As a result of fossil fuel prices and the associated environmental issues, electric vehicles (EVs) have become a substitute for fossil-fueled vehicles. Their use is expected to grow significantly in a short period of time. However, the widespread use of EVs and their large-scale integration into the power system will pose numerous operational and technical challenges. To avoid these issues, it is essential to manage the charging and discharging of EVs. EVs may also be considered sources of dispersed energy storage and used to increase the network’s operation and efficiency with reasonable charge and discharge management. This paper aims to provide a comprehensive and updated review of control structures of EVs in charging stations, objectives of EV management in power systems, and optimization methodologies for charge and discharge management of EVs in energy systems. The goals that can be accomplished with efficient charge and discharge management of EVs are divided into three groups in this paper (network activity, economic, and environmental goals) and analyzed in detail. Additionally, the biggest obstacles that EVs face when participating in vehicle-to-grid (V2G) applications are examined in this paper.

The accelerated evolution of Artificial Intelligence (AI) technology has garnered widespread attention and acclaim across various domains, owing to its remarkable performance in diverse applications. Power systems supporting modern life are no exception to this transformative wave. This paper stands as the first comprehensive review of various AI techniques in power systems, spanning applications such as load forecasting, security assessment, voltage stability assessment, load shedding (LS), false data injection attack (FDIA) detection, state estimation and localization, fault detection and location, and power quality disturbances (PQDs) detection. In addressing the challenges inherent in the practical implementation of AI in power systems, this study introduces two potent tools: the strategic utilization of transfer learning (TL) in conjunction with AI algorithms and the leveraging of digital twin technology. The synergistic integration of these approaches remarkably enhances the performance and accuracy of AI models. Overall, this work aims to contribute to the foundational knowledge necessary for harnessing the full spectrum of AI’s capabilities and to lay the foundation for a future of sustainable energy. Ultimately, it addresses emerging challenges and opens new perspectives for further research in the relevant field.

Considering the strong influence of distributed generation (DG) in electric distribution systems and its impact on network voltage losses and stability, a new challenge has appeared for such systems. In this study, a novel analytical algorithm is proposed to distinguish the optimal location and size of DGs in radial distribution networks based on a new combined index (CI) to reduce active power losses and improve system voltage profiles. To obtain the CI, active power losses and voltage stability indexes were used in the proposed approach. The CI index with sensitivity analysis was effective in decreasing power losses and improving voltage stability. Optimal DG size was determined based on a search algorithm to reduce active power losses. The considered scheme was examined through IEEE 12-bus and 33-bus radial distribution test systems (RDTS), and the obtained results were compared and validated in comparison with other available methods. The results and analysis verified the effectiveness of the proposed algorithm in reducing power losses and improving the distribution system voltage profiles by determining the appropriate location and optimal DG size. In IEEE 12 and 33 bus networks, the minimum voltage increased from 0.9434 p.u and 0.9039 p.u to 0.9907 p.u and 0.9402 p.u, respectively. Additionally, the annual cost of energy losses decreased by 78.23% and 64.37%, respectively.

Recently, deep learning (DL) based dynamic security assessment (DSA) methods have been very successful. However, although a DSA model can be trained well for a specific topology, it often does not perform well for other topologies. Since the topology in real‐world power systems is frequently changing, the performance reduction of DL‐based DSA methods is very serious, which is a challenging and urgent problem. This paper proposes a novel DSA method based on a convolutional neural network (CNN) to solve this problem. In the proposed method, a strong yet simple domain adaptation approach named adaptive batch normalization (AdaBN) is used, which significantly enhances the extensibility and generalizability of the DSA model when the topology changes and eliminates the need to train a large number of models. This approach achieves a deep adaptation effect by modulating the statistics from the source domain to the target domain in all batch normalization layers across the model. Unlike other domain adaptation methods, this method is parameter‐free, requires no additional components, and has advanced performance despite its simplicity. In addition, this paper introduces TGAN‐based data augmentation to deal with the difficulty of costly data collection and labelling. This data augmentation makes the proposed model applicable to small databases. The test results of the proposed method on IEEE 39‐bus and IEEE 118‐bus systems show that this method can evaluate system dynamic security during topology changes and in the face of data noise with high accuracy.

Many real-world power systems operate near voltage stability limits due to rising power demands, limited generation sources, and delays in development projects. Therefore, conducting online voltage stability assessments of power systems is crucial to ensure stable system operation. Various indices have been proposed in recent years to assess voltage stability in this context. One of the main challenges of these indexes for implementation in real-world power systems is their formulation with two-bus and single-line systems and their generalization to multi-bus and multi-line systems, which makes them non-rigorous. In formulating the existing indexes that use the concept of voltage sensitivity to active power, the effect of the lines from which the bus receives active power can be seen separately in evaluating bus voltage stability. At the same time, for accurate evaluation, the set of lines and the received power of all lines should be considered together in formulating the index. To meet this challenge, a new real-time index for voltage stability assessment is introduced in this paper. Furthermore, the effect of distribution systems in voltage stability is investigated in this study using simultaneous modeling transmission and distribution systems. The test results of the proposed index on the power system of the 3-bus system and the IEEE 14, 30, and 118 bus systems show its superior performance compared to the existing index. Specifically, to increase the apparent power loading in the 118-bus system, the maximum error of the proposed index is 3.37%. Meanwhile, for index P and index L, the maximum error is 29.6% and 30.75%, respectively. Finally, the results show that modeling the distribution system in the 3 and 118 bus systems reduces the maximum active power loading by 35.21% and 59.27%, respectively.