Artificial Intelligence (AI) in Power Systems

Lecture 1 (40 min.)
Introductory talk on AI Use Cases Related to Grid Integration
Dr. Lea Boche (EPRI Europe, Ireland)

This presentation provides an in-depth examination of the transformative role artificial intelligence plays in integrating renewable energy sources into modern power grids. We will explore advanced AI applications designed to optimize grid management, improve the accuracy of solar and wind energy forecasting, and maintain grid stability in the face of fluctuating energy inputs. By highlighting practical implementations, this session will demonstrate how AI-driven solutions facilitate intelligent demand response, predictive maintenance, and coordinated operation of distributed energy resources—collectively supporting the development of a more resilient and sustainable energy infrastructure.

Discussion & Short Break (10 min)

Lecture 2 (40 min.)
The Autonomous Grid: Automation, Intelligence and the Future of Power Systems
– Hitachi’s View.
Dr. Milos Subasic (Hitachi Energy, Germany)

Digitalisation is redefining grid operations by replacing fixed, deterministic automation with data-driven, learning systems that keep pace with the twin pressures of rising renewable penetration and growing system complexity. The talk introduces a new “flexible operator” paradigm powered by three innovation streams: (1) machine-learning-based forecasting (“Nostradamus AI”) that delivers high-accuracy load, renewable and price predictions to optimise both real-time actions and long-term planning; (2) intelligent alarm management that clusters and filters alarm floods, reducing operator workload and shifting control rooms from reactive to proactive decision-making; and (3) GPU-accelerated grid analysis that compresses power-flow and security-assessment runtimes to seconds, enabling millisecond-scale situational awareness. Achieving these gains at scale demands open data models, interoperable APIs, and defence-in-depth cybersecurity across TSO–DSO boundaries. With energy-sector spending on AI projected to grow 3.7-fold in the next five years, collaborative, standards-based digital solutions promise to unlock the efficiency, resilience and flexibility required for a net-zero electricity system.

Discussion & Short Break (10 min)

Coffee Break

Lecture 3 (40 min.)
AI for Renewable Energy Forecasting
Ricardo Andrade (INESC TEC, University of Porto, Portugal)

The variability and uncertainty of renewable energy sources (RES) introduce significant challenges for power system management, making accurate forecasting essential. This session will begin with an overview of traditional forecasting methods, covering deterministic and probabilistic forecasts. We will then analyze how advanced feature engineering, particularly the use of spatiotemporal information from Numerical Weather Predictions, can improve the forecasting skill of these methods. The second part of the session will provide a closer look at ongoing research on collaborative forecasting at INESC TEC. This includes innovative techniques that combine market-based mechanisms with ensemble forecasting (i.e., based on data from different suppliers) to improve the precision and reliability of RES forecasts, supported by operational results.

Discussion & Short Break (10 min)

Lecture 4 (40 min.)
Trustworthy AI for Power Systems
Prof. Spyros Chatzivasileiadis (DTU, Denmark

In this talk, we introduce methods that remove the barrier for applying neural networks in real-life power systems. Up to this moment, neural networks have been applied in power systems as a black-box; considering the high risks associated with power system operation, this has presented a major barrier for their adoption in practice. This talk first presents a short overview of the use of AI in power systems, and methods that lead to explainable and trustworthy AI. It then introduces a rigorous framework for Trustworthy Machine Learning in power systems and introduces methods for (i) physics-informed neural networks for power systems, and (ii) obtaining provable guarantees for the neural network performance. Such methods have the potential to build the missing trust of power system operators on neural networks, and unlock a series of new applications in power systems and other safety-critical systems.

Discussion &  Short Break (10 min)

Short Break

Lecture 5 (40 min.)
AI for DER Integration and Flexibility Management
Dr. Gianluca Lipari (EPRI Europe, Ireland)

Artificial intelligence is rapidly transforming Europe’s energy sector by enabling smarter integration of distributed energy resources (DERs) and enhancing system flexibility. Projects like AI-EFFECT unite leading European organizations to develop, test, and validate AI-driven solutions for congestion management, multi-energy systems, and real-time grid optimization, positioning Europe at the forefront of digital energy innovation. By leveraging advanced AI and secure data-sharing platforms, energy utilities and operators can make their systems more efficient, resilient, and capable of supporting a high share of renewables while complying with robust regulatory standards. This discussion will introduce the most promising applications of AI in the distribution grid sector, touching on AI-EFFECT and the Open Power AI consortium.

Discussion & Short Break (10 min)

LUNCH