Abstract

Large data centers can participate in demand response programs\ and receive financial benefits by reducing energy consumption upon utility's request. However, the existing research has only considered demand response by owner-operated data centers (e.g., Google), leaving out another distinctly different yet integral part of the data center industry --- multi-tenant colocation data centers (a.k.a., colocation or "colo"), where the space is shared by multiple tenants for housing self-owned servers. A major hurdle hindering colocation demand response is "split incentive": the colocation operator may desire demand response, but lacks control over the tenants' servers; the tenants, on the other hand, can reduce server energy consumption but may not desire demand response unless they are properly incentivized. In this paper, we present a first-of-its-kind study on colocation demand response and propose an incentive mechanism, called iCODE (incentivizing COlocation tenants for DEmand response), which breaks the split-incentive barrier for colocation demand response. iCODE allows the tenants to voluntarily bid for energy reduction when demand response is needed and receive monetary rewards if their bids are accepted. We formally model tenants' bids and how the colocation operator decides the winning bids to maximize total energy reduction without profit loss. We demonstrate the potential of colocation demand response by using a trace-based simulation to show that iCODE can significantly reduce energy consumption (e.g., up to over 50%) during demand response periods.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.