Artificial Intelligence and IoT-Enabled Power Electronics for Renewable Energy and Smart Grids [Expert View

As Smart Cities development grows, deploying advanced technologies, such as the Internet of Things (IoT), Cyber–Physical Systems, and particularly, Artificial Intelligence (AI), becomes imperative for efficiently managing energy resources. These technologies serve to coalesce elements of the energy life cycle. By integrating smart infrastructures, including renewable energy, electric vehicles, and smart grids, AI emerges as a keystone, improving various urban processes. Using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and the Scopus database, this study meticulously reviews the existing literature, focusing on AI technologies in four principal energy domains: generation, transmission, distribution, and consumption. Additionally, this paper shows the technological gaps when AI is implemented in Smart Cities. A total of 122 peer-reviewed articles are analyzed, and the findings indicate that AI technologies have led to remarkable advancements in each domain. For example, AI algorithms have been employed in energy generation to optimize resource allocation and predictive maintenance, especially in renewable energy. The role of AI in anomaly detection and grid stabilization is significant in transmission and distribution. Therefore, the review outlines trends, high-impact articles, and emerging keyword clusters, offering a comprehensive analytical lens through which the multifaceted applications of AI in Smart City energy sectors can be evaluated. The objective is to provide an extensive analytical framework that outlines the AI techniques currently deployed and elucidates their connected implications for sustainable development in urban energy. This synthesis is aimed at policymakers, urban planners, and researchers interested in leveraging the transformative potential of AI to advance the sustainability and efficiency of Smart City initiatives in the energy sector.

The grid has played a vital role in the evolution of the electricity market; from traditional to smart grids; from fossil fuel power generated electricity grid connections to the integration of other renewable energy forms such as solar and wind power; the grid has played a key role in each step in Taiwan’s move towards energy transition. This study includes Taiwan’s construction of its transmission and distribution network, the recently passed newly revised version of the Electricity Act with its revisions to its transmission and distribution related content, and policies promoting the smart grid as well as issues that the renewable energy grid has raised in both the technical and legal aspects. Taiwan’s electricity supply system is made up of the northern, central and southern systems. The Transmission and distribution grid have been defined as a common carrier, maintaining state-owned monopoly. The smart grid has 6 main facets to promote, including smart generation and dispatch, smart transmission, smart consumers, smart grid electricity grid industry and the establishment of a smart grid environment. Due to the possible effects of the integration of renewable energy generated electricity, there is a vital need for the regulation of the grid’s management and skills.

To address the contradiction between large-scale grid integration of renewable energy and safe grid operation under the goal of carbon neutrality, this paper examines the adaptability and quantifiable contribution of multi-type renewable energy to smart grids. Through a literature review, this paper systematically examines the core attributes of smart grids, renewable energy grid integration technologies, and relevant research on carbon neutrality pathways. It finds that current research lacks analysis of regionalized multi-energy synergy and adaptation and a quantitative model for carbon reduction contributions. Using the Qinghai Province smart grid pilot project as a case study, this paper analyzes its intelligent dispatching system configuration, wind power/photovoltaic power integration scale (12 GW of wind power installed capacity and 8 GW of photovoltaic power installed capacity, with renewable energy accounting for 42%), and carbon reduction results (a 6% increase in renewable energy consumption will reduce carbon emissions by 1.8 million tons in 2023). The paper identifies issues such as delayed dispatching response (12% peak error), low output forecast accuracy (16% error), and gaps in carbon contribution assessment. The method of combining case analysis and data modeling is adopted to propose adaptive optimization strategies and construct a carbon emission reduction quantitative model. The research results can provide a practical basis for regional power grid planning and improve the theoretical system of the integration of carbon neutrality and smart grid.

This paper describes concepts and technical advantages and disadvantages of the distributed generation, micro and smart power grid as well as their relationships. The establishment of these three systems embodies collection and utilization of renewable energy, combination of renewable energy and power grids, and the sharing of renewable energy. The distributed generation is their foundation, and the micro and smart grid are a transition and the ultimate goal respectively. Baise Tiandong County was taken as a case study object to discuss how to design the distributed power, micro grid and smart grid in the urban planning.

Edge infrastructures, including edge computing servers, are increasingly powered by renewable energy and smart grid combined. Two-way energy trading allows the surplus or shortfall of renewable energy to be traded between a server and the smart grid, but is non-trivial due to randomly varying computation demands and renewables. This paper proposes a new online policy, namely, distributed online resource allocation and load management (DORL), which enables such an edge server and its serving devices to minimize their energy cost and energy consumption, respectively, in a fully distributed manner. The key idea is that we employ the stochastic dual-subgradient method to interpret the battery of the server as a virtual queue. Based on the virtual queue and task queues, the CPU frequencies of the devices and the edge server, the offloading transmit rates of the devices (to the server) and the energy trading decisions of the server (with the smart grid) are decoupled over time and among devices, and optimized on an ongoing basis. Furthermore, we prove that the DORL yields a feasible and asymptotically optimal solution with a cost-backlog tradeoff of <inline-formula> <tex-math notation="LaTeX">$[\eta, 1/\eta]$ </tex-math></inline-formula>. Simulations show that the DORL reduces the system cost by nearly 50&#x0025;, as compared to existing benchmarks.

This study presents a comprehensive bibliometric review of 136 academic publications on smart grids, microgrids, and semiconductor technologies in the context of sustainable energy management. Data were collected from the Web of Science Core Collection and analyzed using VOSviewer to identify intellectual structures, thematic clusters, and research trajectories. The results demonstrate the increasing prominence of semiconductor-enabled solutions in advancing renewable energy integration, grid optimization, and energy storage systems. Five major research themes are identified: renewable energy and smart grid integration; distributed microgrid systems; optimization models; control strategies; and system-level resilience and cybersecurity. The analysis reveals a temporal evolution from foundational engineering (2020–2021) to intelligent, digitally enhanced energy systems (2022–2025), with a growing emphasis on electric mobility, digital twins, and advanced energy management techniques, such as convex optimization. Beyond mapping trends, this study underscores critical research gaps in the non-English literature, multi-database integration, and practical deployment. The findings provide actionable insights for researchers, policymakers, and industry leaders by highlighting technological maturity, real-world applications, and strategic implications for energy transition. By aligning digital intelligence, semiconductor innovation, and sustainable energy goals, this review advances a forward-looking agenda for resilient and equitable energy systems.

Nowadays, the basic power grid technology has been relatively mature, but the increasing demand for electricity and the ever-changing mode of electricity consumption prompts us to constantly optimize the grid technology. And the smart grid, which combines computers, AI, and traditional electric power technology, is the trend of the development of power grid technology, which accelerates the development of the discipline, and generates a very large number of academic issues that are worth exploring. It is under this background that the 2024 International Conference on Smart Grid and Artificial Intelligence (SGAI 2024) was held in Guangzhou, China from January 12th to 14th, 2024. It existed as an international platform for academic communications between experts and scholars in the fields of smart grid and artificial intelligence. And it promoted the research and developmental activities in related fields and scientific information interchange among the participants, establishing connections for them to find global partners for potential collaboration in the future. After months of well preparation and hard work, the Proceedings of SGAI 2024 covering a bunch of excellent papers, having been checked through rigorous review to meet the requirements of publication, are smoothly published. These papers feature but are not limited to the following topics: Smart Grid and Distributed Energy, Intelligent Power Equipment, Intelligent Dispatch of Power Grid, Artificial Intelligence Modeling and Simulation, Intelligent Control, etc. We had about 100 participations both as speakers and participants, including scientists, researchers, industrial experts, students, and other practitioners. During the keynote speech part, each keynote speaker was given 30 – 40 minutes for keynote speech, including Prof. Junbo Zhang (South China University of Technology, China) on Using Digital Technology to Support the Safety and Operation Stability of the New-type Power System, Prof. Weinan Gao (Northeastern University, China) on Learning-based Output Regulation of Dynamic Systems and its Applications, Prof. Jinping Liu (Hunan Normal University, China) on Toward Intelligent Monitoring of Operational Conditions of Complex Processes, and Prof. Dr. Mohamed EL-Shimy (Ain Shams University, Egypt) on FACTS-Based Stabilization of Weakly Interconnected Microgrids Using Ga Tuning of POD. These speeches triggered heated discussions and a good number of informal talks among all the participants. We would like to express our gratitude to the organizers, keynote speakers, authors, and all the participants of SGAI 2024, for their fruitful work and contribution to the success of the Conference. We are also thankful to the reviewers for providing constructive criticisms, stimulating comments and suggestions on the manuscripts. Particularly, our special thanks go to Journal of Physics: Conference Series, for the endeavor of all its colleagues in publishing this paper volume. May this event be a spark that ignites many more new inventions in the fields of and related to smart grid and artificial intelligence! List of Committee Members are available in this pdf.

Artificial intelligence (AI) techniques, such as expert systems (ESs), fuzzy logic (FL), and artificial neural networks (ANNs or NNWs) have brought an advancing frontier in power electronics and power engineering. These techniques provide powerful tools for design, simulation, control, estimation, fault diagnostics, and fault-tolerant control in modern smart grid (SG) and renewable energy systems (RESs). The AI technology has gone through fast evolution during last several decades, and their applications have increased rapidly in modern industrial systems. This special issue will remain incomplete without some discussion on AI applications in SG and RESs. The paper will discuss some novel application examples of AI in these areas. These applications are automated design of modern wind generation system and its health monitoring in the operating condition, fault pattern identification of an SG subsystem, and control of SG based on real-time simulator. The concepts of these application examples can be expanded to formulate many other applications. In the beginning of the paper, the basic features of AI that are relevant to these applications have been briefly reviewed.

The management of decentralized energy resources and smart grids needs novel data-driven low-latency applications and services to improve resilience and responsiveness and ensure closer to real-time control. However, the large-scale integration of Internet of Things (IoT) devices has led to the generation of significant amounts of data at the edge of the grid, posing challenges for the traditional cloud-based smart-grid architectures to meet the stringent latency and response time requirements of emerging applications. In this paper, we delve into the energy grid and computational distribution architectures, including edge–fog–cloud models, computational orchestration, and smart-grid frameworks to support the design and offloading of grid applications across the computational continuum. Key factors influencing the offloading process, such as network performance, data and Artificial Intelligence (AI) processes, computational requirements, application-specific factors, and energy efficiency, are analyzed considering the smart-grid operational requirements. We conduct a comprehensive overview of the current research landscape to support decision-making regarding offloading strategies from cloud to fog or edge. The focus is on metaheuristics for identifying near-optimal solutions and reinforcement learning for adaptively optimizing the process. A macro perspective on determining when and what to offload in the smart grid is provided for the next-generation AI applications, offering an overview of the features and trade-offs for selecting between federated learning and edge AI solutions. Finally, the work contributes to a comprehensive understanding of edge offloading in smart grids, providing a Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis to support cost–benefit analysis in decision-making regarding offloading strategies.

The global transition to renewable energy aims to reduce environmental impacts and combat climate change, yet challenges arise due to the intermittent nature of renewable sources, complicating their integration into traditional power grids and requiring advanced management solutions. Smart grid technology presents promising capabilities to optimize renewable energy management, promoting both environmental sustainability and economic efficiency. This study evaluates the environmental and economic impacts of smart grid integration, fo- cusing on carbon emission reductions, enhanced energy efficiency, and cost savings for energy providers and consumers. Using Structural Equation Modeling via SmartPLS, data were collected and analyzed from various stakeholders engaged in renewable energy and smart grid applications, allowing a detailed assessment of the relationships between smart grid integration, environmental outcomes, and economic benefits. Results indicate that smart grid integration significantly reduces carbon emissions and improves energy efficiency by over 30% while economically, it yields substantial cost savings, cutting operational expenses by up to 25% over time. The SmartPLS analysis confirms a positive relationship between smart grid deployment and both environmental and economic outcomes, highlighting that smart grids not only support emission reductions but also deliver considerable financial benefits in renewable energy management. These findings offer important insights for policymakers and industry stakeholders, emphasizing the role of smart grids in advancing sustainable and economically viable global energy systems.

The urgent global shift from fossil fuels to renewable energy sources necessitates innovative solutions to address energy system management challenges. Smart grids, equipped with sophisticated infrastructures, play a crucial role in this transition. This study integrates Artificial Intelligence (AI) into smart grids to enhance their efficiency and reliability, directly supporting the United Nations Sustainable Development Goals (SDGs), particularly SDG 7 (Affordable and Clean Energy), SDG 9 (Industry, Innovation, and Infrastructure), and SDG 11 (Sustainable Cities and Communities). Employing a mixed-methods approach, the research utilizes historical and real-time data, applying machine learning algorithms such as Linear Regression, Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long ShortxTerm Memory (LSTM) for predictive accuracy in energy management. Optimization techniques like Genetic Algorithms and Particle Swarm Optimization (PSO) are also implemented for resource scheduling and grid balancing. The results demonstrate significant improvements, with an 11.76% increase in energy efficiency and grid stability, a 66.67% reduction in prediction errors, and a 20% decrease in operational costs compared to conventional systems. These enhancements highlight the transformative potential of AI in smart grids, promoting more efficient and sustainable energy utilization. The study concludes that AI-driven smart grids are pivotal in achieving the SDGs by providing scalable and efficient solutions for renewable energy integration, thereby fostering sustainable development and reducing environmental impacts.

With electricity market reform and the application scenarios of renewable energy and power demand response, the power system presents the characteristics of openness, uncertainty and complexity. The construction and application of smart power grid have become a trend. The application of artificial intelligence (AI) in smart grid provides powerful technical support for digital power network. Scenarios of AI in smart grid include power supply, power system optimization, power user behaviour analysis, fault diagnosis, etc. Although the application of AI in the smart grid faces many problems, such as insufficient data sample accumulation, insufficient reliability, imperfect infrastructure, lack of special algorithm for power industry, etc., on the whole, AI is a powerful tool to push smart grid into the new generation of power systems and energy networks.

Smart grid opportunities and applications in Turkey

Balanced development of smart grids is becoming an increasingly important issue for the energy sector's successful operation. This article provides a bibliographic review of publications in the study of renewable energy and smart grids' deployment parameters. A sample of works for 2009-2020 from the Scopus® database, which contains bibliographic information about scientific publications in peer-reviewed journals, books, and conferences, was selected for analysis. The authors identified three clusters of research areas using VOSviewer (version 1.6.15) in the context of the impact of geospatial parameters on smart grids' development. The first cluster consists of the financial, human, and temporal components of the geospatial factor of smart grid deployment. The authors found the largest number of links in the first cluster in terms of "costs" (a total of 29 links with an average impact of 9). The second cluster coincides with concepts related to geospatial information systems (GIS), digital storage, information systems, and cartographic information use. Research on renewable energy also belongs to the second cluster of publications. And the third cluster highlights all the concepts of smart grids by their technical types and in the context of optimization. The third cluster focuses on the ideas with the strongest link power. The results of the analysis of the Scopus® database allowed to determine the level and dynamics of scientific interest in the geospatial factors of the development of smart grids over the past 10 years. It is established that research in the field of geospatial factors of smart grid development is carried out by different countries, but the most active analysis of the impact of geospatial parameters on the development of smart grids in the following countries: USA, Canada and China. Based on the use of the Scopus® database, the article identified institutions and organizations that fund the study of geospatial factors and smart grids and made a significant contribution to the development of this topic.

The quick shift from fossil fuels to renewable energy sources like solar, wind, and hydro has brought new challenges in balancing energy generation, demand, and grid stability. Renewable energy is uncertain because it relies on changing environmental conditions. This makes accurate forecasting essential for reliable and efficient energy management. Recent developments in Artificial Intelligence (AI), especially machine learning and deep learning, have shown great promise in tackling these challenges by offering strong and flexible forecasting models. This paper looks at AI-based forecasting methods that improve the accuracy of renewable energy predictions and assist with effective grid management. It examines different approaches, such as neural networks, hybrid models, and probabilistic forecasting frameworks, considering their methods, performance, and suitability for various renewable energy sources. The paper also illustrates how AI-based forecasting helps with cost reduction, sustainability, and the integration of smart grid systems. It discusses limitations like data quality, computational needs, and model clarity, while proposing directions for future research. By bringing together existing advancements and pointing out key gaps, this study highlights how AI can change renewable energy management systems and support global sustainability goals.