What question did this study set out to answer?

This work aims to improve the accuracy of photovoltaic power forecasting by implementing a novel framework.

February 26, 2026Open Access

Interpretable ultra-short-term photovoltaic power forecasting with multi-scale temporal modeling and variable-wise attention

Key Points

This work aims to improve the accuracy of photovoltaic power forecasting by implementing a novel framework.
Developed MKAN-iTransformer framework combining MKAN and iTransformer
Conducted experiments on data from a 30 MW PV plant
Used chronological splits for seasonal evaluation
Measured performance using metrics like MSE, RMSE, and MAE
Achieved best performance in spring, autumn, and winter
In spring: MSE=2.892, RMSE=1.701, MAE=0.864, R²=0.947
In autumn: MSE=2.884, RMSE=1.698, MAE=0.774, R²=0.962
In winter: MSE=1.721, RMSE=1.312, MAE=0.443, R²=0.969
Confirmed the complementarity between MKAN and iTransformer

Abstract

Accurate photovoltaic (PV) power forecasting is essential for grid operation but remains difficult due to nonlinear multi-scale dynamics and seasonal distribution shifts. This work presents MKAN-iTransformer, a cascaded framework that integrates two existing components—the Multi-Scale Kolmogorov–Arnold Network (MKAN) for scale-aware temporal representation learning and iTransformer for variable-wise attention and inter-variable dependency modeling—under a 15-minute single-step setting. Experiments on a real-world 30 MW PV plant dataset from the Chinese State Grid Renewable Energy Generation Forecasting Competition use chronological splits within each season. MKAN-iTransformer achieves the best overall performance in spring, autumn, and winter. In spring, it reaches MSE=2. 892, RMSE=1. 701, MAE=0. 864, and R^{2}=0. 947, improving over LSTM by 23. 5%/12. 5%/20. 5% (MSE/RMSE/MAE). In autumn, it attains MSE=2. 884, RMSE=1. 698, MAE=0. 774, and R^{2}=0. 962, reducing errors vs. iTransformer by 16. 5%/8. 7%/12. 4%. In winter, it achieves MSE=1. 721, RMSE=1. 312, MAE=0. 443, and R^{2}=0. 969, yielding 81. 6%/57. 1%/71. 9% error reductions vs. Transformer. Ablation further confirms the complementarity between MKAN and iTransformer and shows that direct KAN integration can be unstable under winter shifts (KAN-iTransformer: MSE=7. 082, R^{2}=0. 872).

Mark Helpful

Bookmark

Relay

View Full Paper