Search Results (946)

To enhance the accuracy and robustness of short-term photovoltaic (PV) power forecasting, this paper proposes a novel forecasting method that integrates data aggregation, adaptive frequency decomposition (AFD), modified improved beluga whale optimization (MIBWO), and a CNN-GRU-SE hybrid model. First, the Pearson correlation coefficient and the entropy weight method are combined to screen meteorological features that are strongly correlated with PV power output. Considering the geographical distance, a spatial data aggregation strategy is proposed to exploit the spatial correlation among neighboring PV stations and suppress the output volatility of individual stations. Then, the AFD is adopted to adaptively decompose the PV power series into trend and seasonal components, and the MIBWO algorithm is utilized to optimize the cutoff frequency of AFD and key hyperparameters of the CNN-GRU-SE forecasting model simultaneously. Finally, the SHAP method is employed for model interpretability analysis to quantify the contribution of each feature to the prediction results. Simulation results verified the power forecasting accuracy and robustness of the proposed method. Compared with CNN-GRU and BWO-CNN-GRU-SE, the proposed method reduces MAE by 96.23% and 95.03%, respectively. The method maintains stable performance with sunny and cloudy conditions. Full article

This study evaluates how validation design affects the assessment of photovoltaic (PV) inverter fault prediction under sparse operational event conditions. Using an 89-day dataset from 18 co-located inverters at a single PV plant, minute-level SCADA measurements were transformed into 56-step input windows with 15 min future event labels. Three validation configurations were compared under the same XGBoost-based forecasting task: single-equipment temporal validation, pooled temporal validation, and leave-one-equipment-out (LOEO) validation. The results show that the three configurations provide different interpretations of predictive usefulness. Single-equipment validation achieved a mean PR-AUC of 0.699, pooled temporal validation achieved a PR-AUC of 0.637, and LOEO validation achieved a mean PR-AUC of 0.718 with a mean ROC-AUC of 0.930. Bootstrap confidence intervals confirmed that held-out equipment performance estimates were statistically more stable than in extremely sparse short-window settings; for example, held-out equipment 4 achieved a PR-AUC of 0.734 with a 95% confidence interval of 0.704–0.762. Variable-level permutation importance showed that predictive performance was mainly associated with DC-side voltage/current and selected AC-side electrical variables. These findings demonstrate that validation design is not a secondary implementation detail but a substantive methodological choice in PV predictive-maintenance evaluation. The study provides practical guidance for selecting validation strategies according to deployment scenarios, including asset-specific modeling, shared plant-level prediction, and predictive coverage for unseen or data-limited inverters. Full article

Self-contained local forecasting of wind and solar series can improve operational planning of wind farms and photovoltaic (PV) plant day-cycles in addition to numerical models, which are mostly behind time due to high simulation costs. Unstable electricity production requires balancing the availability of renewable energy (RE) with unpredictable user consumption to achieve effective usage. Artificial intelligence (AI) predictive modelling can minimise the intermittent uncertainty in wind and solar resources by trying to eliminate specific problems in RE-detached system reliability and optimal utilisation. The proposed 24 h day-training and prediction scheme comprises the starting detection and the following similarity re-assessment of sampling day-series intervals. Two-point professional weather stations record standard meteorological variables, of which the most relevant are selected as optimal model inputs. Automatic two-layer altitude observation captures key relationships between hill- and lowland-level data, which comply with pattern progress. New biologically inspired differential learning (DfL) is designed and developed to integrate adaptive neurocomputing (evolving node tree components) with customised numerical procedures of operator calculus (OC) based on derivative transforms. DfL enables the representation of uncertain dynamics related to local weather patterns. Angular and frequency data (wind azimuth, temperature, irradiation) are processed together with the amplitudes to solve simple 2-variable partial differential equations (PDEs) in binomial nodes. Differentiated data provide the fruitful information necessary to model upcoming changes in mid-term day horizons. Additional PDE components in periodic form improve the modelling of hidden complex patterns in cycle data. The DfL efficiency was proved in statistical experiments, compared to a variety of elaborated AI techniques, enhanced by selective difference input preprocessing. Successful LSTM-deep and stochastic tree learning shows little inferior model performances, notably in day-ahead estimation of chaotic 24 h wind series, and slightly better approximation of alterative 8 h solar cycles. Free parametric C++ software with the applied archive data is available for additional comparative and reproducible experiments. Full article

Accurate ultra-short-term photovoltaic (PV) power forecasting is essential for secure grid dispatch and renewable-rich system operation, yet it remains difficult because of rapid weather fluctuations and error accumulation in multi-step prediction. This paper proposes a decoupled physics-guided residual-correction framework, built on an attention-based sequence-to-sequence (Seq2Seq) architecture, for deterministic 4 h ahead rolling PV forecasting at 15 min resolution. In the first stage, a physical model maps numerical weather prediction (NWP) inputs to a deterministic baseline trajectory while preserving physical bounds. In the second stage, an Attention-Seq2Seq network learns the structured residual trajectory from historical sequences. The global attention mechanism allows the decoder to focus on the most informative historical states, helping reduce information loss and error accumulation over extended horizons. Experiments on a 22-month real-world PV dataset show that the proposed framework outperforms conventional linear and nonlinear benchmarks, reducing root mean square error (RMSE) and mean absolute error (MAE) by 23.79% and 39.17%, respectively, relative to the physical baseline. The framework also maintains robust instantaneous tracking under rapidly changing cloud conditions and preserves a 30–40% error reduction rate at Steps 12–16, supporting reliable intraday scheduling. Full article

To improve solar irradiance simulation accuracy for precise photovoltaic power forecasting, we developed a hybrid framework combining WRF-Solar numerical simulation and random forest (RF) machine learning for a PV plant in Guangdong, China. Weather conditions were objectively classified into clear, intermittent cloudy, and overcast using the Daily Variability Index (DVI) and Daily Clear-sky Index (DCI). We calibrated the WRF-Solar model’s microphysics and radiative transfer schemes via sensitivity tests to optimize overcast-sky performance, then applied RF correction to the simulated irradiance. Results show that RF correction significantly reduces simulation errors for intermittent and overcast conditions, while the original WRF-Solar outperforms the corrected results under clear skies due to RF overfitting. Full article

Accurate short-term photovoltaic (PV) power forecasting is essential for power system scheduling and market operations. Existing studies have shown the value of numerical weather prediction (NWP), graph-based spatial modeling, and temporal sequence learning, but the boundary of their contributions remains fragmented across many practical forecasting frameworks. In particular, adjacent multi-point NWP information is often not explicitly organized according to its spatial relationships, while historical similar-day power is rarely integrated with graph-structured meteorological features in a unified model. To address this gap, this study develops a short-term PV power forecasting framework that combines multi-point NWP graph construction with similar-day-guided Transformer fusion. First, predicted irradiance from the target site and neighboring NWP points is organized as a graph, and a Graph Convolutional Network (GCN) is used to extract local spatial meteorological features. Second, similar days are identified through a two-stage selection strategy based on Euclidean distance and Pearson correlation, and the corresponding historical power sequences are aggregated as temporal guidance. Finally, the graph-extracted NWP features, similar-day power, and predicted humidity are fused by a Transformer-based temporal modeling module to generate day-ahead PV power forecasts. Experimental results show that the proposed framework outperforms TCN-Transformer, Transformer, GCN, LSTM, and BP on the studied dataset, and maintains favorable performance on additional PV stations. These results indicate that the joint integration of graph-structured multi-point NWP information and historical similar-day power is effective for short-term PV power forecasting. Full article

With the increasing occurrence of extreme high-temperature weather events, the traditional bundled operation of wind power (WP), photovoltaic power (PV), and pumped storage hydropower (PSH) is facing dual challenges, namely intensified renewable energy fluctuations and insufficient flexible regulation capability of PSH. Therefore, this paper proposes an optimal scheduling strategy for bundled operation based on capacity interval matching of PSH with WP and PV under extreme high-temperature weather. First, typical scenarios are generated based on a Time-series Generative Adversarial Network (TimeGAN), and an interval matching transaction model is established based on the forecast intervals of WP and PV capacity and the corrected intervals of PSH capacity. Second, considering PSH as an independent market entity, a bi-level optimization model is constructed, in which the upper-level objective is to maximize the revenue of PSH, while the lower-level objective is to minimize the total cost of the joint clearing of the energy and ancillary service markets. Finally, simulation case studies verify that under extreme high-temperature weather, the proposed optimal scheduling method increases the bundled operation capacity by 17.9% and improves the revenue of PSH in the reserve ancillary service market by 14.8%, thereby effectively enhancing the economic performance of PSH while ensuring the safe and stable operation of the system. Full article

The output power of photovoltaic (PV) systems is influenced by various environmental factors, exhibiting strong nonlinearity and non-stationarity, which poses significant challenges for accurate forecasting. To address these issues, this paper proposes a short-term PV power forecasting method based on wavelet convolutional neural networks and an improved Transformer. First, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to decompose the original PV power sequence into several intrinsic mode functions (IMFs). Fuzzy entropy is then utilized to evaluate the complexity of each component, and subsequences with similar entropy values are reconstructed to reduce the non-stationarity of the original series. Subsequently, Pearson correlation coefficients and the maximal information coefficient (MIC) are applied to capture both linear and nonlinear relationships between each reconstructed component and meteorological features, enabling the selection of strongly correlated variables. On this basis, a wavelet convolutional network (WTConv) is introduced to perform multi-scale decomposition and frequency-band feature extraction on the reconstructed components by integrating wavelet transform with convolution operations, effectively expanding the receptive field and extracting deep-seated features of the sequences. Finally, an improved iTransformer model is adopted for time-series modeling, leveraging its inverted encoding structure and self-attention mechanism to fully capture long-term dependencies among multivariate variables. The proposed model is validated using actual power data from a PV plant in Ningxia, China, across four seasons. Comprehensive experiments, including ablation studies, comparative analyses, loss function convergence evaluation, and Diebold–Mariano significance tests, are conducted to thoroughly assess the model’s effectiveness and superiority. Experimental results demonstrate that the proposed model achieves excellent prediction accuracy and stability in spring, summer, autumn, and winter, showing strong potential for engineering applications. Full article

Accurate photovoltaic (PV) power prediction under limited experimental data remains a significant challenge, particularly when purely data-driven models generate predictions that violate fundamental physical constraints. This study proposes a physics-regularized neural network framework for data-efficient PV power modeling using only 45 real experimental measurements of irradiance and temperature. To address data sparsity while preserving physical realism, a physics-guided synthetic augmentation strategy is introduced to generate additional training samples strictly within experimentally validated operating bounds. The proposed Physics-Informed Neural Network (PINN) incorporates two complementary physical constraints directly into the training objective: (i) enforcement of the Shockley–Queisser thermodynamic efficiency limit to maintain compliance with theoretical conversion bounds and (ii) monotonicity regularization to ensure non-negative power gradients with respect to irradiance. Unlike conventional post-processing correction methods, these physical constraints are embedded during model training, enabling simultaneous improvement in predictive accuracy and physical consistency. When benchmarked against a structurally identical unconstrained Artificial Neural Network (ANN), the proposed framework achieves strong predictive performance (R² = 0.9947, RMSE = 5.21 W) while reducing monotonicity violations by approximately 82%. Robustness evaluations under extrapolated irradiance conditions and elevated temperature scenarios further demonstrate stable and physically admissible behavior beyond the training domain. Overall, the results demonstrate that integrating limited experimental measurements with embedded physical priors enables reliable and physically consistent PV power prediction in sparse-data environments, highlighting the potential of physics-regularized learning for renewable energy modeling applications. Full article

Accurate photovoltaic (PV) power forecasting is essential for the efficient operation of residential energy systems and microgrids, as reliable short-term predictions enable improved energy scheduling, demand management, and operational planning in distributed energy environments. In this study, one-hour-ahead forecasting of residential PV power generation is investigated using real-world data collected from multiple households within an Irish energy community. Several deep-learning architectures, including long short-term memory (LSTM), gated recurrent unit (GRU), convolutional neural networks (CNN), CNN–LSTM hybrid networks, and attention-based LSTM models, are evaluated and compared with a seasonal autoregressive integrated moving average (SARIMA) statistical model. A sliding-window approach is employed to transform the PV time series into a supervised learning problem. To ensure statistical robustness, deep-learning models are evaluated using a multi-run framework, and results are reported as mean ± standard deviation based on MAE, RMSE, MAPE, and R² metrics across multiple households. The results indicate that deep-learning models achieve consistently strong forecasting performance, with GRU frequently providing the most reliable predictions across several households. For instance, in House 5, GRU achieved an RMSE of 142.02 ± 1.87 W and an R² of 0.694 ± 0.008, while in Houses 11 and 13 it attained R² values of 0.837 ± 0.002 and 0.835 0.08, respectively. However, performance varied across households, reflecting the influence of data variability and generation patterns on model effectiveness. In comparison, the SARIMA model demonstrated competitive performance and, in certain cases, outperformed deep-learning models. For example, in House 4, it achieved the lowest RMSE of 90.68 W and the highest R² of 0.709. Overall, these findings highlight that while deep-learning models offer greater adaptability and stability, statistical models remain effective for more regular PV generation patterns. Consequently, the study emphasizes the importance of evaluating forecasting models under realistic household-level conditions and demonstrates that both deep-learning and statistical approaches can provide short-term PV forecasting. Full article

High renewable penetration reduces effective inertia and increases frequency variability in microgrids, thereby limiting the performance of purely reactive frequency regulation. This paper presents a two-timescale frequency-support strategy based on bidirectional electric vehicles. The main novelty lies in introducing a learning-assisted correction layer between forecast-based aggregate regulation and final EV-level dispatch. Rather than replacing the predictive controller with an end-to-end data-driven policy, this layer uses measured fleet-state information to correct the supervisory aggregate request online before a final feasibility-preserving dispatch stage converts it into executable vehicle-level commands under concurrent power, energy, plug-in, and departure constraints. A supervisory predictive layer determines the aggregate support action from forecasted photovoltaic and load disturbances, whereas a lower real-time dispatch layer redistributes that action across the available fleet. Feasibility is enforced through an explicit projection stage prior to actuation. The method is assessed in simulation using measured campus operating profiles of irradiance, temperature, demand, frequency, and electric-vehicle availability. Across four representative operating days, the proposed strategy reduced the mean cumulative frequency deviation by 30.3% relative to droop control and by 24.7% relative to predictive-only operation, while reducing the mean time outside the admissible frequency band by 22.2% and 20.0%, respectively. Zero post-projection constraint violations were observed in all evaluated cases. These gains were obtained at the expense of higher actuation usage, thereby making the regulation–usage trade-off explicit. Full article

Photovoltaic (PV) inverter fault prediction is critical for maintaining system reliability and minimizing energy loss. While recent studies have improved predictive accuracy using data-driven approaches, most evaluations remain focused on offline settings and do not address how probabilistic predictions are translated into operational decisions. This study investigates multi-horizon fault prediction for PV inverters under real-world constraints, with a particular focus on decision-level behavior. A modular prediction framework is implemented by combining transformer-based TimeXer embeddings with probabilistic classification using XGBoost. The model operates on sliding-window sensor data and produces fault probabilities across multiple future horizons. To support operational use, these probabilities are aggregated into a single risk score, and threshold-based alarm policies are evaluated through a systematic threshold sweep. The results show that predictive performance varies across horizons, with usable lead-time information concentrated in near-term predictions. Under severe class imbalance, imbalance-aware training significantly improves detection performance in precision–recall space, but performance remains sensitive to temporal variation. Most importantly, the threshold-sweep analysis reveals a structural trade-off between detection performance and alarm burden, where achieving moderate early-warning capability requires substantially increased alarm rates. These findings indicate that improving predictive accuracy alone is insufficient for practical deployment. Instead, decision-level behavior must be explicitly considered when designing predictive maintenance systems under operational constraints. Full article

Accurate forecasting of wind and photovoltaic power remains challenging due to the strong nonlinearity, nonstationarity, and seasonal heterogeneity of renewable generation series. To address this issue, this study proposes a hybrid forecasting framework integrating time–frequency joint analysis (TFAA), temporal convolutional networks (TCN), long short-term memory (LSTM), and multi-head self-attention (MHSA). Wavelet transform is used to extract frequency-domain representations, which are jointly encoded with the original time-domain sequence through a dual-branch architecture and adaptively fused. The fused features are then processed by a TCN-LSTM backbone to capture both long-range dependencies and short-term dynamics, while MHSA is introduced to enhance global contextual modeling. Experiments on wind-farm and photovoltaic datasets from China, together with external validation on the NREL WIND Toolkit and the GEFCom2014 Solar benchmark, show that the proposed model achieves the best overall seasonal performance and maintains competitive improvements on public benchmarks. Additional ablation studies, repeated-run statistical validation, persistence-based skill-score analysis, prediction-interval evaluation, ramp-event assessment, meteorological-driver enrichment, permutation-based driver attribution, regime-conditioned error diagnostics, and transferability evidence analysis further confirm the effectiveness, robustness, physical consistency, and practical applicability of the proposed framework. The results indicate that the proposed model provides a reliable and operationally relevant solution for short-term wind and photovoltaic power forecasting. These findings further support sustainable renewable-energy integration, smart-grid dispatch, and low-carbon power-system operation. Full article

Against the backdrop of the global energy structure accelerating its transition towards a clean and low-carbon model, rooftop-distributed photovoltaic (PV) systems are playing an increasingly prominent strategic role in urban energy supply systems, owing to their notable advantages such as environmental friendliness and high spatial utilization efficiency. Consequently, they are becoming a critical pillar in advancing urban energy transformation and enhancing sustainable development. This paper aims to explore deep learning-based techniques for assessing the potential of large-scale distributed PV installations. To accurately evaluate their dynamic power generation capability, a hybrid prediction model integrating variational mode decomposition (VMD), the mutual information (MI) method, and a cascaded xLSTM-Informer network is proposed. Firstly, the model preprocesses key meteorological sequences using VMD, decomposing them into modal components of different frequencies. Subsequently, the MI method is employed to extract critical sequences. Then, the xLSTM module is utilized to learn the long-term complex dependencies between meteorological conditions and PV power output, while the Informer network captures key global temporal patterns, achieving high-precision time-series forecasting of PV generation. Finally, employing the forecasted time-series power curve as the core input, a comprehensive analytical framework for PV installation potential is constructed, integrating assessments of technical feasibility, economic viability, and environmental performance. This framework aims to scientifically estimate the admissible installed capacity and system value of distributed PV systems, thereby providing a dynamic basis for decision-making in urban planning. Full article

Cloud cover significantly reduces the electrical power output of photovoltaic systems, making accurate short-term cloud movement predictions essential for reliable solar energy production planning. This article presents a deep learning framework that directly estimates cloud movement from ground-based all-sky camera images, rather than predicting future production from past power data. The system is based on a three-step process: First, a lightweight Convolutional Neural Network segments cloud regions and produces probabilistic masks that represent the spatial distribution of clouds in a compact and computationally efficient manner. This allows subsequent models to focus on the geometry of clouds rather than irrelevant visual features such as illumination changes. Second, a Vector Quantized Variational Autoencoder compresses these masks into discrete latent token sequences, reducing dimensionality while preserving fundamental cloud structure patterns. Third, a GPT-style autoregressive transformer learns temporal dependencies in this token space and predicts future sequences based on past observations, enabling iterative multi-step predictions, where each prediction serves as the input for subsequent time steps. Our evaluations show an average intersection-over-union ratio of 0.92 and a pixel accuracy of 0.96 for single-step (5 s ahead) predictions, while performance smoothly decreases to an intersection-over-union ratio of 0.65 and an accuracy of 0.80 in 10 min autoregressive propagation. The framework also provides prediction uncertainty estimates through token-level entropy measurement, which shows positive correlation with prediction error and serves as a confidence indicator for downstream decision-making in solar energy forecasting applications. Full article