Artificial Intelligence-Based Multiscale Temporal Modeling for Anomaly Detection in Cloud Services

TL;DR

This paper introduces a novel Transformer-based multiscale temporal modeling approach for anomaly detection in cloud services, effectively capturing long-range dependencies and multi-granularity features to improve detection accuracy and robustness.

Contribution

It presents an integrated multiscale feature perception framework with an attention-weighted fusion mechanism within a Transformer architecture for enhanced anomaly detection in cloud environments.

Findings

Outperforms baseline models in precision, recall, AUC, and F1-score.

Maintains stability under various noise and perturbation conditions.

Effective in complex, high-dimensional cloud monitoring data.

Abstract

This study proposes an anomaly detection method based on the Transformer architecture with integrated multiscale feature perception, aiming to address the limitations of temporal modeling and scale-aware feature representation in cloud service environments. The method first employs an improved Transformer module to perform temporal modeling on high-dimensional monitoring data, using a self-attention mechanism to capture long-range dependencies and contextual semantics. Then, a multiscale feature construction path is introduced to extract temporal features at different granularities through downsampling and parallel encoding. An attention-weighted fusion module is designed to dynamically adjust the contribution of each scale to the final decision, enhancing the model's robustness in anomaly pattern modeling. In the input modeling stage, standardized multidimensional time series are constructed, covering core signals such as CPU utilization, memory usage, and task scheduling states, while positional encoding is used to strengthen the model's temporal awareness. A systematic experimental setup is designed to evaluate performance, including comparative experiments and hyperparameter sensitivity analysis, focusing on the impact of optimizers, learning rates, anomaly ratios, and noise levels. Experimental results show that the proposed method outperforms mainstream baseline models in key metrics, including precision, recall, AUC, and F1-score, and maintains strong stability and detection performance under various perturbation conditions, demonstrating its superior capability in complex cloud environments.