Computer servers in cloud data centers are known to consume a huge amount of energy in their operations. For energy saving, load balancing has been used but it is only effective when CPU loads are predicted accurately. Noise in the energy consumption data is often a detrimental factor responsible for the CPU load prediction error. In prior arts, denoising has not been considered as an approach to subside the prediction error. Therefore, a novel prediction approach called CEEMDAN-RIDGE that is centered on denoising is proposed and reported in this paper. Firstly, CEEMDAN is applied to decompose the CPU consumption data which is in the form of a time series. The curvature similarity between a pair of the original series and its corresponding decomposed series is measured. By referencing to this similarity measure, an effective series is obtained from filtration of the noise series. The effective series after the noise series is filtered out is reconstructed to a new fitting curve for CPU load prediction. The prediction accuracy is further enhanced by doing some error correction called RIDGE, which is made possible by predicting the error a priori from the historical error data from the previous prediction. In order to validate CEEMDAN-RIDGE, a series of experiments are conducted with Google trace data. The experiment results show that the LSTM model using the proposed CPU load prediction approach outperforms other models significantly in three performance metrics: RMSE, MAE and MAPE.

众所周知，云数据中心中的计算机服务器在运行中会消耗大量能量。为了节能，已经使用了负载平衡，但是仅在准确预测CPU负载时才有效。能耗数据中的噪声通常是导致CPU负载预测错误的有害因素。在现有技术中，降噪尚未被认为是消除预测误差的方法。因此，本文提出并报道了一种以降噪为中心的新型预测方法CEEMDAN-RIDGE。首先，使用CEEMDAN分解时间序列形式的CPU消耗数据。测量一对原始序列及其对应的分解序列之间的曲率相似性。通过参考这种相似性度量，一个有效的序列是从噪声序列的过滤中获得的。滤除噪声序列后的有效序列将重建为一条新的拟合曲线，用于预测CPU负载。通过执行一些称为RIDGE的错误校正，可以进一步提高预测精度，这可以通过从先前预测的历史错误数据中先验预测错误来实现。为了验证CEEMDAN-RIDGE，对Google跟踪数据进行了一系列实验。实验结果表明，使用建议的CPU负载预测方法的LSTM模型在三个性能指标（RMSE，MAE和MAPE）上明显优于其他模型。通过执行一些称为RIDGE的错误校正，可以进一步提高预测精度，这可以通过从先前预测的历史错误数据中先验预测错误来实现。为了验证CEEMDAN-RIDGE，对Google跟踪数据进行了一系列实验。实验结果表明，使用建议的CPU负载预测方法的LSTM模型在三个性能指标（RMSE，MAE和MAPE）上明显优于其他模型。通过执行一些称为RIDGE的错误校正，可以进一步提高预测精度，这可以通过从先前预测的历史错误数据中先验预测错误来实现。为了验证CEEMDAN-RIDGE，对Google跟踪数据进行了一系列实验。实验结果表明，使用建议的CPU负载预测方法的LSTM模型在三个性能指标（RMSE，MAE和MAPE）上明显优于其他模型。