WorkloadDiff: Conditional Denoising Diffusion Probabilistic Models for Cloud Workload Prediction

Weiping Zheng

doi:10.1109/TCC.2024.3461649

Return

WorkloadDiff: Conditional Denoising Diffusion Probabilistic Models for Cloud Workload Prediction

2024-10-01

PRE

DOI：10.1109/TCC.2024.3461649

Original

Original request for help

Save

Abstract

En 中文

Accurate workload forecasting plays a crucial role in optimizing resource allocation, enhancing performance, and reducing energy consumption in cloud data centers. Deep learning-based methods have emerged as the dominant approach in this field, exhibiting exceptional performance. However, most existing methods lack the ability to quantify confidence, limiting their practical decision-making utility. To address this limitation, we propose a novel denoising diffusion probabilistic model (DDPM)-based method, termed WorkloadDiff, for multivariate probabilistic workload prediction. WorkloadDiff leverages both original and noisy signals from input conditions using a two-path neural network. Additionally, we introduce a multi-scale feature extraction method and an adaptive fusion approach to capture diverse temporal patterns within the workload. To enhance consistency between conditions and predicted values, we incorporate a resampling strategy into the inference of WorkloadDiff. Extensive experiments conducted on four public datasets demonstrate the superior performance of WorkloadDiff over all baseline models, establishing it as a robust tool for resource management in cloud data centers.

Keywords:

Predictive models

Cloud computing

Diffusion models

Time series analysis

Data models

Hidden Markov models

Forecasting

Cloud workload prediction

diffusion models

resource management

resampling