The incorporation of renewable energy sources in power grids has necessitated innovative solutions for effective energy management. Smart grids have emerged as transformative systems which integrate consumer, generator and dual-role entities to deliver secure, sustainable and economical electricity supplies. This review explores the important role of artificial intelligence and machine learning approaches in managing the developing stability characteristics of smart grids. This work starts with a discussion of the smart grid’s dynamic structures and subsequently transitions into an overview of machine learning approaches that explore various algorithms and their applications to enhance smart grid operations. A comprehensive analysis of frameworks illustrates how machine learning and artificial intelligence solve issues related to distributed energy supplies, load management and contingency planning. This review includes general pseudocode and schematic architectures of artificial intelligence and machine learning methods which are categorized into supervised, semi-supervised, unsupervised and reinforcement learning. It includes support vector machines, decision trees, artificial neural networks, extreme learning machines and probabilistic graphical models, as well as reinforcement strategies like dynamic programming, Monte Carlo methods, temporal difference learning and Deep Q-networks, etc. Examination extends to stability, voltage and frequency regulation along with fault detection methods that highlight their applications in increasing smart grid operational boundaries. The review underlines the various arrays of machine learning algorithms that emphasize the integration of reinforcement learning as a pivotal enhancement in intelligent decision-making within smart grid environments. As a resource this review offers insights for researchers, practitioners and policymakers by providing a roadmap for leveraging intelligent technologies in smart grid control and stability analysis.

In this paper, a novel self-adaptive control method based on a digital twin is developed and investigated for a multi-input multi-output (MIMO) nonlinear system, which is a heating, ventilation, and air-conditioning system. For this purpose, hardware-in-loop (HIL) and software-in-loop (SIL) are integrated to develop the digital twin control concept in a straightforward manner. A nonlinear integral backstepping (NIB) model-free control technique is integrated with the HIL (implemented as a physical controller) and SIL (implemented as a virtual controller) controllers to control the HVAC system without the need for dynamic feature identification. The main goal is to design the virtual controller to minimize the distinction between system outputs in the SIL and HIL setups. For this purpose, Deep Reinforcement Learning (DRL) is applied to update the NIB controller coefficients of the virtual controller based on the measured data of the physical controller. Since the temperature and humidity of HVAC systems should be regulated, the NIB controllers in the HIL and SIL are designed by the DRL algorithm in a multi-objective scheme (MO). In particular, the simulations of the HIL and SIL environments are coupled by a new advanced tool: function mockup interface (FMI) standard. The Functional Mock-up Unit (FMU) is adopted into the FMI interface for data exchange. The extensive research of HIL and SIL controllers shows that the system outputs of the virtual controller are controlled exactly according to the physical controller.

The Wireless Charging Electric Transit Bus (WCETB) is an innovative electric transportation technology that receives power wirelessly from underground power transmitters. Since the battery in the bus can be wirelessly charged during the moving, the need to stop for the vehicle at the charging station is eliminated, and recharging time is remarkably decreased. One of the best methodologies to commercialize the WCETB technology is to economically allocate the power tracks on considered routes while optimally determining the battery size of the vehicle at the same time. In this paper, the planning of the power transmitters and the capacity of the battery size for a WCETB with a multi-route model is optimally designed by Deep Deterministic Policy Gradient (DDPG). In particular, the DDPG algorithm is adopted in this model, an appropriate reward function is defined for the multiple route problem, and the optimal problem is solved by adopting the training ability of deep neural networks (DNNs), i.e., Actor and Critic neural networks. A complex Nguyen-Dupuis (N-D) traffic network with multiple routes is considered a case study to evaluate the validity and performance of the proposed deep learning scheme from a systematic point of view. Numerical analysis along with sensitivity examination confirms the efficiency of the optimal design and solution process.

Droop control is at the first level of the control hierarchy and does not require communication. Having high reliability, is usually used in inverter‐based microgrids. The microgrid can operate as an island, and it can also be connected to the main or auxiliary grid. By reviewing the extensive literature on the role of the controller in inverter‐based microgrids for the island mode of operation, in this study, the droop regulation strategy has been covered briefly and compactly. Droop regulation is an example of decentralized regulation in basic control, and its importance is revealed in the island mode of operation when it is possible to share power in all facilities without needing to communicate with other units. Disadvantages of common droop control, such as slow transient dynamics and low energy quality for non‐linear and unbalanced loads, have limited its use in advanced microgrids. Therefore, various methods to improve the common droop control have been investigated so far, some of which have been mentioned. This study highlights the application of droop control strategies in order to coordinate distributed generation units in the microgrid. About 180 published studies in this field have been reviewed, classified and indexed for quick reference.

The reliability of DC-link capacitor-banks (CBs) encounters many challenges due to their usage in electric vehicles. Heavy shocks may damage the internal capacitors without shutting down the CB. The fundamental development obstacles of CBs are: lack of considering capacitor degradation in reliability assessment, the impact of unforeseen sudden internal capacitor faults in forecasting CB lifetime, and the faults consequence on CB degradation. The sudden faults change the CB capacitance, which leads to reliability change. To more accurately estimate the reliability, the type of the fault needs to be detected for predicting the correct post-fault capacitance. To address these practical problems, a new CB model and reliability assessment formula covering all fault types are first presented, then, a new analog fault-detection method is presented, and a combination of online-learning long short-term memory (LSTM) and fault-detection method is subsequently performed, which adapt the sudden internal CB faults with the LSTM to correctly predict the CB degradation. To confirm the correct LSTM operation, four capacitors degradation is practically recorded for 2000-hours, and the off-line faultless degradation values predicted by the LSTM are compared with the actual data. The experimental findings validate the applicability of the proposed method. All experimental codes-data are attached.