Search

Abstract The increasing energy consumption and changing load variations place a significant burden on the sophisticated utility grid, which affects the source's dependability and quality. Researchers examining modern power networks must focus on those factors to prevent grid breakdowns. Superior power quality (PQ) is still intended to make sure everything runs smoothly under diverse organizations. The main cause of PQ problems, however, is now renewable energy used in power electronic converters that are integrated into the electrical grid. Even though new, better solutions are still being developed, adhering to international standards have been strongly advised. Consequently, microgrid clusters powered through renewable energy and incorporating multiple structures in an urban area has been proposed in this paper. This increases the dependability of the power sources by managing the energy that is available inside the cluster instead of having it focused around the utility grid. Additionally, a deep belief network model based on Improved Dwarf Mongoose Optimization is recommended for regulating the inverter by generating optimal pulse‐width modulated signals that increases the quality of the power supplies. When compared to other conventional techniques, the suggested technique possesses less real power and reactive power setting duration of 0.8 ms and 0.75 ms, respectively.

Abstract Owing to increased energy demand, renewable energy sources have recently reached greater heights in the power industry. In this regard, integrating renewable energy with the power grid system has become essential in meeting consumer's energy demands. The novelty in this article is the design of an advanced Aalborg inverter with a reduced number of switches which results in enhanced system performance by reducing the switching losses. Integrating renewable energy sources with the power grid network has gained massive importance in supplying electric power to consumers. Integrating the power grid with renewable energy has become possible with the implementation of grid tie inverters. The only drawback in implementing renewable energy sources with the power grid is that the output of the resources varies from time to time in nature. Voltage Source Inverter‐based grid system requires two or three‐stage inverters for interfacing power units to transfer DC energy into the power grid network. To reduce the switching frequency across the system, many new excellent inverters have been designed to ensure the healthy operation of the system operating at a higher frequency. This article has been coined with the investigation of a novel buck and boosts converter‐based inverter operation named Aalborg inverter. The inverter operates at a higher frequency and minimum voltage drop across the inductor, where only one power stage has been implied to enhance the system's reliability and efficiency. This novel Aalborg inverter is applied and investigated for photovoltaic application.

The photovoltaic (PV) system stands out as a viable energy source due to its environmental friendliness and cleanliness. The conversion rate at which solar power generation is still relatively low due to limitations imposed by advances in PV technology. For PV systems, an appropriate model with precise internal parameters is considerably more crucial to increase conversion efficiency further. Different PV mathematical models, such as single‐diode, two‐diode, and three‐diode, are available to model the PV system. Investigators are interested in assessing the accurate PV model parameters through the experimental voltage–current (I–V) samples or using the manufacturer's specifications. At the same time, the difficulty is in accurately assessing and developing a more trustworthy PV model with well‐optimized parameters. To address the parameter estimation of various solar PV models, in this article, a new bio‐inspired algorithm called Brownian random walk‐based Sand Cat Swarm Optimization Algorithm (SCSOA) named Boosted SCSOA (BSCSOA) is proposed and developed. Along with the Brownian random strategy, chaotic tent drift is also used to enhance the exploration and exploitation of SCSOA, and the proposed BSCSOA is applied to different models to estimate their parameters accurately. The effectiveness of the suggested BSCSOA is compared with other well‐known algorithms, including the basic SCSOA, in terms of statistical measures and fitness values. The obtained results demonstrated the superiority of the BSCSOA over the other algorithms for all PV models of the cell and module. [ABSTRACT FROM AUTHOR]

The accurate classification of power quality disturbances (PQDs) is crucial for advancing real‐time monitoring and classification systems within the modern power grid. The proposed system must ensure dependable, safeguarded, and stable operating conditions amidst diverse power quality issues. This paper presents an approach to classifying power quality disturbances using a deep learning model that synergizes deep convolutional neural networks (DCNN) and Bidirectional Long Short‐Term Memory (BiLSTM). This amalgamation effectively extracts and classifies disturbance signals in real time, grounded on noise levels. The initial feature extraction from the signal is accomplished through a time‐frequency matrix. Subsequently, secondary extraction employs the BiLSTM layer to intricately and significantly classify disturbances in the power signal. This aids in transforming high‐dimensional matrices into a reduced set for enhanced performance. The detailed classification is facilitated by the softmax layer. The simulation results support the power quality evaluations under varied constraints and underscore the substantial classification of power quality disturbances through the DCNN‐BiLSTM algorithm, in comparison to alternative classification algorithms in terms of computational speed and accuracy. [ABSTRACT FROM AUTHOR]