Fault type diagnosis is a very important tool to maintain the continuity of power transformer operation. Dissolved gas analysis (DGA) is one of the most effective and widely used techniques for predicting the power transformer fault types. In this paper, a convolutional neural network (CNN) model is proposed based on the DGA approach to accurately predict transformer fault types under different noise levels in measurements. The proposed model is applied with three categories of input ratios: conventional ratios (Rogers'4 ratios, IEC 60599 ratios, Duval triangle ratios), new ratios (five gas percentage ratios and new form six ratios), and hybrid ratios (conventional and new ratios together). The proposed model is trained and tested based on 589 dataset samples collected from electrical utilities and literature with varying noise levels up to ±20%. The results indicate that the CNN model with hybrid input ratios has superior prediction accuracy. The high accuracy of the proposed model is validated in comparison with conventional and recently published AI approaches. The proposed model is implemented based on MATLAB/toolbox 2020b.

The increase in industrial and commercial applications of photovoltaic systems (PV) has a significant impact on the increase in interest in studying the improvement of the efficiency of these systems. Estimating the efficiency of PV is considered one of the most important problems facing those in charge of manufacturing these systems, which makes it interesting to many researchers. The difficulty in estimating the efficiency of PV is due to the high non-linear current–voltage characteristics and power–voltage characteristics. In addition, the absence of ample efficiency information in the manufacturers’ datasheets has led to the development of an effective electrical mathematical equivalent model necessary to simulate the PV module. In this paper, an application for an optimization algorithm named Wild Horse Optimizer (WHO) is proposed to extract the parameters of a double-diode PV model (DDM), modified double-diode PV model (MDDM), triple-diode PV model (TDM), and modified triple-diode PV model (MTDM). This study focuses on two main objectives. The first concerns comparing the original models (DDM and TDM) and their modification (MDDM and MTDM). The second concerns the algorithm behavior with the optimization problem and comparing this behavior with other recent algorithms. The evaluation process uses different methods, such as Root Mean Square Error (RMSE) for accuracy and statistical analysis for robustness. Based on the results obtained by the WHO, the estimated parameters using the WHO are more accurate than those obtained by the other studied optimization algorithms; furthermore, the MDDM and MTDM modifications enhanced the original DDM and TDM efficiencies.

This article proposes an intelligent control strategy to enhance the frequency dynamic performance of interconnected multi-source power systems composing of thermal, hydro, and gas power plants and the high penetration level of wind energy. The proposed control strategy is based on a combination of fuzzy logic control with a proportional-integral-derivative (PID) controller to overcome the PID limitations during abnormal conditions. Moreover, a newly adopted optimization technique namely Arithmetic optimization algorithm (AOA) is proposed to fine-tune the proposed fuzzy-PID controller to overcome the disadvantages of conventional and heuristic optimization techniques (i.e., long time in estimating controller parameters-slow convergence curves). Furthermore, the effect of the high voltage direct current link is taken into account in the studied interconnected power system to eliminate the AC transmission disadvantages (i.e., frequent tripping during oscillations in large power systems–high level of fault current). The dynamic performance analysis confirms the superiority of the proposed fuzzy-PID controller based on the AOA compared to the fuzzy-PID controller based on a hybrid local unimodal sampling and teaching learning-based optimization (TLBO) in terms of minimum objective function value and overshoots and undershoots oscillation measurement. Also, the AOA’s proficiency has been verified over several other powerful optimization techniques; differential evolution, TLBO using the PID controller. Moreover, the simulation results ensure the effectiveness and robustness of the proposed fuzzy-PID controller using the AOA in achieving better performance under several contingencies; different load variations, the high penetration level of the wind power, and system uncertainties compared to other literature controllers adjusting by various optimization techniques.

In recent years, optimal sizing and location of reactive power resources are drawing much attention to help the operators of the utilities to enhance the power system operations. Therefore, this work presents a new version of grey wolf optimiser (GWO) to solve the problem of optimal reactive power resources sizing for power system operation enhancement. The proposed method which called improved grey wolf optimiser (IGWO) can be derived by modifying the exploration–exploitation balance in the conventional GWO to enhance its rate of convergence. Also, the weighted distance strategy is employed in the proposed IGWO to overcome the drawback of the conventional GWO. Optimal reactive power resources sizing problem is non‐linear and non‐convex optimisation problem. To solve this problem, different objective functions are used. These objective functions are minimisation of generating cost, minimisation of transmission power loss and voltage profile improvement. The validity and superiority of the proposed IGWO method are tested using three standard IEEE systems for normal and contingency conditions. Then the results are compared with those obtained from other recently published algorithms. The simulation results show that the proposed IGWO method is more accurate and efficient than other recently published algorithms.

In this research work, an adaptive TS‐fuzzy based RBF neural network (ATSFRBFNN) algorithm based maximum power point tracker (MPPT) is employed for grid integrated photovoltaic (PV) system. The novel learning algorithm provides accurate and rapid PV power tracking under fluctuating solar insolation. However, an improved damping circulating current limiting inverter controller is employed to generate gating signal of voltage source inverter and to deliver reduced harmonic constant, less power loss, mitigation of power quality issues regulation of Dc‐link voltage utilization for grid integrated PV system under steady, and transient weather conditions. The experimental results justify the improved system performance under varying operating conditions. The behaviour of novel hybrid PV MPPT structure is compared with TS‐fuzzy, RBFNN, and GA‐RBF for higher tracking efficacy, least tracking deviation, accurate responses, and zero steady‐state power oscillation around MPP region.