Nowadays, a large number of cloud services have been published and hosted by geo-distributed cloud data centers (Geo-2DCs). In spite of numerous benefits, those Geo-2DCs face significant challenges such as dynamic resource scaling where workload forecasting plays a crucial role in addressing such a challenge. High accuracy and fast learning are key indicators for workload forecasting and the literature has witnessed a lot of efforts. This work proposes an integrated forecasting method, equipped with noise filtering and data frequency representation, named Savitzky-Golay and Wavelet-supported Stochastic Configuration Networks (SGW-SCN), to predict the amount of workload in future time slots. In this approach, the workload time series is first smoothed by a Savitzky-Golay filter and then decomposed into multiple components via wavelet decomposition. With stochastic configuration networks, an integrated model is established to characterize statistical characteristics of both trend and detail components. Extensive results have demonstrated that the proposed method achieves higher forecasting accuracy and faster learning speed than typical forecasting methods.

With their fast development and deployment, the cloud data center providing a large number of service which has become the most import service of Internet.. In spite of numerous benefits, their providers face some challenging issues. Workload forecasting plays a crucial role in addressing them. Accuracy and fast learning are the key performances. Its consistent efforts have been made for their improvement. This work proposes an integrated forecasting method that combines Savitzky-Golay filtering and wavelet decomposition with Stochastic Configuration Networks to get the workload forcast in the next period. In this study, we adopt Savitzky-Golay filtering to smoothing a task number sequence, and then the smoothed series is decomposed into multiple components by wavelet decomposition. Based on them, integrated prediction model is for the first time established and the statistical characteristics of trend and detailed components can be well characterized. The results of our study demonstrate that the proposed method has better performance than some typical methods.

With the development of Information and Communication Technology (ICT), the service provided by cloud data centers has become a new pattern of Internet services. The prediction of the number of arriving tasks plays a crucial role in resource allocation and optimization for cloud data center providers. This work proposes a hybrid method that combines wavelet decomposition and autoregressive integrated moving average (ARIMA) to predict it at the next time interval. In this approach, the task time series is smoothed by Savitzky-Golay filtering, and then the smoothed time series is decomposed into multiple components via wavelet decomposition. An ARIMA model is established for the statistical characteristics of the trend and components, respectively. Finally, their prediction results are reconstructed via wavelet reduction and the predicted number of arriving tasks is obtained. Experimental results demonstrate that the hybrid method achieves better prediction results compared with some typical prediction methods including ARIMA and neural networks.