A Cross-Workload Power Prediction Method Based on Transfer Gaussian Process Regression in Cloud Data Centers

Nowadays, machine learning (ML)-based power prediction models for servers have shown remarkable performance, leveraging large volumes of labeled data for training. However, collecting extensive labeled power data from servers in cloud data centers incurs substantial costs. Additionally, varying resource demands across different workloads (e.g., CPU-intensive, memory-intensive, and I/O-intensive) lead to significant differences in power consumption behaviors, known as domain shift. Consequently, power data collected from one type of workload cannot effectively train power prediction models for other workloads, limiting the exploration of the collected power data. To tackle these challenges, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TGCP</i>, a cross-workload power prediction method based on multi-source transfer Gaussian process regression. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TGCP</i> transfers knowledge from abundant power data across multiple source workloads to a target workload with limited power data. Furthermore, Continuous normalizing flows adjust the posterior prediction distribution of Gaussian process, making it locally non-Gaussian, enhancing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TGCP</i>'s ability to handle real-world power data distribution. This method enhances prediction accuracy for the target workload while reducing the expense of acquiring power data for real cloud data centers. Experimental results on a realistic power consumption dataset demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TGCP</i> surpasses four traditional ML methods and three transfer learning methods in cross-workload power prediction.