• Energy Research
• 2025-2025close
• other engineering and technologies close
• CN close
• MA close
• CA close

Background: Machine Learning (ML) techniques have successfully replaced traditional control algorithms in recent years due to their ability to carry out complicated tasks with significant efficiency and accuracy. Objective: The main objective of the current work is to investigate and compare the performances of different ML models in modeling Maximum Power Point Tracking (MPPT) control for a wind turbine system. The main advantage of the designed MPPT based on ML is that it does not require any detailed mathematical model or prior knowledge of the system, such as turbine parameters or aerodynamic properties, unlike traditional MPPT techniques. Methods: The ML models included in this study were Support Vector Machines, Regression Trees, and Ensemble Trees. Their design was performed through a training process, and their performances were evaluated based on various metrics. During the training phase, the ML models were selected to understand the basic concept of the control strategy and extract essential hidden connections between the inputs and the output of the system. Results: The effectiveness of the control method was investigated using MATLAB/Simulink. The findings of this study revealed that ML models were effective in modeling the MPPT for the studied wind power system, which provides an interesting and sophisticated alternative to classical control methods for wind systems. Conclusion: The ML models designed allow for optimal operation of the system with a simple structure that is independent of system parameters and wind speed measurement and is adaptable for any kind of system.

Background: In recent years, the integration of renewable energy sources into the grid has increased exponentially. However, one significant challenge in integrating these renewable sources into the grid is intermittency. Objective: To address this challenge, accurate PV power forecasting techniques are crucial for operations and maintenance and day-to-day operations monitoring in solar plants. Methods: In the present work, a hybrid approach that combines Deep Learning (DL) and Numerical Weather Prediction (NWP) with electrical models for PV power forecasting is proposed Results: The outcomes of the study involve evaluating the performance of the proposed model in comparison to a Physical model and a DL model for predicting solar PV power one day ahead and two days ahead. The results indicate that the prediction accuracy of PV power decreases and the error rates increase when forecasting two days ahead, as compared to one day ahead. Conclusion: The obtained results demonstrate that DL models combined with NWP and electrical models can improve PV Power forecasting compared to a Physical model and a DL model.

In optimizing performance and extending the lifespan of lithium batteries, accurate state prediction is pivotal. Traditional regression and classification methods have achieved some success in battery state prediction. However, the efficacy of these data-driven approaches heavily relies on the availability and quality of public datasets. Additionally, generating electrochemical data predominantly through battery experiments is a lengthy and costly process, making it challenging to acquire high-quality electrochemical data. This difficulty, coupled with data incompleteness, significantly impacts prediction accuracy. Addressing these challenges, this study introduces the End of Life (EOL) and Equivalent Cycle Life (ECL) as conditions for generative AI models. By integrating an embedding layer into the CVAE model, we developed the Refined Conditional Variational Autoencoder (RCVAE). Through preprocessing data into a quasi-video format, our study achieves an integrated synthesis of electrochemical data, including voltage, current, temperature, and charging capacity, which is then processed by the RCVAE model. Coupled with customized training and inference algorithms, this model can generate specific electrochemical data for EOL and ECL under supervised conditions. This method provides users with a comprehensive electrochemical dataset, pioneering a new research domain for the artificial synthesis of lithium battery data. Furthermore, based on the detailed synthetic data, various battery state indicators can be calculated, offering new perspectives and possibilities for lithium battery performance prediction.

Machine learning's application in solar-thermal desalination is limited by data shortage and inconsistent analysis. This study develops an optimized dataset collection and analysis process for the representative solar still. By ultra-hydrophilic treatment on the condensation cover, the dataset collection process reduces the collection time by 83.3%. Over 1,000 datasets are collected, which is nearly one order of magnitude larger than up-to-date works. Then, a new interdisciplinary process flow is proposed. Some meaningful results are obtained that were not addressed by previous studies. It is found that Radom Forest might be a better choice for datasets larger than 1,000 due to both high accuracy and fast speed. Besides, the dataset range affects the quantified importance (weighted value) of factors significantly, with up to a 115% increment. Moreover, the results show that machine learning has a high accuracy on the extrapolation prediction of productivity, where the minimum mean relative prediction error is just around 4%. The results of this work not only show the necessity of the dataset characteristics' effect but also provide a standard process for studying solar-thermal desalination by machine learning, which would pave the way for interdisciplinary study.

Background: The recent development of small-scale, decentralized generation from renewable sources and the fall in the price of the equipment needed for this operation have given a new role to the distribution networks, which is to collect the energy produced by the smallest generation plants and deliver it to the end customers. However, the national Grid Codes present technical requirements in terms of FRT and particularly LVRT and HVRT which are imposed on PV plants connected to medium voltage distribution networks, to ensure the energy needed by the loads connected to the network at the time of the failure and especially sensitive ones. Methods:: In this paper, an intelligent neural network approach is applied to the DVR control circuit to enable the requirements of the sensitive load connected near the PCC, and the system is tested in the presence of a non-linear load to demonstrate its efficiency for all situations. The proposed strategy is based on the implementation of an improved ANFIS and ANN control which are compared to a tuned PI controller, the approach intends to meet the technical requirement of the recently approved Grid Code in Morocco. The simulation is performed using MATLAB Simulink. Results: The proposed approach brings great improvement to the load side voltage waveforms, and numerical experiment findings demonstrate that it can successfully guarantee the technical requirements of the electrical grid code. Conclusion: The results obtained show better behavior of the system using ANFIS and ANN control strategy in the presence of a nonlinear load and a significant improvement of the voltage THD.

Background: The use of solar energy through photovoltaic arrays is continually expanding and has recently been regarded as one of the cleanest sources of energy. Increasing the amount of electricity provided to the load is one method for lowering the cost of solar systems. Contrarily, altering the load creates a divergence from the maximum power point (MPP) and changes the operating point of the solar conversion system. Methods: Due to this, attention has been given to MPPT techniques that can be used with solar systems in numerous research investigations. In this paper, we implement an MPPT method based on an Artificial Neural Network (ANN). This method combined two controllers, ANN and fuzzy logic controller, under the name ANN-Fuzzy logic hybrid. In the first stage, ANN can determine Vmpp from irradiation and temperature, and both of them are variable. In the second stage, this Vmpp has been corrected by implementing Fuzzy logic in order to minimize the error of the voltage and VmPP. Results: ANN-fuzzy hybrid has been simulated in Matlab-Simulink and was found to be the best solution to follow the maximum power point when irradiation and temperature are varied. The energy extracted from PV is delivered to a battery in order to inject this power into the smart grid by using an inverter controlled by PID. Finally, a LC filter has been used to eliminate the harmonics and compensate for the reactive power. Conclusion: For energy storage, we consider the utilization of lithium-ion batteries, which are recognized as an optimal solution for storing energy efficiently. To manage the charge and discharge of the battery, we employ a PID controller and a buck-boost converter. Through this research, we aim to explore the performance and effectiveness of the hybrid ANN-fuzzy simulation for the boost converter system. By combining the capabilities of ANN and fuzzy logic, we expect to achieve improved control and optimization of the power conversion processes in the system. Additionally, the integration of lithium-ion batteries and the use of the PID controller and buck-boost converter allow for efficient management of energy storage and retrieval. Overall, this study investigates the hybrid ANN-fuzzy simulation for the boost converter system, highlighting the integration of various components and control techniques to enhance the performance and efficiency of the system.