NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series
This addresses a critical problem for network operators by providing accurate forecasts in high-stakes, heavy-tailed regimes, though it is incremental in applying modern AI to Mandelbrot-inspired statistical regimes.
The paper tackles forecasting for bursty and intermittent network telemetry time series, which are underexplored in AI, by introducing NetBurst, an event-centric framework that reduces Mean Average Scaled Error by 13–605x compared to strong baselines while preserving burstiness and improving clustering.
Forecasting on widely used benchmark time series data (e.g., ETT, Electricity, Taxi, and Exchange Rate, etc.) has favored smooth, seasonal series, but network telemetry time series -- traffic measurements at service, IP, or subnet granularity -- are instead highly bursty and intermittent, with heavy-tailed bursts and highly variable inactive periods. These properties place the latter in the statistical regimes made famous and popularized more than 20 years ago by B.~Mandelbrot. Yet forecasting such time series with modern-day AI architectures remains underexplored. We introduce NetBurst, an event-centric framework that reformulates forecasting as predicting when bursts occur and how large they are, using quantile-based codebooks and dual autoregressors. Across large-scale sets of production network telemetry time series and compared to strong baselines, such as Chronos, NetBurst reduces Mean Average Scaled Error (MASE) by 13--605x on service-level time series while preserving burstiness and producing embeddings that cluster 5x more cleanly than Chronos. In effect, our work highlights the benefits that modern AI can reap from leveraging Mandelbrot's pioneering studies for forecasting in bursty, intermittent, and heavy-tailed regimes, where its operational value for high-stakes decision making is of paramount interest.