Results indicate that embedding physical constraints into data-driven forecasting models can improve PV power prediction accuracy, and shows stronger robustness and generalization performance under heterogeneous operating conditions, although its effectiveness is contingent on relatively stable data distributions.
Abstract
Accurate photovoltaic (PV) power forecasting is essential for reliable microgrid operation, efficient energy dispatch, and improved utilization of renewable energy resources. Existing forecasting methods often have limited capacity to represent the nonlinear relationships between meteorological conditions and PV power output. They also tend to underrepresent the temporal dynamics of PV generation and the physical principles governing photovoltaic energy conversion. To address these limitations, this study proposes a hybrid forecasting framework, CNN-LSTM-PINNs, that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Physics-Informed Neural Networks (PINNs). In the proposed framework, CNNs extract spatial dependencies among multivariate meteorological variables, LSTM networks capture temporal dependencies in PV generation, and PINNs incorporate soft physical constraints derived from photovoltaic energy conversion mechanisms. The proposed model is evaluated using publicly available datasets from three large-scale PV power stations in China, with observations recorded at 15-min intervals. The empirical results show that CNN-LSTM-PINNs outperform the conventional CNN-LSTM benchmark across the primary station-level datasets. Relative to the benchmark model, the proposed framework reduces Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) and improves the coefficient of determination (R2). These results indicate that embedding physical constraints into data-driven forecasting models can improve PV power prediction accuracy. The model also shows stronger robustness and generalization performance under heterogeneous operating conditions, although its effectiveness is contingent on relatively stable data distributions. Feature-importance analysis further indicates that global horizontal irradiance (GHI) and irradiance-derived variables are the most informative predictors of PV power output. Overall, this study provides a physics-informed hybrid modeling approach for high-resolution PV power forecasting in microgrid applications.
With the increasing penetration of photovoltaic power in power systems, accurate photovoltaic power forecasting is important for dispatch optimization, and renewable energy accommodation. To address the problem that data-driven models may ignore photovoltaic generation mechanisms and produce physically inconsistent forecasting results, this paper proposes a CNN-LSTM-PINN photovoltaic power forecasting method based on data–mechanism fusion. The proposed method introduces physics-informed neural networks into a CNN-LSTM temporal forecasting structure, transforms the physical relationship among photovoltaic power, irradiance, and temperature into differentiable constraints, and constructs physical constraint losses based on partial-derivative direction relationships and power boundary conditions, enabling the model to fit historical data while satisfying photovoltaic generation mechanisms. Experimental results show that the proposed method achieves RMSE, MAE, and R2 values of 1.0583, 0.5727, and 0.8912 on the photovoltaic plant dataset, respectively, outperforming PINN CNN-LSTM, LSTM, and traditional machine learning models. Under a 0.30 noise pertur-bation level, its RMSE increases by only 2.86%, demonstrating good stability and anti-disturbance capability.
Qian Lei, Yongxu Chen, Qingyang Li et al.· 2026 5th International Confe...· 0 citations
This study presents a comprehensive analysis of renewable energy forecasting using deep learning techniques, focusing on short-term and medium-term prediction horizons, and shows that deep learning models provide significantly better forecasting accuracy, particularly under highly variable weather conditions.
Lucas Martin, Chloe Bernard· International Journal of Mod...· 0 citations
An optimized forecasting framework using Long Short-Term Memory (LSTM) networks is introduced, confirming the model’s excellent accuracy and its value for improving power system dispatch and resource planning.
Accurately predicting the power generation of distributed photovoltaic (PV) power plants is extremely challenging due to their heterogeneity and complex temporal variations. To address these issues, this paper proposes a clustering-based prediction framework that combines K-means clustering with our proposed model. First, a multidimensional feature representation is constructed to characterize the statistical properties, dynamic fluctuations, and meteorological correlations of PV power plants. This feature representation is then used to classify the power plants into homogeneous clusters. For each cluster, a hybrid deep learning model is developed to capture local temporal patterns and long-term dependencies, with a focus on key time steps. Finally, the outputs of all clusters are aggregated to obtain the regional power generation prediction results. Experimental results demonstrate that the proposed method outperforms the baseline model on multiple error metrics, proving its effectiveness in predicting the power generation of multiple PV power plants.
Jian Tang, Lu-Lu Lin· European Conference on Elect...· 0 citations
The integration of renewable energy, such as solar and wind power, is essential for the development of zero-carbon smart cities. Reliable short-term and medium-term predictions help reduce dependence on fossil-fuel reserves and facilitate more reasonable decisions in urban systems. This study develops a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) model for forecasting multi-source renewable energy. The convolutional layers can extract local temporal patterns from meteorological variables, while the LSTM layers model sequential dependencies over longer horizons. To improve transparency, Local Interpretable Model-agnostic Explanations (LIME) is applied to examine how input variables influence predictions. Experiments are conducted using data from the National Renewable Energy Laboratory, including the National Solar Radiation Database and the Wind Integration National Dataset. Compared with standalone CNNs, LSTMs, and conventional learning models, the hybrid model achieves lower prediction error, with Mean Absolute Percentage Error typically below 3% for forecasting next-day values. Results indicate that higher forecasting accuracy can contribute to reduced renewable curtailment and to more stable, reasonable decisions in smart cities. The proposed framework offers a practical, interpretable approach to renewable energy forecasting in urban systems.
Jia-Cheng Ran· Applied and Computational En...· 0 citations
This study provides an in-depth comparative analysis of four state-of-the-art neural architectures, confirming that high-fidelity point forecasts and rigorously quantified uncertainty can be achieved simultaneously, providing a clear path toward more dependable PV dispatch, reserve allocation, and market participation.
Saloni Dhingra, G. Gruosso, G. Storti Gajani· Neural computing & applicati...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
