Power Systems Transition Simulation Using Artificial Neural Networks and Surrogate Modelling

Authors:
Preprint
Publisher website
Google Scholar
Abstract
Transforming energy supply systems is vital for achieving a sustainable, carbon-neutral future. However, this transformation entails significant complexity, driven by the integration of carbon-free energy sources, tightly coupled technical and economic subsystems, and the need to ensure reliability, resilience, and affordability. Addressing these challenges requires advanced planning approaches capable of capturing uncertainty, multiple stakeholder perspectives, and system dynamics across temporal and spatial scales. In response, this article presents an integrated planning and operational framework that combines multi-actor, multi-criteria, and multi-stage stochastic optimization with surrogate modelling and artificial intelligence. The proposed approach enhances scalability, computational efficiency, and precision in the planning and operation of future energy systems. A case study illustrates its effectiveness in supporting high-resolution, uncertainty-aware decision-making.

This publication has 60 references indexed in Scilit: