Safety in Multi-Agent Systems: Reputation Based on Dossier

نویسندگان

  • André Pinz Borges
  • Vanderson Botelho
  • Osmar Betazzi Dordal
  • Bráulio Coelho Ávila
  • Edson Emílio Scalabrin
چکیده

A multi-agent architecture possesses versatility when solving complex problems in various research fields. In open systems, in which agents are unknown to each other a priori, their trust relationship is an essential subject. Hence, we present a reputation model based on dossier, which grants authenticity and reliability of exchanged information to its participants. This model has been applied to a classical problem in the railway sector, e.g., to define economical driving plans for freight trains. At least three agents are placed for each station, to plan, operate and manage plans. Planning and management skills are conducted by stationary agents, and the operating skills are conducted by mobile agents. Each locomotive has in its on-board computer a container for accommodating agents and transport mobile agents, either to complete an assignment or return to the station of origin. Empirical results show that sharing experiences improves the efficiency of the generation of plans, and that the use of the reputation based on dossier guarantees the veracity of the testimonies, therefore decreasing the need to centralize the information.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

On the Simulation of Global Reputation Systems

Reputation systems evolve as a mechanism to build trust in virtual communities. In this paper we evaluate different metrics for computing reputation in multi-agent systems. We present a formal model for describing metrics in reputation systems and show how different well-known global reputation metrics are expressed by it. Based on the model a generic simulation framework for reputation metrics...

متن کامل

Comparing and Evaluating Metrics for Reputation Systems by Simulation

Reputation systems evolve as a mechanism to build trust in virtual communities. In this paper we evaluate different metrics for computing reputation in multi-agent systems. We present a formal model for describing metrics in reputation systems and show how different well-known global reputation metrics are expressed by it. Based on the model a generic simulation framework for reputation metrics...

متن کامل

Voltage Coordination of FACTS Devices in Power Systems Using RL-Based Multi-Agent Systems

This paper describes how multi-agent system technology can be used as the underpinning platform for voltage control in power systems. In this study, some FACTS (flexible AC transmission systems) devices are properly designed to coordinate their decisions and actions in order to provide a coordinated secondary voltage control mechanism based on multi-agent theory. Each device here is modeled as ...

متن کامل

Neural trust model for multi-agent systems

Introducing trust and reputation into multi-agent systems can significantly improve the quality and efficiency of the systems. The computational trust and reputation also creates an environment of survival of the fittest to help agents recognize and eliminate malevolent agents in the virtual society. The thesis redefines the computational trust and analyzes its features from different aspects. ...

متن کامل

Agent-based Modeling for Differentiated Admission in P2P systems Using Evolutionary Game Theory Focused on Ownership Reputation

P2P systems, which are composed of unknown agents, have many problems in data sharing and creating. The main problem is concerned with the absence of the proper incentive mechanism for cooperating and feeding the systems. If the participants of P2P systems are not supported by proper incentives for data sharing and creating, the systems will starve from resources through extinction of sharers a...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015