Photovoltaic Power Prediction and SHAP Interpretability Analysis Based on Multi-Model Comparative Learning

Xiaoxi Dai; Yicheng Yang

doi:10.54097/ktr7gn53

Authors

Xiaoxi Dai
Yicheng Yang

DOI:

https://doi.org/10.54097/ktr7gn53

Keywords:

machine learning, photovoltaic power, model prediction, SHAP.

Abstract

In recent years, photovoltaic (PV) power generation has been developing rapidly, but its power instability poses a challenge to the stable operation of power systems. In this study, three machine learning models, CatBoost, Random Forest, and Support Vector Regression (SVR), were used for PV power prediction, and it was found that the SVR model performed the best, with the highest fit between predicted and true values (R² ≈ 0. 95) and the smallest fluctuation in residual error (-50% to 50%). Through SHAP analysis, the study reveals that illumination intensity is the most critical variable affecting PV power generation with a contribution of more than 70%. Additional machine learning models and optimization algorithms can be further explored in the future to improve prediction performance. In summary, this study provides an effective combinatorial machine learning method for high-precision PV power prediction, revealing the dominant role of key factors such as illumination intensity on the prediction results. Future research directions include optimizing the model structure and integrating multi-source data to further improve the accuracy and reliability of PV power prediction.

Downloads

Download data is not yet available.

References

[1] Monica B, Adrián R, Raul G, et al. Photovoltaic Power Generation Forecasting for Regional Assessment Using Machine Learning[J]. Energies, 2022, 15(23): 8895-8895.

[2] J. KI. Solar Photovoltaic Power Forecasting: A Review[J]. Sustainability, 2022,14(24): 17005-17005.

[3] Sameer D A, Jehad A, Osama A, et al. A feature transformation and extraction approach-based artificial neural network for an improved production prediction of grid-connected solar photovoltaic systems[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022, 44(4): 9232-9254.

[4] Connor S, Mominul A, Alhussein A. Machine learning for forecasting a photovoltaic (PV) generation system[J]. Energy, 2023, 278.

[5] Huifang F, Chunsheng Y. A novel hybrid model for short-term prediction of PV power based on KS-CEEMDAN-SE-LSTM[J]. Renewable Energy Focus, 2023, 47100497.

[6] Diwaker P, Aanchal K, Prerna G. An Enhanced Drift-Free Perturb and Observe Maximum Power Point Tracking Method Using Hybrid Metaheuristic Algorithm for a Solar Photovoltaic Power System[J]. Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 2023, 48(2): 759-779.

[7] Li D, Zhu D, Tao T, et al. Power Generation Prediction for Photovoltaic System of Hose-Drawn Traveler Based on Machine Learning Models[J]. Processes, 2023, 12(1).

[8] Yuan J, Tang X, Yuan W. Exploring Pathways toward the Development of High-Proportion Solar Photovoltaic Generation for Carbon Neutrality: The Example of China[J]. Processes, 2023, 12(1).

[9] Li G, Ding C, Zhao N, et al. Research on a novel photovoltaic power forecasting model based on parallel long and short-term time series network[J]. Energy, 2024, 293130621.

[10] Tercha W, Tadjer A S, Chekired F, et al. Machine Learning-Based Forecasting of Temperature and Solar Irradiance for Photovoltaic Systems[J]. Energies, 2024, 17(5).

[11] Hou Z, Zhang Y, Liu Q, et al. A hybrid machine learning forecasting model for photovoltaic power[J]. Energy Reports, 2024, 115125-5138.

[12] Wang A, Lin Q, Liu C, et al. Sustainable Energy Development: Reviewing Carbon Emission Reduction in Photovoltaic Power Systems[J]. Sustainability, 2024, 16(23): 10428-10428.

[13] López D R, Rojas L M J, Sevil A S J, et al. Optimising Grid-Connected PV-Battery Systems for Energy Arbitrage and Frequency Containment Reserve[J]. Batteries, 2024, 10(12): 427-427.

[14] Wang Y, Lee S, Li C, et al. Techno-economic evaluation of solar photovoltaic power production in China for sustainable development and the environment[J]. Environment, Development and Sustainability, 2024, (prepublish): 1-30.

[15] Chen R, Gao S, Zhao Y, et al. A hybrid model based on the photovoltaic conversion model and artificial neural network model for short-term photovoltaic power forecasting[J]. Frontiers in Energy Research, 2024, 121446422-1446422.

[16] Pan C, Liu Y, Oh Y, et al. Short-Term Photovoltaic Power Forecasting Using PV Data and Sky Images in an Auto Cross Modal Correlation Attention Multimodal Framework[J]. Energies, 2024, 17(24): 6378-6378.

[17] Mbey F C, Kakeu F J V, Boum T A, et al. Solar photovoltaic generation and electrical demand forecasting using multi-objective deep learning model for smart grid systems[J]. Cogent Engineering, 2024, 11(1).

[18] Runqi Z, Xiangyu W, Xiaochong G, et al.Analysis of Investment Efficiency in New Energy Projects by Traditional Energy Enterprises: A Case Study of Rooftop Photovoltaic Power Projects in the Chongqing Regional Market[J]. Proceedings of Business and Economic Studies, 2024, 7(6): 73-82.