SWIFT: Spatio-temporal Wavelet Integrated Forecasting Framework for Workload Traces
For cloud resource management, SWIFT provides a highly efficient and accurate forecasting method that handles volatile workloads and sudden bursts.
SWIFT achieves state-of-the-art accuracy in cloud workload forecasting with linear complexity, reducing prediction error by up to 31.04% and latency by 79.74%.
Accurate cloud workload forecasting is pivotal for efficient resource management but remains challenging as workloads are highly volatile and prone to sudden bursts. Although wavelets preserve temporal locality, rigid fixed bases struggle with complex patterns and isolated processing neglects critical spatial dependencies. To address this, we propose SWIFT, a pure convolutional framework designed for high-efficiency workload forecasting. We introduce a Learnable Cascaded Wavelet Path that reformulates the traditional fixed wavelet bases into adaptive convolutional operators, enabling precise, data-driven feature peeling. Complementing this, our Multivariate Interaction Module sequentially models inter-variable spatial and intra-variable feature interactions to stabilize and refine noisy workload states. Extensive experiments demonstrate that SWIFT achieves SOTA accuracy with linear O(L) complexity, reducing prediction error by up to 31.04% while cutting latency by 79.74%.