A bi-objective model to optimize reliability and cost of system with a choice of redundancy strategies

• Published in: Computers & industrial engineering Vol. 63; no. 1; pp. 109 - 119
• Main Authors: Chambari, Amirhossain, Rahmati, Seyed Habib A., Najafi, Amir Abbas, karimi, Aida
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 01.08.2012; Pergamon Press Inc
• Subjects: Algorithms; Bi-objective; Electric communication systems; Genetic algorithms; Heuristic; Mathematical analysis; Mathematical models; MOPSO; NSGA-II; Optimization; Optimization algorithms; Redundancy; Redundancy allocation problem; Reliability; Resource allocation; Series–parallel systems; Strategy; Studies; Redundancy allocation problem; MOPSO; NSGA-II; Bi-objective; Series–parallel systems
• ISSN: 0360-8352; 1879-0550
• DOI: 10.1016/j.cie.2012.02.004

► We have developed a new bi-objective model for the redundancy allocation problem. ► Maximization of system reliability and minimization of total system cost are our objectives. ► To solve the model, NSGA-II and MOPSO are proposed. ► Parameter tuning is done by RSM. ► Six multi-objective metrics are used to analysis the performance of the algorithms. Reliability problems are an important type of optimization problems that are motivated by different needs of real-world applications such as telecommunication systems, transformation systems, and electrical systems, so on. This paper studies a special type of these problems which is called redundancy allocation problem (RAP) and develops a bi-objective RAP (BORAP). The model includes non-repairable series–parallel systems in which the redundancy strategy is considered as a decision variable for individual subsystems. The objective functions of the model are (1) maximizing system reliability and (2) minimizing the system cost. Meanwhile, subject to system-level constraint, the best redundancy strategy among active or cold-standby, component type, and the redundancy level for each subsystem should be determined. To have a more practical model, we have also considered non-constant component hazard functions and imperfect switching of cold-standby redundant component. To solve the model, since RAP belong to the NP-hard class of the optimization problems, two effective multi-objective metaheuristic algorithms named non-dominated sorting genetic algorithms (NSGA-II) and multi-objective particle swarm optimization (MOPSO) are proposed. Finally, the performance of the algorithms is analyzed on a typical case and conclusions are demonstrated.