Evolving power system operator rules for real-time congestion management
Year: 2026
Type: article
Abstract: The growing integration of renewable energy sources and the widespread electrification of the energy demand have significantly reduced the capacity margin of the electrical grid. This demands a more flexible approach to grid operation, for instance, combining real-time topology optimization and redispatching. Traditional expert-driven decision-making rules may become insufficient to manage the increasing complexity of real-time grid operations and derive remedial actions under the N-1 contingency. This work proposes a novel hybrid AI framework for power grid topology control that integrates genetic network programming (GNP), reinforcement learning, and decision trees. A new variant of GNP is introduced that is capable of evolving the decision-making rules by learning from data in a reinforcement learning framework. The graph-based evolutionary structure of GNP and decision trees enables transparent, traceable reasoning. The proposed method outperforms both a baseline expert system and a state-of-the-art deep reinforcement learning agent on the IEEE 118-bus system, achieving up to an 28% improvement in a key performance metric used in the Learning to Run a Power Network (L2RPN) competition. • New genetic network programming variant that learns from data via reinforcement learning. • Hybrid graph and decision tree method provides clear decision logic and interpretability. • Time-efficient and scalable to large power grids with contingency scenarios and renewables. • Outperforms expert systems and deep reinforcement learning agents on the IEEE 118-bus system.
Source: Energy and AI
Authors: Ferinar Moaidi, Ricardo J. Bessa
Institutions: Universidade do Porto, INESC TEC
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,630
Awards: G5528393427, G6796382581
OpenAlex ID: W7118886200