ASTFNet: An Adaptive Spatio-Temporal Fault Prediction Framework for Dynamic Edge Networks
- 1 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network and Service Management
- Vol. 23, 5107-5121
Abstract
Edge computing plays a critical role in supporting low-latency IoT applications, yet the susceptibility of edge nodes to faults can disrupt services and degrade Quality of Service (QoS). Fault prediction offers a proactive solution by identifying potential failures through spatio-temporal feature learning from historical observations. However, existing spatio-temporal prediction models are typically designed for fixed network topologies with predefined input-output structures, which limits their effectiveness in dynamic edge networks where nodes are frequently added or removed. Adapting these models to topology variations often requires full retraining or architectural redesign, resulting in substantial computational overhead and limited real-time applicability. To overcome these limitations, this paper proposes ASTFNet, an adaptive spatio-temporal fault prediction framework for dynamic edge networks. The framework integrates a spatio-temporal fault prediction model that incorporates node identity embeddings to enable flexible representation learning under evolving topologies and an adaptive fine-tuning mechanism that detects topology changes and performs targeted model updates without full retraining. Experiments on real-world datasets demonstrate that ASTFNet significantly reduces retraining time while maintaining high prediction accuracy and achieves robust performance under dynamic node additions and removals.Keywords
Funding Information
- Natural Science Foundation of Guangxi Zhuang Autonomous Region (2025GXNSFBA069393)
- Specific Research Project of Guangxi for Research Bases and Talents (AD25069071)
This publication has 40 references indexed in Scilit:
- Edge-Cloud-Assisted Multivariate Time Series Data-Based VAR and Sequential Encoder–Decoder Framework for Multi-Disease PredictionArabian Journal for Science and Engineering, 2025
- Short-term coalbed methane concentration prediction and early warning based on the STL-ENN-GRU hybrid modelEarth Science Informatics, 2025
- A survey of dynamic graph neural networksFrontiers of Computer Science, 2024
- Fault prediction of bearings based on LSTM and statistical process analysisReliability Engineering & System Safety, 2021
- A Survey on Cloudlets, Mobile Edge, and Fog Computing2021
- Energy-Aware Resource Scheduling with Fault-Tolerance in Edge Computing2019
- Temporal Convolutional Networks: A Unified Approach to Action Segmentation2016
- SPSRG: a prediction approach for correlated failures in distributed computing systemsCluster Computing, 2016
- Deep Residual Learning for Image Recognition2016
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998