DAWN – Data-driven Analysis and Optimization of Low Voltage Networks

The growing use of renewable energy sources and the shift towards electric mobility are causing greater fluctuations in the energy system. In order to maintain smooth operation, accurate real-time information is becoming increasingly important. However, there is currently a lack of high-resolution, up-to-date data on grid load, and many forecasting models rely on incomplete or inaccurate information, particularly with regard to PV systems, electric charging stations, and battery storage. These data gaps result in the suboptimal use of resources and incur additional costs, such as those associated with balancing energy.

DAWN’s goal is to optimize the use of resources in the energy system by consistently digitizing it and making effective use of existing and newly collected data. To this end, a robust data foundation will first be established to serve as the basis for more accurate forecasts and targeted operational decisions. The first step is to collect and analyze relevant measurement data, including that from smart meters and additional measurements in the low-voltage grid, if necessary. This information will then be incorporated into improved grid calculations and forecasting methods. Additionally, data-driven analysis and forecasting models are developed, identifying potential optimizations.

The project addresses questions that are essential for grid operators and energy suppliers alike, forming the basis for the development of an innovation ecosystem within the smart grid sector. For grid operators, the project investigates how smart meter data can be used to improve understanding of customer installation behavior, such as that of PV systems or electric vehicle charging points. The focus is on identifying characteristic system features and their impact on the grid, as well as developing synthetic load and generation profiles further. Additionally, the project analyzes elasticity, i.e., the potential flexibility in consumption and generation behavio

For energy suppliers, the focus is on using real-time data to more accurately predict the residual load within a balance group. This includes selecting and counting the number of customer installations from which live data should be collected and considering seasonal and situational fluctuations.

Additionally, the project is investigating the feasibility of establishing an Austrian competence center for smart grid data management based on the results.

Salzburg Research analyzes smart meter data to provide energy suppliers and network operators with relevant information.