Journal of Intelligent Manufacturing, 15, 131±140, 2004 # 2004 Kluwer Academic Publishers. Manufactured in The Netherlands. On-line maintenance job scheduling and assignment to resources in distributed systems by heuristic-based optimization KOSSI P. ADZAKPA, KONDO H. ADJALLAH*and FAROUKYALAOUI Institute of Computer Sciences and Engineering of Troyes Industrial Systems Optimization Group, Department of Industrial Systems Engineering, Troyes University of Technology±12, rue Marie Curie, BP 2060 10010 Troyes, France E-mail: kondo.adjallah@utt.fr Received April 2002 and accepted June 2003 A heuristic-based optimization algorithm is proposed in this paper for on-line scheduling and assignment of preventive maintenance jobs to processors, to minimize under availability constraints, on a given time-window, the total cost of the maintenance operations of a distributed system. This algorithm minimizes the cost of discharge of preventive maintenance tasks or jobs, while assigning the tasks along with balancing the processors load. It is shown that the problem is NP-hard. To solve it, the concept of job emergency is introduced and the priority rule for total ¯ow time (PRTF) criterion is used in an adapted heuristic job-scheduling model. In addition, the algorithm considers the constraints of precedence among consecutive standby jobs and their emergency. It is depicted the speci®c properties of the proposed heuristic allowing jobs scheduling in the right order. Computational results illustrate the ef®ciency of the approach implemented on different system con®gurations. Keywords: Processors allocation, multi-objective optimization, job scheduling, distributed system, ¯ow-time, availability, maintenance 1. Introduction In support for the optimum operation of a production system, related maintenance activities must be organized to operate at their optimum level of performance on the basis of appropriate job sche- duling and processors assignment. In many cases, these requirements are subject to cost, availability and real time constraints. Delay times relative to starting or completion dates of preventive jobs in maintenance activities as well as insuf®cient completion time credit assigned to preventive or corrective maintenance jobs due to production constraints lead in general to the deterioration of the reliability, maintainability, avail- ability and life time performance of production systems. The economic background related to the problem of on-line maintenance job scheduling and assignment to processor has led to an upsurge of research effort to ®nd appropriate solutions. Recent investigations in the ®eld of organizing maintenance jobs have focused on planning and scheduling of maintenance activities or jobs with different purposes: minimization of the queuing of maintenance jobs, allocation of repair men to jobs, economic renewal of components, optimal window assignment to maintenance operations, and maximi- zation of availability and reliability. These objectives are often coupled with job cost minimization. Investigations are focused on speci®c systems, *Author for correspondence.