Search

Accurate photovoltaic (PV) energy forecasting plays a crucial role in the efficient operation of PV power stations. This study presents a novel hybrid machine-learning (ML) model that combines Gaussian process regression with wavelet packet decomposition to forecast PV power half an hour ahead. The proposed technique was applied to the PV energy database of a station located in Algeria and its performance was compared to that of traditional forecasting models. Performance evaluations demonstrate the superiority of the proposed approach over conventional ML methods, including Gaussian process regression, extreme learning machines, artificial neural networks and support vector machines, across all seasons. The proposed model exhibits lower normalized root mean square error (nRMSE) (2.116%) and root mean square error (RMSE) (208.233 kW) values, along with a higher coefficient of determination (R 2) of 99.881%. Furthermore, the exceptional performance of the model is maintained even when tested with various prediction horizons. However, as the forecast horizon extends from 1.5 to 5.5 hours, the prediction accuracy decreases, evident by the increase in the RMSE (710.839 kW) and nRMSE (7.276%), and a decrease in R 2 (98.462%). Comparative analysis with recent studies reveals that our approach consistently delivers competitive or superior results. This study provides empirical evidence supporting the effectiveness of the proposed hybrid ML model, suggesting its potential as a reliable tool for enhancing PV power forecasting accuracy, thereby contributing to more efficient grid management. [ABSTRACT FROM AUTHOR]

Accurate measurements of solar radiation are required to ensure that power and energy systems continue to function effectively and securely. On the other hand, estimating it is extremely challenging due to the non-stationary behaviour and randomness of its components. In this research, a novel hybrid forecasting model, namely complete ensemble empirical mode decomposition with adaptive noise–Gaussian process regression (CEEMDAN–GPR), has been developed for daily global solar radiation prediction. The non-stationary global solar radiation series is transformed by CEEMDAN into regular subsets. After that, the GPR model uses these subsets as inputs to perform its prediction. According to the results of this research, the performance of the developed hybrid model is superior to two widely used hybrid models for solar radiation forecasting, namely wavelet–GPR and wavelet packet–GPR, in terms of mean square error, root mean square error, coefficient of determination and relative root mean square error values, which reached 3.23 MJ/m2/day, 1.80 MJ/m2/day, 95.56%, and 8.80%, respectively (for one-step forward forecasting). The proposed hybrid model can be used to ensure the safe and reliable operation of the electricity system. [ABSTRACT FROM AUTHOR]

Integrating photovoltaic power into the power system can offer significant economic and environmental benefits. However, the intermittent and random nature of photovoltaic power generation poses a challenge to the current power system's planning and operation. Accurate photovoltaic power generation forecasting is crucial for delivering high-quality electric energy to consumers and increasing system reliability.In this study, a multi-stage approach is proposed. In the first stage, three decomposition techniques (Iterative Filtering decomposition, Variational Mode Decomposition, and Wavelet Packet Decomposition) are employed for time series decomposition. Then, for each Intrinsic Mode Function (IMF) component resulting from the decomposition block, five machine learning and three deep learning algorithms are utilized, serving as local forecasting models. In the final forecast phase, the best forecasting result for each regressor is selected during the reconstruction phase. Two years of photovoltaic power data recorded in three grid-connected photovoltaic systems installed in South Algeria were utilized for training and testing the proposed forecasting models. Upon comprehensive analysis and examination of the outcomes, the proposed method exhibits the lowest normalized Root Mean Square Error values across all forecast horizons and monitoring stations. Particularly, for forecasting steps at time intervals +1, +3, and +5, the proposed method attains an average normalized Root Mean Square Error, showcasing its efficacy: 0.709%, 2.097%, and 3.241% for station 1; 1.147%, 3.546%, and 5.347% for station 2; and 0.922%, 2.158%, and 4.539% for station 3. The experimental results underscore the superiority of our approach over conventional regression algorithms, thus substantiating its prowess in delivering robust and competitive performance outcomes. [ABSTRACT FROM AUTHOR]

Accurate and effective forecasting of short-term global solar radiation is critical for the development of photovoltaic systems, particularly for integration into existing grid systems. However, its non-stationary characteristics caused by climatic factors make its estimation extremely challenging. In this regard, a newly designed learning technique for multi-hour global solar radiation forecasting is proposed based on a time-varying filter-empirical mode decomposition (TVF-EMD), feature selection, and extreme learning machine (ELM) as an essence regression. The proposed hybridization strategy consists of three main steps for understanding the fundamental behavioral aspects of hourly global solar radiation data. The first phase employs the TVF-EMD algorithm to deal with the variability of global solar radiation data by separating it into a series of more stable and constant subseries. Then, the feature selection step is employed to evaluate and identify distinctive features set from the whole decomposed subseries by means of the RReliefF algorithm. The selected feature sets are used to train and optimize our forecasting extreme learning machine model, then the tuned ELM model is used to assess the forecasting accuracy. The proposed TVF-EMD-RF-ELM model is evaluated and validated in different regions in Algeria with various climate conditions. The forecasting findings of the TVF-EMD algorithm demonstrate high accuracy compared to the recent version of empirical mode decomposition CEEMDAN. Overall forecasting periods, the TVF-EMD-RF-ELM model produces an error less than 8.3% in terms of normalized root mean square error nRMSE in all studied regions. • A detailed review of different decomposition techniques for global solar radiation forecasting. • An improved artificial intelligence model for multi-hour solar radiation forecasting has been developed. • A regional examination is established, with three sites. • The proposed hybrid model is validated against several models. • The suggested model has been validated for its ability to forecast hourly global solar radiation. [ABSTRACT FROM AUTHOR]