Accurate Photovoltaic Power Prediction Research Articles

A hybrid neural network based solar PV power classification with time series data for bend, Oregon

ABSTRACT Photovoltaic (PV) power classification model has become a significant alternative to PV power point forecasting model in which classes of future PV powers are estimated. In this work, a novel PV power classification model which could be realized using feed forward neural network (FFNN) trained with a hybrid meta-heuristic approach is proposed to forecast the classes of future PV powers. The insisted classification model is implemented to classify three classes of PV power for the location Oregon city of United States of America (USA) with latitude 43.8041 0 N , longitude 120.5542 0 W , and altitude of 1124 m. The meta-heuristic approach comprising of Levy Flight (Levy)-Sine Cosine Algorithm (SCA)-Particle Swarm Optimization (PSO) is utilized for training the parameters of FFNN by minimizing the root mean square error RMSE . The results disclose that the proposed approach attained the most accurate prediction of PV power with % MAPE = 2.38 for the month of November as well as high classification accuracy with PCA = 94.96 % in the month of April. Based on the obtained results, the proposed LF-SCA-PSO trained FFNN outperformed the existing hybrid models in both prediction and classification and hence possess the potential to be a new alternative to assist engineers in predicting the PV power of solar systems at short- and long-time horizons.

Novel applications of various neural network models for prediction of photovoltaic system power under outdoor condition of mountainous region

The geography and landscape of mountainous locations are frequently varied, which causes uneven solar radiation exposure in different places which leads to photovoltaic (PV) power generation variation drastically. Therefore accurate PV power prediction is essential for industries in optimize energy production, Energy Planning and Grid Integration, Energy Storage Integration in such diverse conditions. This study aims to predict the power produced by a 2.680 kWp PV under outdoor condition in mountainous region at different time intervals of 10 seconds, 1 minute, 30 minutes, 1 hour and 1 day using different data analytics models. The results show that the radial basis neural network was the most effective model for the intervals of 10 seconds, 1 minute, 30 minutes, and 1 day. Its RMSE was 19.11 W for the 10-second interval, 22.83 W for the 1-minute interval, 25.94 W for the 30-minute interval, and 9.08 W for the 1-day interval. With an RMSE of 23.22 W, the Kernel Ridge Regressor had the best performance for the 1-hour period. This suggests that the model with only two parameters such as temperature and irradiance predict PV power more accurately. The findings can be applied to improve PV system design and performance by precisely forecasting the systems' power output in different weather scenarios.

Combined IXGBoost-KELM short-term photovoltaic power prediction model based on multidimensional similar day clustering and dual decomposition

Accurate photovoltaic power prediction is important to ensure stable and safe operation of microgrids. However, due to the high volatility of photovoltaic power data, the prediction accuracy of traditional prediction models is often unsatisfactory. To ensure stable operation of microgrids, this study proposes a combined improved extreme gradient boosting-kernel extreme learning machine short-term photovoltaic power prediction model consisting of multidimensional similar day clustering and dual decomposition. Initially, gray relation analysis, Pearson correlation coefficient, and Kmeans++ are used for clustering to obtain high-precision similar days. Subsequently, a dual signal decomposition model based on variational modal decomposition and complete ensemble empirical mode decomposition with adaptive noise is proposed. Finally, predictions are made using a combination of predictive models with complementary strengths and weaknesses, and the prediction results of each component are fitted with under three weather conditions, the average root mean square error is reduced by 78.02%,62.99%, and 62.48%, and the average mean absolute error is reduced by 82.55%, 71.13%, and 67.07% in comparison with the baseline model. The results show that the model is effective in improving the prediction accuracy in a variety of different environments.

Dual-dimension Time-GGAN data augmentation method for improving the performance of deep learning models for PV power forecasting

Solar energy has intermittency and volatility, which poses a serious challenge to the stable and safe operation of the power grid. Accurate photovoltaic power prediction is one of the key technologies to solve this problem. Due to the larger volume of data collected by photovoltaic systems, deep learning methods are more in-depth in the field of photovoltaic power prediction. However, photovoltaic power generation data also has more diversity and lower value density, which brings more severe challenges to the feature extraction ability of prediction models. Photovoltaic power prediction methods with deep data mining capabilities are urgently needed to address these issues. This paper proposes a dual-dimensional time series adversarial neural network based on gated recurrent neural network (Dd_Time_GGAN) to enhance low-value-density photovoltaic data by two dimensions (time dimension and feature dimension) and obtain high-value-density feature data. by replacing the generator and optimizer to improve the performance of network-enhanced data, the training time of the network was reduced by 26% by adjusting the iteration times of each stage of the network. Then, combining the two mainstream deep neural networks LSTM and CNN models in the current photovoltaic forecast field to achieve ultra-short-term photovoltaic power prediction. The experimental data is two-year operation data of a photovoltaic station in China. The experimental results show that compared with only using raw sample data, using enhanced data proposed by the data augmentation method combined with raw sample data as input, both types of deep learning prediction models have higher prediction accuracy. The accuracy of the LSTM prediction model improved by 3.1%, and the CNN prediction model improved by 2.3%. It proves that through data enhancement, the prediction accuracy of the photovoltaic power prediction model can be improved.

Short-term Power Prediction Method of Photovoltaic Based on Output Clustering in Smart Grid

Accurate photovoltaic power prediction can ensure the smart grid's safe and stable operation, as well as reasonable energy scheduling. Weather influences photovoltaic output, which is irregular and unstable, and photovoltaic output is similar under similar meteorological conditions. The paper proposes a solar power forecast model based on Mean-Shift clustering, support vector machine (SVM), and residual neural network (ResNet) in this regard. Firstly, the Mean-Shift algorithm is used to cluster similar days. Then, the SVM model is constructed to learn the similarity between the data of each meteorological type, and the similar day matching is performed on the forecast day. Finally, the short-term photovoltaic output prediction based on ResNet algorithm is carried out for the corresponding weather type. The suggested method's high forecast accuracy and stability are confirmed by experimental examination of a commercial photovoltaic power station.

Photovoltaic power forecasting with a long short-term memory autoencoder networks

In many developed countries, photovoltaic solar power, which is considered the most cost-effective renewable energy source, accounts for a major portion of electricity production. The photovoltaic (PV) power generation is unpredictable and imprecise due to its high variation that can be caused of meteorological elements, to reduce the negative influence of the use of PV power, accurate PV power prediction is of crucial significance for the secure and efficient operation of photovoltaic power system operation. In light of this, we propose a long short-term memory (LSTM) autoencoder (AE) for photovoltaic power forecasting. Initially, to generate encoded sequences the LSTM-encoder extracts the characteristics from the input data. Then the LSTM-decoder decoded the encoded sequences to advance them to the last dense layer for photovoltaic power prediction. Furthermore, we conducted experiments using a 23.40 kW PV power plants dataset from DKASC in Australia. The results have confirmed that the LSTM-AE model can achieve better prediction accuracy than the benchmark deep learning methods, in terms of mean absolute error (MAE), mean square error (MSE), mean bias error (MBE), root mean square error (RMSE) and coefficient of determination (R $$^2$$ ) performance measures. When the results are analyzed, the LSTM-AE model gives the best results with average RMSE, MAE, and R $$^2$$ to 0.0762 kW, 0.0389 kW, and 99.93 $$\%$$ , respectively. The experimental results confirm that proposed method with the highest R $$^2$$ values and minimum forecasting errors compared to the benchmark models can effectively improve stable performance and achieve better accurate photovoltaic power forecasting.

Very short-term probabilistic prediction of PV based on multi-period error distribution

• Empirical mode decomposition based on long short-term memory and backpropagation neural network (EEMD-LSTM-BP) is proposed. • EEMD is utilized to study the characteristic of wave behaviors in different frequency domains. • LSTM and BP are used to determine intrinsic mode functions (IMFs) and remaining components. • Based on the dataset of PV stations in Ningxia Province, the case studies verify the method's feasibility. As the penetration rate of photovoltaic (PV) in the grid increases, enormous challenges have been brought into power grid dispatcher's operation. Efficient and accurate PV power prediction is the key to solve this problem. Considering multi-period error distribution (MPED), a novel probabilistic prediction approach via ensemble empirical mode decomposition based on long short-term memory and backpropagation neural network (EEMD-LSTM-BP) is proposed. EEMD is utilized to study the characteristic of wave behaviors in different frequency domains. LSTM and BP are used to determine intrinsic mode functions (IMFs) and remaining components, respectively. Afterward, based on the prediction errors, PV power output fluctuation in different periods is analysed. The segment points are determined by Nadaraya-Watson (N-W) kernel regression. The bounds of prediction intervals (PIs) are quantified based on the error probability distribution. Based on the dataset of PV stations in Ningxia Province, the case studies verify the method's feasibility.

Photovoltaic Power Prediction Model Using Pre-train and Fine-tune Paradigm Based on LightGBM and XGBoost

Accurate photovoltaic power prediction is crucial for optimizing the performance of photovoltaic power plants and ensuring the stability of the power grid. However, existing forecasting methods are challenged when predicting the power output of multiple plants with different geographical locations and environmental conditions simultaneously, due to the complexity of the underlying factors that affect power generation. To address this issue, this paper proposes a novel LightGBM-XGBoost photovoltaic power prediction model based on a pre-training and fine-tuning paradigm. The model leverages a large dataset to pre-train and learn rich feature representations within meteorological elements, which are then fine-tuned on specific downstream tasks to improve prediction accuracy and generalization ability. Experimental verification is conducted using data from three photovoltaic generators operating in Guangdong, China. Results demonstrate that the proposed model outperforms other methods when predicting the power output of multiple plants with different conditions simultaneously, highlighting the effectiveness of the proposed approach. Overall, this work contributes to advancing the state-of-the-art in photovoltaic power prediction and has practical implications for improving the control and scheduling of photovoltaic power plants, as well as ensuring the stability and security of the power grid.

Prediction of Photovoltaic Power by the Informer Model Based on Convolutional Neural Network

Accurate prediction of photovoltaic power is of great significance to the safe operation of power grids. In order to improve the prediction accuracy, a similar day clustering convolutional neural network (CNN)–informer model was proposed to predict the photovoltaic power. Based on correlation analysis, it was determined that global horizontal radiation was the meteorological factor that had the greatest impact on photovoltaic power, and the dataset was divided into four categories according to the correlation between meteorological factors and photovoltaic power fluctuation characteristics; then, a CNN was used to extract the feature information and trends of different subsets, and the features output by CNN were fused and input into the informer model. The informer model was used to establish the temporal feature relationship between historical data, and the final photovoltaic power generation power prediction result was obtained. The experimental results show that the proposed CNN–informer prediction method has high accuracy and stability in photovoltaic power generation prediction and outperforms other deep learning methods.

Short-term photovoltaic power forecasting based on signal decomposition and machine learning optimization

Owing to the continuous increase in the proportion of solar generation accounting for the total global generation, real-time management of solar power has become indispensable. Moreover, accurate prediction of photovoltaic power is emerging as an important link to support grid operations and reflect real-life scenarios. Various studies have led to the design of several forecasting models. Nevertheless, most predictors do not focus on the effects of the factors of photovoltaic modules on the forecast results. To fill this gap, in this paper, a novel multivariable hybrid prediction system combining signal decomposition, artificial intelligence models, deep learning models, and a swarm intelligence optimization strategy is proposed. This system fully utilizes independent variable features (including the module temperature) to efficiently enhance the precision and efficiency of photovoltaic forecasting. In particular, it is proved that a Pareto-optimal solution can be obtained using the designed system. Using three datasets obtained from Safi-Morocco, the presented system is verified by comparative experiments, and its remarkable advantages in terms of forecasting are demonstrated. Specifically, using the three datasets, the symmetric mean absolute percentage errors obtained by the presented forecast system are 2.129%, 2.335%, and 3.654%, respectively, which are significantly lower than those achieved with other comparison models. Furthermore, a comprehensive and rational evaluation methodology is employed to assess the predictive capability of the developed system. The evaluation results show that the system is effective in improving the forecasting efficiency and outperforms other benchmark models.

An integrated framework of gated recurrent unit based on improved sine cosine algorithm for photovoltaic power forecasting

Accurate prediction of photovoltaic power is of great significance to the storage and utilization of solar power. In this research, a deep learning model for photovoltaic power prediction based on gated recurrent unit network (GRU), improved sine cosine algorithm (ISCA), and complete ensemble empirical mode decomposition (CEEMD) is proposed. Firstly, CEEMD is used to decompose the original photovoltaic data into several intrinsic mode function (IMF) components and one residual. Secondly, each sub-pattern after decomposition is processed by partial least-squares analysis (PLS). Third, the nonlinear strategy is used to improve SCA, and the Hill-climbing strategy is added to the local search part to improve the performance of the algorithm. Fourth, each sub-pattern is predicted by GRU, then the learning rate and the number of hidden layer neurons of GRU are optimized by the ISCA. Finally, the predicted results of each sub-model are combined to generate the final prediction results. In this study, the proposed model is applied to four photovoltaic power data sets, and different experimental comparison models are established. The experimental results show that the CEEMD-PLS-ISCA-GRU model in this study can obtain good prediction results in all data sets.

A Hybrid Improved Whale Optimization Algorithm with Support Vector Machine for Short-Term Photovoltaic Power Prediction

ABSTRACT Presently, the grid-connected scale from photovoltaic (PV) system is getting higher among renewable power generations. However, the PV output power can be affected by different meteorological conditions due to PV randomness and volatility. Accordingly, reasonable generation plans can be well arranged using accurate PV power prediction among various types of energy sources, thus reducing the effect of PV system on the grid. To resolve this problem, a PV output power prediction model, namely IMWOASVM, is proposed based on the combination of improved whale optimization algorithm (IMWOA) and support vector machine (SVM). The IMWOA is used to optimize the kernel function parameter and penalty coefficient in SVM. The optimal parameter and coefficient values can then be input to SVM for enhancing the PV prediction. The performance results verify that the coefficient of determination using the IMWOA model can reach beyond 99% in both sunny and cloudy days. Simultaneously, the mean absolute errors on sunny and cloudy days are 0.0251 and 0.0705, respectively. The root mean square errors in sunny and cloudy days are 2.17% and 1.03%, respectively. The results confirm that the proposed model effectively increases the accuracy of the PV output power prediction and is superior to existing methods.

Photovoltaic power prediction of LSTM model based on Pearson feature selection

Accurate photovoltaic power prediction is the basis for realizing high-efficiency utilization of new energy in large-scale regional power grids. In order to deal with the influence and restriction of many factors such as ambient temperature, relative temperature and solar irradiance in the prediction of photovoltaic power generation, a photovoltaic power prediction method based on Pearson coefficient is proposed in this paper. In the prediction model, Pearson coefficients were used for correlation tests to remove irrelevant features. The remaining features were modeled using a long short-term memory network for regression prediction, and the final conclusions were drawn. The results of the algorithm show that the modified long short-term memory network has improved the mean absolute error and mean squared error of the predicted values. The prediction method, which can achieve short-term prediction of PV power and can reduce the impact of noise on PV power prediction. This research provides important support for the engineering application of energy internet related technologies to guarantee the stable operation of the power grid as well as to arrange reasonable dispatch.

Kalman Filter Photovoltaic Power Prediction Model Based on Forecasting Experience

A Kalman filter photovoltaic (PV) power prediction model based on forecasting experience is proposed to solve the problem that the accuracy of the prediction method based on historical experience is reduced under anomalous situations. This study uses the hourly solar irradiance forecasting model, numerical weather prediction (NWP) data, and the photoelectric conversion model to calculate the ground irradiance and PV power generation, which are used as the forecasting experience data. The dynamic equation of the Kalman filter model is obtained by fitting the forecasting data to make the prediction model with the future situation information properties while solving the modeling difficulties caused by the transcendental equation characteristic of the photoelectric conversion model. In the iterative process of the Kalman filter algorithm, the measured power is used to correct the prediction error and significantly limit the error variability so as to realize the ultra-short-term accurate prediction of PV power and ultimately improve the management of PV energy storage power stations. The comparative analysis through DKASC data simulation verifies that the results show that the proposed model is effective and can achieve better results in predictive accuracy.

A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine

Accurate photovoltaic power prediction is important to ensure the safety, stability, and economic operation of the power system after high photovoltaic demand. However, due to the intermittent and stochastic volatility characteristics of photovoltaic power, it is difficult to build satisfactory photovoltaic power prediction models. In this study, a similar day-based ultrashort-term multi-step ahead prediction model of photovoltaic power is proposed, which combines enhanced colliding bodies optimization (ECBO), variational mode decomposition (VMD), and a deep extreme learning machine (DELM). First, a new training data selection method based on grey correlation analysis and a Pearson correlation coefficient is proposed to find days that are similar to the predicted day. Second, the variational mode decomposition, based on enhanced colliding bodies optimization, is used to decompose the original photovoltaic power data into an ensemble of components with different amplitudes and frequencies, in which a new fitness function is designed based on a weighted-permutation entropy algorithm. Finally, the deep extreme learning machine network is employed to complete the prediction of each component, and the enhanced colliding bodies optimization algorithm is utilized again to obtain the optimal neuron numbers in hidden layers of the deep extreme learning machine; the ultimate prediction results of the photovoltaic power is obtained by reconstructing the prediction value of each component. The proposed model is tested with data from a real-world photovoltaic power station located in Xinjiang, China. The experimental results show that: (a) among all the competing models, the proposed model can achieve the highest multi-step prediction accuracy; (b) a qualitative breakthrough on the prediction accuracy improvement has been made by the proposed model in the 1-step and 2-step ahead prediction; (c) only a few parameters need to be tuned manually in the whole prediction process; the proposed model has good intelligence capabilities and can be easily applied and popularized in the practical projects.

An Improved Whale Algorithm for Support Vector Machine Prediction of Photovoltaic Power Generation

Accurate prediction of photovoltaic power is conducive to the application of clean energy and sustainable development. An improved whale algorithm is proposed to optimize the Support Vector Machine model. The characteristic of the model is that it needs less training data to symmetrically adapt to the prediction conditions of different weather, and has high prediction accuracy in different weather conditions. This study aims to (1) select light intensity, ambient temperature and relative humidity, which are strictly related to photovoltaic output power as the input data; (2) apply wavelet soft threshold denoising to preprocess input data to reduce the noise contained in input data to symmetrically enhance the adaptability of the prediction model in different weather conditions; (3) improve the whale algorithm by using tent chaotic mapping, nonlinear disturbance and differential evolution algorithm; (4) apply the improved whale algorithm to optimize the Support Vector Machine model in order to improve the prediction accuracy of the prediction model. The experiment proves that the short-term prediction model of photovoltaic power based on symmetry concept achieves ideal accuracy in different weather. The systematic method for output power prediction of renewable energy is conductive to reducing the workload of predicting the output power and to promoting the application of clean energy and sustainable development.

A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network

Accurate photovoltaic power forecasting is of great help to the operation of photovoltaic power generation system. However, due to the instability, intermittence, and randomness of solar energy, accurate prediction of photovoltaic power forecasting becomes very difficult. In this paper, the convolutional neural network, long short-term memory network, and hybrid model based on convolutional neural network and long short-term memory network models were proposed, and are applied to the obtained data in DKASC, Alice Springs photovoltaic system. The mean absolute percentage error, root mean square error, and mean absolute error indicators are used to evaluate the performance of the prediction model in this paper. The results showed that when the input sequence is increased, the accuracy of the model is also improved, and the prediction effect of the hybrid model is the best, followed by that of convolutional neural network. While long short-term memory network had the worst prediction effect, the training time was the shortest. However, not the longer the input sequence is, the better the prediction will be. This may be related to the characteristics of the time series itself. The results of the deep learning model proposed in this paper on photovoltaic power prediction also indicate that deep learning is very helpful for improving the accuracy of PV power prediction.