Accurate cloud workload forecasting is pivotal for efficient resource management but remains challenging due to the highly volatile nature of workloads and sudden bursts. While 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%.
Blogger's Review: The SWIFT framework significantly enhances workload forecasting accuracy and efficiency through its innovative learnable wavelet path and multivariate interaction module, showcasing the powerful potential of convolutional networks in handling spatio-temporal data. Its advantages in complex pattern processing are worthy of broader application across various domains.