网格计算经济模型中的价格协商和管制  

Pricing Strategies for Grid Computational Economy

作　　者：吴健[1] 邓磊[1] 胡正国[1] 

机构地区：[1]西北工业大学计算机学院,陕西西安710072

出　　处：《西北工业大学学报》2008年第4期497-502,共6页Journal of Northwestern Polytechnical University

摘　　要：价格协商和管制是保证网格计算经济模型稳定和有效运行的基础。文中提出了一种计算经济的价格模型,包括价格协商和管制功能。价格协商中,实现了一个Tàtonnement的迭代过程。价格管制则采用以拉姆士定价为基础的最高限价管制模型。仿真实验表明,该价格模型比拍卖机制,在公平性、有效性和均衡性上都有更好的效果,同时也有助于提高交易量和吞吐量。Purpose. There exist already many pricing strategies for grid computational economy. The full paper begins with the discussion of a number of strategies mentioned in Refs. 2 through 7. We present our strategy which we hope is better than those discussed. In the full paper, we explain our strategy in some detail; here we just give a briefing. Our strategy consists of price negotiation and price regulation. The explanation in the full paper centers around two topics： （1） Tatonnement process, which implements the price negotiation between GSC （Grid Services Consumer） and GSP （Grid Services Provider）; in the Tatonnement process, pricing is dependent on the demand for resources in the market; （2） price regulation, which is based on the Ramsey Pricing and the Price cap proposed by Stephen Littlechild. Finally we performed computer simulations to compare the performance of our strategy with that of the auction model in Ref. 10 by Rich Wolski et al. The computer simulation results, shown in Table 1 in the full paper, show preliminarily that our strategy is better than that of Ref. 10 in that： （1） the throughput is higher by 28.6%, and （2） the average utilization ratio of CPU increases by18. 08%.

关 键 词：网格计算经济 T&tonnement过程 价格管制 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]