Daily Load Forecasting Using Explainable AI-Driven Method With Integrated Error Correlation

IEEE Access, vol. 13, pp. 207496–207510

Abstract

This paper presents a novel, explainable, and weather-independent day-ahead load forecasting (DALF). The proposed methodology integrates calendar-based segmentation using Classification and Regression Trees (CART), hybrid modeling with Multiple Linear Regression (MLR) and Gaussian Process Regression (GPR), and post-hoc error correction via Generalized Least Squares with Autoregressive Residuals (GLSAR). To enhance interpretability, Shapley Additive exPlanations (SHAP) are employed to quantify the influence of lagged load features and calendar variables across segmented forecasts. The framework is evaluated on real-world half-hourly data from the Electricity Generating Authority of Thailand (EGAT), encompassing both regular and holiday-specific load profiles. Experimental results demonstrate that the MLR–GPR–GLSAR configuration achieves superior performance, with a Mean Absolute Percentage Error (MAPE) of 0.72% and an R² of 0.99, outperforming Generalized Additive Models (GAM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGB), Convolutional Long Short-Term Memory (CNN-LSTM), and Neural Hierarchical Interpolation for Time Series (NHITS), as baselines. The proposed framework offers a scalable and interpretable solution for utilities operating in data-sparse environments. These findings affirm the importance of residual autocorrelation correction and calendar-aware segmentation in advancing DALF accuracy and transparency.

Authors 7

1. Ei Thu Thu Tun

   Thammasat University

   Affiliation as printed

   School of Management Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

   Sirindhorn International Institute of Technology, School of Management Technology, Thammasat University, Pathum Thani, Thailand

2. Kamal Chapagain

   Kathmandu University

   Affiliation as printed

   Department of Electrical and Electronics Engineering, Kathmandu University, Dhulikhel, Nepal

   Department of Electrical & Electronics Engineering, Kathmandu University, Nepal

3. Pyae Pyae Phyo Aachen Institute for Automation of Complex Power Systems

   RWTH Aachen University

   Affiliation as printed

   Institute for Automation of Complex Power Systems, RWTH Aachen University, Aachen, Germany

   Institute for Automation of Complex Power Systems, RWTH Aachen University, Germany

4. Yung-Cheol Byun

   Jeju National University

   Affiliation as printed

   Department of Computer Engineering, Head of RIS Office for High-Intelligent Service, Jeju National University, Jeju-si, South Korea

   Department of Computer Engineering, Head of RIS Office for High-Intelligent Service, Jeju National University, Korea

5. Vannak Seng

   Thammasat University

   Affiliation as printed

   School of Management Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

   Sirindhorn International Institute of Technology, School of Management Technology, Thammasat University, Pathum Thani, Thailand

6. Panharith Chhom

   Thammasat University

   Affiliation as printed

   School of Information, Computer, and Communication Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

   Sirindhorn International Institute of Technology, School of Information, Computer, and Communication Technology, Thammasat University, Pathum Thani, Thailand

7. Chawalit Jeenanunta

   Thammasat University

   Affiliation as printed

   School of Management Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

   Sirindhorn International Institute of Technology, School of Management Technology, Thammasat University, Pathum Thani, Thailand