基于优化双层分解与差异化建模的数据中心CPU利用率预测OA
CPU utilization prediction for data centers based on optimized two-stage decomposition and differentiated modeling
针对数据中心中央处理器(CPU)利用率序列具有非线性、非平稳、多时间尺度耦合及高频扰动显著等特点,提出了一种基于优化双层分解、特征筛选与频段差异化建模的组合预测方法.首先,以谷歌数据中心2021年CPU利用率时序数据为研究对象,配置与其时间戳一致的28项气象环境特征,采用24 h滑动时间窗口构造监督学习样本,并按照时间先后顺序将3月、6月、10月和12月数据划分为训练集、验证集和测试集.其次,采用澳洲野狗优化算法对改进的自适应噪声完全集合经验模态分解参数进行寻优,实现原始序列的一次分解;根据各本征模态函数分量零交叉率的分布特征,将其重构为高频、中频和低频分量;进一步采用足球队训练算法优化变分模态分解参数,对高频分量进行二次分解,以提取细粒度波动特征.然后,采用轻量梯度提升机特征重要性排序与验证集决定系数曲线相结合的两阶段方法,为不同子序列分别确定最优输入特征集合.最后,对变化平稳、趋势性较强的中低频分量采用自适应核极限学习机进行预测,对波动剧烈、时序关系复杂的高频分量采用双向时间卷积网络-双向长短期记忆网络-多头自注意力组合模型进行预测,并将各子序列预测结果叠加重构得到最终的CPU利用率预测值.算例结果表明,两阶段特征筛选后,6月样本的平均绝对误差和均方根误差分别由0.026 0和0.032 5降至0.019 9和0.025 8,决定系数由0.824 3提高至0.887 5;所提模型在不同月份均表现出较高的预测精度和稳定性,其中10月和12月的决定系数分别达到0.963 1和0.903 3.研究结果表明,优化双层分解能够有效降低原始序列复杂度,差异化建模能够充分发挥不同预测模型在各频段上的优势,可为数据中心资源配置、运行状态评估及能耗分析提供参考.
The central processing unit(CPU)utilization series in data centers has the characteristics of nonlinearity,non-stationarity,multi-timescale coupling,and significant high-frequency disturbance.In view of these characteristics,a combined prediction method based on optimized two-stage decomposition,feature selection,and differentiated modeling across frequency bands was proposed.The CPU utilization time-series data of the Google data center from 2021 were selected as the research object.A total of 28 meteorological and environmental features consistent with the timestamps were configured.Supervised learning samples were constructed using a 24 h sliding time window,and data from March,June,October,and December were divided chronologically into training,validation,and test sets.The dingo optimization algorithm(DOA)was used to optimize the parameters of improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN),thereby achieving the primary decomposition of the original series.Based on the distribution characteristics of the zero-crossing rates of the intrinsic mode function(IMF)components,these components were reconstructed into high-,medium-,and low-frequency components.Furthermore,the football team training algorithm(FTTA)was used to optimize the parameters of variational mode decomposition(VMD),and secondary decomposition was performed on the high-frequency components to extract fine-grained fluctuation features.Subsequently,a two-stage approach combining light gradient boosting machine(LightGBM)feature importance ranking with validation-set coefficient of determination curves was used to determine the optimal input feature set for each subsequence.An adaptive kernel extreme learning machine was used to predict the medium-and low-frequency components with relatively stable variations and strong trends,whereas a combined bidirectional temporal convolutional network-bidirectional long short-term memory network-multi-head self-attention model was used to predict the high-frequency components with intense fluctuations and complex temporal relationships.The prediction results of all subsequences were superimposed and reconstructed to obtain the final CPU utilization predicted values.Case study results showed that after two-stage feature selection,the mean absolute error and root mean square error for the June samples decreased from 0.026 0 and 0.032 5 to 0.019 9 and 0.025 8,respectively,while the coefficient of determination increased from 0.824 3 to 0.887 5.The proposed model exhibited high prediction accuracy and stability across different months,with the coefficients of determination reaching 0.963 1 and 0.903 3 in October and December,respectively.The results indicate that optimized two-stage decomposition can effectively reduce the complexity of the original series,while differentiated modeling can fully leverage the advantages of different prediction models across frequency bands,providing a reference for data center resource allocation,operational status assessment,and energy consumption analysis.
朱虹谕;宋凯宇;武晓栋;黄亚松;刘一宁;张冬冬;张杰
内蒙古工业大学 新能源学院,内蒙古 鄂尔多斯 017010||内蒙古工业大学 风能太阳能利用技术教育部重点实验室,呼和浩特 010051||内蒙古工业大学 大规模储能技术教育部工程研究中心,呼和浩特 010051内蒙古工业大学 新能源学院,内蒙古 鄂尔多斯 017010内蒙古工业大学 新能源学院,内蒙古 鄂尔多斯 017010||内蒙古工业大学 风能太阳能利用技术教育部重点实验室,呼和浩特 010051广西大学 电气工程学院,南宁 530004内蒙古工业大学 新能源学院,内蒙古 鄂尔多斯 017010||广西大学 电气工程学院,南宁 530004内蒙古工业大学 新能源学院,内蒙古 鄂尔多斯 017010||内蒙古工业大学 风能太阳能利用技术教育部重点实验室,呼和浩特 010051||内蒙古工业大学 大规模储能技术教育部工程研究中心,呼和浩特 010051||内蒙古工业大学 内蒙古自治区新能源与储能技术重点实验室,呼和浩特 010051内蒙古工业大学 风能太阳能利用技术教育部重点实验室,呼和浩特 010051||内蒙古工业大学 大规模储能技术教育部工程研究中心,呼和浩特 010051||内蒙古工业大学 内蒙古自治区新能源与储能技术重点实验室,呼和浩特 010051||北京邮电大学集成电路学院,北京 100876
能源科技
数据中心CPU利用率预测优化双层分解特征筛选差异化建模算电协同
data centersCPU utilization predictionoptimized two-stage decompositionfeature selectiondifferentiated modelingcomputing-electricity coordination
《综合智慧能源》 2026 (8)
29-43,15
国家重点研发计划项目(2026YFE0211200)国家自然科学基金项目(52677064)内蒙古自治区自然科学基金项目(2026QC0364,2026QC0321)National Key R&D Program Project(2026YFE0211200)National Natural Science Foundation of China(52677064)Inner Mongolia Natural Science Foundation(2026QC0364,2026QC0321)
评论