A Multi-criteria Method for Resource Discovery in Distributed Systems Using Deductive Fuzzy System

Distributed systems are sets of independent computers which aimed for the purpose of decentralization. All the decisions in such systems are made in the completely distributed manner. For the extensive use and utilization of the full range of resources in the distributed systems, certain strategies are needed for discovering resources. Resource discovery refers to searching for and locating candidate resources for a task in the current work environment. However, search and inquiry should be done in accordance with the dynamicity and extension of the environment. Resource discovery is one of the most important challenges in distributed systems. Hence, in this paper, a fuzzy deduction system was used to propose a method for discovering a multi-criteria resource in distributed systems' context. By taking into account trust, bandwidth and speed as the input parameters, the proposed method allocates the most appropriate resource based on users' request and service-level agreement. The results obtained from simulations and the comparison of the proposed method with the other methods indicates that the degree of occupied bandwidth is significantly reduced. Also, system overhead had a descending trend due to the appropriate response time and the additional computation elimination approach. Consequently, users' satisfaction and the entire system efficiency are enhanced.