Operation optimization of data center based on multi-station integration

Abstract

With the rapid development and extensive application of Internet technology, the data information grows exponentially. The proposal of the multi-station integration mode not only provides effective assistance for the development of the big data industry, but also put forward a new direction for the energy-saving operation of data centers. This paper presents a cooperative operation architecture of the fusion station covering substation, data center and energy storage power station, and establishes a mixed integer nonlinear programming model which aims at minimizing the annual total cost. The analysis of the role of data migration and energy storage scheduling are carried out by case study. The calculation results showed that, the typical daily operation cost was reduced by 10.52% and the annual total cost was reduced by 5.96% after the implementation of the data migration and the energy storage scheduling. Results demonstrate that on the premise of satisfying the delay constraint, the complementary scheduling of each fusion station can be realized through a certain data migration strategy, hence reducing the cost. Furthermore, the energy storage scheduling can transfer the peak load to the valley load, thus significantly decreasing operation costs.