A Green Energy Application in Energy Management Systems by an Artificial Intelligence-Based Solar Radiation Forecasting Model

A comprehensive analysis of the emerging modern trends in research on photovoltaic systems and desalination in the era of artificial intelligence and machine learning

Integration of photovoltaic (PV) systems, desalination technologies, and Artificial Intelligence (AI) combined with Machine Learning (ML) has introduced a new era of remarkable research and innovation. This review article thoroughly examines the recent advancements in the field, focusing on the interplay between PV systems and water desalination within the framework of AI and ML applications, along with it analyses current research to identify significant patterns, obstacles, and prospects in this interdisciplinary field. Furthermore, review examines the incorporation of AI and ML methods in improving the performance of PV systems. This includes raising their efficiency, implementing predictive maintenance strategies, and enabling real-time monitoring. It also explores the transformative influence of intelligent algorithms on desalination techniques, specifically addressing concerns pertaining to energy usage, scalability, and environmental sustainability. This article provides a thorough analysis of the current literature, identifying areas where research is lacking and suggesting potential future avenues for investigation. These advancements have resulted in increased efficiency, decreased expenses, and improved sustainability of PV system. By utilizing artificial intelligence technologies, freshwater productivity can increase by 10 % and efficiency. This review offers significant and informative perspectives for researchers, engineers, and policymakers involved in renewable energy and water technology. It sheds light on the latest advancements in photovoltaic systems and desalination, which are facilitated by AI and ML. The review aims to guide towards a more sustainable and technologically advanced future.

Modeling and estimation of the optimal tilt angle, maximum incident solar radiation, and global radiation index of the photovoltaic system

This research was designed to apply measured and theoretically derived models to estimate the optimal tilt angle (β), maximum incident solar radiation (H_T), and global radiation index (GRI) in Lagos and 37 metropolitan cities in Nigeria. Six modules were mounted at different tilt angles with two modules north-facing, three south-facing, and one positioned horizontally to determine the orientation and tilt angle performance. Overall, the 16.8° module 4 south-facing tilted emerged as the best performing module for H_T, with maximum output power, and much more than 6.174 annual earned energy reported on module 6 mounted horizontally. The GRI obtained from the six solar modules revealed a significant coefficient of 1.0269 for module 1 north-facing, 0.9923 for module 2 north-facing, 1.0217 for module 3 south-facing, 0.9609 for module 4 south-facing, and 1.0232 for module 5 south-facing for the values obtained from the horizontally positioned module 6. In-depth statistical analysis of the effectiveness of values observed against the predicted values to estimate the optimal and maximum inclination angle of incident solar radiation using error metrics and GPI revealed that model 5, model 12, model 14, model 17, and model 14 outperform the other estimation models in their respective categories. A similar statistical analysis of model 14 with the best performance was performed to estimate the best inclination angle in 37 metropolitan cities in Nigeria compared to two models consolidated in the literature; model 14 performed admirably in terms of accuracy compared to the two models obtained from the literature.

A Comparative Study of Time Series Forecasting of Solar Energy Based on Irradiance Classification

Sustainable energy systems rely on energy yield from renewable resources such as solar radiation and wind, which are typically not on-demand and need to be stored or immediately consumed. Solar irradiance is a highly stochastic phenomenon depending on fluctuating atmospheric conditions, in particular clouds and aerosols. The complexity of weather conditions in terms of many variable parameters and their inherent unpredictability limit the performance and accuracy of solar power forecasting models. As renewable power penetration in electricity grids increases due to the rapid increase in the installation of photovoltaics (PV) systems, the resulting challenges are amplified. A regional PV power prediction system is presented and evaluated by providing forecasts up to 72 h ahead with an hourly time resolution. The proposed approach is based on a local radiation forecast model developed by Blue Sky. In this paper, we propose a novel method of deriving forecast equations by using an irradiance classification approach to cluster the dataset. A separate equation is derived using the GEKKO optimization tool, and an algorithm is assigned for each cluster. Several other linear regressions, time series and machine learning (ML) models are applied and compared. A feature selection process is used to select the most important weather parameters for solar power generation. Finally, considering the prediction errors in each cluster, a weighted average and an average ensemble model are also developed. The focus of this paper is the comparison of the capability and performance of statistical and ML methods for producing a reliable hourly day-ahead forecast of PV power by applying different skill scores. The proposed models are evaluated, results are compared for different models and the probabilistic time series forecast is presented. Results show that the irradiance classification approach reduces the forecasting error by a considerable margin, and the proposed GEKKO optimized model outperforms other machine learning and ensemble models. These findings also emphasize the potential of ML-based methods, which perform better in low-power and high-cloud conditions, as well as the need to build an ensemble or hybrid model based on different ML algorithms to achieve improved projections.

Deep learning neural network tools for proteomics

Mass-spectrometry-based proteomics enables quantitative analysis of thousands of human proteins. However, experimental and computational challenges restrict progress in the field. This review summarizes the recent flurry of machine-learning strategies using artificial deep neural networks (or "deep learning") that have started to break barriers and accelerate progress in the field of shotgun proteomics. Deep learning now accurately predicts physicochemical properties of peptides from their sequence, including tandem mass spectra and retention time. Furthermore, deep learning methods exist for nearly every aspect of the modern proteomics workflow, enabling improved feature selection, peptide identification, and protein inference.

Future research tendencies for solar energy management using a bibliometric analysis, 2000-2019

Using the Scopus database between the years of 2000 and 2019, a bibliometric study was done to analyze the scientific publications in the area of photovoltaic solar energy management. From the preliminary analysis of future research tendencies, ten possibilities of study topics were developed; and due to that it was possible to assume that even though many studies of technological development are found, some insights can still be approached in a way that the practical implementation of solar systems photovoltaic is better used. This data was validated by the analysis performed with the Scimat scientific mapping software under a longitudinal structure, verifying the future tendencies researches mentioned previously.

Control Strategy of the Pumped Storage Unit to Deal with the Fluctuation of Wind and Photovoltaic Power in Microgrid

With the development and utilization of distributed energy and microgrid, distributed energy storage has become a new development trend. However, small pumped storage units have the advantages of flexible engineering location, low investment, quick effect, low requirements on transmission lines, and a better solution to the peak load demand of the system. Therefore, it is more and more used in the microgrid, and it conducts joint dispatching with wind power, photovoltaic, and other clean energies. To solve the capacity problem of small pumped storage units within the microgrid, a new control strategy is proposed in this paper. Two pumped storage units are used for joint operations. Taking the smoothed combined output power of wind power, photovoltaic power, and pumped storage power as the target, and considering the limitations of transmission lines, the constraints of wind power and photovoltaic power fields as well as the restrictions of pumped storage power units and corresponding reservoirs are taken into account. In this paper, social particle swarm optimization (SPSO) with improved weight is used to calculate and solve the model. The effectiveness of the new control strategy is verified.

An Intelligent Lightning Warning System Based on Electromagnetic Field and Neural Network

Prediction of lightning occurrence has significant relevance for reducing potential damage to electric installations, buildings, and humans. However, the existing lightning warning system (LWS) operates using the threshold method and has low prediction accuracy. In this paper, an intelligent LWS based on an electromagnetic field and the artificial neural network was developed for improving lightning prediction accuracy. An electric field mill sensor and a pair of loop antennas were designed to detect the real-time electric field and the magnetic field induced by lightning, respectively. The change rate of electric field, temperature, and humidity acquired 2 min before lightning strikes, were used for developing the neural network using the back propagation algorithm. After observing and predicting lightning strikes over six months, it was verified that the proposed LWS had a prediction accuracy of 93.9%.