ABSTRACT This paper presents the implications of integrating deep reinforcement learning (DRL) and the Internet of Things (IoT) in optimizing energy management, specifically in smart buildings for sustainable urban development. It further explores how DRL, along with real‐time IoT sensor‐based data, helps improve energy performance in responding to actual HVAC, lighting and renewable energy conditions. Key techniques like genetic algorithms, particle swarm optimization and hybrid techniques are critically examined in maintaining an equilibrium between energy consumption versus renewable sourcing in smart building models. Boundary‐preserving strategies and federated learning appear as techniques addressing expansibility and information protection difficulties, notably over IOT systems. Further research would include technology in local processing and situation‐responsive DRL to enhance more independent, user‐focused and ecologically responsive buildings. This review provides a roadmap for implementing robust, privacy‐conscious AI frameworks in smart buildings, underlining their potential to cut energy use and contribute to broader environmental goals.

ABSTRACT Extreme weather events driven by climate change pose increasing threats to power system security, particularly in electricity systems with high penetration of renewable energy and growing dependence on digital infrastructure. This paper examines the challenges and opportunities of enhancing power system resilience against low‐probability but high‐impact events by integrating cross‐domain perspectives from meteorology, artificial intelligence (AI), communication networks, and data centres. We review how different categories of extreme weather affect generation, networks, loads, and cyber‐communication layers, and highlight limitations of existing resilience studies. Advanced AI techniques, including deep learning and deep reinforcement learning, are discussed as key enablers for scalable, adaptive, and time‐critical resilience enhancement. Furthermore, the emerging role of data centres is analysed, emphasising their dual nature as both stressors and flexible demand, local generation, and computational support. This work aims to provide insights into existing challenges and potential solutions for enhancing power system resilience amid energy transitions and digitalisation.

ABSTRACT This paper addresses issues in wind power DC transmission systems, such as difficulty in maintaining power delivery during rectifier‐side faults and frequent overvoltage occurrences during inverter‐side faults. A hybrid topology comprising a rectifier‐side MMC and an inverter‐side LCC‐MMC configuration is proposed, along with corresponding enhanced control strategies. The characteristics of the proposed hybrid HVDC under bilateral AC faults are investigated. Results indicate that during single‐phase faults on the rectifier side, the proposed model and control strategy can maintain transmitted power at 0.54 p.u. or higher, preventing power transmission interruptions. Compared to conventional control strategies for inverter‐side hybrid DC transmission systems, the minimum power transmission value increases by 11%. Under inverter‐side AC faults, wind power output can track power variations during the disturbance. During a single‐phase‐to‐ground fault, the DC voltage of the receiving‐end MMC is limited to within 1.13 p.u., and during a three‐phase short‐circuit fault, it is restricted to within 1.29 p.u., remaining below the safety threshold of 1.3 p.u. Consequently, the proposed system effectively ensures the long‐distance and reliable transmission of wind power, making it suitable for the dependable delivery of large‐scale offshore wind power.

ABSTRACT Regarding the time‐series scenario generation of regional wind power, conventional methods face challenges in accurately characterizing the variation patterns of the wind power under installed capacity expansion. To address this issue, this paper presents a historical meteorological data‐driven regional wind power scenario generation approach, which can generate time‐series regional wind power scenarios under historical weather conditions and expected wind power capacity expansion. First, wind power aggregation points (WPAPs) in the study region are selected based on the consistency of the wind turbine models and wind speeds among wind farms. Then, the wind speed spatial distribution in the study region is classified into several patterns, and a dual‐layer convolutional neural network (DCNN) is designed to model the dependence of the regional wind power on wind speeds and installed capacities at WPAPs for each pattern. Finally, the expected installed capacities of wind power are aggregated to WPAPs to enable the trained DCNN models to generate regional wind power scenarios driven by the historical weather data. By means of the meteorological reanalysis data, the proposed approach can provide time‐series regional wind power scenarios with heterogeneity and a high degree of credibility for long‐term planning. Case studies in Shandong Province, China, are carried out to verify the effectiveness of the proposed approach.

Abstract With the emergence of the Smart Grid concept, utility companies require more active participation of home users in the power sector. This changing paradigm is enabled by the wide deployment of multiple home assets such as small renewable‐based generators or storage facilities. In this context, consumers are no longer conceived as pure loads but also active agents that can exchange energy with the grid. To promote this active participation, utility companies promote different price‐based demand response programs to change the consumer patterns on pursuing a more efficient and economic system operation. In this regard, home energy management programs are becoming an essential tool for efficiently managing the different home users while addressing multiple demand response goals at minimum cost. In essence, a home energy management system is a computational optimization tool, which has to handle multiple uncertainties brought by weather forecast or energy pricing. This paper tackles this issue by developing a novel robust home energy management program based on interval optimization. In contrast to other related approaches, the proposal avoids the explicit use of interval arithmetic. Instead, the different uncertain parameters are sequentially incorporated into the scheduling task through different stages and interval‐based formulation. The developed methodology incorporates weather, load, energy pricing and plug‐in electric vehicle related uncertainties. A benchmark case study in a smart prosumer layout serves to prove the effectiveness of the new approach.

Abstract The unnecessary prolonged operating time of conventional current differential protection under high‐impedance DC line faults is an important issue affecting the continuity of power supply. This issue originates from the extreme differential current fluctuation under fault conditions. This paper presents a reinforced pilot protection algorithm for bipolar CSC‐HVDC transmission lines to achieve a selective and sensitive performance without sacrificing the protection speed. In this regard, the characteristics of low‐frequency transient modal currents are investigated along with the impact of discharging capacitive current under various fault conditions. Based on the features arising from line‐mode compensated currents, it is shown that their opposite changing directions induces a positive high‐value differential current during DC line faults, whereas the compensated line‐mode currents follow the same changing trend under external faults. After detecting internal faults, the faulted pole is detected by utilizing the polarity of ground‐mode components. Compared to other pilot protections, the proposed protection provides more reliability, selectivity, and sensitivity with high operating speed. Moreover, it has robust performance against discharging capacitive current, asynchronous measurement, line parameters uncertainty, and noise. Various simulation tests are performed on a ±500 kV HVDC test system in PSCAD to verify effectiveness of the proposed protection.