The ongoing transformation of electric power systems is driven by the increasing integration of renewable energy resources, the proliferation of distributed energy technologies, and the rapid advancement of digitalization. This tutorial presents a comprehensive overview of emerging trends and enabling technologies shaping the future energy landscape, including smart grids, microgrids, energy storage systems, artificial intelligence, Internet of Things (IoT), big data analytics, blockchain, and digital twin technologies. The tutorial discusses their roles in enhancing grid reliability, operational efficiency, flexibility, and sustainability while facilitating the large-scale integration of renewable energy sources. Furthermore, key technical, economic, regulatory, and cybersecurity challenges associated with the modernization of power systems are examined. The tutorial aims to provide researchers, engineers, and industry professionals with a holistic perspective on the technological developments and strategic directions that are defining the next generation of sustainable and intelligent energy systems.

Prof. Dr. Erdal Irmak, IEEE Senior Member, is a Professor of Electrical Engineering at Gazi University, Türkiye. His research interests include power system operation and control, renewable energy integration, smart grids, microgrids, energy storage systems, and the cybersecurity of critical infrastructures. He has authored more than 160 scientific publications, most of which are indexed in the Web of Science, and has led or participated in numerous national and international research and industrial projects. His recent work focuses on smart grid control, distributed energy resources, digital twin technologies, real-time energy management, and advanced power quality monitoring systems. Prof. Irmak serves as Editor or Associate Editor for several international journals and has held key organizational and technical roles in numerous IEEE-sponsored conferences. He currently serves as Head of the Smart Grids Graduate Program at Gazi University and teaches undergraduate and graduate courses in Electric Power Systems, Smart Grids, and Electrical Energy Distribution.

The rapid integration of renewable energy resources, distributed energy systems, electric vehicles, and intelligent sensing technologies has significantly increased the complexity of modern power systems. Traditional monitoring, control, and decision-making approaches are no longer sufficient to address the challenges posed by highly dynamic and data-intensive smart grid environments. Artificial Intelligence (AI) has emerged as a key enabling technology for improving the reliability, efficiency, resilience, and sustainability of next-generation power systems.

This tutorial provides a comprehensive theoretical overview of AI technologies applied to smart grids, covering the evolution from conventional Machine Learning techniques to modern Edge Intelligence paradigms. It introduces the fundamental concepts of Artificial Intelligence, including Machine Learning, Deep Learning, and Reinforcement Learning, and examines their roles in addressing key challenges in modern power systems. Major application areas such as load forecasting, renewable energy prediction, fault detection, predictive maintenance, power quality assessment, and intelligent energy management are presented through representative examples.

The transition from cloud-centric AI architectures to edge-based intelligent systems is also discussed, highlighting the advantages of Edge AI and TinyML for real-time, low-latency, energy-efficient, and privacy-preserving smart grid applications. In addition, emerging research topics, including Explainable AI (XAI), Federated Learning, Digital Twins, Graph Neural Networks, and Foundation Models, are introduced to provide participants with insights into future developments in intelligent power systems. Participants will gain a broad understanding of the current AI landscape in smart grids, its practical applications, and the technological trends that are expected to shape the next generation of autonomous, resilient, and data-driven energy systems.

Prof. Dr. Erdal Bekiroglu completed his undergraduate studies in Electrical Education at Gazi University in 1994 and received his M.Sc. and Ph.D. degrees from the Institute of Science and Technology, Gazi University, in 1998 and 2004, respectively. He served as a Research Assistant at Gazi University between 1996 and 2003. From 2004 to 2024, he worked as an Assistant Professor, Associate Professor, and Professor in the Department of Electrical and Electronics Engineering, Faculty of Engineering, Bolu Abant Izzet Baysal University. In February 2024, he joined Gazi University, initially with the Faculty of Engineering, Department of Software Engineering. He is currently a Professor at the Faculty of Technology, Department of Electrical and Electronics Engineering, Gazi University. His research interests include computer-controlled systems, electrical machine drives and control, smart grids, renewable energy systems, and artificial intelligence. He has served as Program Chair for the International Conference on Renewable Energy Research and Applications (ICRERA) and the International Conference on Smart Grid (icSmartGrid). He is a member of the Editorial Board of the International Journal of Smart Grid. Prof. Dr. Bekiroglu has published numerous journal and conference papers in his research areas. His key qualifications include expertise in vocational and technical education, the design and management of scientific projects, and academic leadership. He has also served as Head of the Department of Electrical and Electronics Engineering and as Secretary General of Bolu Abant Izzet Baysal University.

Smart grids represent one of the most critical cyber-physical infrastructures in modern society, combining power generation, transmission, distribution, advanced metering infrastructure, SCADA systems, industrial control systems, and digital communication networks into highly interconnected operational environments. While this integration improves efficiency, reliability, and real-time monitoring, it also expands the cyber attack surface of energy infrastructures and exposes them to increasingly sophisticated adversarial campaigns. In this context, cyber threat intelligence (CTI) offers a proactive approach for identifying threats, understanding adversary behavior, and strengthening smart grid security.

This training session examines smart grid security through a CTI-driven perspective across three dimensions. First, we establish the foundational asymmetry between IT and OT security models, emphasizing the safety, availability, latency, legacy system, and physical-impact constraints that shape smart grid defense. We survey the evolution of cyber threats targeting energy and industrial infrastructures, from Stuxnet and BlackEnergy to Industroyer, ransomware operations, supply-chain compromises, and recent state-sponsored activity against critical infrastructure, while mapping observed behaviors against the MITRE ATT&CK for ICS framework.

Second, we analyze how CTI can support smart grid protection through the collection, enrichment, correlation, and operationalization of intelligence from vulnerability databases, malware reports, incident disclosures, sectoral advisories, STIX/TAXII feeds, and information-sharing communities. Particular attention is given to extracting indicators of compromise, tactics, techniques, and procedures, targeted assets, attacker objectives, and potential operational impacts on substations, smart meters, SCADA components, remote terminal units, and grid communication networks. These intelligence outputs are examined in relation to risk assessment, detection engineering, threat hunting, incident response, and strategic decision-making.

Third, we consider the emerging role of large language models in smart grid CTI workflows. LLMs can assist analysts through automated TTP extraction from unstructured reports, multilingual intelligence processing, correlation of heterogeneous threat data, and retrieval-augmented generation architectures grounded in trusted CTI sources. At the same time, we critically address their limitations and adversarial implications, including hallucination, weak explainability, prompt injection, data poisoning, and the use of generative AI to scale reconnaissance, spearphishing, and social engineering against energy-sector personnel.

We conclude by identifying open research problems with high practical relevance: the absence of standardized benchmark datasets for smart grid CTI model evaluation, the unresolved tension between explainability requirements in safety-critical infrastructure and current LLM opacity, and the lack of mature governance and responsible disclosure norms for dual-use AI capabilities targeting energy systems. These gaps represent concrete opportunities for rigorous contribution at the intersection of smart grid security, cyber threat intelligence, operational technology defense, and AI safety.

Recep Ozbay received the B.Sc. degree in electrical and electronics engineering and the B.Sc. degree in business administration from Anadolu University, Eskişehir, Türkiye, in 2012 and 2013, respectively, and the M.Sc. degree in internet and information technology management from Afyon Kocatepe University, Afyon, Türkiye, in 2016. He is currently pursuing the Ph.D. degree in forensic sciences at Gazi University, Ankara, Türkiye. From 2012 to 2016, he was a Cybersecurity Researcher at the TÜBİTAK BİLGEM Cyber Security Institute, where he contributed to more than 30 projects for government and defense organizations and served as an instructor in licensed penetration testing and cybersecurity training programs. Since 2021, he has been a Freelance Security Researcher, focusing on AI-driven cybersecurity, open-source intelligence (OSINT) methodologies, and active cyber defense. His current research interests include large language models for cyber threat intelligence, adversarial defense strategies, and forensic applications of artificial intelligence.

Uraz Yavanoglu received the bachelor's degree in computer engineering from Atilim University in 2005, the master's degree in computer engineering from Gazi University, Türkiye, in 2009, and the Ph.D. degree in 2014. His main research fields are computer engineering and its applications in data security, large language models, machine learning, big data, and image processing. He has been an Assistant Professor with the Department of Computer Engineering, Faculty of Engineering, Gazi University, since 2014.

Modern smart grid systems heavily rely on power electronic converters for energy conversion, power flow control, and grid integration. These converters are widely used in renewable energy, battery storage, electric vehicle, and distributed generation applications.

Power electronic converters such as DC-DC converters, grid-connected inverters, and bidirectional converters operate under nonlinear and uncertain conditions. Load variations, renewable energy fluctuations, parameter uncertainties, and grid disturbances create major challenges for controller design and system operation.

Conventional control methods such as PI and PID controllers are still widely used due to their simple structure and practical implementation. However, these methods often exhibit limited performance under uncertain operating conditions, fast disturbances, and strong nonlinearities.

For this reason, advanced control methods have attracted considerable attention in power electronics and smart grid applications. Approaches such as model predictive control, adaptive control, robust control, nonlinear control, and sliding mode control have been widely investigated to improve dynamic performance, disturbance rejection, and system robustness. Among these methods, sliding mode control and higher-order approaches such as super-twisting sliding mode control offer strong robustness against disturbances and model uncertainties.

Intelligent control methods provide additional flexibility for converter systems operating under nonlinear and uncertain conditions. Fuzzy logic control has been widely applied in power electronics because of its ability to handle uncertainty and system nonlinearities without requiring highly accurate mathematical models. In addition to conventional fuzzy systems, Type-2 and Type-3 fuzzy approaches, neuro-fuzzy systems, and hybrid intelligent controllers offer improved adaptability and control performance in complex operating environments.

AI-enhanced approaches have opened new directions in converter control and energy management. AI methods are increasingly used to support controller tuning, predictive analysis, fault diagnosis, predictive maintenance, and system optimization. Machine learning, reinforcement learning, digital twin technologies, and data-driven optimization methods provide new opportunities for adaptive and autonomous converter operation.

This tutorial presents advanced, intelligent, and AI-enhanced control methods for power electronic converters used in smart grid applications. The tutorial begins with converter fundamentals and control challenges in renewable energy systems, battery energy storage systems, electric vehicles, and microgrids.

The tutorial then covers classical and advanced control methods, including PI/PID control, model predictive control, adaptive control, robust control, nonlinear control, and sliding mode control. Intelligent control methods, including fuzzy logic, Type-2 fuzzy systems, Type-3 fuzzy systems, and hybrid control structures, are also discussed.

The final part focuses on AI-enhanced methods for converter control and system monitoring. Topics include machine learning-assisted optimization, reinforcement learning-based control, fault diagnosis, predictive analytics, and digital twin-supported monitoring. Practical examples from photovoltaic systems, battery energy storage systems, EV charging systems, and smart microgrids are included throughout the tutorial.

This tutorial is intended for researchers, graduate students, engineers, and industry professionals working in smart grid systems, renewable energy systems, power electronics, and intelligent control applications. The tutorial aims to provide both theoretical background and practical insight into modern converter control methods for next-generation energy systems.

Dr. Korhan Kayisli is a researcher and faculty member at Gazi University. His research interests include power electronics, smart grid systems, renewable energy systems, intelligent control, and artificial intelligence applications in energy systems. He has authored numerous scientific publications in international journals and conferences in the areas of power electronics, smart grids, renewable energy systems, and intelligent energy management. His research focuses on power converter control, energy management, optimization, and AI-supported energy applications. Dr. Kayisli is an IEEE Senior Member and actively contributes to the academic community through research, editorial, and conference activities. He serves on the editorial boards of several international journals and has held organizing, technical committee, and program committee positions in many international conferences. His recent work focuses on intelligent energy systems, advanced power electronic applications, and AI-enhanced control methods for next-generation smart grid systems.

Engineers who work already years in the development of Renewable Energy Equipment know that the price of generated solar kWh is going gradually down and can reach very low levels. Unfortunately, the end user prices of energy are not lower and much more complex. The global energy system is to be regarded as a whole, not just the low price of renewable energy. In Portugal (and Spain) the renewable energy has shown in 2025 how fragile is that system.

The environment we have now is to be understood, no matter if it is human society’s fault or not, and to make right, not precipitated decisions. The environment is getting gradually worse as a place to live in, but the human population should not be forced to suffer. The renewables were announced as the only solution by Al Gore and Greta Thunberg, but are renewable energies THE solution that will save humanity? Should we put ALL public subsidies on randomly intermittent renewable energies? Is it a visionary or an ideological choice (again)? What is more, the highly haphazard and low portions of renewable energy require STORAGE. The result was the Smart Grid, in order to stabilize the unequal small producers with huge consumers, quite displaced in time. Is this combination Sustainable? Quite unlikely! Also because human beings and human societies still want to live — longer and healthy, all of them.

How to proceed, if we still want to continue with renewables, even though the feeling is of an ideology surrounding the “Energieverwendung”, i.e. the “Energy Transition”? Based on the available problems and solutions, the choices are very limited.

First choice — High power, hundreds of MW and MWh: hydropower, being renewable but not friendly to human beings and nature (drinkable water); or nuclear, not welcomed by many. This is like going back to classical dispatching, not likely for ever.

Second choice (maybe the only one) — Energy Storage. (A) Lowest power, a few kW and kWh: batteries, highly polluting, short life; or fuel cells, with similar problems. (B) Middle power: small nuclear reactors, not much different from the biggest brothers. Hydrogen power can be the solution, if it were not so expensive.

Hydrogen is claimed as a common future of the grid. Is it? It is necessary to analyze the future possibilities!

Stanimir Stoyanov Valtchev is a Professor (Professor Jubilado / Emeritus) in the Department of Electrical and Computer Engineering at the NOVA School of Science and Technology (Faculdade de Ciencias e Tecnologia), Universidade NOVA de Lisboa, Portugal, where his disciplinary area is Energy. His research interests include power electronics, energy harvesting from the environment, renewable energies, wireless energy transfer, and medical equipment. His representative publications include work on super-resonant converters and resonant power conversion published in IEEE journals.