Journal Article

Efficient Method for Photovoltaic Power Generation Forecasting Based on State Space Modeling and BiTCN

Luo, Shuai, Ji, Yulong, Chen, Hu, Dai, Guowei

2024

Overview

As global carbon reduction initiatives progress and the new energy sector rapidly develops, photovoltaic (PV) power generation is playing an increasingly significant role in renewable energy. Accurate PV output forecasting, influenced by meteorological factors, is essential for efficient energy management. This paper presents an optimal hybrid forecasting strategy, integrating bidirectional temporal convolutional networks (BiTCN), dynamic convolution (DC), bidirectional long short-term memory networks (BiLSTM), and a novel mixed-state space model (Mixed-SSM). The mixed-SSM combines the state space model (SSM), multilayer perceptron (MLP), and multi-head self-attention mechanism (MHSA) to capture complementary temporal, nonlinear, and long-term features. Pearson and Spearman correlation analyses are used to select features strongly correlated with PV output, improving the prediction correlation coefficient (R2) by at least 0.87%. The K-Means++ algorithm further enhances input data features, achieving a maximum R2 of 86.9% and a positive R2 gain of 6.62%. Compared with BiTCN variants such as BiTCN-BiGRU, BiTCN-transformer, and BiTCN-LSTM, the proposed method delivers a mean absolute error (MAE) of 1.1%, root mean squared error (RMSE) of 1.2%, and an R2 of 89.1%. These results demonstrate the model’s effectiveness in forecasting PV power and supporting low-carbon, safe grid operation.

• Publisher: MDPI AG,MDPI
• Subject: Accuracy / Algorithms / Alternative energy sources / Artificial intelligence / Comparative analysis / Deep learning / Efficiency / Feature selection / Forecasting techniques / Forecasts and trends / intelligent fusion / Machine learning / Measurement / Methods / Neural networks / Optimization / photovoltaic power forecasting / Photovoltaic power generation / Renewable resources / Solar energy / state space model / Time series / time series prediction / Weather forecasting