Simulation of a Peer to Peer Market for Grid Computing
Simulation of a Peer to Peer Market for Grid Computing
复制标题
网格计算的点对点市场模拟
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
F. Ortuño
中科院分区：
文献类型：
--
作者：
U. Harder;F. Ortuño
本文研究了网格计算的点对点网络的市场经济。我们提出了一个P2P网络的模拟，其中节点要么需要资源，要么提供资源，例如CPU时间。我们研究了Erdős-Renyi和Barabasi-Albert网络类型的P2P网络的市场行为，这些网络类型从4,096个节点到1,048,576个节点不等。我们发现，利用和市场行为取决于网络类型，而不是规模。同样，不同的价格更新算法对价格发展的影响也不大，这更多是由网络类型决定的。我们还测量系统中的平均缓冲区大小和消息数量。对于Barabasi-Albert网络，我们发现每个节点的缓冲大小对系统中的价格发展有影响。研究结果对P2P网格计算系统（如全球开放网格）的设计者有指导意义。
In this paper we investigate the market economy of a Peer-to-Peer network for Grid Computing. We present a simulation of P2P network where nodes either require or offer resources, which can be thought as CPU time for example. We examine the market behaviour of the P2P network for Erdős-Renyi and Barabasi-Albert networks types of different sizes ranging from 4,096 nodes to 1,048,576 nodes. We find that utilisation and market behaviour depend on the network type but not the size. Similarly, different price update algorithms have little effect on the price development, which is more determined by the network type. We also measure the average buffer size and number of messages in the system. For the Barabasi-Albert network, we find that the buffer size of each node has an effect on the price development in the system. The results are useful to guide designers of P2P Grid computing systems, like the Global Open Grid.