This study presents an intelligent fault classification method for identification of transformer winding fault through transfer function (TF) analysis. For this analysis support vector machine (SVM) is used. The required data for training and testing of SVM are obtained by measurement on two groups of transformers (one is a classic 20 kV transformer and the other is a model transformer) under intact condition and under different fault conditions (axial displacement, radial deformation, disc space variation and short circuit of winding). Two different features extracted from the measured TFs are then used as the inputs to SVM classifier for fault classification. The accuracy of proposed method is compared with the accuracy of past well-known works. This comparison indicates that the proposed method can be used as a reliable method for transformer winding fault recognition.

This paper proposes an effective method for very accurate parameter estimation of single- and double-diode solar cell models. For this purpose, unknown parameters of model are estimated by minimization of an objective function using a new highly effective modified version of artificial bee colony (ABC) algorithm. The proposed algorithm is used for parameter estimation of single- and double-diode models and the results are compared, from different aspects, with recently developed related works (including those applied GA, CPSO, PS, SA, IGHS, ABSO, ABC, GGHS, and IADE for this purpose). The proposed algorithm is also compared with other modified explanations of ABC algorithm. The results show that the proposed strategy is considerably faster and more accurate compared to all the previous studies.

In this paper, a methodology of sizing optimization of a stand-alone hybrid PV/wind/battery power generation system (HPWGS) is proposed. The main objective of this optimization is to minimize the total annual cost (TAC) of the hybrid system considering power balanced constraint and determination of the optimal number of wind turbines, PV panels, and batteries. For this purpose, a new meta-heuristic nature-inspired algorithm, called Grey Wolf Optimizer is utilized. The obtained results show that the proposed methodology finds optimal sizing of the HPWGS easily with fast convergence and lower cost. Comparing the results of this new method with the well-known published works in the literature, the superior capabilities of this proposed method are demonstrated. Moreover, the results show that the reliability characteristics are weakened with decreasing the component availability, and the supply reliability of the HPWGS is improved by increasing the inverter efficiency while the TAC is decreased. Furthermore, the HPWGS can cover the load demand variations with high reliability.

In this paper, the design of a hybrid renewable energy PV/wind/battery system is proposed for improving the load supply reliability over a study horizon considering the Net Present Cost (NPC) as the objective function to minimize. The NPC includes the costs related to the investment, replacement, operation, and maintenance of the hybrid system. The considered reliability index is the deficit power-hourly interruption probability of the load demand. The decision variables are the number of PV panels, wind turbines and batteries, capacity of transferred power by inverter, angle of PV panels, and wind tower height. To solve the optimization problem, a new algorithm named improved crow search algorithm (ICSA) is proposed. The design of the system is done for Zanjan city, Iran based on real data of solar radiation and wind speed of this area. The performance of the proposed ICSA is compared with crow search algorithm (CSA) and particle swarm optimization methods in different combinations of system. This comparison shows that the proposed ICSA algorithm has better performance than other methods.