The methods of artificial intelligence (AI) have been used in the planning and operation of electric power systems for more than 40 years. In recent years, due to the development of microprocessor and data storage technologies, the effectiveness of this use has greatly increased. This paper provides a systematic overview of the application of AI, including the use of machine learning (ML) in the electric power system. The potential application areas are divided into four blocks and the classification matrix has been used for clustering the AI application tasks. Furthermore, the data acquisition methods for setting the parameters of AI and ML algorithms are presented and discussed in a systematic way, considering the supervised and unsupervised learning methods. Based on this, three complex application examples, being wind power generation forecasting, smart grid security assessment (using two methods), and automatic system fault detection are presented and discussed in detail. A summary and outlook conclude the paper.

The use of lithium-ion battery energy storage (BES) has grown rapidly during the past year for both mobile and stationary applications. For mobile applications, BES units are used in the range of 10–120 kWh. Power grid applications of BES are characterized by much higher capacities (range of MWh) and this area particularly has great potential regarding the expected energy system transition in the next years. The optimal operation of BES by an energy storage management system is usually predictive and based strongly on the knowledge about the state of charge (SOC) of the battery. The SOC depends on many factors (e.g. material, electrical and thermal state of the battery), so that an accurate assessment of the battery SOC is complex. The SOC intermediate prediction methods are based on the battery models. The modeling of BES is divided into three types: fundamental (based on material issues), electrical equivalent circuit (based on electrical modeling) and balancing (based on a reservoir model). Each of these models requires parameterization based on measurements of input/output parameters. These models are used for SOC modelbased calculation and in battery system simulation for optimal battery sizing and planning. Empirical SOC assessment methods currently remain the most popular because they allow practical application, but the accuracy of the assessment, which is the key factor for optimal operation, must also be strongly considered. This scientific contribution is divided into two papers. Paper part I will present a holistic overview of the main methods of SOC assessment. Physical measurement methods, battery modeling and the methodology of using the model as a digital twin of a battery are addressed and discussed. Furthermore, adaptive methods and methods of artificial intelligence, which are important for the SOC calculation, are presented. In paper part II, examples of the application areas are presented and their accuracy is discussed.

Climate change is driving the transformation of energy systems from fossil to renewable energies. In industry, power supply systems and electro-mobility, the need for electrical energy storage is rising sharply. Lithium-based batteries are one of the most widely used technologies. Operating parameters must be determined to control the storage system within the approved operating limits. Operating outside the limits, i.e., exceeding or falling below the permitted cell voltage, can lead to faster aging or destruction of the cell. Accurate cell information is required for optimal and efficient system operation. The key is high-precision measurements, sufficiently accurate battery cell and system models, and efficient control algorithms. Increasing demands on the efficiency and dynamics of better systems require a high degree of accuracy in determining the state of health and state of charge (SOC). These scientific contributions to the above topics are divided into two parts. In the first part of the paper, a holistic overview of the main SOC assessment methods is given. Physical measurement methods, battery modeling, and the methodology of using the model as a digital twin of a battery are addressed and discussed. In addition, adaptive methods and artificial intelligence methods that are important for SOC calculation are presented. Part two of the paper presents examples of the application areas and discusses their accuracy.

The methods of Artificial Intelligence (AI) have been used in the planning and operation of power systems for more than 40 years. In recent years, due to the development of microprocessor and data storage technologies, the effectiveness of this use has greatly increased. This paper provides a systematic overview of the application of AI including the use of Machine Learning (ML) to the power system. The potential application areas are divided into four blocks and the classification matrix has been used for clustering the AI application tasks. Furthermore, the data acquisition methods for setting the parameters of AI and ML algorithms are presented and discussed in a systematic way considering the supervised and unsupervised learning methods. Based on this, three complex application examples: wind power generation forecasting, smart grid security as-sessment (using two methods), and automatic system fault detection are presented and discussed in detail. Summary and outlook conclude the paper.

Zusammenfassung: Der Artikel befasst sich mit der Entwicklung intelligenter MicroGrids in lokalen Verteilungsnetzen und der dafür notwendigen Informations- und Kommunikationstechnik-Infrastruktur (IKT) und deren Rahmenbedingungen. Die geopolitischen und technischen Bedingungen für die Schaffung moderner Energiesysteme erfordern die Einführung fortschrittlicher Telemetriesysteme. Der Beitrag stellt das Konzept zweier realer Demonstrationssysteme vor, die für die Verwaltung und Kontrolle von Energiegeräten in Verteilnetzen sowie für den Energiefluss zwischen ausgewählten Punkten im Netz entwickelt wurden. Es werden zwei unabhängig voneinander arbeitende Systeme in Deutschland und Österreich vorgestellt, um die Integrität und Zuverlässigkeit des Betriebs von erneuerbaren Energie Anlagen zu erhöhen. In dem Artikel werden ebenfalls Lösungsszenarien und positive Aspekte der einzelnen getesteten Systeme vorgestellt. Der Artikel soll den Nachweis erbringen, dass die Flexibilität dieser Systeme bei der Anpassung an sich ändernde Netzparameter, Kundenverhalten und Anforderungen der Netzbetreiber erhöht werden muss.