Fault diagnosis in photovoltaic (PV) arrays is essential in enhancing power output as well as the useful life span of a PV system. Severe faults such as Partial Shading (PS) and high impedance faults, low location mismatch, and the presence of Maximum Power Point Tracking (MPPT) make fault detection challenging in harsh environmental conditions. In this regard, there have been several attempts made by various researchers to identify PV array faults. However, most of the previous work has focused on fault detection and classification in only a few faulty scenarios. This paper presents a novel approach that utilizes deep two-dimensional (2-D) Convolutional Neural Networks (CNN) to extract features from 2-D scalograms generated from PV system data in order to effectively detect and classify PV system faults. An in-depth quantitative evaluation of the proposed approach is presented and compared with previous classification methods for PV array faults-both classical machine learning based and deep learning based. Unlike contemporary work, five different faulty cases (including faults in PS-on which no work has been done before in the machine learning domain) have been considered in our study, along with the incorporation of MPPT. We generate a consistent dataset over which to compare ours and previous approaches, to make for the first (to the best of our knowledge) comprehensive and meaningful comparative evaluation of fault diagnosis. It is observed that the proposed method involving fine-tuned pre-trained CNN outperforms existing techniques, achieving a high fault detection accuracy of 73.53%. Our study also highlights the importance of representative and discriminative features to classify faults (as opposed to the use of raw data), especially in the noisy scenario, where our method achieves the best performance of 70.45%. We believe that our work will serve to guide future research in PV system fault diagnosis. INDEX TERMS Photovoltaic array, maximum power point tracking, fault classification, convolutional neural network, scalograms, transfer learning.

No abstract

This paper is aimed at modelling of a distinct smart charging station for electric vehicles (EVs) that is suitable for DC quick EV charging while ensuring minimum stress on the power grid. Operation of the charging station is managed in such a way that it is either supplied by photovoltaic (PV) power or the power grid, and the vehicle-to-grid (V2G) is also implemented for improving the stability of the grid during peak load hours. The PV interfaced DC/DC converter and grid interfaced DC/AC bidirectional converter share a DC bus. A smooth transition of one operating mode to another demonstrates the effectiveness of the employed control strategy. Modelling and control of the different components are explained and are implemented in Simulink. Simulations illustrate the feasible behaviour of the charging station under all operating modes in terms of the four-way interaction among PV, EVs and the grid along with V2G operation. Additionally, a business model is discussed with comprehensive analysis of cost estimation for the deployment of charging facilities in a residential area. It has been recognized that EVs bring new opportunities in terms of providing regulation services and consumption flexibility by varying the recharging power at a certain time instant. The paper also discusses the potential financial incentives required to inspire EV owners for active participation in the demand response mechanism.

During the last few years, assessment and evaluation of power quality index due to large-scale penetration of electric vehicles in the system have gained significant attention. Voltage unbalance in the low voltage distribution network is amongst the main power quality issues caused by electric vehicles and therefore it has been quantified and analyzed in this paper. A CIGRE benchmark model of low voltage distribution network is taken as test network and simulations are performed on a sample urban power distribution network. An electric vehicle grid integration and its charging model is implemented in Simulink. Results for two charging strategies including uncontrolled charging and tariff based electric vehicle charging under different electric vehicle penetration levels and uneven charging scenarios have been obtained. The presented results show that an uneven EV charging scenario can cause significant voltage unbalance that goes beyond its allowed limit of 2 %.