Cloud Resource Demand Prediction using Differential Evolution based Learning

Today's digital world generates ample amount of data through interconnected heterogeneous devices that must be stored and processed efficiently for uninterrupted services. The distributed infrastructures have shown the capability of addressing the storage and computing issues of big data. The cloud paradigm is enabled with characteristics including multi-tenancy, on-demand, virtualization, scalability and many more. However, the cloud resources must be used efficiently to reduce power consumption and carbon footprints. This paper presents a workload prediction scheme based on differential evolution that can be used for effective virtual machine allocation. The forecast accuracy of the proposed scheme is evaluated over Google's real world trace and compared with existing state-of-art prediction approaches. We observed a significant reduction in forecast error upto 71% and 88% over back propagation and linear regression based forecasting approaches respectively.