ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration
摘要
Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment new capacity is ready to serve traffic. In practice, this cold-start duration can vary substantially across environments and even across consecutive scale-out events. We present ADAPT (Adaptive Duration Approximation for Predictive Timing), an online EWMA estimator that tracks coldstart duration at runtime. ADAPT feeds a dynamic planning horizon, FH-OPT, into a Model Predictive Controller (MPC) that optimizes replica counts over a rolling window. Together, these components form a closed-loop proactive autoscaling design that adapts its lookahead based on measured provisioning delay. Evaluated across three policies (MPC+LSTM, MPC+Prophet, HPA) and six workload archetypes with five random seeds, MPC+LSTM achieves below 5% SLA violation on all workloads, compared with 7-19% for reactive HPA and up to 28.7% for MPC+Prophet on bimodal traffic.
引用
@article{arxiv.2605.15788,
title = {ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration},
author = {Himanshu Singh Baghel},
journal= {arXiv preprint arXiv:2605.15788},
year = {2026}
}
备注
9 pages, 5 figures, 3 tables. Includes reproducible simulation framework for proactive Kubernetes autoscaling with adaptive cold-start estimation and MPC-based scaling. Source code and experiment configurations available at: https://github.com/Himanshu21035/autoscaling_research