Goal-oriented graph generation for transmission expansion planning


Loading...

Date

2025-06-01

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

The electrification strategies that are being designed to meet sustainability objectives and rising energy demands pose significant challenges for power systems worldwide and require Transmission Expansion Planning (TEP). This study adopts a risk-informed approach to TEP, formulated as a multi-objective optimization problem that concurrently minimizes systemic risks and expansion costs. Given the intractability of this problem with conventional solvers, we turn to artificial intelligence techniques. In particular, we conceptualize power grids as graphs and introduce a goal-oriented graph generation methodology using deep reinforcement learning. We extend welfare-Q learning, a modified variant of Q-learning tailored to yield high rewards across multiple dimensions, by incorporating geometric deep learning for function approximation. This allows us to account for system security while minimizing grid expansion costs. Notably, system risk is evaluated by incorporating a Graph Neural Network (GNN) cascading failure meta-model into the proposed approach. The TEP method is applied to the IEEE 118-bus system, and the efficacy of this novel technique is compared against the state of the art. We conclude that the deep reinforcement learning method can compete with established methods for multi-objective optimization, identifying expansion strategies that improve system security at reduced costs. Furthermore, we test the robustness of the meta-model against topology changes in the transmission network, demonstrating its applicability to novel grid configurations.

Publication status

published

Editor

Book title

Volume

149

Pages / Article No.

110350

Publisher

Elsevier

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Transmission expansion planning; Power grid; Cascading failures; Multi-objective optimization; Deep reinforcement learning; Neural networks; Graph representation learning

Organisational unit

09452 - Sansavini, Giovanni / Sansavini, Giovanni check_circle

Notes

Funding

Related publications and datasets

Is cited by: