Optimization of Smart Grids and Renewable Energy Systems Using AI and Semiconductor Technologies

The world’s energy industry is experiencing a significant transformation due to increased energy consumption, the rise in renewable energy usage, and the demand for sustainability. This review paper explores the potential for transformation offered by Artificial Intelligence (AI) in improving energy infrastructure, specifically looking at how it can be used in managing smart grids, predicting maintenance needs, and integrating renewable energy sources. Machine learning (ML) and deep learning (DL) are crucial AI technologies that have become necessary for enhancing grid stability, reducing operational costs, and improving energy efficiency. AI-powered predictive maintenance has proven to lower unexpected downtime by 40%, while AI-based demand forecasting has reached prediction accuracy of 90%, allowing utilities to efficiently manage supply and demand. In addition, AI helps tackle the issues of fluctuating renewable energy by playing a key role in enhancing energy storage and distribution in nations like Denmark and the US. Moreover, cryptographic frameworks such as Elliptic Curve Cryptography (ECC) and Post-Quantum Cryptography (PQC) offer robust security measures to protect AI-driven energy systems. ECC provides lightweight, efficient encryption ideal for IoT-enabled grids, while PQC frameworks, like the SIKE algorithm, ensure long-term resilience against quantum computing threats, safeguarding critical infrastructure. Nevertheless, obstacles like limited data access, cybersecurity weaknesses, and financial limitations continue to hinder widespread AI implementation, especially in less developed areas. This review emphasizes the significance of adopting essential strategies such as smart grid development, public-private collaborations, strong regulatory frameworks, and standardized data-sharing protocols. It is essential to have strong implementation and monitoring systems, improved cybersecurity measures, and ongoing investment in AI research in order to fully harness AI’s ability to revolutionize energy systems. By tackling these obstacles, AI has the potential to significantly impact the development of a more enduring, productive, and flexible worldwide energy system, hastening the shift towards a renewable-focused energy landscape.

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.

Introduction: To date, a variety of studies have been published on the topic of long term energy system transition. Most studies on future energy systems, however, have a shorter time frame or adopt a supranational focus (e.g. the Energy Roadmap, 2011 or the World Energy Outlook, 2015). It then constitutes a sincere challenge to perform a national energy system transition study with as time horizon 2050 and covering a far-reaching transformation of the energy system. VITO, together with the FPB (Federal Planning Bureau) and ICEDD, performed a study to scrutinise the transition of the Belgian national energy system towards a future mix entirely based on renewable energy sources. The focus on renewable energy sources and on building a national energy system completely running on renewable energy can be traced back to three main concerns: – Climate change: Renewable energy sources (RES) are a major instrument in the fight against climate change as RES do not release (net) greenhouse gas emissions. – Security...

The intersection of artificial intelligence (AI) and renewable energy systems is transforming how energy is generated, distributed, and consumed. This paper explores AI's applications in three key renewable energy sectors: solar, wind, and green hydrogen. AI technologies such as machine learning, neural networks, and predictive analytics address critical challenges such as the variability and intermittency of renewable resources. Additionally, AI-enhanced renewable systems have broader implications, such as democratizing energy access, fostering economic growth, and aligning with global climate goals like the Paris Agreement and the United Nations' Sustainable Development Goals. By leveraging the synergies between AI and renewable energy, society can achieve a cleaner, more resilient, and equitable energy future, critical for combating climate change and promoting global sustainability. This paper highlights the transformative potential of AI while offering insights into overcoming barriers to its widespread adoption in renewable energy systems.

The increasing global demand for clean energy has driven the rapid integration of renewable energy sources such as photovoltaic (PV) and wind energy into the electrical grid. However, the intermittent and variable nature of these energy sources necessitates the development of highly efficient and reliable power conversion systems to ensure stable and high-quality power delivery. Multilevel inverters (MLIs) have emerged as a promising solution due to their capability to generate near-sinusoidal output voltages with significantly reduced harmonic distortion, lower electromagnetic interference, and minimal switching losses compared to conventional two-level inverters. This paper presents an in-depth study on the design and optimization of MLIs specifically tailored for renewable energy applications, including stand-alone and grid-connected PV systems, wind energy systems, and hybrid renewable setups. Key design considerations are explored, including the selection of suitable topologies such as diode-clamped, flying capacitor, and cascaded H-bridge inverters, each evaluated based on their performance metrics, cost, and scalability. Advanced modulation strategies, such as sinusoidal pulse-width modulation (SPWM), space vector pulse-width modulation (SVPWM), and selective harmonic elimination (SHE), are analyzed for their effectiveness in improving power quality and reducing harmonic distortion. Additionally, the role of voltage balancing techniques, thermal management systems, and wide bandgap (WBG) semiconductors in enhancing efficiency and reliability is discussed. Optimization techniques targeting efficiency improvement, power loss reduction, and enhanced fault tolerance are elaborated, alongside emerging trends in the use of artificial intelligence (AI) and machine learning (ML) for real-time control and predictive maintenance. Challenges in grid synchronization, fault detection, and control complexity are critically assessed, with potential solutions proposed to address these issues. The paper also highlights recent advancements in modular multilevel inverter designs and their applicability in distributed energy systems, energy storage integration, and microgrids. By synthesizing the latest research and technological advancements, this study provides a comprehensive framework for the design, optimization, and deployment of MLIs in renewable energy systems. The insights gained underscore the critical role of MLIs in facilitating the large-scale adoption of renewable energy and achieving global sustainability goals, while paving the way for future innovations in power electronics and renewable energy integration.

IoT applications for building energy management, enhanced by artificial intelligence (AI), have the potential to transform how energy is consumed, monitored, and optimized, especially in distributed energy systems. By using IoT sensors and smart meters, buildings can collect real-time data on energy usage patterns, occupancy, temperature, and lighting conditions.AI algorithms then analyze this data to identify inefficiencies, predict energy demand, and suggest or automate adjustments to optimize energy use. Integrating renewable energy sources, such as solar panels and wind turbines, into distributed systems uses IoT-based monitoring to ensure maximum efficiency in energy generation and use. These systems also enable dynamic energy pricing and load balancing, allowing buildings to participate in smart grids by storing or selling excess energy.AI-based predictive maintenance ensures that renewable energy systems, such as inverters and batteries, operate efficiently, minimizing downtime. The case studies show how IoT and AI are driving sustainable development by reducing energy consumption and carbon footprints in residential, commercial, and industrial buildings. Blockchain and IoT can further secure transactions and data in distributed systems, increasing trust, sustainability, and scalability. The combination of IoT, AI, and renewable energy sources is in line with global energy trends, promoting decentralized and greener energy systems. The case study highlights that adopting IoT and AI for energy management offers not only environmental benefits but also economic benefits, such as cost savings and energy independence. The best achieved accuracy was 0.8179 (RMSE 0.01). The overall effectiveness rating was 9/10; thus, AI-based IoT solutions are a feasible, cost-effective, and sustainable approach to office energy management.

I am proudly presenting this special issue to the professional communities of the world. Power electronics is an extremely important element in modern smart grid and renewable energy systems. Basically, it uses high-efficiency switching power semiconductor devices to convert and control electrical power with the help of dc-to-dc, dc-to-ac, ac-to-dc, and ac-to-ac converters that are applied extensively in industrial, commercial, residential, transportation, aerospace, military, and utility systems. Power electronics plays significant role in modern industrial automation and high-efficiency energy systems that include renewable energy systems (such as wind and photovoltaic), bulk energy storage, electric and hybrid vehicles, and energy-efficiency improvement of electrical equipment. In modern electric power grid, power electronics is indispensable in high-voltage dc (HVDC) system, static VAR compensators (SVCs), flexible ac transmission system (FACTS)-based active and reactive power flow control, uninterruptible power system (UPS), fuel-cell-based energy system, etc. After a dynamic technology evolution for nearly five decades, power electronics has now grown possibly as the most important technology in the 21st century. Currently, most of our energy comes from fossil fuels and nuclear power plants. Fossil fuels cause environmental pollution that causes global warming or climate change problems. Nuclear energy is clean in that respect, but it has safety and radioactive waste disposal problems. For these reasons, the whole world is now turning toward renewable energy, where power electronics is an indispensable ingredient.

A deep learning-based forecasting model for renewable energy scenarios to guide sustainable energy policy: A case study of Korea

Renewable energy (RE) has been identified as an appropriate response to climate change and fossil fuel depletion by many governmental bodies. It has shifted the energy industry towards renewable and sustainable energy systems over the last few decades. This expansion has also increased the demand of specialists for design, installation and maintenance of different RE systems. Most people working in this sector are not well trained or educated enough whereas some of them are not even aware of sustainability. This has shifted towards formulation, model, develop and incorporation of new courses and programmes that would provide sufficient knowledge and skill in the sustainable RE sector. Moreover, the implementation of these new RE courses shouldn’t be limited to engineering level but also focuses on providing basic knowledge to everyone working in this field. Hence, in the present study, two-course structures have been suggested, i.e. general course which would offer basic knowledge and awareness of different RE systems in school level (including primary, elementary, intermediate and secondary) and in the professional programmes (Industrial Training Institute (ITI), diploma, undergraduate, postgraduate and research). Moreover, adequate knowledge would be provided not only in the theoretical field but also in the practical field depending upon the level of programme. Furthermore, undergraduate, postgraduate and research levels students would be provided with a broad knowledge of science, engineering design, planning and implementation of RE systems, while ITI and diploma level would acquire skill development and training in the RE systems.

The energy domain worldwide is experiencing high transformative pressure due to the imperative of climate change and new opportunities brought by various rapidly evolving digital technologies. Particularly, this change is affecting smart grids (SGs), which are increasingly shifting toward utilizing renewable and distributed energy sources. The natural intermittency of these energy sources increases the complexity of SG operations, such as ensuring continuity of energy supply and demand response balancing. In mitigation of these challenges, the tools and complex approaches that digitalization can provide have shown themselves particularly advantageous. There is a solid body of work showing how technologies like the Internet of Things (IoT), distributed ledgers, edge and cloud computing, machine learning (ML), etc., can be applied to address a variety of technical and economic problems in the energy sector, emphasizing SGs. This paper presents the most comprehensive literature review to date on digitalization in renewable energy source-based SGs, synthesizing over 200 studies across data analytics, artificial intelligence and ML, digital twins, edge–fog–cloud computing, the IoT, advanced metering infrastructure, and distributed ledger technologies. Unlike previous reviews, which are often limited to a single technology or narrow application, this work provides a cross-technology synthesis linking technical and financial aspects, identifies consolidated research gaps, and proposes a unified research agenda. The review further highlights future trends, including large language models, 6G communications, and distributed autonomous organizations, and discusses their implications for both industry practice and academic research.

15 - Renewable energy and sustainable development: A global approach towards artificial intelligence

Machine intelligence or artificial intelligence (AI) helps in the transformation of green chemistry by improving the sustainable consumption and production. The present study specifically focuses on the green chemistry aspects as how AI technologies are used to enhance the chemical processing, utilization of environment friendly solvents, and even monitor the processing through real time techniques. Enhancements achieved in other areas include yield of the desired products in various reactions, decrease in amounts of waste produced, and improvement in energy consumption. Nevertheless, there are still some unexplored problems which are still relevant now included data quality problems, limitations on model interpretability, and AI interface with the current systems. AI technologies also face other challenges that are attributed to the economic nature, which includes high initial costs and challenges of proving viability of the investments. In the same aspect, standards and ethical issues should be observed when it comes for applying AI in chemical processes. Even more studies also point out about research opportunities to advance such as refining the underpinning data fusion techniques, to design the interpretable AI models, and to expand the potential applications considering the new fields such as biodegradable materials and renewable energy systems. Therefore, overcoming interdisciplinary collaborations and ethical issues will be vital to the development of AI for green chemistry. If these difficulties are to be met and AI’s potential harnessed, the chemical industry can go a long way toward making real improvements to a range of environmental and economic metrics.

Recently, renewable energy (RE) has become popular due to its benefits, such as being inexpensive, low-carbon, ecologically friendly, steady, and reliable. The RE sources are gradually combined with non-renewable energy (NRE) sources into electric grids to satisfy energy demands. Since energy utilization is highly related to national energy policy, energy prediction using artificial intelligence (AI) and deep learning (DL) based models can be employed for energy prediction on RE and NRE power resources. Predicting energy consumption of RE and NRE sources using effective models becomes necessary. With this motivation, this study presents a new multimodal fusion-based predictive tool for energy consumption prediction (MDLFM-ECP) of RE and NRE power sources. Actual data may influence the prediction performance of the results in prediction approaches. The proposed MDLFM-ECP technique involves pre-processing, fusion-based prediction, and hyperparameter optimization. In addition, the MDLFM-ECP technique involves the fusion of four deep learning (DL) models, namely long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), deep belief network (DBN), and gated recurrent unit (GRU). Moreover, the chaotic cat swarm optimization (CCSO) algorithm is applied to tune the hyperparameters of the DL models. The design of the CCSO algorithm for optimal hyperparameter tuning of the DL models, showing the novelty of the work. A series of simulations took place to validate the superior performance of the proposed method, and the simulation outcome emphasized the improved results of the MDLFM-ECP technique over the recent approaches with minimum overall mean absolute percentage error of 3.58%.

Two popular renewable energy sources of solar irradiation and wind speed usually offer amiable intervention, especially for rural electrification. They are useful in rural areas where the supply of electricity by the national grid infrastructure is not a viable option economically. By the gift of nature, multiple renewable energy sources are often available in those areas. Optionally, these renewable energy sources can be combined to help minimize the cost of energy production contingent on the cost of operation, the amount of energy produced, the load demand, and the environmental factors. The objective of this research task is to propose a framework for meeting the power load demand of consumers while optimizing the operational costs of hybrid renewable energy from solar and wind power. A nature-inspired/meta-heuristic optimization method is proposed in this framework, to minimize the cost of the hybrid energy subject to the required constraints from the renewable energy system. The proposed algorithm was applied to solve a hybrid energy problem. Experimentation with empirical data is conducted, and KSA is evaluated against other nature-inspired algorithms such as BAT and WSAMP with minus previous steps. The real-life data were collected in Ghana from energy farms in Accra, Kumasi and Navrongo. The efficacy of the energy optimization is found to be sensitive to the meta-heuristic algorithms (KSA, BAT and WSAMP with minus previous step). The experiment result shows that by using KSA algorithm in hybridizing solar and wind energy, the cost of electricity could be minimized and adequately meet the demand of consumers.KeywordsEdge computing deviceHybrid renewable energy systemIoT deviceKestrel-based search algorithmKestroidMeta-heuristic algorithm

The article is devoted to the study of the application of artificial intelligence technologies in law enforcement activities in Ukraine and the world. The purpose of the article is to analyze the international and domestic experience of using digital technologies in law enforcement activities, to identify the shortcomings of the legal regulation of the use of artificial intelligence in this area, to provide proposals for its improvement in Ukraine. It was found that one of the countries that is actively expanding the use of artificial intelligence and successfully introducing relevant technologies into public administration is China. The artificial intelligence system which is used in China called «Zero Trust». The purpose of using this system is to prevent the commission of corruption offenses. It is emphasized, that the disadvantage of the «Zero Trust» system is that artificial intelligence, identifying the cause of corruption, does not indicate the algorithms and principles of this process. At the same time, the experience of using artificial intelligence in the field of preventing and combating corruption in Ukraine is considered when carrying out automated verification of persons declarations of authorized to perform state and local government functions. Ways of improving legal regulation when conducting financial control of declarations using artificial intelligence technologies are proposed. It has been found that artificial intelligence is widely used in the USA to predict the prevalence and state of crime. It was emphasized that Ukraine also has experience in the application of artificial intelligence technologies in law enforcement activities. Artificial intelligence is used in the development and implementation of departmental specialized intelligent software, the implementation of operative and investigative actions (for the recognition of video objects observation by comparing images in social networks, etc). It was concluded that artificial intelligence and digital technologies help to quickly process large volumes of information in the investigation and prevention of criminal activity. Modern developments in the field of artificial intelligence and advanced digital technologies, which are implemented in foreign countries to prevent and fight crime, are of great importance for the improvement of legal regulation in this field in Ukraine.