CNN ‐based deep learning technique for improved H7 TLI with grid‐connected photovoltaic systems

Abstract

In this article, a three-phase transformerless inverter (TLI) for a solar photovoltaic (PV) system connected to a high-power grid are proposed, which has advantages of better performance and lower cost. The primary concern about the TLI is fluctuations in the common-mode voltage, which impacts switching frequency leakage current and grid interface system. An improved H7 common-mode voltage (CMV) clamped TLI with discontinuous pulse width modulation (DPWM) is designed using a conventional neural network (CNN)based deep learning approach. In this, a completely minimized leakage current is obtained to avoid CMV transients. The proposed PV-connected improved H7-TLI provides low-loss DC-side decoupling, which further reduces leakage current and isolation of the PV system during off-grid. In addition, the effects of several factors on CNN deep learning performance are explored, including training data size, image resolution, and network configuration. The proposed technique has the potential to be used in a test instrument for intelligent signal analysis or used in an artificial intelligence system. Switching loss is analyzed using proposed and existing H7 inverters under different load conditions. To verify the theoretical explanation, existing H7 inverters is analyzed by MATLAB/Simulink, and the outcomes are tested experimentally. The total harmonic distortion (THD) analysis of proposed and existing topology is analyzed and compared. The THD values of the existing and proposed topology are 3.74% and 3.23%, respectively.

Optimized RNN-oriented power quality enhancement and THD reduction for micro grid integration of PV system with MLI: Crow Search-based Harris Hawks Optimization concept

“…The time domain parameter analysis in terms of various measures such as settling time, peak time, rise time, and steady state error with respect to methods like ANN, CNN, RNN and introduced CS-HHO is shown in Figure 7. Table 5 clearly reveals that the time utilized is less with the proposed Ramasamy and Perumal (2021) 10.9 6.2 7.9 6.3 RNN Yildirim (2005) 10.3 8.5 8.1 3.9 CS-HHO 9.6 0.1 6.2 1.1 CS-HHO than the other methods. Hence, it can be clearly stated that the time domain parameter analysis is better with CS-HHO than the other methods for the developed PV system with MLI.…”

A Comprehensive Review on Multilevel Inverters for Grid-Tied System Applications

“…Grid-connected PV inverter topologies typically fall into one of two kinds depending on the transformer utilized-transformer-based topologies and transformer-less topolo-Energies 2022, 15, 6315 6 of 40 gies [46]. Galvanic isolation between the DC source and the utility grid is achieved in the inverters by using line-frequency transformers.…”

Power quality improvement using a 31-level multi-level inverter with bio-inspired optimization approach

“…Power systems with defects that cause damage produce their elements as an outcome of the overheating process (Kumar et al, 2018;Dhanamjayulu et al, 2019;Khare et al, 2020;Lal and Thankachan, 2021). Additionally, there are certain common problems in these power systems, such as harmonic distortion, voltage sag, transient, and spikes (Arjunagi and Patil, 2021;Parida et al, 2021;Ramasamy and Perumal, 2021;Aarthi et al, 2023). With the help of Spider Monkey optimization CNN, MLI tackles the aforementioned issues and provides a high output voltage.…”