Data-Driven Flexibility Capability Modeling of Internet Data Center Considering Task Dependency

The power consumption flexibility provided by the energy-intensive Internet data centers (IDCs) has been extensively studied as a potential solution for enhancing the flexibility of power systems. In IDCs, computational workloads are further divided into potentially interdependent tasks. To assess the power consumption flexibility of IDCs, it is necessary to consider the interdependency of computational tasks. However, there are no methods for deriving a task dependency-aware IDC load model that is easy to embed in the operation of power systems to fully utilize the power consumption flexibility of IDCs. To this end, this paper proposes a framework to derive a compatible task dependency-aware IDC load model. A linear IDC load model is formulated based on typical batch workloads given by a task dependency-aware clustering framework. Afterward, the Cost-Oriented Progressive Vertex Enumeration (COPVE) algorithm is proposed to derive an easy-to-embed IDC load model from the original linear model. Experiments show that the derived IDC load model accurately reflects the feasible region of the original IDC load model with fewer constraints compared with the model derived by the advanced Progressive Vertex Enumeration (PVE) algorithm.