Privacy preserving clock auction for emergency demand response in colocation data centers

Abstract

Emergency Demand Response (EDR) is crucial for improving the grid reliability and for meeting the power demand during crisis. Power-hungry data centers have been facing an urge to reduce their consumption to meet the EDR. The energy reduction in colocation data centers which house servers for multiple tenants (e.g., Equinix) that are better targets for EDR is less explored than the energy reduction in owner-operated data centers (e.g., Google). Existing EDR mechanisms incentivize tenants energy reduction. Such designs can either be gamed by strategic tenants or untrustworthy colocation operators for illegal gains. These serious privacy concerns stand as barrier preventing the tenants' participation in EDR. This paper addresses such concerns by proposing a privacy-preserving and strategy-proof mechanism using descending clock auction. Privacy is protected by implementing homomorphic encryption for aggregation of energy through clock auction, where operator can only know the aggregate of the tenants' values or bids but not their individual private values or confidential information submitted to meet the EDR. We evaluate the privacy and performance of this scheme by formulation through descending clock auction, in which the amount of energy the tenants are willing to reduce for a given price to meet EDR is protected.