Hermann de Meer

Anna Volkova, Mahdieh Hatamian, Alina Anapyanova et al.

The emergence of artificial intelligence and digitization of the power grid introduced numerous effective application scenarios for AI-based services for the smart grid. Nevertheless, adopting AI in critical infrastructures presents challenges due to unclear regulations and lacking risk quantification techniques. Regulated and accountable approaches for integrating AI-based services into the smart grid could accelerate the adoption of innovative methods in daily practices and address society's general safety concerns. This paper contributes to this objective by defining accountability and highlighting its importance for AI-based services in the energy sector. It underlines the current shortcomings of the AI Act and proposes an approach to address these issues in a potential delegated act. The proposed technical approach for developing and operating accountable AI-based smart grid services allows for assessing different service life cycle phases and identifying related accountability risks.

Jan Stenner, Alexander Kilian, Sebastian Peitz et al.

This paper studies Reinforcement Learning as an online controller for curtailment-aware workload shifting in wind-turbine-integrated high-performance computing (HPC) data centers. We introduce a reproducible fixed-day simulation framework with synthetic wind and price signals and delayed completion feedback, designed to be extensible toward more complex scenarios. As a controlled benchmarking basis, we then focus on the minimal case with one wind turbine and one co-located data center. In this setting, pure Reinforcement Learning exhibits a pronounced credit-assignment problem and tends to underuse free wind energy early in the day. We therefore evaluate two complementary countermeasures: optimization-based Imitation Learning and potential-based Reward Shaping. Across multi-seed training and a 200-day test set, Proximal Policy Optimization (PPO) and a Soft Actor-Critic (SAC) variant with an additional on-policy update routine achieve strong empirical performance among learned policies, and both Imitation Learning and Reward Shaping provide improvements in relevant configurations. A performance gap to the optimizer remains, which is expected: the optimizer plans offline with full-day foresight, whereas Reinforcement Learning must decide online from current observations without future realizations. The benchmark and ablation results provide a transparent basis for extending the approach toward richer multi-site and continuous-time scenarios.