Abstract-Since huge power consumption of large data centers has become a crucial problem recently, power models, especially precise models, turn out to be important for service providers to learn about the application status in order to make wise decisions. In this paper, we focus on the power modeling of typical applications upon Linux platforms, including CPU-intensive applications, memory-intensive applications, and networkintensive applications. We established models for these different types of applications respectively based on the collection of massive realistic data and further calibrated these models. Error analysis was also given after comparing the computed values with the actual measured data. Finally, synthetic model for the hybrid application execution scenario was figured out and discussed.