| 摘要: |
| 工作负载的准确预测对于云资源管理至关重要. 然而, 现有预测模型通常使用固化结构从不同视角提取序列特征, 导致不同模型结构之间难以灵活组合以进一步提升预测性能. 提出一种基于软演员-评论家算法(soft actor-critic, SAC)的多视角工作负载预测集成框架SAC-MWF. 首先, 设计一组特征序列构建方法来生成多视角特征序列, 该方法能够以低成本从历史窗口生成特征序列, 从而引导模型关注不同视角下的云工作负载序列模式. 其次, 在历史窗口和特征序列上分别训练基础预测模型和若干特征预测模型, 以捕获不同视角下的云工作负载模式. 最后, 利用SAC算法集成基础预测模型和特征预测模型, 生成最终的云工作负载预测. 在3个数据集上的实验结果表明, SAC-MWF方法在有效性和计算效率方面表现优秀. |
| 关键词: 云计算 工作负载预测 强化学习 多视角工作负载 |
| DOI：10.13328/j.cnki.jos.007424 |
| 分类号:TP311 |
| 基金项目:国家自然科学基金(62472329, 62072342); 国家重点研发计划 (2022YFB3304300) |
|
| SAC-based Ensemble Framework for Multi-view Workload Forecasting in Cloud Computing |
|
ZENG Wen-Xuan1, YING Shi1, LI Tian-Gang1, TIAN Xiang-Bo1, JIANG Yu-Hong2, LIU Hu-Jie3, HAO Shi-Kui3
|
|
1.School of Computer Science, Wuhan University, Wuhan 430072, China;2.School of Computer Science, China University of Geosciences, Wuhan 430078, China;3.Hubei ChuTianYun Co. Ltd., Wuhan 430076, China
|
| Abstract: |
| Accurate workload forecasting is essential for effective cloud resource management. However, existing models typically employ fixed architectures to extract sequential features from different perspectives, which limits the flexibility of combining various model structures to further improve forecasting performance. To address this limitation, a novel ensemble framework SAC-MWF is proposed based on the soft actor-critic (SAC) algorithm for multi-view workload forecasting. A set of feature sequence construction methods is developed to generate multi-view feature sequences at low computational cost from historical windows, enabling the model to focus on workload patterns from different perspectives. Subsequently, a base prediction model and several feature prediction models are trained on historical windows and their corresponding feature sequences, respectively, to capture workload dynamics from different views. Finally, the SAC algorithm is employed to integrate these models to generate the final forecast. Experimental results on three datasets demonstrate that SAC-MWF performs excellently in terms of effectiveness and computational efficiency. |
| Key words: cloud computing workload forecasting reinforcement learning multi-view workload |
