In this paper, ensemble-based machine learning models with gradient boosting machine and random forest are proposed for predicting the power production from six different solar PV systems. The models are based on three year’s performance of a 1.2 MW grid-integrated solar photo-voltaic (PV) power plant. After cleaning the data for errors and outliers, the model features were chosen on the basis of principal component analysis. Accuracies of the developed models were tested and compared with the performance of models based on other supervised learning algorithms, such as k-nearest neighbour and support vector machines. Though the accuracies of the models varied with the type of PV systems, in general, the machine learned models developed under the study could perform well in predicting the power output from different solar PV technologies under varying working environments. For example, the average root mean square error of the models based on the gradient boosting machines, random forest, k-nearest neighbour, and support vector machines are 17.59 kW, 17.14 kW, 18.74 kW, and 16.91 kW, respectively. Corresponding averages of mean absolute errors are 8.28 kW, 7.88 kW, 14.45 kW, and 6.89 kW. Comparing the different modelling methods, the decision-tree-based ensembled algorithms and support vector machine models outperformed the approach based on the k-nearest neighbour method. With these high accuracies and lower computational costs compared with the deep learning approaches, the proposed ensembled models could be good options for PV performance predictions used in real and near-real-time applications.

Power developed by the wind turbines, at different wind velocities, is a key information required for the successful design and efficient management of wind energy projects. Conventionally, for these applications, manufacturer’s power curves are used in estimating the velocity–power characteristics of the turbines. However, performance of the turbines under actual field environments may significantly differ from the manufacturer’s power curves, which are derived under ‘standard’ conditions. In case of existing wind projects with sufficient performance data, the velocity–power variations can better be defined using artificially intelligent models. In this paper, we compare the performance of four such models by applying them to a 2-MW onshore wind turbine. Models based on ANN, KNN, SVM and MARS were developed and tested using the SCADA data collected from the turbine. All the AI models performed significantly better than the manufacturer’s power curve. Among the AI methods, SVM-based predictions showed the highest accuracy. A site-specific performance curve for the turbine, based on the SVM model, is presented. Wider adaptability of this approach has been demonstrated by successfully implementing the model for a 3.6-MW wind turbine, working under offshore environment. Being “site-specific data” driven, the proposed models are more accurate and hence better choice for applications like short-term wind power forecasting and pro-diagnostics of wind turbines.

In this paper, a two-input, single-output (TISO) DC-DC converter for electric vehicle charging applications with solar photovoltaic (PV) as one of the sources is discussed. A novel, simple, and effective control strategy with maximum power point tracking (MPPT) to maximize power from PV while maintaining a constant bus voltage is proposed. A 100 V, 100 W TISO DC-DC converter is designed and comprehensive simulations are conducted under different conditions. The system characteristics are validated by comparing the results with a conventional P&O algorithm and multiple step size P&O algorithm. The proposed control strategy can precisely generate control signals to track MPPT while maintaining the bus voltage by controlling the output of a fixed DC source according to the changes in PV generation. The overall efficiency of the proposed approach is 98.67%, and the average output voltage is 99.09 V under selected conditions. The overall average output voltage ripple is 0.22% with the proposed approach, while it is 2.91% and 1.55% with the conventional P&O and multiple step size P&O MPPT techniques, respectively. Further, a 500 V, 17 kW high-power converter is designed and a simulation is carried out. The high-power converter provides an average output voltage of 496.92 V with an overall efficiency of 98.72%, and the average output voltage ripple is 0.16%. The results obtained from the simulation under the selected conditions lead to the conclusion that the converter has better efficiency and less variation in the output voltage at higher power levels with the proposed control technique.

Microgrids are energy systems that can operate independently or in conjunction with the main electricity grid. Their purpose is to link different energy sources, enhance customer participation in energy markets, and improve energy system efficiency and flexibility. However, regulatory, technical, and financial obstacles hinder their deployment. To comprehend the current state of the field, this study utilized citation network analysis (CNA) methodology to examine over 1500 scholarly publications on microgrid research and development (R&D). The study employed modularity-based clustering analysis, which identified seven distinct research clusters, each related to a specific area of study. Cluster 1, focused on control strategies for microgrids, had the highest proportion of publications (23%) and the maximum citation link count (151), while Cluster 4, which examined microgrid stability, had the lowest proportion of papers (10%). On average, each publication within each cluster had four citation links. The citation network of microgrid research was partitioned using cluster analysis, which aided in identifying the main evolutionary paths of each subfield. This allowed for the precise tracing of their evolution, ultimately pinpointing emerging fronts and challenges. The identification of key pathways led to the discovery of significant studies and emerging patterns, highlighting research priorities in the field of microgrids. The study also revealed several research gaps and concerns, such as the need for further investigation into technical and economic feasibility, legislation, and standardization of microgrid technology. Overall, this study provides a comprehensive understanding of the evolution of microgrid research and identifies potential directions for future research.