Search

Abstract Solar photovoltaic (PV) power generation is susceptible to environmental factors, and redundant features can disrupt prediction accuracy. To achieve rapid and accurate online prediction, we propose a method that combines Principal Component Analysis (PCA) with a multi-strategy improved Squirrel Search Algorithm (SSA) to optimize Support Vector Machine (MISSA-SVM) for prediction. Initially, to mitigate the impact of redundant features on prediction accuracy, KPCA is employed for feature dimensionality reduction. Subsequently, SVM is suggested as the foundational algorithm for constructing the prediction model. Furthermore, to address the influence of hyperparameter selection on model performance, SSA is introduced for optimizing SVM hyperparameters, with the aim of establishing the optimal prediction model. Moreover, to enhance solution efficiency and accuracy, a multi-strategy approach termed MISSA is proposed, which integrates Population Initialization based on the Tent map, Nonlinear Predator Presence Probability, Chaotic-based Dynamic Opposition-based Learning, and Selection Strategy, to refine SSA. Finally, through case studies, the performance of MISSA optimization is assessed using challenging CEC2021 test functions, demonstrating its high optimization performance, stability, and significance. Subsequently, the performance of the prediction model is validated using two datasets, showcasing that the proposed prediction method achieves high accuracy and robust prediction stability.

Photovoltaic (PV) technology converts solar energy into electrical energy, and the PV industry is an essential renewable energy industry. However, the amount of power generated through PV systems is closely related to unpredictable and uncontrollable environmental factors such as solar radiation, temperature, humidity, cloud cover, and wind speed. Particularly, changes in temperature and solar radiation can substantially affect power generation, causing a sudden surplus or reduction in the power output. Nevertheless, accurately predicting the energy produced by PV power generation systems is crucial. This paper proposes a hybrid model comprising a convolutional neural network (CNN) and long short-term memory (LSTM) for stable power generation forecasting. The CNN classifies weather conditions, while the LSTM learns power generation patterns based on the weather conditions. The proposed model was trained and tested using the PV power output data from a power plant in Busan, Korea. Quantitative and qualitative evaluations were performed to verify the performance of the model. The proposed model achieved a mean absolute percentage error of 4.58 on a sunny day and 7.06 on a cloudy day in the quantitative evaluation. The experimental results suggest that precise power generation forecasting is possible using the proposed model according to instantaneous changes in power generation patterns. Moreover, the proposed model can help optimize PV power plant operations. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) technology converts solar energy into electrical energy, and the PV industry is an essential renewable energy industry. However, the amount of power generated through PV systems is closely related to unpredictable and uncontrollable environmental factors such as solar radiation, temperature, humidity, cloud cover, and wind speed. Particularly, changes in temperature and solar radiation can substantially affect power generation, causing a sudden surplus or reduction in the power output. Nevertheless, accurately predicting the energy produced by PV power generation systems is crucial. This paper proposes a hybrid model comprising a convolutional neural network (CNN) and long short-term memory (LSTM) for stable power generation forecasting. The CNN classifies weather conditions, while the LSTM learns power generation patterns based on the weather conditions. The proposed model was trained and tested using the PV power output data from a power plant in Busan, Korea. Quantitative and qualitative evaluations were performed to verify the performance of the model. The proposed model achieved a mean absolute percentage error of 4.58 on a sunny day and 7.06 on a cloudy day in the quantitative evaluation. The experimental results suggest that precise power generation forecasting is possible using the proposed model according to instantaneous changes in power generation patterns. Moreover, the proposed model can help optimize PV power plant operations.

As the relative importance of renewable energy in electric power systems increases, the prediction of photovoltaic (PV) power generation has become a crucial technology, for improving stability in the operation of next-generation power systems, such as microgrid and virtual power plants (VPP). In order to improve the accuracy of PV power generation forecasting, a fair amount of research has been applied to weather forecast data (to a learning process). Despite these efforts, the problems of forecasting PV power generation remains challenging since existing methods show limited accuracy due to inappropriate cloud amount forecast data, which are strongly correlated with PV power generation. To address this problem, we propose a PV power forecasting model, including a cloud amount forecasting network trained with satellite images. In addition, our proposed model adopts convolutional self-attention to effectively capture historical features, and thus acquire helpful information from weather forecasts. To show the efficacy of the proposed cloud amount forecast network, we conduct extensive experiments on PV power generation forecasting with and without the cloud amount forecast network. The experimental results show that the Mean Absolute Percentage Error (MAPE) of our proposed prediction model, combined with the cloud amount forecast network, are reduced by 22.5% compared to the model without the cloud amount forecast network.

The problem of Photovoltaic (PV) power generation forecasting is becoming crucial as the penetration level of Distributed Energy Resources (DERs) increases in microgrids and Virtual Power Plants (VPPs). In order to improve the stability of power systems, a fair amount of research has been proposed for increasing prediction performance in practical environments through statistical, machine learning, deep learning, and hybrid approaches. Despite these efforts, the problem of forecasting PV power generation remains to be challenging in power system operations since existing methods show limited accuracy and thus are not sufficiently practical enough to be widely deployed. Many existing methods using long historical data suffer from the long-term dependency problem and are not able to produce high prediction accuracy due to their failure to fully utilize all features of long sequence inputs. To address this problem, we propose a deep learning-based PV power generation forecasting model called Convolutional Self-Attention based Long Short-Term Memory (LSTM). By using the convolutional self-attention mechanism, we can significantly improve prediction accuracy by capturing the local context of the data and generating keys and queries that fit the local context. To validate the applicability of the proposed model, we conduct extensive experiments on both PV power generation forecasting using a real world dataset and power consumption forecasting. The experimental results of power generation forecasting using the real world datasets show that the MAPEs of the proposed model are much lower, in fact by 7.7%, 6%, 3.9% compared to the Deep Neural Network (DNN), LSTM and LSTM with the canonical self-attention, respectively. As for power consumption forecasting, the proposed model exhibits 32%, 17% and 44% lower Mean Absolute Percentage Error (MAPE) than the DNN, LSTM and LSTM with the canonical self-attention, respectively.

High quality photovoltaic (PV) power prediction intervals (PIs) are essential to power system operation and planning. To improve the reliability and sharpness of PIs, in this paper, a new method is proposed, which involves the model uncertainties and noise uncertainties, and PIs are constructed with a two-step formulation. In the first step, the variance of model uncertainties is obtained by using extreme learning machine to make deterministic forecasts of PV power. In the second stage, innovative PI-based cost function is developed to optimize the parameters of ELM and noise uncertainties are quantization in terms of variance. The performance of the proposed approach is examined by using the PV power and meteorological data measured from 1kW rooftop DC micro-grid system. The validity of the proposed method is verified by comparing the experimental analysis with other benchmarking methods, and the results exhibit a superior performance. [ABSTRACT FROM AUTHOR]

As the relative importance of renewable energy in electric power systems increases, the prediction of photovoltaic (PV) power generation has become a crucial technology, for improving stability in the operation of next-generation power systems, such as microgrid and virtual power plants (VPP). In order to improve the accuracy of PV power generation forecasting, a fair amount of research has been applied to weather forecast data (to a learning process). Despite these efforts, the problems of forecasting PV power generation remains challenging since existing methods show limited accuracy due to inappropriate cloud amount forecast data, which are strongly correlated with PV power generation. To address this problem, we propose a PV power forecasting model, including a cloud amount forecasting network trained with satellite images. In addition, our proposed model adopts convolutional self-attention to effectively capture historical features, and thus acquire helpful information from weather forecasts. To show the efficacy of the proposed cloud amount forecast network, we conduct extensive experiments on PV power generation forecasting with and without the cloud amount forecast network. The experimental results show that the Mean Absolute Percentage Error (MAPE) of our proposed prediction model, combined with the cloud amount forecast network, are reduced by 22.5% compared to the model without the cloud amount forecast network. [ABSTRACT FROM AUTHOR]

The photovoltaic (PV) industry is an important part of the renewable energy industry. With the growing use of PV systems, interest in their operation and maintenance (O&M) is increasing. In this regard, analyses of power generation efficiency and inverter efficiency are very important. The first step in efficiency analysis is solar power estimation based on environment sensor data. In this study, solar power was estimated using a univariate linear regression model. The estimated solar power data were cross-validated with the actual solar power data obtained from the inverter. The results provide information on the power generation efficiency of the inverter. The linear estimation model developed in this study was validated using a single PV system. It is possible to apply the coefficients presented in this study to other PV systems, even though the nature and error rates of the collected data may vary depending on the inverter manufacturer. To apply the proposed model to PV systems with different power generation capacities, reconstructing the model according to the power generation capacity is necessary. [ABSTRACT FROM AUTHOR]

The problem of Photovoltaic (PV) power generation forecasting is becoming crucial as the penetration level of Distributed Energy Resources (DERs) increases in microgrids and Virtual Power Plants (VPPs). In order to improve the stability of power systems, a fair amount of research has been proposed for increasing prediction performance in practical environments through statistical, machine learning, deep learning, and hybrid approaches. Despite these efforts, the problem of forecasting PV power generation remains to be challenging in power system operations since existing methods show limited accuracy and thus are not sufficiently practical enough to be widely deployed. Many existing methods using long historical data suffer from the long-term dependency problem and are not able to produce high prediction accuracy due to their failure to fully utilize all features of long sequence inputs. To address this problem, we propose a deep learning-based PV power generation forecasting model called Convolutional Self-Attention based Long Short-Term Memory (LSTM). By using the convolutional self-attention mechanism, we can significantly improve prediction accuracy by capturing the local context of the data and generating keys and queries that fit the local context. To validate the applicability of the proposed model, we conduct extensive experiments on both PV power generation forecasting using a real world dataset and power consumption forecasting. The experimental results of power generation forecasting using the real world datasets show that the MAPEs of the proposed model are much lower, in fact by 7.7%, 6%, 3.9% compared to the Deep Neural Network (DNN), LSTM and LSTM with the canonical self-attention, respectively. As for power consumption forecasting, the proposed model exhibits 32%, 17% and 44% lower Mean Absolute Percentage Error (MAPE) than the DNN, LSTM and LSTM with the canonical self-attention, respectively. [ABSTRACT FROM AUTHOR]

To mitigate solar curtailment caused by large-scale development of photovoltaic (PV) power generation, accurate forecasting of PV power generation is important. A hybrid forecasting model was constructed that combines random forest (RF), improved grey ideal value approximation (IGIVA), complementary ensemble empirical mode decomposition (CEEMD), the particle swarm optimization algorithm based on dynamic inertia factor (DIFPSO), and backpropagation neural network (BPNN), called RF-CEEMD-DIFPSO-BPNN. PV power generation is affected by many factors. The RF method is used to calculate the importance degree and rank the factors, then eliminate the less important factors. Then, the importance degree calculated by RF is transferred as the weight values to the IGIVA model to screen the similar days of different weather types to improve the data quality of the training sets. Then, the original power sequence is decomposed into intrinsic mode functions (IMFs) at different frequencies and a residual component by CEEMD to weaken the fluctuation of the original sequence. We empirically analyzed a PV power plant to verify the effectiveness of the hybrid model, which proved that the RF-CEEMD-DIFPSO-BPNN is a promising approach in terms of PV power generation forecasting. • A novel hybrid photovoltaic power generation forecasting model is proposed. • The feature set is effectively selected by random forest (RF), similar days is select by improved grey ideal value approximation to enhance the quality of input data, the original power sequence is decomposed by complementary ensemble empirical mode decomposition (CEEMD). • The forecasting accuracy of BPNN is enhanced by particle swarm optimization algorithm based on dynamic inertia factor (DIFPSO) and the RF-CEEMD-DIFPSOBPNN model evidently achieves higher forecasting accuracy than other models. [ABSTRACT FROM AUTHOR]