This paper presents a novel integrated multi‐Machine Learning (ML) system architecture for the protection of bipolar HVDC transmission line in which different ML models of Support Vector Machine (SVM) and K‐Nearest Neighbours (KNN) are used for fault detection and classification. The KNN fault type classifier is designed as a dual‐purpose module, which besides its main task of fault type detection, acts as a redundant module for unsure fault declaration from the startup unit. Gradients and standard deviations of DC current, voltage, harmonic current, and a correlation coefficient between the aerial and zero modes of DC current are appropriate feature vector extracted from single‐end signal measuring. Overall, 154 training cases and 53 main test cases are obtained by simulating various fault and non‐fault states on a $\pm$650 kV‐1000 km Current Source Converter (CSC)–HVDC using an EMTDC/PSCAD platform. The ML modules are trained in MATLAB and tested under different severe conditions with a total of 2220 test cases. Besides low training data requirements, the obtained results show that the proposed algorithm is accurate and fast enough to detect and distinguish a variety of internal faults and pseudo‐faults/external faults thanks to the appropriate feature vectors and the proposed system architecture.

In recent years, there has been a substantial growth in renewable energy sources and among these sources, solar energy is known as one of the best energies. The increasing adoption of solar energy across various applications underscores its significance in the renewable energy landscape. The integration of large-scale photovoltaic power plants into the primary power grid necessitates efficient and reliable power conversion processes, particularly as there is a growing demand for enhanced controllability and flexibility from the grid side. Power electronic converters, bolstered by advancements in control and information technologies, play a pivotal role in facilitating large-scale power generation from solar energy. High-power multilevel inverters have emerged as a compelling solution for addressing the escalating energy requirements. This paper aims to delve into the exploration of diverse structural configurations and technical hurdles encountered in high-power multilevel inverter topologies, alongside the associated control systems and modulation techniques tailored for application in large-scale photovoltaic power plants (LS-PV-PP) systems. A comprehensive analysis of high-power multilevel inverter topologies within solar PV systems is presented herein. Subsequently, an exhaustive examination of the control methods and strategies employed in high-power multilevel inverter systems is conducted, with a comparative evaluation against alternative approaches. Lastly, the paper delves into a discussion on prominent modulation methods utilized in multilevel power inverters, assessing their performance characteristics in various operational scenarios.

In some recent articles, the vulnerability of phasor measurement unit (PMU) to the time synchronisation attack by spoofing its global positioning system (GPS) has been highlighted as a threat to power grid protection, control and monitoring system. Having spoofed PMU GPS signals, one can manipulate the measurements and inject bad data to power grid protection and monitoring system. The existing anti‐spoofing methods are all based on GPS signal analysis. The mentioned methods are just able to detect spoofing without any data refinement as the data of power grid has not been practically used in calculations. Furthermore, some of these methods lose their certainty in noisy and harsh environments due to low power of GPS signals. A novel anti‐spoofing algorithm has been proposed based on power grid infrastructures which can join to any of the existing anti‐spoofing algorithm to empower spoofing detection process. The proposed algorithm adopts phasor measurement analysis and state estimation methods to detect spoofing. The composite of this algorithm with any of the existing algorithms will not only cover the probable malfunctioning in spoofing detection but also be able to refine counterfeit measurements.

This paper models and investigates the incorporation of economic transmission switching (TS) into integrated generation and transmission maintenance scheduling (IMS) and the effect of transmission switching on integrated maintenance scheduling (IMSwTS). To ensure security of power system over maintenance horizon, N‐1 criteria is considered in the model. The N‐1 secure IMSwTS problem is formulated as a mixed‐integer linear programming model (MILP). The MILP model of this paper cannot be solved with commercial solver in a reasonable time; therefore, with the aim of solving high computational burden, the model is decomposed into TS subproblem and IMS subproblem, and each subproblem variables related to other subproblem is fixed. The proposed model and decomposition approach are implemented on IEEE modified 24‐bus reliability test system and solved by using the CPLEX solver under GAMS modeling environments. The results demonstrate that considering TS in IMS alters the maintenance schedule and brings cost saving.