Photovoltaic Power Prediction Research Articles

Wind turbine and PV power prediction using a deterministic data-driven model with variational mode decomposition preprocessing

This study develops a method for accurately forecasting solar radiation (SR), wind speed (WS), and air temperature (AT) for the coming 24 hours in order to predict energy production from photovoltaic (PV) panels and wind turbines (WT) in positive energy buildings. Input data are pre-processed through variational mode decomposition (VMD) for broadband feature extraction, which is then decomposed into smooth modes. The application of the Salp Swarm Algorithm (SSA) aims to optimize VMD parameters to enhance the precision of feature extraction. A thorough data analysis is performed to identify the essential input features. Residual pre-processing between input variables and their decomposed modes further enhances model performance. The stacking algorithm (SA) is used to predict both modes and residuals of the input data. Performance evaluation using metrics such as root mean square error (RMSE), normalized root mean square error (NRMSE), mean absolute error (MAE), and normalized mean absolute error (NMAE) indicates a reduction in error rates across measurement scales. For example, under adverse weather conditions, the NRMSE and NMAE for PV power are 2.50% and 1.95%, respectively.

Seasonal short-term photovoltaic power prediction based on GSK–BiGRU–XGboost considering correlation of meteorological factors

Seasonal short-term photovoltaic power prediction based on GSK–BiGRU–XGboost considering correlation of meteorological factors

A Convolutional Neural Network–Long Short-Term Memory–Attention Solar Photovoltaic Power Prediction–Correction Model Based on the Division of Twenty-Four Solar Terms

The prevalence of extreme weather events gives rise to a significant degree of prediction bias in the forecasting of photovoltaic (PV) power. In order to enhance the precision of forecasting outcomes, this study examines the interrelationships between China’s 24 conventional solar terms and extreme meteorological events. Additionally, it proposes a methodology for estimating the short-term generation of PV power based on the division of solar term time series. Firstly, given that the meteorological data from the same festival is more representative of the climate state at the current prediction moment, the sample data are grouped according to the 24 festival time nodes. Secondly, a convolutional neural network–long short-term memory (CNN-LSTM) PV power prediction model based on an Attention mechanism is proposed. This model extracts temporal change information from nonlinear sample data through LSTM, and a CNN link is added at the front end of LSTM to address the issue of LSTM being unable to obtain the spatial linkage of multiple features. Additionally, an Attention mechanism is incorporated at the back end of the CNN to obtain the feature information of crucial time steps, further reducing the multi-step prediction error. Concurrently, a PV power error prediction model is constructed to rectify the outcomes of the aforementioned prediction model. The examination of the measured data from PV power stations and the comparison and analysis with other prediction models demonstrate that the model presented in this paper can effectively enhance the accuracy of PV power predictions.

Short-term interval prediction strategy of photovoltaic power based on meteorological reconstruction with spatiotemporal correlation and multi-factor interval constraints

Short-term photovoltaic (PV) power interval prediction provides a basis for day-ahead power dispatching and generation planning. However, the current gridded numerical weather prediction (NWP) has poor matching in specific PV stations, and the lack of consideration of PV power mutation characteristics and historical correlation in interval prediction, which further limit the improvement of PV power prediction accuracy. In this regard, this paper proposes a novel short-term interval prediction strategy for PV power. Based on the second-order extended hidden Markov model (HMM), the key meteorological elements of the PV station with poor matching are reconstructed. In the interval prediction, the trend mutation and historical correlation characteristics of the PV sequence are fully considered, and a PV power interval prediction method that combines three factors such as trend change, time correlation and numerical mutation is proposed. The proposed method is applied to a PV station in Jilin, China. The results show that compared with other methods, the RMSE of the proposed method is reduced by 5.3 % on average, and the CWC is reduced by at least 2.1 %, which verifies the effectiveness of the proposed method.

A novel digital-twin approach based on transformer for photovoltaic power prediction

The prediction of photovoltaic (PV) system performance has been intensively studied as it plays an important role in the context of sustainability and renewable energy generation. In this paper, a digital twin (DT) model based on a domain-matched transformer is proposed using convolutional neural network (CNN) for domain-invariant feature extraction, transformer for PV performance prediction, and domain adaptation neural network (DANN) for domain adaptation. The effectiveness of the proposed framework is validated using a PV power prediction dataset. The results indicate an accuracy improvement of up to 39.99% in model performance. Additionally, experiments with varying numbers of timestamps demonstrate enhanced PV power prediction performance as parameters are continuously updated within the DT framework, offering a reliable solution for real-time and adaptive PV power forecasting.

Research on stacking ensemble method for day-ahead ultra-short-term prediction of photovoltaic power

Research on stacking ensemble method for day-ahead ultra-short-term prediction of photovoltaic power

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.

An error-corrected deep Autoformer model via Bayesian optimization algorithm and secondary decomposition for photovoltaic power prediction

Accurate PV power prediction is crucial for stable grid operation and rational dispatch. However, due to the instability of PV power generation, PV power prediction still has great challenges. Therefore, an Autoformer model based on secondary decomposition, Bayesian optimization and error correction for PV power prediction. In order to reduce the complexity of the data and fully extract the features, two decomposition methods are employed. First, empirical mode decomposition (EMD) is applied to decompose the PV power series at the first level. Then, the sample entropy (SE) is introduced to measure the complexity of each component, and the variational mode decomposition (VMD) is employed to implement secondary decomposition of the component with the highest complexity. Secondly, a Bayesian optimization algorithm enhanced Autoformer model is developed for predicting each component, and the predicted component results are aggregated to obtain preliminary PV power prediction results. Finally, the preliminary prediction results are error corrected using a least squares support vector machine. A four-month PV dataset from a PV power plant in Hangzhou, China is utilized to validate the effectiveness of the proposed model. The experimental results show that the model after primary decomposition is superior to the single model, and the prediction accuracy is substantially improved after secondary decomposition. The proposed model has the best prediction performance in predicting the PV power for different seasons, which shows good robustness.

PSO–LSTM–Markov Coupled Photovoltaic Power Prediction Based on Sunny, Cloudy and Rainy Weather

PSO–LSTM–Markov Coupled Photovoltaic Power Prediction Based on Sunny, Cloudy and Rainy Weather

An integrated binary metaheuristic approach in dynamic unit commitment and economic emission dispatch for hybrid energy systems

The current generation portfolio is obligated to incorporate zero-emissions energy sources, predominantly wind and solar, due to the depletion of fossil fuels and the alarming rate of global warming. In the current scenario, power engineers must devise a compromised solution that not only advocates for the adoption of renewable energy sources (RES) but also efficiently schedules all conventional power generation units to balance the increasing load demand while simultaneously minimizing fuel costs and harmful emissions that are currently addressed by Unit Commitment (UC) and Combined Economic Emission Dispatch (CEED) problem solutions. However, the integration of renewable energy resources (RES) further complicates the UC-CEED problem due to their intermittent nature. Recently, metaheuristic algorithms are acquiring momentum in resolving constrained UC-CEED problems due to their improved global solution ability, adaptability, and derivative-free construction. In this research, a computationally efficient binary hybrid version of crow search algorithm and improvised grey wolf optimization is proposed, namely Crow Search Improved Binary Grey Wolf Optimization Algorithm (CS-BIGWO) by inclusion of nonlinear control parameter, weight-based position updating, and mutation approach. Statistical results on standard mathematical functions prove the supremacy of the proposed algorithm over conventional algorithms. Further, a novel optimization strategy is devised by integrating enhanced lambda iteration with the CS-BIGWO algorithm (CS-BIGWO-λ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\lambda$$\\end{document}) to solve a day-ahead UC-CEED problem of the hybrid energy system incorporating cost functions of RES. For the model, a day-ahead forecast of wind power and solar photovoltaic power is obtained by using the Levy-Flight Chaotic Whale Optimization Algorithm optimized Extreme Learning Machines(LCWOA-ELM). The proposed algorithm is tested for the UC-CEED solution of an IEEE-39 bus system with two distinct cases: (1) without RES integration and (2) with RES integration. Several independent trial runs are executed, and the performance of the algorithms is assessed based on optimal UC schedules, fuel cost, emission quantization, convergence curve, and computational time. For case 1, the proposed algorithm resulted in a percentage reduction of 0.1021% in fuel cost and 0.7995% in emission. In contrast, for test case 2, it resulted in a percentage reduction of 0.12896% in fuel cost and 0.772% in emission with the proposed algorithm. The results validate the dominance of the proposed methodology over existing methods in terms of lower fuel costs and emissions.

Distributed photovoltaic power forecasting based on personalized federated adversarial learning

Existing distributed photovoltaic (PV) power forecasting methods fail to address the impact of sample scarcity and heterogeneity in PV power data. Moreover, training a single prediction model proves challenging to meet the personalized forecasting needs of different PV stations in distributed environments. This paper proposes a personalized federated generative adversarial network (PFedGAN)-based DPV power forecasting method. Leveraging the federated learning (FL) framework, it achieves collaborative training of prediction models among DPV stations while preserving data privacy. y introducing generative adversarial networks (GAN) and personalized strategy optimization into the FL training process, it alleviates data scarcity issues and reduces the impact of data heterogeneity. A TimesNet-DeepAR (TNE-DeepAR) power prediction model is designed, where the TimesNet module extracts correlations between PV power data from different time periods, and the DeepAR module facilitates PV power prediction, mitigating the effects of meteorological factors' multi-periodic variations on PV power. Experimental results show that the proposed hybrid prediction model reduces the average mean absolute percentage error (MAPE) by 30–40 % compared to single models. The proposed approach reduces the MAPE by 9.79 % compared to traditional methods and by 49.62 % for PV stations with scarce data.

Solar and Wind Energy Feasibility for a Water Treatment and Recirculation System Intended for Carniculture: Comparative Study Between the Cities Of Monteiro and Sousa – Paraíba – Brazil

Objective: This article presents a comparative study of renewable solar and wind energy production capacity between Monteiro and Sousa cities, located in the semi-arid region of Paraíba state, Brazil, to analyze the feasibility of using solar panels and/or wind turbines for energy supply in a water recirculation and treatment model applied to carciniculture. Method: A hypothetical-deductive method was employed and a bibliographic character was adopted in the research, taking as basis technical-scientific work information. Additionally, the research also presents quantitative theory, since it makes use of quantifiable results presented from measurable data that need to be properly expressed. A composite system was proposed, initially consisting of six identical units exposed in Figure 1, disposed under a roof, over which photovoltaic plates are placed for the supply of electrical energy to the hydraulic pumps contained in the system. The modeling study was based on wind speed and solar irradiance data in the cities of Monteiro and Sousa, with coordinates latitude -37.1214299 and longitude -7.8983769, and latitude -38.2285597 and longitude -6.7671611. These information were extracted from the Terraclimate database, using scripts written in Java and Python languages for extraction and processing. To predict wind power energy, the average wind speed in meters per second was used for each month, from January 1st, 2010 to December 31st, 2020. For modeling of photovoltaic power prediction, the average short-wave irradiance (W/m²) per month was considered, during the same period. To establish the monthly mean temperature, the average temperatures in Celsius were considered for the period from January 1st, 2010 to December 31st, 2020. For verification of the sufficiency of wind and photovoltaic systems for energy production maintenance, the energy demand of the System of Carciniculture was compared with the energy production by each of the sources considered, and based on the analysis made, it was defined which is the best energy production systemto be used and the best city where the defined system will be installed. Results and conclusions: The results show that the use of solar energy is economical, reduces social impacts generating employment and elevates environmental awareness, and has low environmental impact. The study found that solar energy generation capacity is sufficient and most suitable to keep the shrimp farming system running throughout the year, with observed variations between 226.8 kWh/month and 299.7 kWh/month in Souza city, and between 232.2 kWh/month and 369.0 kWh/month in Monteiro city, quantities more than enough for energy supply of the shrimp culture system, which presents a demand of 207.4 kWh/month. Implications of the research: The study points out that renewable energy can be an alternative more economical than other methods of energy generation, which could be a positive response to environmental and economic problems affecting the northeastern region, especially along the São Francisco River transposition, where Monteiro and Souza cities are among the last to receive it. Originality/Value: The use of solar energy is a viable solution for providing energy to shrimp culture. Additionally, the study also points out that this method may be more economical than other methods of energy generation.

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

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.

Medium- and Long-Term Distributed Photovoltaic Power Prediction Based on Multiple Time Series Feature and Multiple-Model Fusion

Distributed photovoltaic power stations have advantages such as local direct power supply and reduced transmission energy consumption, and whose demands are constantly being developed. Conducting research on medium- and long-term distributed photovoltaic prediction will have significant value for applications such as the electricity trade market, power grid operation, and the planning of new power stations. Due to characteristics such as long time dependence, disperse power stations, and strong randomness, making accurate and stable predictions becomes very difficult. In this research, we propose a multiple time series feature and multiple-model fusion-based ensemble learning model for medium- and long-term distributed photovoltaic power prediction (M2E-DPV). Considering the wave influence and the differences in distributions in different areas of photovoltaic power, multiple feature combinations are designed to increase feature expression ability and adaptability. Based on the boost ensemble learning model, trained on a single model of different time scale features, the optimal scoring strategy is used for multiple model fusion in the rolling prediction process, and finally, time-segmented probabilistic correction is performed. The experiment results show the effectiveness of the M2E-DPV under multiple feature combinations and multi-model fusion strategies. The average MAPE, R2, and ACC indicators are 0.15, 0.96, and 0.91, respectively. Compared with other methods, there is a significant improvement, indicating that the prediction ability of the model framework proposed in this paper is advanced and robust.

Enhancing Photovoltaic Power Predictions with Deep Physical Chain Model

Predicting solar power generation is a complex challenge with multiple issues, such as data quality and choice of methods, which are crucial to effectively integrate solar power into power grids and manage photovoltaic plants. This study creates a hybrid methodology to improve the accuracy of short-term power prediction forecasts using a model called Transformer Bi-LSTM (Bidirectional Long Short-Term Memory). This model, which combines elements from the transformer architecture and bidirectional LSTM (Long–Short-Term Memory), is evaluated using two strategies: the first strategy makes a direct prediction using meteorological data, while the second employs a chain of deep learning models based on transfer learning, thus simulating the traditional physical chain model. The proposed approach improves performance and allows you to incorporate physical models to refine forecasts. The results outperform existing methods on metrics such as mean absolute error, specifically by around 24%, which could positively impact power grid operation and solar adoption.

Sky images based photovoltaic power forecasting: A novel approach with optimized VMD and Vision Mamba

As the global demand for sustainable energy sources continues to grow, accurate prediction of photovoltaic power generation is crucial for optimizing the utilization of solar resources and enhancing the efficiency of photovoltaic systems. To improve the accuracy of photovoltaic power forecasting, this paper proposes a novel hybrid predictive model that integrates Optimized Variational Mode Decomposition (VMD), Vision Mamba (Vim) for extracting features from sky images, and advanced mechanisms like Patch Embedding and Variate-wise Cross-Attention. Initially, the proposed model employs SAO-optimized VMD to decompose the photovoltaic power series into high, medium, and low-frequency components. Subsequently, these components are patched to serve as input for the subsequent layers. In the third step, exogenous variables, including meteorological and image data, are introduced and processed through Variate Embedding combined with cross-attention mechanisms to capture the intricate interactions between these variables. Finally, by integrating the outputs from all processing steps through normalization and feed-forward layers, the final predictive results are produced. Experimental evaluations across different seasons demonstrate significant enhancements in forecasting accuracy, with the model achieving Root Mean Square Error (RMSE) values of 0.3587 in spring, 0.4376 in summer, 0.3544 in autumn, and 0.3493 in winter. Similarly, Mean Absolute Error (MAE) and Mean Squared Error (MSE) across these seasons underscore the model's effectiveness. This model offers new technical means for photovoltaic power forecasting and provides valuable decision support for the optimization and management of photovoltaic power systems.

Reliable Prediction of Solar Photovoltaic Power and Module Efficiency using Bayesian Surrogate Assisted Explainable Data-Driven Model

This study proposes a Bayesian surrogate-driven explainable deep neural network model to predict and interpret the module efficiency and maximum output power of three commercially available photovoltaic modules: monocrystalline silicon, polycrystalline silicon, and amorphous silicon during the winter season. In addition, the influence of the photovoltaic material and ambient conditions on the predicted power and module efficiency is investigated. The model inputs include solar irradiance, module material (monocrystalline, polycrystalline, and amorphous silicon), season of the year (months), and time of day (morning to evening). Experiments were conducted on these three modules during the winter using data from Rawalpindi, Pakistan. These data were then fed into the deep neural network model to train and yield predictions. Several preprocessing techniques such as logarithmic transformation, square root, cube root, reciprocal, and exponential transformations are employed to improve the linearity of distributed data. For hyper-parameters optimization, Gaussian process, gradient boost regression trees, and random forest are used. The results show that the optimal deep neural network using random forest surrogate model along with square root and exponential transformation is able to predict the maximum power output and module efficiency of the considered photovoltaic modules for the entire investigated period with a correlation coefficient, R2 = 0.998. The least accurate model (R2=0.991) is a Gaussian process using simple data distribution. These results hold valuable insights for predicting and optimizing the performance of other solar photovoltaic modules in various climates and different seasons of the year.

A novel hybrid model based on evolving multi-quantile long and short-term memory neural network for ultra-short-term probabilistic forecasting of photovoltaic power

Probabilistic forecasting is extremely crucial in eliminating uncertainty in photovoltaic (PV) power generation. Quantile regression long and short-term memory neural network (QRLSTM) is widely recognized as promising methods for PV power probabilistic forecasting due to their strong generalization ability. However, these models train the model for each quantile individually, which lacks consideration of the correlation and monotonicity between quantiles, and multiple training leads to excessive computational complexity. Furthermore, the non-differentiable pinball loss function generated by QR places significant demands on the optimization algorithms. To address these issues, this paper proposes an evolutive distributed chaotic particle swarm optimization (EDCPSO)-optimized multi-quantile LSTM (MQLSTM) to achieve high-quality probabilistic PV power prediction. MQLSTM is a multi-output network structure that simultaneously outputs all quantile estimates and adopts a loss function with all quantile scores and non-crossing constraints to guide the training of the model. This approach not only improves the quality and reasonableness of quantile estimations, but also reduces computational difficulty. Then, from the perspective of evolutionary computation, considering the weight parameters of each connection layer in MQLSTM as decision variables, we convert the probabilistic forecasting into an optimization problem and propose a EDCPSO to solve the training difficulty. It implements a targeted distributed chaos strategy based on the evolutionary state to improve convergence speed and search capability. The proposed model is tested to be superior in real cases.

Predictive control technique for solar photovoltaic power forecasting

An accurate estimation of photovoltaic (PV) power production is crucial for organising and regulating solar PV power plants. The suitable prediction is often affected by the variable nature of solar resources, system location and some internal/external disturbances, such as system effectiveness, climatic factors, etc. This paper develops a novel strategy for applying a predictive control technique to PV power forecasting applications in a smart grid environment. The strategy develops the model predictive control (MPC) under demand response (DR) and some data-driven methods. It has been found that it is challenging to model an MPC for solar power forecasting regardless of its robustness and ability to handle constraints and disturbance. Thus, an optimal quadratic performance index-based MPC scheme is formulated to model a forecasting method for a PV power prediction. This strategy is then compared with some machine learning approaches. The developed strategies solve the problem of accurately estimating the direct current (DC) power yielded from the PV plant in a real-world implementation. The study also considers external disturbances to evaluate the significance of the developed methods for a suitable forecast. Therefore, this study optimally demonstrates that an accurate solar PV DC power prediction can relatively be estimated with an appropriate strategy, such as MPC and MLs, considering the system disturbances. This study also offers promising results for intelligent and real-time energy resource estimation that assist in developing the solar power sector.

Enhancing photovoltaic power prediction using a CNN-LSTM-attention hybrid model with Bayesian hyperparameter optimization

Improving the accuracy of solar power forecasting is crucial to ensure grid stability, optimize solar power plant operations, and enhance grid dispatch efficiency. Although hybrid neural network models can effectively address the complexities of environmental data and power prediction uncertainties, challenges such as labor-intensive parameter adjustments and complex optimization processes persist. Thus, this study proposed a novel approach for solar power prediction using a hybrid model (CNN-LSTM-attention) that combines a convolutional neural network (CNN), long short- term memory (LSTM), and attention mechanisms. The model incorporates Bayesian optimization to refine the parameters and enhance the prediction accuracy. To prepare high-quality training data, the solar power data were first preprocessed, including feature selection, data cleaning, imputation, and smoothing. The processed data were then used to train a hybrid model based on the CNN-LSTM-attention architecture, followed by hyperparameter optimization employing Bayesian methods. The experimental results indicated that within acceptable model training times, the CNN-LSTM-attention model outperformed the LSTM, GRU, CNN-LSTM, CNN-LSTM with autoencoders, and parallel CNN-LSTM attention models. Furthermore, following Bayesian optimization, the optimized model demonstrated significantly reduced prediction errors during periods of data volatility compared to the original model, as evidenced by MRE evaluations. This highlights the clear advantage of the optimized model in forecasting fluctuating data.