A Two-Stage Auction Mechanism for Cloud Resource Allocation

The contemporary literature on cloud resource allocation is mostly focused on studying the interactions between customers and cloud managers. Nevertheless, the recent growth in the customers' demands and the emergence of private cloud providers (CPs) entice the cloud managers to rent extra resources from the CPs so as to handle their backlogged tasks and attract more customers. This also renders the interactions between the cloud managers and the CPs an important problem to study. In this paper, we investigate both interactions through a two-stage auction mechanism. For the interactions between customers and cloud managers, we adopt the options-based sequential auctions (OBSAs) to design the cloud resource allocation paradigm. As compared to existing works, our framework can handle customers with heterogeneous demands, provide truthfulness as the dominant strategy, enjoy a simple winner determination procedure, and preclude the delayed entrance issue. We also provide the performance analysis of the OBSAs, which is among the first in literature. Regarding the interactions between cloud managers and CPs, we propose two parallel markets for resource gathering, and capture the selfishness of the CPs by their offered prices. We conduct a comprehensive analysis of the two markets and identify the bidding strategies of the cloud managers.

Automated summary

This paper investigates the interactions between customers and cloud managers, as well as between cloud managers and CPs, proposing a two-stage auction mechanism and two parallel resource gathering markets. Innovations include handling heterogeneous customer demands, truthfulness as the dominant strategy, a simple winner determination procedure, and avoidance of delayed entrance issues.