Search

Multilevel inverter (MLI) synthesizes the preferred level of alternating voltage from multiple input sources of lower-level direct voltage. By adopting a suitable harmonic elimination technique, the MLI produces stepped sinusoidal waveforms with reduced total harmonic distortion (THD) without using any filter-based applications. MLI will be an apt choice for industries operating under medium- and high-power alternating current (AC) drives, and this finds application in interfacing non-conventional energy sources with power grid lines. This paper emphasizes a novel design of performance-enhanced cascaded MLI (PEC-MLI) with less quantity of switching devices for renewable energy system. The desired switching of MLI cost function is calculated using Genetic Algorithm (GA), and the appraised firing angle is calculated and the same is given as input to the Pulse Width Modulation (PWM) technique coded with chosen Nearest Voltage Level (NVL) control scheme. The gating signals generated for switching devices with the control strategies of NVL—PWM and hybrid PWM techniques using Genetic Algorithm. The MATLAB/Simulink model successfully evaluates the performance of proposed MLI. The simulated results analyze the system efficiency by comparing it with other similar MLI configuration cited in recent research articles. An effective realization of proposed MLI is experimented successfully and whose results are found be satisfactory with the simulated results. [ABSTRACT FROM AUTHOR]

Classification plays a crucial role in big data, especially in e-commerce operations. Deep learning (DL) research has become a new means to provide a better solution to the problem of classification. In this paper, a deep learning spiking neural network model with the objective of building and testing a more biologically plausible network is proposed. The model is simulated using NengoDL simulator along with TensorFlow in a python environment. The performance of the model is evaluated using FashionMNIST dataset owing to its complexity than the existing MNIST dataset. The results provided better performance, and advantages are viewed in terms of area efficiency due to the use of lesser number of neurons, increasingly biologically plausible network and ease of implementation in hardware like FPGA as SNN is involved. [ABSTRACT FROM AUTHOR]

Summary: High quality and reliability of distributed power systems (DPS) play the major role in the telecommunications, industries, and home applications. The controlling of bidirectional power flow with the varied input and output voltage is the major issue in the distributed power systems due to the low settling time and the harmonics generated in them. The control signal provided to the switching devices used in the DC‐DC converter topologies is responsible for controlling the power flow. This paper presents the enhanced controller that receives the feedback signal as the input and generates the pulses necessary for the switching devices in the converter. The modeling of the feedback signal with the feedback‐integrated transfer function (FITF) provides the pulse density‐modulation (PDM) pulses to the switching section. The DC‐DC converter uses the DPS as front end, and this is a microgrid system. The FITF‐PDM reduces the losses in the switches and improves the output voltage level of the isolated bidirectional DC‐DC converter with the minimum settling time. The employment of zero current transition (ZCT) with the FITF‐PDM pulses boosts up the input voltage level to control the bidirectional power flow. The variations in the pulse density with respect to the variations in the feedback signal (error signal) are responsible for the update of the controlling function. The proposed FITF‐PDM is processes in simulation and compared with the existing control structures in terms of regulation efficiency assures the effectiveness of proposed DC‐DC modeling in the real‐time applications. [ABSTRACT FROM AUTHOR]