STiFF-Net: Spatial-Temporal Insights via Image-Driven Feature Fusion for Workload Prediction in Intelligent Cloud Data Centers

作者：Yao Lu, Xiaoqin Yu, Siqi Li, Haowen Zheng, Jie Cui, Hong Zhong, Lu Liu, Geyong Min · 发表于：IEEE Transactions on Cloud Computing · 年份：2025 · DOI：10.1109/tcc.2025.3628344 · 被引用次数：1 · 研究领域：Cloud Computing and Resource Management、IoT and Edge/Fog Computing、Software System Performance and Reliability

The rapid growth of Cloud Computing, Artificial Intelligence, and Big Data cloud workloads, intensifying resource contention, operational costs, and carbon emissions due to underutilized data centers. Accurate workload prediction is thus for proactive resource management and improved utilization of Cloud data centers. However, traditional statistical and machine learning methods struggle with the dynamic, high-dimensional, and heterogeneous nature of cloud workloads. This paper proposes STiFF, a novel prediction framework that, for the first time in workload forecasting, transforms time series data into graph-based image representations to capture spatiotemporal dependencies. STiFF integrates three key modules: (1) a Two-Dimensional Moving Average Decomposition (2D-MAD) for trend smoothing, (2) a Global-Local Feature Extraction (GLE) module combining CNNs and Transformers for hierarchical pattern learning, and (3) a Multi-modal Feature Fusion (MFF) module leveraging attention mechanisms and partial prior knowledge. Extensive experiments on four real-world datasets demonstrate that STiFF achieves an average error reduction of 62.14%, with a maximum of 90.84%, and outperforms state-of-the-art methods in 84.375% of the evaluated cases.