Providing efficient mechanism for allocation and management of resources is essential for realizing a computational grid. Since resource providers and consumers may be independent bodies in a computing grid platform, negotiation among these participants is
MDAs to Market-Oriented Grids . 46
2. FROM E-COMMERCE TO G-COMMERCE
As pointed out in [8], both e-commerce systems and market-oriented grids share a common objective because in both systems, business transactions are carried out via a network such as the Internet. While one envisions more specific types of products such as computational power, storage, and associated services to be traded in market-oriented grids, e-commerce systems generally and potentially deal with a wide range of products. In some cases, adapting an e-commerce system for one kind of product to be used in trading another product involves minor or perhaps minimal modifications. Hence, it seems plausible to think that (some) agents developed for e-commerce generally share some (or many) of the design principles for agents in market-oriented grids. For instance, an e-Negotiation agent shares the same objective as a negotiation agent in market-oriented grids because they are both expected to be designed to optimize utilities of buyers (resource consumers) or sellers (resource providers) through some forms of bargaining strategies. While the determination of their utility functions may not necessarily be similar, previously proven and useful negotiation strategies adopted by e-Negotiation agents can also be (potentially) adopted by negotiation agents in market-oriented grids. However, as discussed in section 2.1, there are additional design issues that may need to be addressed.
2.1. Resource Negotiation in a Computational Grid
Negotiation activities in a grid-computing platform are required because participating parties are independent bodies [8] with different policies, objectives and requirements. Through negotiation, players in a grid marketplace, i.e., resource owners (or service providers) and consumers [4], are given the opportunity to maximize their return-on-investment and minimize their cost (the price they pay) respectively. In addition, it is envisioned that negotiation in a market-oriented grid must take into consideration the following:
(i) the dynamics of the computing environment
(ii) the speed at which resources are allocated or de-allocated.
While factor (i) is an essential consideration because resources and services are constantly being added or removed from the grid [8, 16], factor (ii) is important because any delay incurred on waiting for a resource assignment is perceived as an overhead [3]. Both factors (i) and (ii) collectively help to define some of the design considerations of G-commerce negotiation agents listed as follows:
(i) market factors: To optimize their returns, G-commerce negotiation agents should consider factors such as opportunity and competitions
(ii) time constraint: G-commerce negotiation agents should be sensitive to deadlines (iii) tradeoff: To consider the tradeoff between the benefit of using a suboptimal (or slightly more expensive) resource that can be located and allocated more quickly and the benefit of using the best (or least expensive) resource which may be more difficult to acquire. Like time constraint, this consideration relates to the issue of overhead [3].
Although there are many existing e-Negotiation agents (eg, just to name a few: Kasbah
[17], Faratin et al. negotiation decision functions [18], Fuzzy e-Negotiation Agent (FeNA)
[19]), none of these agents was designed to take into consideration all the three design issues mentioned above. In Kasbah [17], relaxation of bids/offers is largely determined
ACM SIGecom Exchanges, Vol. 5, No. 2, November 2004, Pages 45–53.
(Market-oriented Process Organization of R&D) R&D 研发变革管理(Change ...(Market-Driven NPD Process Management) 研发项目管理(R&D Project Management)...
Market-driven energy pricing necessary to ensure China...It will be argued that a market-oriented ...At the same time, investment in grids annually ...
ON GRIDS AND SOLUTIONS FROM RESIDUAL MINIMIZATION by Hiroaki Nishikawa A dissertation...A little surprisingly, the grid movement driven by this simple minimizat...
A Market Mechanism for Energy Allocation in Micro-CHP Grids 微网能量的市场...A study from Emerging Energy Research [16] states that today wind power ...
热门文档