Maximizing Cloud Provider Profit from Equilibrium Price Auctions

Chen

2014

Wireless Pers Commun

160

As mobile computing has been developed for decades, a new model for mobile computing, namely, mobile cloud computing, emerges resulting from the marriage of powerful yet affordable mobile devices and cloud computing. In this paper we survey existing mobile cloud computing applications, as well as speculate future generation mobile cloud computing applications. We provide insights for the enabling technologies and challenges that lie ahead for us to move forward from mobile computing to mobile cloud computing for building the next generation mobile cloud applications. For each of the challenges, we provide a survey of existing solutions, identify research gaps, and suggest future research areas.

Section: Cloud Pricingmentioning

confidence: 99%

Section: Cloud Pricingmentioning

confidence: 99%

A Survey of Mobile Cloud Computing Applications: Perspectives and Challenges

Chen

2014

Wireless Pers Commun

160

“…As one of major advantages of spot instances, many researchers pay attention to how can users utilize spot instances to reduce their monetary cost [9], [10], [11], [12], [13]. Besides the user cost, many works also focus on the pricing schema for maximizing the profi t of cloud providers [14], [15], [16], [17]. However, all above works do not consider the impact of pricing on future revenue.…”

Section: Related Workmentioning

confidence: 99%

Present or Future: Optimal Pricing for Spot Instances

2013 IEEE 33rd International Conference on Distributed Computing Systems

Dou

et al. 2013

The recent years witnessed rapid emergence and proliferation of cloud computing. To fully utilize the compute resources, some cloud operators provide spot resources. Spot resources allow customers to bid on unused capacity. However, pricing policy of spot resources should be carefully designed and the impact on both present and future should be considered. For the present, the cloud provider can set a higher price to gain extra revenue. For the future, higher price will shift more requests with lower prices to later time and reduce the revenue of future. Meanwhile, the quality of service should be considered either since bad QoS will incur loss of potential users.In this paper, we present a demand curve to model the impact of pricing on the present and future revenue. Then we formulate the revenue maximization problem as a time-average optimization problem. Next, since this basic model fails to provide information of service delay, we extend it to a more generalized one that ensures the worst-case delay of user requests. While the future knowledge of arrival requests is unknown, it is necessary to design online algorithms for the optimization problems. We apply Lyapunov optimization framework and design an effi cient online algorithm which dose not require any future knowledge of requests arrival. Evaluations based on real-life datacenter workload and Amazon EC2 Spot Price illustrate effi ciency of our algorithms.

“…In [10], a heuristic approach based on linear programming is proposed to maximize provider's profit as well as optimize its resource allocation. In [11], a user request is attached with a budget constraint as well as utility functions for all required resources such as CPU, memory and bandwidth, and then the optimal resource allocation and scheduling need to consider both factors.…”

Section: Related Workmentioning

confidence: 99%

Prioritizing and Scheduling Service Requests under Time Constraints

Dargahi

Bhuiyan

2014 IEEE International Conference on Services Computing

2014

This paper presents a game theoretic model and an iterative bidding framework for the service request prioritizing and scheduling problem in Software as a Service (SaaS) environments. We focus on a type of settings in which the service provider's existing capacity is over demanded and customers' service requests are constrained with completion times. To gain more profit, the provider needs to prioritize customers' requests based on their profitability and schedule as many profitable requests as possible. The prioritizing and scheduling problem is considered in a strategic setting in which customers' values on the service requests are their private information that is not known to the provider, which calls for economic based models.The key issue here is how to maximize economic social welfare across all customers given the presence of customers' selfinterests. We propose an iterative bidding framework as a multilateral negotiation platform for the service provider and its customers to allocate compute capacity among service requests. The proposed bidding framework is evaluated by a computational study. The data from the experiments show that the proposed approach produces near optimal solutions with moderate information revelation. It also scales well to large size problem instances.