Deep learning (DL) is an exciting field of interest for many researchers and business. Due to a massive leap in DL based research, many domains like Business, science and government sectors make use of DL for various applications. This work puts forward the importance of DL and its application in a few critical electrical segments. Initially, an introduction to Artificial Intelligence (AI) and Machine Learning (ML) is presented. Then the need for DL and the popular architectures, algorithms and frameworks used are presented. A summary of different techniques used in DL is outlined, and finally, a review on the application of deep learning techniques in some popular electrical applications is presented. Five critical electrical applications, namely identification of bearing faults, hot spots on the surface of PV panels, insulator faults, an inspection of power lines and Electric vehicles have been considered for review in this work. The primary aim of this work is to present chronologically, a survey of different areas in which it applies DL along with their architectures, frameworks and techniques to provide a deeper understanding of DL for widespread use in real-time applications.

Solar Photovoltaic (PV) systems have been in use predominantly since the last decade. Inverter fed PV grid topologies are being used prominently to meet power requirements and to insert renewable forms of energy into power grids. At present, coping with growing electricity demands is a major challenge. This paper presents a detailed review of topological advancements in PV-Grid Tied Inverters along with the advantages, disadvantages and main features of each. The different types of inverters used in the literature in this context are presented. Reactive power is one of the ancillary services provided by PV. It is recommended that reactive power from the inverter to grid be injected for reactive power compensation in localized networks. This practice is being implemented in many countries, and researchers have been trying to find an optimal way of injecting reactive power into grids considering grid codes and requirements. Keeping in mind the importance of grid codes and standards, a review of grid integration, the popular configurations available in literature, Synchronization methods and standards is presented, citing the key features of each kind. For successful integration with a grid, coordination between the support devices used for reactive power compensation and their optimal reactive power capacity is important for stability in grid power. Hence, the most important and recommended intelligent algorithms for the optimization and proper coordination are peer reviewed and presented. Thus, an overview of Solar PV energy-fed inverters connected to the grid is presented in this paper, which can serve as a guide for researchers and policymakers.

The multidimensional purposes of grid-tied hybrid renewable system such as tracking of maximum power, increasing the power conversion efficiency, reducing the harmonic distortions in the injected current and control over power injected into the grid are presented in this paper by developing a laboratory-scale setup. To ensure continuous current operation at the shoot through mode of grid connected inverter, a switched Z-source converter is utilized at the PV side. The PWM rectifier connected with the wind turbine transforms AC power into dc. Individual power converters with conventional PI controllers have been dedicated for each power source, and control strategy uses only one reference voltage so as to increase the maximum power tracking speed from both PV and wind sources. The battery energy management is performed by artificial neural network (ANN) to enhance the stable power flow and increase the lifespan of the storage system. Finally, the voltage at the point of common coupling is fed to ANN-based space vector-modulated three-phase inverter and the converted AC power is injected to the grid. The overall system performance is measured by estimating the quality of injected power. A stable operation of the proposed microgrid system is verified by varying input and load at the grid. A continuous-time simulation model is realized in MATLAB and is validated using experimental prototype. This benchmark system provides various research scopes for the future smart grids.

The extensive usage of power electronic components creates harmonics in the voltage and current, because of which, the quality of delivered power gets affected. Therefore, it is essential to improve the quality of power, as we reveal in this paper. The problems of load voltage, source current, and power factors are mitigated by utilizing the unified power flow controller (UPFC), in which a combination of series and shunt converters are combined through a DC-link capacitor. To retain the link voltage and to maximize the delivered power, a PV module is introduced with a high gain converter, named the switched clamped diode boost (SCDB) converter, in which the grey wolf optimization (GWO) algorithm is instigated for tracking the maximum power. To retain the link-voltage of the capacitor, the artificial neural network (ANN) is implemented. A proper control of UPFC is highly essential, which is achieved by the reference current generation with the aid of a hybrid algorithm. A genetic algorithm, hybridized with the radial basis function neural network (RBFNN), is utilized for the generation of a switching sequence, and the generated pulse has been given to both the series and shunt converters through the PWM generator. Thus, the source current and load voltage harmonics are mitigated with reactive power compensation, which results in attaining a unity power factor. The projected methodology is simulated by MATLAB and it is perceived that the total harmonic distortion (THD) of 0.84% is attained, with almost a unity power factor, and this is validated with FPGA Spartan 6E hardware.