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

2025-11-07

AI Summary

To address the challenge of AI-based fault prediction models in smart grids failing to adapt to emerging fault types and operational domains amid dynamic grid evolution, this paper proposes ProDER—a continual learning framework integrating prototype-guided memory replay, feature-space regularization, and logit distillation. ProDER jointly tackles both class-incremental and domain-incremental learning challenges within a unified architecture. We design four progressive evaluation scenarios to simulate realistic grid evolution. Experimental results demonstrate that ProDER achieves exceptional stability: accuracy degradation is only 0.045 for fault-type prediction and 0.015 for domain (operational region) prediction—substantially outperforming state-of-the-art continual learning methods. By balancing plasticity and stability, ProDER establishes a scalable, incremental learning paradigm for long-term, reliable fault prediction in evolving smart grids.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Addresses AI model adaptation to new fault types in evolving smart grids
• Solves reliability issues in fault prediction under changing operational zones
• Overcomes performance degradation in continual learning for grid environments

Innovation

• Continual learning framework adapts to evolving smart grids
• Prototype-based replay integrates regularization and distillation
• Unified approach maintains accuracy in incremental scenarios