Active rule learning using decision tree for resource management in Grid computing

摘要: Grid computing is becoming a mainstream technology for large-scale resource sharing and distributed system integration. One underlying challenge in the management. In this paper, active rule learning considered management computing. Rule very important updating rules an database system. However, it also difficult because of lack methodology support. A decision tree can be used to cope with problems arising semantic extraction, termination analysis set updates. Also our aim learn new attributes rules, such as time load balancing, regard instances real environment that provide. work, trees built parallel on training data sets based original set. Each learned reduced thence conflicting resolved. Results from cross validation experiments suggest approach may effectively applied learning.