Associating+Memory+Through+CaseBased+Immune+Mechanisms+for+Dynamic+JobShop+Scheduling.pdfVIP

TSINGHUA SCIENCE AND TECHNOLOGY ISSN 1007-0214 10/21 pp422-427 Volume 9, Number 4, August 2004 Associating Memory Through Case-Based Immune Mechanisms * for Dynamic Job-Shop Scheduling YIN Wenjun (尹文君), LIU Min (刘 民)**, WU Cheng (吴 澄) Department of Automation, Tsinghua University, Beijing 100084, China Abstract: Knowledge plays an active role in job-shop scheduling , especially in dynamic environments. A novel case-based immune framework was developed for static and dynamic job-shop problems, using the associative memory and knowledge reuse from case-based reasoning (CBR) and immune response mechanisms. A 2-level similarity index which combines both job routing and problem solution characteristics based on DNA matching ideas was defined for both the CBR and immune algorithms. A CBR-embedded immune algorithms (CBR-IAs) framework was then developed focusing on case retrieval and adaptation methods. In static environments, the CBR-IAs have excellent population diversity and fast convergence which are necessary for dynamic problems with jobs arriving and leaving continually. The results with dy- namic scheduling problems further confirm the CBR-IAs effectiveness as a problem solving method with knowledge reuse. Key words: case-based reasoning; immune algorithm; 2-level similarity; machine learning; dynamic job- shop scheduling Introduction space increases. Another important but less reported learning met