Predictive Intent Maintenance with Intent Drift Detection in Next Generation Network
Chukwuemeka Muonagor, Mounir Bensalem, Admela Jukan
TL;DR
This work tackles maintaining deployed intents in Intent-Based Networking by introducing an intent drift detection module that leverages unsupervised time-series analysis. It evaluates seven ML models plus a greedy baseline to detect drift from network throughput data, identifying DBSCAN as the most effective in accuracy and latency. The results highlight tradeoffs between model accuracy, response time, and memory usage, and demonstrate the feasibility of predictive intent maintenance in IBN. The findings inform practical deployment choices and outline open directions for reducing false positives and extending drift detection to diverse intents.
Abstract
Intent-Based Networking (IBN) is a known concept for enabling the autonomous configuration and self-adaptation of networks. One of the major issues in IBN is maintaining the applied intent due the effects of drifts over time, which is the gradual degradation in the fulfillment of the intents, before they fail. Despite its critical role to intent assurance and maintenance, intent drift detection was largely overlooked in the literature. To fill this gap, we propose an intent drift detection algorithm for predictive maintenance of intents which can use various unsupervised learning techniques (Affinity Propagation, DBSCAN, Gaussian Mixture Models, Hierarchical clustering, K-Means clustering, OPTICS, One-Class SVM), here applied and comparatively analyzed due to their simplicity, yet efficiency in detecting drifts. The results show that DBSCAN is the best model for detecting the intent drifts. The worst performance is exhibited by the Affinity Propagation model, reflected in its poorest accuracy and latency values.