The “POWERCAST” project, funded by FFG, aims to enhance the cost and supply efficiency of power grids by predicting and optimizing power loads using AI-supported forecasting models. RISC Software GmbH contributes its expertise to the development of new AI models and takes on the consortium leadership.
The overarching goal of the POWERCAST project is to facilitate the economically efficient and technically robust integration of large amounts of volatile renewable energy, especially wind and solar energy, into the Austrian power grid. For this purpose, a new adaptive AI model will be developed that integrates multiple updatable information sources to provide accurate load forecasts and insights into key influencing factors. The need is urgent: errors in load forecasts have significantly worsened over the years, as modeling techniques for energy systems have proven too static for influencing factors such as photovoltaic (PV) systems and electromobility, which are subject to constant change due to rapid technological progress. This leads to an increasing discrepancy between model predictions and actual conditions. These inaccuracies require costly, short-term adjustments, which ultimately burden not only energy suppliers but also end consumers, primarily in sectors with high energy consumption.
Urgent Need for Accurate Predictions for Energy Systems
The insufficient accuracy of current prediction models for volatile electricity production, such as wind and solar energy, leads to significant deviations between predicted and actual loads. These deviations not only strain grid stability but also incur additional costs for end consumers.
Goals of POWERCAST: Short-term Forecasts and Grid Stability
The following goals are focused on in POWERCAST:
- The first goal is to provide better short-term forecasts for grid operators to conduct daily checks for compliance with safety standards, particularly the n-1 criterion, whose assurance is already critical due to the high amounts of volatile renewable energy. These forecasts are also crucial for the economic efficiency of power grids, as they can potentially save millions of euros in balancing energy costs.
- The second goal addresses the development that many requested PV systems for residential buildings are not approved by the grid operator due to risks to grid reliability from high feed-in. These rejections hinder the energy transition and frustrate consumers. Through an early warning system for extreme loads, operators could dynamically restrict feed-in until the critical situation is over. As an advantage, no PV system would have to be rejected, paving the way for faster expansion of PV and thereby contributing to the faster achievement of Austria’s renewable energy goals.
In this context, POWERCAST aims to introduce a new paradigm in load forecasting that considers the dynamic nature of consumption and production structures in energy systems. It seeks to provide forecasting models that adapt to rapid changes in key factors such as producers and consumers within the considered area and can be transferred to new but similar scenarios and data using adaptive artificial intelligence (AI) methods.
Reducing Energy Costs and Utilizing New Energy Sources
The POWERCAST project has the potential to generate financial benefits and improve the sustainability of the energy system. By developing more accurate forecasting models, system-wide costs can potentially be reduced, and the integration of renewable energies facilitated. The project is clearly aligned with the EU’s goals of significantly increasing the share of renewable energy and achieving climate neutrality by 2050, and it will help address the current and future challenges in power grid optimization.
Partners
The consortium, RISC Software GmbH, LINZ NETZ GmbH, Austrian Power Grid AG, Energy Institute at Johannes Kepler University Linz, and HAKOM Time-Series GmbH, pools its expertise and resources to ensure the project’s success and is represented by the Federal Ministry for Climate Protection, Environment, Energy, Mobility, Innovation, and Technology and financed by the Austrian Research Promotion Agency (FFG) through the AI for Green 2023 call. The consortium combines competencies and experience in various fields such as data management, data analysis, energy economics, and management.
