【作者】 许丽媛；

【导师】 孟祥旭；

【作者基本信息】 山东大学 ， 计算机软件与理论， 2013， 硕士

【摘要】 当前全球化竞争不断加剧,企业要寻求新的发展,必须专注于自己的核心业务,将自己擅长的方面发挥到极致；同时,企业对于自己不擅长的业务可能需要借助于其他企业的制造服务和能力,因此企业间的资源共享和业务协作更加频繁。随着互联网的不断发展和在制造行业中的应用,网络化制造在一定程度上实现了交易的自动化,突破了空间地域对企业经营范围和方式的约束,降低了企业成本。但当前的网络化制造仍存在一些问题,如服务模式固定、没有实现制造资源动态智能的分配和共享等,这些问题限制了其进一步推广应用。云计算、物联网等新兴技术的快速发展为探索新的制造模式带来契机,一种新型的网络化制造模式——云制造应运而生。云制造模式中,各种分散的制造资源和能力均被封装为服务,用户以“按需使用”的方式使用各种服务,从而实现资源共享与业务协同。云制造模式基于市场机制实现服务过程,需要解决服务交易的问题。传统的电子交易方式如定价、拍卖交易模式在一定程度上实现了信息共享和交易操作的电子化。但是,云制造是一个开放式的动态环境,制造服务往往有多个属性特征,用户对服务不同属性有着各自的偏好需求,以上交易方式尚不能适应云制造中服务交易的需求。服务协商是一种灵活的交易方式,交易各方通过一个类似讨价还价的过程表达自己的需求和偏好。随着人工智能、Agent等技术的不断发展,自动协商成为目前制造资源和能力交易中普遍采用的方式。本文以制造企业之间的服务交易为背景,研究了基于Agent的自动服务协商,论文主要工作和创新点如下：本文提出一个面向云制造的服务交易框架,该框架支持基于Agent的多元化交易。交易中市场充分发挥撮合作用,首先表现在根据服务提供者和服务使用者注册的供需信息对交易进行初次撮合,对于协商交易,市场的撮合作用还体现在协商过程中,在本文提出的协商模型中,我们充分考虑了这一点。本文以云制造平台为中间Agent,提出一种基于同步提议的服务协商模型,服务提供者和服务使用者将各自的提议同步提交给中间Agent,由中间Agent经过判断对双方的交易进行撮合,通过这种方式,可以加快协商进程,并使交易双方不必担心暴露自己的交易偏好。协商过程中,使用遗传算法进化提议,提议基于时间和对方行为进行让步,体现了多Agent交互时相互适应和学习的特点。最后,本文以云制造服务平台为基础,结合基于同步提议的服务协商方法,实现了自动协商的相关模块,并对基于同步提议的双边自动协商模型进行了实验验证和分析。通过实验分析,验证了该模型的可行性和优越性。下一步的研究工作主要在描述分类服务、调整协商策略以保证双赢解等方面展开。更多还原

【Abstract】 With the increasing competition of globalization, the enterprises must focus on their core business and maximize their competitive advantages to seek long-term development. Concerning the business in which they are not professional, they may need the help of manufacturing services and capabilities from other enterprises. Thus resource sharing and business collaboration between enterprises becomes much more significant than ever. With the continuous development of the Internet, networked manufacturing appears. To a certain extent, it achieves automation of transactions, breaks through the geographical space constraints on the scope and manner of business and reduces the cost of enterprise. But some problems, such as fixed service model and inability to implement the allocation and sharing of resources dynamically and so on, still exist in current networked manufacturing domain, which limit its further promotion.The rapid growth of new technologies such as cloud computing and Internet of Things provides a new way to explore service modes in cloud manufacturing. Cloud manufacturing, which is a new networked manufacturing mode, is comings into being. Under the cloud manufacturing mode, various kinds of manufacturing resources and capabilities are encapsulated as services. The users achieve the integrated services in an on-demand way to realize resources sharing and business collaboration.Cloud manufacturing mode needs service trading based on market mechanisms. Traditional market mechanisms for e-commerce such as fixed-pricing and auctions can partly share information and trade electronically. Since cloud manufacturing is under an open and dynamic environments and the character of a service is often decided by multiple attributes, the mechanisms above cannot meet the requirements of multi-attribute based service trading.Negotiation is a flexible way for service trading. During the negotiation process, service providers and consumers express their own demands and preferences through bargaining. With the development of some technologies such as artificial intelligence and agent technology, automated negotiation mode is used generally in service trading. With the background of service trading between manufacturing enterprises, this thesis researches agent-based automated negotiation. The main contributions of the thesis are as follows: We present a service trading framework for cloud manufacturing which supports diversified trading based on agent technology. In service trading, the market plays a key role in the process of matching supply and demand between service provider and consumer. For service negotiation trade, the market also works in the negotiation process. We take full account of this in the proposed negotiation model.We propose a service negotiation model based on simultaneous offer. In this model, the cloud manufacturing platform serves as a third party mediator. Service providers and consumers send their offers to the mediator and then after evaluating these offers, the mediator will make proposals. In this way, the negotiation can be speeded up and both parties don’t need to worry about exposing their private information to their opponent. We used genetic algorithm to generate offer which considers both time and opponent’s behavior to compute concession. The algorithm reflects the adaptive and learning characteristics in multi-agent interaction.Finally, we implement the module of automated negotiation with the above method under the manufacturing information platform. Through theoretical and experimental analysis, the model proposed in this thesis is feasible and can work better than current alternating-offer bilateral negotiation model. Future work is mainly about how to describe detailed service and adjust the negotiation strategy to ensure a win-win solution.更多还原