Short-term Photovoltaic Research Articles

Small-Sample Short-Term Photovoltaic Output Prediction Model Based on GRA-SSA-GNNM Method

The precision of photovoltaic (PV) output forecasting results is crucial to the reliability of the intelligent distribution network and multi-energy supplementary system. This work aims to address problems of insufficient research related to the short-term prediction of small-sample PV power generation and the low prediction accuracy in the previous research. A hybrid prediction model based on grey relation analysis (GRA) combined with the sparrow search algorithm (SSA) and the grey neural network model (GNNM) is proposed. In this paper, GRA is utilized to reduce the dimension of meteorological features of the samples. Then, the GNNM is used to perform regression analysis on the input features after reducing the dimension of meteorological features of the samples, and the parameters of the GNNM are optimized via SSA. A limited dataset was used to compare several models in different seasons and weather conditions. The prediction results agree well with the data from the PV power plant in Xinjiang, indicating that the GRA-SSA-GNNM model developed in this work effectively achieves a high precision estimation in short-term PV power generation output prediction and has a promising application in this field.

A Short-term PV Power Prediction and Uncertainty Analysis Model Based on CEEMDAN and AHA-BP

The stochastic and intermittent nature of photovoltaic (PV) generation brings a series of scheduling problems to the power system. An effective prediction of PV power is essential to minimize the impact of uncertainty. Therefore, this paper presents an integrated prediction model with complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), the artificial hummingbird algorithm (AHA), and the BP neural network (BPNN) for predicting power generation from PV power plants, and a methodology for uncertainty analysis by using the nonparametric kernel density estimation (NPKDE). First, one month of PV power is decomposed into an array of components using CEEMDAN. Then, the weights and thresholds of the BPNN are optimized by using AHA. These components are trained using the BPNN. Finally, the final prediction results are obtained by superimposing the components, and NPKDE is employed to compute the probability density and confidence interval of the prediction error. The proposed prediction method demonstrates superior predictive performance in comparison with other models. Also, the NPKDE approach better describes the accuracy of the probability density distribution.

CGAformer: Multi-scale feature Transformer with MLP architecture for short-term photovoltaic power forecasting

Accurately predicting the output power of photovoltaic (PV) systems is an effective means to ensure the reliable and economical operation of grid-connected PV systems. Aiming at the characteristics of PV power generation such as strong volatility, high intermittency and obvious periodicity, a hybrid model named CGAformer based on One-Dimensional Convolutional Neural Networks (CNN1D), Global Additive Attention (GADAttention), and Auto-Correlation is proposed for short-term PV power generation prediction. The model uses CNN1D to extract local features and obtains global weights by improving the GADAttetion obtained by additive attention. Auto-Correlation integrates local features and global weights and identifies repeated patterns in the sequence to obtain highly coupled multi-scale features, and finally generates the final prediction results through Multilayer Perceptron (MLP). In order to verify the effectiveness of the model, this paper uses a historical dataset from a PV system located in Uluru, Australia for sufficient experiments. In the comparative experiments, The overall average RMSE and MAE of CGAformer are improved by 6.82% and 20.46% respectively compared with long short-term memory (LSTM). In addition, ablation experiments and seasonal analysis are used to verify the effectiveness of the model and its excellent generalization ability for different seasons.

Short-Term Photovoltaic Power Probabilistic Forecasting Based on Temporal Decomposition and Vine Copula

With the large-scale development of solar power generation, highly uncertain photovoltaic (PV) power output has an increasing impact on distribution networks. PV power generation has complex correlations with various weather factors, while the time series embodies multiple temporal characteristics. To more accurately quantify the uncertainty of PV power generation, this paper proposes a short-term PV power probabilistic forecasting method based on the combination of decomposition prediction and multidimensional variable dependency modeling. First, a seasonal and trend decomposition using a Loess (STL)-based PV time series feature decomposition model is constructed to obtain periodic, trend, and residual components representing different characteristics. For different components, this paper develops a periodic component prediction model based on TimeMixer for multi-scale temporal feature mixing, a long short-term memory (LSTM)-based trend component extraction and prediction model, and a multidimensional PV residual probability density prediction model optimized by Vine Copula optimized with Q-Learning. These components’ results form a short-term PV probabilistic forecasting method that considers both temporal features and multidimensional variable correlations. Experimentation with data from the Desert Knowledge Australia Solar Center (DKASC) demonstrates that the proposed method reduced root mean square error (RMSE) and mean absolute percentage error (MAPE) by at least 14.8% and 22%, respectively, compared to recent benchmark models. In probability interval prediction, while improving accuracy by 4% at a 95% confidence interval, the interval width decreased by 19%. The results show that the proposed approach has stronger adaptability and higher accuracy, which can provide more valuable references for power grid planning and decision support.

Multi-scale RWKV with 2-dimensional temporal convolutional network for short-term photovoltaic power forecasting

Improving the accuracy of Photovoltaic (PV) power forecasting is crucial for optimizing the schedule of power stations and maintaining the grid stability. However, PV power generation exhibits complex periodicity and is significantly influenced by weather conditions, introducing instability, intermittency, and randomness, making accurate PV power forecasting a challenging task. Therefore, this study proposes a multi-scale Receptance Weighted Key Value with 2-Dimensional Temporal Convolutional Network (MSRWKV-2DTCN) for PV power forecasting, which can learn periodicity and interdependencies of data and improve forecasting accuracy. Firstly, the proposed model identifies multi-periodicity of PV power data with the Fast Fourier Transform (FFT). Subsequently, we combine these identified periods with the canonical time mixing block of Receptance Weighted Key Value (RWKV) and introduce a multi-scale time mixing block to learn periodicity of data. Finally, to explore complex interdependencies of historical data, we replace the channel-mixing block of RWKV with a multi-scale 2-Dimensional Temporal Convolutional Network (2D TCN). Experiments were conducted on real-world datasets collected from Yulara solar system in Australia to validate the performance of the proposed model. Comparisons with other PV power forecasting models and ablation studies confirm that the MSRWKV-2DTCN achieves higher accuracy in short-term PV power forecasting.

Machine Learning Approaches for Short-Term Photovoltaic Power Forecasting

A photovoltaic (PV) power forecasting prediction is a crucial stage to utilize the stability, quality, and management of a hybrid power grid due to its dependency on weather conditions. In this paper, a short-term PV forecasting prediction model based on actual operational data collected from the PV experimental prototype installed at the engineering college of Misan University in Iraq is designed using various machine learning techniques. The collected data are initially classified into three diverse groups of atmosphere conditions—sunny, cloudy, and rainy meteorological cases—for various seasons. The data are taken for 3 min intervals to monitor the swift variations in PV power generation caused by atmospheric changes such as cloud movement or sudden changes in sunlight intensity. Then, an artificial neural network (ANN) technique is used based on the gray wolf optimization (GWO) and genetic algorithm (GA) as learning methods to enhance the prediction of PV energy by optimizing the number of hidden layers and neurons of the ANN model. The Python approach is used to design the forecasting prediction models based on four fitness functions: R2, MAE, RMSE, and MSE. The results suggest that the ANN model based on the GA algorithm accommodates the most accurate PV generation pattern in three different climatic condition tests, outperforming the conventional ANN and GWO-ANN forecasting models, as evidenced by the highest Pearson correlation coefficient values of 0.9574, 0.9347, and 0.8965 under sunny, cloudy, and rainy conditions, respectively.

Interpretable feature selection and deep learning for short-term probabilistic PV power forecasting in buildings using local monitoring data

Accurate probabilistic forecasting of photovoltaic (PV) power is crucial for optimizing energy scheduling in smart buildings and ensuring the low-carbon, efficient operation of building energy management systems (BEMS). However, existing feature selection techniques fail to guarantee that the selected features genuinely impact the output of forecasting models. Additionally, traditional black-box deep learning models lack clarity on whether their output truly relies on those selected features. These challenges limit the accuracy of forecasting models. To address these challenges, a novel methodology named temporal importance model explanation and temporal fusion transformers (TIME-TFT) model is proposed. Firstly, the TIME method is employed for feature selection, and interpretable outputs are used to identify important global features. Secondly, the TFT model is then utilized for forecasting tasks, providing interpretable outputs to track back to the features that TFT model pays attention to. Finally, the consistency between the interpretable outputs of TIME method and TFT model is examined to confirm predictions are based on genuinely learned selected features. Empirical studies demonstrate the superiority of the proposed TIME-TFT system, outperforming comparable models with an R2 of 0.9546. In summary, the interpretable outputs not only improve the accuracy of predictions but also provides visual evidence for predictions, thereby bolstering effectiveness and credibility in engineering practices.

Short-Term Photovoltaic Power Prediction Based on a Digital Twin Model

Due to the influence of meteorological conditions, shipboard photovoltaic (PV) systems have problems such as large fluctuation and inaccurate prediction of the output power. In this paper, a short-term PV power prediction method based on a novel digital twin (DT) model and BiLSTM is proposed. Firstly, a PV mechanism model and a data-driven model were established, in which the data-driven model was updated iteratively in real time using the sliding time window update method; then, these two models were converged to construct a PV DT model according to the DS evidence theory. Secondly, a BiLSTM model was built to make short-term predictions of the PV power using the augmented dataset of the DT model as an input. Finally, the method was tested and verified by experiments and further compared with main PV prediction methods. The research results indicate the following: firstly, the absolute error of the DT model was smaller than that of the mechanism model and the data-driven model, being as low as 5.62 W after the data update of the data-driven model; thus, the DT model realized data augmentation and high fidelity. Secondly, compared to several main PV prediction models, the PV DT model combined with BiLSTM had the lowest RMSE, MAE, and MAPE; the best followability; and the smallest absolute error under different weather conditions, which was especially obvious under cloudy weather conditions. In summary, the method can accurately predict the shipboard PV power, which has great theoretical significance and application value for improving the economy and reliability of solar ship operation.

Short-Term Solar Power Prediction using Machine Learning Algorithms : A High Performing approach

The use of solar energy is growing in popularity across the globe as a clean and sustainable energy source. Nevertheless, integrating solar power into the grid and guaranteeing a steady supply of electricity is made more difficult by the weather patterns’ tendency to cause unpredictability in solar power generation. One potential solution to these issues is the use of machine learning (ML) techniques for short term solar photovoltaic (PV) power forecasting. This research looks into how well various machine learning algorithms work for short-term PV power forecasting. It also offers a summary of the variables that affect time-series data performance and suggests high-performance methods. Long Short-term Memory (LSTM), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were tested on an 88,494-item dataset with 20 features at a 15-minute resolution. As accuracy metrics, root mean square error (RMSE) and mean square error (MSE) show that ANNs and LSTM perform better than SVM. The superiority of the suggested methods is demonstrated by a careful comparison with recently published results. The reason for the effectiveness of ANNs and LSTMs is their capacity to represent the complex and non-linear relationships found in the data. Short-term solar power forecasting is complex, and SVMs are better equipped to handle linear relationships. These findings will be a useful guidance for those who intend to work in the field of PV power forecasting, even though further research is required to generalize this observation. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 9(1), 2022 P 82-95

Short-term PV power data prediction based on improved FCM with WTEEMD and adaptive weather weights

Photovoltaic (PV) systems are commonly used in zero energy buildings(ZEBs) due to their high efficiency and convenience. However, PV systems are affected by meteorological factors with nonlinearities and stochasticity in the power generation process, which leads to inaccurate prediction of PV power, affects the relationship between energy supply and user demand, and then has a significant impact on the stability of PV grid connection. To address these challenges, this paper proposes a WTEEMD-FCM-IGWO-LSTM method for the numerical prediction of PV power. Firstly, for the noise interference in the meteorological data of PV power generation collected from PV power stations, this paper proposes an Ensemble Empirical Mode Decomposition (EEMD) method based on the wavelet threshold algorithm improvement (WTEEMD) for noise reduction and reconstruction of meteorological data to enhance the signal-to-noise ratio in the data. Secondly, considering the stochastic nature of unstable meteorological factors, an improved fuzzy C-mean clustering (FCM) method is employed to classify the PV power process dataset and enhance the correlation between meteorological factors and power data. Subsequently, prediction models for the power values of the PV power generation process under each of the three meteorological conditions are developed using Long Short-Term Memory (LSTM) based on the classified sample data. Finally, the proposed model is evaluated through simulation using historical Australian PV data. The experimental results show that it is possible to accurately predict the power of PV power generation, improve the utilization of clean energy, and support the sustainable development of ZEBs.

Short-term photovoltaic power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model

In order to further improve the accuracy of photovoltaic (PV) power prediction and the stability of power system, a short-term PV power prediction model based on hierarchical clustering of K-means++ algorithm and deep learning hybrid model is proposed in this paper. First, hierarchical clustering of the K-means++ algorithm is used to cluster historical data into different weather scenes according to different seasons. Second, a hybrid model combining convolutional neural network (CNN), squeeze-and-excitation attention mechanism (SEAM), and bidirectional long short-term memory (BILSTM) neural network is constructed to capture long-term dependencies in time series, and the improved pelican optimization algorithm (IPOA) is used to optimize the hyperparameters in the prediction model. Finally, an example for modeling analysis is conducted by using the actual output and meteorological data of a PV power station in the Ili region of Xinjiang, China. The effectiveness and accuracy of the proposed model are verified by comparing with LSTM, BILSTM, CNN-BILSTM, and POA-CNN-SEAM-BILSTM models, and the superiority of IPOA is verified by comparing with particle swarm optimization and whale optimization algorithm. The results show that the proposed model can obtain better results under different weather scenes in different seasons, and the prediction accuracy of the model optimized by IPOA is further improved.

Short-term PV power prediction based on meteorological similarity days and SSA-BiLSTM

Accurate short-term photovoltaic (PV) power forecasting can reduce the un- certainty of PV power generation, which is crucial for grid operation as well as energy dispatch. Considering the influence of seasonal and meteorological factors on short-term PV power prediction, a short-term PV power predic- tion method based on meteorological similarity day and sparrow search algo- rithm and bi-directional long and short-term memory network combination (SSA-BiLSTM) is proposed. Firstly, the correlation between meteorological factors and PV power generation is calculated by using Pearson coefficients, getting the strongly correlated meteorological factors affecting PV power generation; afterwards,the historical data of the strongly correlated meteorological factors are clustered by fuzzy C-means clustering to achieve meteorological similar day clustering; then, the best similar day is selected from the meteorological similar day according to the test day seasonal features and meteorological data, and Forming a training set with historical data, and training the original BiLSTM network. the SSA algorithm was used to find the optimal BiLSTM network parameters. Finally, Using the optimal parameters construct BiLSTM network to achieve short-term PV power prediction. The experiments were conducted with historical data from a PV power plant in Xinjiang, and also compared with existing prediction algorithms.The results show that the accuracy of PV power prediction in different weather conditions is 33.1 %, 31.9 % and 24.1 % higher than that under the same intelligent optimization algorithm and different neural networks, the accuracy of PV power prediction in different weather conditions is 27.9 %, 24.7 % and 18.0 % higher than that under the different intelligent algorithms and same neural network. Therefore, the algorithm in this paper has better accuracy in short-term PV power prediction under different seasons and different weather conditions.

Short-Term Photovoltaic Power Prediction Using Nonlinear Spiking Neural P Systems

To ensure high-quality electricity, improve the dependability of power systems, reduce carbon emissions, and promote the sustainable development of clean energy, short-term photovoltaic (PV) power prediction is crucial. However, PV power is highly stochastic and volatile, making accurate predictions of PV power very difficult. To address this challenging prediction problem, in this paper, a novel method to predict the short-term PV power using a nonlinear spiking neural P system-based ESN model has been proposed. First, we combine a nonlinear spiking neural P (NSNP) system with a neural-like computational model, enabling it to effectively capture the complex nonlinear trends in PV sequences. Furthermore, an NSNP system featuring a layer is designed. Input weights and NSNP reservoir weights are randomly initialized in the proposed model, while the output weights are trained by the Ridge Regression algorithm, which is motivated by the learning mechanism of echo state networks (ESNs), providing the model with an adaptability to complex nonlinear trends in PV sequences and granting it greater flexibility. Three case studies are conducted on real datasets from Alice Springs, Australia, comparing the proposed model with 11 baseline models. The outcomes of the experiments exhibit that the model performs well in tasks of PV power prediction.

A hybrid model of CNN and LSTM autoencoder-based short-term PV power generation forecasting

AbstractSolar energy is one of the main renewable energies available to fulfill global clean energy targets. The main issue of solar energy like other renewable energies is its randomness and intermittency which affects power grids stability. As a solution for this issue, energy storage units could be used to store surplus energy and reuse it during low solar generation intervals. Also, in order to sustain stable power grid and better grid operation and energy storage management, photovoltaic (PV) power forecasting is inevitable. In this paper, new hybrid model based on deep learning techniques is proposed to predict short-term PV power generation. The proposed model incorporates convolutional neural network (CNN) and long short-term memory (LSTM) autoencoder network. The new model differentiates itself in accomplishing high prediction accuracy by extracting spatial features in time series via CNN layers and temporal features between the time series data through LSTM. The introduced model is tested on dataset of power generation from southern UK solar farm and the weather data corresponding to same location and time intervals; the forecasting performance of the suggested model is evaluated in metrics of root-mean-square error (RMSE) and mean absolute error (MAE). The used model is compared with different models from the literature either of pure type of network such as LSTM and gated recurrent unit (GRU) or hybrid combination of different networks like CNN-LSTM and CNN-GRU. The results show that proposed model provides enhanced results and reduces training time significantly compared to other competitive models, where the performance of the proposed model improved averagely by 5% to 25% in terms of RMSE and MAE performance metrics, and the execution time of training significantly reduced with almost 70% less compared to other models.

Multistage spatio-temporal attention network based on NODE for short-term PV power forecasting

Photovoltaic (PV) power has attracted widespread attention from many countries around the world due to its clean and renewable characteristics. To ensure the stable operation of the power system, accurate PV power forecasting has become a mandatory and challenging task. Currently, deep learning methods have become a vital approach in the field of PV power forecasting. In this work, a multistage attention neural network based on neural ordinary differential equation (MANODE) is proposed to address the main limitations of previous deep learning methods applied to PV power forecasting. Based on the neural ordinary differential equation (NODE), MANODE optimizes the long short-term memory network (LSTM) and temporal convolutional neural network (TCN), and combines the attention mechanism to achieve fine-grained spatio-temporal information extraction of PV series. In addition, the proposed MANODE model is applied to three different PV series collected from the Alice Springs meteorological station. Compared to previous state-of-the-art methods, the proposed method reduces the PV power forecasting error by at least 12.05%, 13.15%, and 9.71% on three different PV datasets, in terms of mean absolute error metric. The average errors of the MANODE method in four-hour-ahead PV power forecasting on the three datasets are 0.321, 0.350, and 0.567.

A Somogy megyében megvalósítható fotovoltaikus potenciál első számítása és hatása a CO2-kibocsátás csökkentésére és a munkahelyteremtésre

Due to the current climate urgency, it is necessary to accelerate an energy transition towards renewable energies. To this end, the European Union has set ambitious energy targets. However, in member countries such as Hungary, nuclear energy and fossil fuels continue playing a major role in the energy mix. Nevertheless, this country has a large solar photovoltaic (PV) potential that is hardly exploited, especially in the southern counties, and its technical potential has been less analysed. With the aim to estimate the short-term implementable solar PV potential in Somogy county in southern Hungary, a multi-criteria spatial approach which integrates environmental, technical (with economic attributes), and geographical (with social-acceptability attributes) GIS-based constraints with existing local power plant considerations was employed. Results show that Somogy has a short-term implementable solar PV potential of 2.7 GWp This power potential is about 25 times more than the current installed capacity for generating electricity in Somogy and represents 45% of the national target by 2030 for installed solar PV capacity in Hungary. Furthermore, this potential could create almost 35,000 direct jobs and avoid the emissions of 1.16–2.65 MtCO2 to the atmosphere. The findings and future studies suggested in this work are significant for both local and national levels and could contribute with insights on how to meet climate targets and accelerate energy independence with socio-economic benefits.

Short-Term Photovoltaic Power Forecasting Based on a Feature Rise-Dimensional Two-Layer Ensemble Learning Model

Photovoltaic (PV) power generation has brought about enormous economic and environmental benefits, promoting sustainable development. However, due to the intermittency and volatility of PV power, the high penetration rate of PV power generation may pose challenges to the planning and operation of power systems. Accurate PV power forecasting is crucial for the safe and stable operation of the power grid. This paper proposes a short-term PV power forecasting method using K-means clustering, ensemble learning (EL), a feature rise-dimensional (FRD) approach, and quantile regression (QR) to improve the accuracy of deterministic and probabilistic forecasting of PV power. The K-means clustering algorithm was used to construct weather categories. The EL method was used to construct a two-layer ensemble learning (TLEL) model based on the eXtreme gradient boosting (XGBoost), random forest (RF), CatBoost, and long short-term memory (LSTM) models. The FRD approach was used to optimize the TLEL model, construct the FRD-XGBoost-LSTM (R-XGBL), FRD-RF-LSTM (R-RFL), and FRD-CatBoost-LSTM (R-CatBL) models, and combine them with the results of the TLEL model using the reciprocal error method, in order to obtain the deterministic forecasting results of the FRD-TLEL model. The QR was used to obtain probability forecasting results with different confidence intervals. The experiments were conducted with data at a time level of 15 min from the Desert Knowledge Australia Solar Center (DKASC) to forecast the PV power of a certain day. Compared to other models, the proposed FRD-TLEL model has the lowest root mean square error (RMSE) and mean absolute percentage error (MAPE) in different seasons and weather types. In probability interval forecasting, the 95%, 75%, and 50% confidence intervals all have good forecasting intervals. The results indicate that the proposed PV power forecasting method exhibits a superior performance in forecasting accuracy compared to other methods.

A novel hybrid model for short-term prediction of PV power based on KS-CEEMDAN-SE-LSTM

Accurate prediction of photovoltaic (PV) power plays a pivotal role in ensuring safe and stable grid operation, enhancing power supply quality, and facilitating proactive grid management to mitigate power fluctuations. This paper introduces a novel hybrid model named KS-CEEMDAN-SE-LSTM, which combines K-Shape (KS) clustering, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample entropy (SE), and Long Short-Term Memory (LSTM) techniques. To improve the accuracy of PV power prediction, three advanced preprocessing techniques, KS clustering, CEEMDAN and SE, are employed for feature extraction before prediction. In the proposed approach, KS clustering is employed to capture the similarity features of PV power. Subsequently, CEEMDAN decomposes the PV power into multiple intrinsic mode functions (IMFs) to reduce the influence of non-stationary and noisy features in power prediction. To further enhance prediction accuracy and streamline computational complexity, SE methods and K-means clustering are utilized to reconstruct the decomposed IMFs into new sub-sequences with refined granularity features. Finally, the LSTM model is applied to predict each reconstructed sub-sequence, and the ultimate prediction results are obtained by aggregating the predictions from all sub-sequences. The effectiveness of this method is demonstrated using real-world PV power data collected from China. Comprehensive experiments substantiate that the proposed KS-CEEMDAN-SE-LSTM model outperforms benchmark methods in short-term PV power prediction.

Resource efficient PV power forecasting: Transductive transfer learning based hybrid deep learning model for smart grid in Industry 5.0

This paper presents an innovative approach for enhancing power output forecasting of Photovoltaic (PV) power plants in dynamic environmental conditions using a Hybrid Deep Learning Model (DLM). The hybrid DLM employs a synergy of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Bidirectional LSTM (Bi-LSTM), effectively capturing spatial and temporal dependencies within weather data crucial for accurate predictions. To optimize the DLM’s performance efficiently, a unique Kepler Optimization Algorithm (KOA) is introduced for hyperparameter tuning, drawing inspiration from Kepler’s laws of planetary motion. By leveraging KOA, the DLM attains optimal hyperparameter configurations, elevating power output prediction precision. Additionally, this study integrates Transductive Transfer Learning (TTL) with the deep learning models to enhance resource efficiency. By leveraging knowledge gained from previously learned tasks, TTL enables the DLM to improve its forecasting capabilities while minimizing resource utilization. Datasets encompassing environmental parameters and PV plant-generated power across diverse sites are employed for DLM training and testing. Three hybrid models, amalgamating KOA, CNN, LSTM, and Bi-LSTM techniques, are introduced and evaluated. Comparative assessment of these models across distinct PV sites yields insightful observations. Performance evaluation, focused on short-term PV power forecasting, underscores the hybrid DLM’s superiority over individual CNN and LSTM models. This hybrid approach achieves remarkable accuracy and resilience in predicting power output under varying weather conditions, showcasing its potential for efficient PV power plant management.

Geometric Deep-Learning-Based Spatiotemporal Forecasting for Inverter-Based Solar Power

Conventional power grids dominated by synchronous generators gradually shift to variable renewable-energy-integrated grids. With the growth of building-level photovoltaic (PV) panels and other inverter-based resource (IBR) deployments in recent years, market retailers and distribution operators have had to deal with the additional operational and management challenges posed by unobserved energy flow if its behind-the-meter (BTM) configuration. Also, the intermittent and stochastic nature of IBR-based solar power introduces uncertainty into the net load forecasting of electric distribution systems. Hence, management and control with high uncertainty in load prediction due to unobservable PV is a technical challenge. This article presents deep-learning-based algorithms for BTM PV power generation using a limited number of sensors in a given distribution system and extending to adjacent geographical areas. The proposed BTM PV forecasting method is based on geometric deep learning—a spatiotemporal graph neural network by processing the relationship between data in a non-Euclidean graph structure. The predictions of short-term BTM PV are aggregated with loss estimation at the data aggregation point with the net load forecasting to compute the true load forecasting with superior performance. The developed BTM PV forecasting method significantly improved true load forecasting results, which were validated and analyzed using a collection of actual BTM PV and load measurements in a test distribution feeder.