Enhancing situational awareness in low-voltage grids through digital process twins and data-driven methods

The low-voltage power grid is experiencing significant transformations due to the integration of renewable energy sources and the introduction of new types of loads, including electric vehicles, electric heat pumps, and smart home systems. These developments add complexity and variability, posing significant challenges to conventional grid management methods. As a result, there is a growing need for digitalization, particularly in low-voltage grids, to support timely and informed decision-making by distribution system operators. In response, the implementation of digital technologies, particularly digital process twins, has emerged as a promising solution. Digital process twins provide a model of grid operations, capturing both manual and automated tasks. Digital process twins provide real-time simulation and analysis of the power grid, enabling operators to visualize and manage the grid's behavior effectively. By leveraging real-time data analysis and artificial intelligence, digital process twins facilitate a deeper understanding of grid operations, enhancing the ability to preempt potential issues and thus improving the grid’s stability and reliability. The core objective of this thesis is to enhance situational awareness within low-voltage grids by utilizing the advanced capabilities of digital process twins. This involves employing sophisticated data-driven methodologies to forecast potential critical scenarios and detect anomalies that could disrupt grid functionality, capabilities that are essential for adapting to new consumer behaviors, managing potential grid failures, and accommodating the variable nature of renewable energy sources. Moreover, this research addresses the growing complexity and operational demands of modern power systems, which often challenge distribution system operators' ability to maintain a comprehensive and accurate understanding of the grid state. These challenges can hinder their ability to attain the necessary level of situational awareness required to make informed decisions and respond effectively to incidents. This thesis aims to demonstrate how digital process twins can be strategically utilized to improve situational awareness in the low-voltage grid. By utilizing data and artificial intelligence-driven insights, this research aims to establish a foundation for a more resilient and efficient power system, ensuring the grid is well-equipped to meet the demands of an increasingly complex and rapidly evolving energy environment.