Optimizing data center energy consumption via energy complementarity scheduling
Year: 2024
Type: article
Abstract: Data centers are facilities used to transfer, accelerate, display, compute, and store data on network infrastructure, characterized by high heat dissipation, stable operation, and high energy consumption. Gradually replacing fossil fuel power generation with renewable energy sources such as wind and solar energy is an effective way to reduce carbon emissions from data centers. However, it is also necessary to consider the response time of data center services and the stability of renewable energy sources. Based on a review of existing research, this paper proposes an energy supply solution for data centers that combines solar power generation, the purchase of thermal power, and self-purchased natural gas generation, especially in regions where solar energy is abundant but wind energy is insufficient. The analysis starts from the perspectives of both supply and demand to examine the energy supply and demand of data centers. Then, by integrating the concept of source-load matching, the paper adds an analysis of the correlation between the total output on the supply side and the load on the demand side in the optimization of multi-energy complementarity in data centers. Finally, through data simulation and result analysis, the results show that this model can improve the matching ability of various generators on the supply side to the demand side load, thereby reducing the operating costs of data centers.
Source: Energy Reports
Authors: Xuehui Liu, Guisheng Hou, Lei Yang
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,700
OpenAlex ID: W4404907121