Summary To eliminate problems of traditional perturb and observe (TPO) maximum power point tracking (MPPT) relying on large scale variable speed wind energy conversion system (VS‐WECS), this paper suggests a variable step size perturb and observe (VS‐PO) MPPT algorithm. The VS‐PO technique is performed to split the power‐speed (P‐ω) curve with four segments every with a particular step size. A large step size is chosen for the two segments distant from the MPP. Otherwise, a smaller step size can be implemented. The proposed algorithm can achieve the maximum power without large oscillations and reduce the settling time under different wind speed conditions, which means high tracking efficiency. Moreover, the model reference adaptive control (MRC) is applied instead of a PI controller to regulate the rotor speed, which maximizes the extracted power. Also, the MRC successful for reducing the large oscillation and settling time compared with the PI controller. The suggested control technique is tested over a 1.5 MW DFIG WECS by MATLAB/Simulink software.
To treat the stochastic wind nature, it is required to attain all available power from the wind energy conversion system (WECS). Therefore, several maximum power point tracking (MPPT) techniques are utilized. Among them, hill-climbing search (HCS) techniques are widely implemented owing to their various features. Regarding current HCS techniques, the rotor speed is mainly perturbed using predefined constants or objective functions, which makes the selection of step sizes a multifaceted task. These limitations are directly reflected in the overall dynamic WECS performance such as tracking speed, power fluctuations, and system efficiency. To deal with the challenges of the existing HCS techniques, this paper proposes a new adaptive HCS (AD-HCS) technique with self-adjustable step size using model reference adaptive control (MRAC) based on the PID controller. Firstly, the mechanical power fluctuations are detected, then the MRAC continuously optimizes the PID gains so as to generate an appropriate dynamic step size until harvesting the maximum power point (MPP) under the optimal tracking conditions. Looking specifically at the simulation results, the proposed AD-HCS technique exhibits low oscillations around the MPP and a small settling time. Moreover, WECS efficiency is increased by 5% and 2% compared to the conventional and recent HCS techniques, respectively. Finally, the studied system is confirmed over a 1.5 MW, gird-tied, double-fed induction generator (DFIG) WECS using MATLAB/Simulink.
To deal with the challenges of the solar photovoltaic (PV) energy source due to the continuous variations of the climatic conditions such as temperature and solar radiation, output power prediction is one of the most important research trends nowadays. In this paper, a multilayer feedforward neural network (MLFFNN) is executed to foresee the power for a solar PV power station. The MLFFNN employs the temperature and radiation as the inputs and the power as the output. For training and testing the MLFFNN, data of 6 days are acquired from a real PV power station in Egypt. The first five days are employed to train the MLFFNN using Levenberg-Marquardt (LM) algorithm. While the data of the sixth day, are used to check the effectiveness and the generalization ability of the trained MLFFNN. The results prove that the trained MLFFNN is working very well and efficient to predict the PV output power correctly.
Solar photovoltaics (PV) is considered an auspicious key to dealing with energy catastrophes and ecological contamination. This type of renewable energy is based on climatic conditions to produce electrical power. In this article, a multilayer feedforward neural network (MLFFNN) is implemented to predict and forecast the output power for a solar PV power station. The MLFFNN is designed using the module temperature and the solar radiation as the two main only inputs, whereas the expected power is its output. Data of approximately one week (6-days) are obtained from a real PV power station in Egypt. The data of the first five days are used to train the MLFFNN. The training of the designed MLFFNN is executed using two types of learning algorithms: Levenberg-Marquardt (LM) and error backpropagation (EBP). The data of the sixth day, which are not used for the training, are used to check the efficiency and the generalization capability of the trained MLFFNN by both algorithms. The results provide evidence that the trained MLFFNN is running very well and efficiently to predict the power correctly. The results obtained from the trained MLFFNN by LM (MLFFNN-LM) are compared with the corresponding ones obtained by the MLFFNN trained by EBP (MLFFNN-EBP). From this comparison, the MLFFNN-LM has slightly lower performance in the training stage and slightly better performance in the stage of effectiveness investigation compared with the MLFFNN-EBP. Finally, a comparison with other previously published approaches is presented. Indeed, predicting the power correctly using the artificial NN is useful to avoid the fall of the power that maybe happen at any time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.