistic prediction intervals. Experiments using 18 days of real industrial data validate the model’s performance. Results show superior robustness and accuracy compared with LSTM, BiLSTM, and GRU. The proposed model achieves perfect prediction interval coverage probability (PICP = 1.0), narrow normalized interval width (PINAW = 0.0828), and minimal CWC = 0.0828, while baseline models exhibit low coverage or excessively wide intervals. These findings confirm that the method provides both reliable and sharp uncertainty quantification, making it suitable for practical energy forecasting applications.
Downloads
References
[1] Quilumba FL, Lee W-J, Huang H, Wang DY, and Szabados RL. Using Smart Meter Data to Improve the Accuracy of Intraday Load Forecasting Considering Customer Behavior Similarities. IEEE Transactions on Smart Grid. 2015; 6(2):911–18. https://doi.org/10.1109/TSG.2014.2364233.
[2] Liu B, Nowotarski J, Hong T, and Weron R. Probabilistic Load Forecasting via Quantile Regression Averaging on Sister Forecasts. IEEE Transactions on Smart Grid. 2017; 8(2):730–37. https://doi.org/10.1109/TSG.2015.2437877.
[3] Liu J-X and Leu J-S. LARSI-Tpe-Xgb: Short-Term Load Forecasting by Load-Adaptive Relative Strength Index and Fusion of Tree-Structured Parzen Estimator and Xgboost. IEEE Transactions on Power Delivery. 2025; 40(3):1318–30. https://doi.org/10.1109/TPWRD.2025.3545638.
[4] Lauricella M and Fagiano L. Day-Ahead and Intra-Day Building Load Forecast with Uncertainty Bounds Using Small Data Batches. IEEE Transactions on Control Systems Technology. 2023; 31(6):2584–95. https://doi.org/10.1109/TCST.2023.3274955.
[5] Ren L, Deng J, Song W, Zio E, and Cattani C. A Fractional Brownian Motion Model for Forecasting Lost Load and Time Interval Between Power Outages. IEEE Access. 2021; 9:6623–32. https://doi.org/10.1109/ACCESS.2020.3048499.
[6] Fan S, Methaprayoon K, and Lee W-J. Multiregion Load Forecasting for System with Large Geographical Area. IEEE Transactions on Industry Applications. 2009; 45(4):1452–9. https://doi.org/10.1109/TIA.2009.2023569.
[7] Son J, Cha J, Kim H, and Wi Y-M. Day-Ahead Short-Term Load Forecasting for Holidays Based on Modification of Similar Days’ Load Profiles. IEEE Access. 2022; 10:17864–80. https://doi.org/10.1109/ACCESS.2022.3150344.
[8] Azeem A, Ismail I, Jameel SM, and Harindran VR. Electrical Load Forecasting Models for Different Generation Modalities: A Review. IEEE Access. 2021; 9:142239–63. https://doi.org/10.1109/ACCESS.2021.3120731.
[9] Ranaweera DK, Karady GG, and Farmer RG. Effect of Probabilistic Inputs on Neural Network-Based Electric Load Forecasting. IEEE Transactions on Neural Networks. 1996; 7(6):1528–32. https://doi.org/10.1109/72.548183.
[10] Smyl S, Dudek G, and Pełka P. ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting. IEEE Transactions on Neural Networks and Learning Systems. 2024; 35(8):11346–58. https://doi.org/10.1109/TNNLS.2023.3259149.
[11] Faustine A, and Pereira L. FPSeq2Q: Fully Parameterized Sequence to Quantile Regression for Net-Load Forecasting with Uncertainty Estimates. IEEE Transactions on Smart Grid. 2022; 13(3):2440–51. https://doi.org/10.1109/TSG.2022.3148699.
[12] Park K, Yoon S, and Hwang E. Hybrid Load Forecasting for Mixed-Use Complex Based on the Characteristic Load Decomposition by Pilot Signals. IEEE Access. 2019; 7:12297–12306. https://doi.org/10.1109/ACCESS.2019.2892475.
[13] Madhukumar M, Sebastian A, Liang X, Jamil M, and Shabbir MNSK. Regression Model-Based Short-Term Load Forecasting for University Campus Load. IEEE Access. 2022; 10:8891–8905. https://doi.org/10.1109/ACCESS.2022.3144206.
[14] Khosravi A, Nahavandi S, and Creighton D. Construction of Optimal Prediction Intervals for Load Forecasting Problems. IEEE Transactions on Power Systems. 2010; 25(3):1496–1503. https://doi.org/10.1109/TPWRS.2010.2042309.
[15] Quan H, Srinivasan D, and Khosravi A. Incorporating Wind Power Forecast Uncertainties into Stochastic Unit Commitment Using Neural Network-Based Prediction Intervals. IEEE Transactions on Neural Networks and Learning Systems. 2015; 26(9):2123–35. https://doi.org/10.1109/TNNLS.2014.2376696.
[16] He Y, Zhu J, and Wang S. A Novel Neural Network-Based Multiobjective Evolution Lower Upper Bound Estimation Method for Electricity Load Interval Forecast. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2024; 54(5):3069–83. https://doi.org/10.1109/TSMC.2024.3352665.
[17] Gross G, and Galiana FD. Short-Term Load Forecasting. Proceedings of the IEEE. 1987; 75(12):1558–73. https://doi.org/10.1109/PROC.1987.13927.
[18] Christiaanse WR. Short-Term Load Forecasting Using General Exponential Smoothing. IEEE Transactions on Power Apparatus and Systems. 1971; PAS-90(2):900–911. https://doi.org/10.1109/TPAS.1971.293123.
[19] Vangipuram SR, and Giridhar AV. Short Term Residential Load Forecasting Using Temporal Weather Based Embedding Stacked Lstms. IEEE Latin America Transactions. 2025; 23(6):497–507. https://doi.org/10.1109/TLA.2025.11007195.
[20] Zhou Q, Tesfatsion L, and Liu C-C. Short-Term Congestion Forecasting in Wholesale Power Markets. IEEE Transactions on Power Systems. 2011; 26(4):2185–96. https://doi.org/10.1109/TPWRS.2011.2123118.
[21] Methaprayoon K, Lee W-J, Rasmiddatta S, Liao JR, and Ross RJ. Multistage Artificial Neural Network Short-Term Load Forecasting Engine with Front-End Weather Forecast. IEEE Transactions on Industry Applications. 2007; 43(6):1410–6. https://doi.org/10.1109/TIA.2007.908190.
[22] Fan S, Chen L, and Lee W-J. Short-Term Load Forecasting Using Comprehensive Combination Based on Multimeteorological Information. IEEE Transactions on Industry Applications. 2009; 45(4):1460–6. https://doi.org/10.1109/TIA.2009.2023571.
[23] Fan S, and Hyndman RJ. Short-Term Load Forecasting Based on a Semi-Parametric Additive Model. IEEE Transactions on Power Systems. 2012; 27(1):134–41. https://doi.org/10.1109/TPWRS.2011.2162082.
[24] Muzumdar AA, Modi CN, M MG, and Vyjayanthi C. Designing a Robust and Accurate Model for Consumer-Centric Short-Term Load Forecasting in Microgrid Environment. IEEE Systems Journal. 2022; 16(2):2448–59. https://doi.org/10.1109/JSYST.2021.3073493.
[25] Wang Y, Xia Q, and Kang C. Secondary Forecasting Based on Deviation Analysis for Short-Term Load Forecasting. IEEE Transactions on Power Systems. 2011; 26(2):500–507. https://doi.org/10.1109/TPWRS.2010.2052638.
[26] Masood Z, Gantassi R, and Choi Y. Enhancing Short-Term Electric Load Forecasting for Households Using Quantile Lstm and Clustering-Based Probabilistic Approach. IEEE Access. 2024; 12:77257–68. https://doi.org/10.1109/ACCESS.2024.3406439.
[27] Sáez D, Ávila F, Olivares D, Cañizares C, and Marín L. Fuzzy Prediction Interval Models for Forecasting Renewable Resources and Loads in Microgrids. IEEE Transactions on Smart Grid. 2015; 6(2):548–56. https://doi.org/10.1109/TSG.2014.2377178.
[28] Chen Z, Du C, Zhang B, Yang C, and Gui W. A Cybersecure Distribution-Free Learning Model for Interval Forecasting of Power Load Under Cyberattacks. IEEE Transactions on Industrial Informatics. 2025; 21(3):2540–9. https://doi.org/10.1109/TII.2024.3507946.
[29] Zhao C, Wan C, Song Y, and Cao Z. Optimal Nonparametric Prediction Intervals of Electricity Load. IEEE Transactions on Power Systems. 2020; 35(3):2467–70. https://doi.org/10.1109/TPWRS.2020.2965799.
[30] Zhang Y, Wen H, Wu Q, and Ai Q. Optimal Adaptive Prediction Intervals for Electricity Load Forecasting in Distribution Systems via Reinforcement Learning. IEEE Transactions on Smart Grid. 2023; 14(4):3259–70. https://doi.org/10.1109/TSG.2022.3226423
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rui Hua, Tao Han, Yue Ran, Qiongxiao Wu
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
