ProDER: A Continual Learning Approach for Fault Prediction in Evolving Smart Grids

TL;DR

ProDER introduces a continual learning framework with a novel replay-based approach to improve fault prediction in evolving smart grids, maintaining high accuracy amid changing fault types and operational zones.

Contribution

The paper presents ProDER, a new replay-based continual learning method tailored for smart grid fault prediction, addressing the challenge of evolving environments.

Findings

ProDER outperforms existing CL techniques in fault prediction accuracy.

Achieves minimal accuracy drops of 0.045 for fault types and 0.015 for fault zones.

Demonstrates practical applicability for real-world smart grid fault prediction.

Abstract

As smart grids evolve to meet growing energy demands and modern operational challenges, the ability to accurately predict faults becomes increasingly critical. However, existing AI-based fault prediction models struggle to ensure reliability in evolving environments where they are required to adapt to new fault types and operational zones. In this paper, we propose a continual learning (CL) framework in the smart grid context to evolve the model together with the environment. We design four realistic evaluation scenarios grounded in class-incremental and domain-incremental learning to emulate evolving grid conditions. We further introduce Prototype-based Dark Experience Replay (ProDER), a unified replay-based approach that integrates prototype-based feature regularization, logit distillation, and a prototype-guided replay memory. ProDER achieves the best performance among tested CL techniques, with only a 0.045 accuracy drop for fault type prediction and 0.015 for fault zone prediction. These results demonstrate the practicality of CL for scalable, real-world fault prediction in smart grids.