Grid Commerce, Market-Driven G-Negotiation, and Grid Resource Management

Abstract

Abstract-Although the management of resources is essential for realizing a computational grid, providing an efficient resource allocation mechanism is a complex undertaking. Since Grid providers and consumers may be independent bodies, negotiation among them is necessary. The contribution of this paper is showing that market-driven agents (MDAs) are appropriate tools for Grid resource negotiation. MDAs are e-negotiation agents designed with the flexibility of: 1) making adjustable amounts of concession taking into account market rivalry, outside options, and time preferences and 2) relaxing bargaining terms in the face of intense pressure. A heterogeneous testbed consisting of several types of e-negotiation agents to simulate a Grid computing environment was developed. It compares the performance of MDAs against other e-negotiation agents (e.g., Kasbah) in a Grid-commerce environment. Empirical results show that MDAs generally achieve: 1) higher budget efficiencies in many market situations than other e-negotiation agents in the testbed and 2) higher success rates in acquiring Grid resources under high Grid loadings.

Evolving Fuzzy Rules for Relaxed-Criteria Negotiation

“…The negotiation protocol in [3], [5], [6], and [21] enhances the alternating offers protocol [10] by slightly relaxing the criteria for agents to reach a consensus. The relaxed-criteria negotiation protocol in this work is given in Section III-A.…”

“…Following [3], [5], [6], and [21], the negotiation activities among buyer agents and seller agents are specified as follows.…”

“…Whereas negotiation agents described in [3], [5], [6], and [21] are designed to reach agreements with more flexibility, the relaxed-criteria rules are manually constructed. This section describes an approach in which relaxed-criteria rules of MDAs are evolved as they negotiate in a series of different emarkets.…”

“…Whereas there is a huge literature on bargaining approaches based on game theory (e.g., [7]- [13]), and automated negotiation for e-commerce (e.g., [14]- [22]), in many of the existing negotiation agents, the decision to reach an agreement is made when the current (counter-)proposals of two negotiating agents coincide. Most of these agents (except for [3], [5], [6], [21], and [22]) were not designed with the flexibility to slightly relax their bargaining terms to reach a consensus more rapidly (and perhaps with more certainty) in the face of intense ne-gotiation pressure. In some applications (e.g., grid resource management [2]- [6]), being more successful in negotiating for resources more rapidly is a desirable property because any delay incurring on waiting for resources would be perceived as an overhead [2].…”

Strategic agents for multi-resource negotiation

“…This research provides a deep understanding of the influence of sophisticated negotiation mechanisms on individual agents' performance in dynamic environments, and hence contributes to the construction of effective problem-solving approaches in open environments. The proposed approach can be used for designing negotiation agents in many practical applications like service composition [34], Grid resource management [43], and supply chain [50].…”