Abstract
Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral content, product launches, and user behavior degrade offline-trained models rapidly. Naive online learning recovers accuracy but incurs prohibitive per-step compute cost. We propose AdaptLSTM, an adaptive online framework that detects drift via validation-calibrated thresholds and applies selective, targeted updates. On the Alibaba Machine Trace, AdaptLSTM recovers 54\% of Naive Online's improvement at 20\% cost ($2.7\times$ efficiency, $p=0.002$ over 10 seeds). On the more volatile Container Trace, it achieves 96\% at 20\% cost ($4.8\times$ efficiency, $+75\%$ MAE reduction over Static). Unlike classical drift detectors (ADWIN, DDM, Page-Hinkley) which fail to trigger on regression-scale error streams, AdaptLSTM fires 42 times over 301 steps and outperforms matched-budget baselines. Wall-clock profiling shows $1.33\times$ throughput gain and 45\% update-time reduction. The framework is model-agnostic: identical Pareto patterns hold for LSTM, GRU, and Transformer backbones.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Miao, X., Yang, B., & Cai, Z. (2026). AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift. https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift
MLA 9
Miao, Xinhua, et al. "AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift." https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift.
Chicago (author–date)
Miao, Xinhua, Bowei Yang, and Zhengong Cai. 2026. "AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift." https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift.
Harvard
Miao, X., Yang, B. and Cai, Z. (2026) 'AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift', Available at: https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift.
Vancouver
Miao X, Yang B, Cai Z. AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift. https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift
IEEE
X. Miao, B. Yang, and Z. Cai, "AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift," https://omanscience.com/en/articles/adaptlstm-efficient-adaptive-online-learning-for-cloud-workload-forecasting-under-distribution-drift.