基于Agent的分布式协商策略在供应链动态计划中的应用

在分布式协作环境中，多个商业实体或执行单元，为达成某一共同决策而进行有效地协商，提出一种基于Agent的分布式协商机制和算法。采用智能Agent技术，使各Agent代表各自商业实体或执行单元的利益与其他商业实体Agent为达成某一共同决策进行协商。协商机制中使用了偏好模型的概念，并将Agent的偏好及约束看作私有信息。算法中采用了建议的全局偏好评估和冲突消解。通过实例对提出的分布式协商算法进行了仿真。仿真结果说明，使用全局偏好评估可使协商结果从全局来看更为理想；使用冲突消解明显提高了协商的成功率。最后，分析并扩展了该分布式协商算法的应用范围。

Agent-based distributed negotiation algorithm for dynamic scheduling problem

To solve the problem of several different businesses entities with different objective preferences and constraints which negotiating for a common decision in a distributed collaborative environment,an Agent-based distributed negotiation mechanism and algorithm was proposed.Intelligent Agent technology was used in this mechanism,where each Agent represented a business entity's interest to negotiate with others for a common decision.Concept of preference model was used in this negotiation mechanism.Agent's preferences and constraints in preference model were regarded as private information.Proposed global preference evaluation and conflict resolutions during negation were applied in this negotiation algorithm.This distributed negotiation algorithm was simulated via an example.The result of simulations showed that the global preference evaluation for proposes has made the negotiation result much more optimal,and besides,the using of conflict resolution during negotiation improved negotiation's success rate evidently. Finally,this Agent-based distributed negotiation algorithm's application was analyzed and extended.