Boosted regression for predicting CPU utilization in the cloud with periodicity

Predicting CPU usage is crucial to cloud resource management. Precise CPU prediction, however, is a tough challenge due to the variable and dynamic nature of CPUs. In this paper, we introduce TrAdaBoost.WLP, a novel regression transfer boosting method that employs Long Short-Term Memory (LSTM) netwo...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2024-12, Vol.80 (18), p.26036-26060
Main Authors: Quoc, Khanh Nguyen, Tong, Van, Dao, Cuong, Le, Tuyen Ngoc, Tran, Duc
Format: Article
Language:English
Subjects:
Autoregressive models
Compilers
Computer Science
Interpreters
Periodic variations
Predictions
Processor Architectures
Programming Languages
Resource management
Statistical analysis
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Predicting CPU usage is crucial to cloud resource management. Precise CPU prediction, however, is a tough challenge due to the variable and dynamic nature of CPUs. In this paper, we introduce TrAdaBoost.WLP, a novel regression transfer boosting method that employs Long Short-Term Memory (LSTM) networks for CPU consumption prediction. Concretely, a dedicated Periodicity-aware LSTM (PA-LSTM) model is specifically developed to take into account the use of periodically repeated patterns in time series data while making predictions. To adjust for variations in CPU demands, multiple PA-LSTMs are trained and concatenated in TrAdaBoost.WLP using a boosting mechanism. TrAdaBoost.WLP and benchmarks have been thoroughly evaluated on two datasets: 160 Microsoft Azure VMs and 8 Google cluster traces. The experimental results show that TrAdaBoost.WLP can produce promising performance, improving by 32.4% and 59.3% in terms of mean squared error compared to the standard Probabilistic LSTM and ARIMA.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-024-06451-9