Joint optimization of mission abort and system structure considering dynamic tasks

• Published in: Reliability engineering & system safety 2023-06, Vol.234, p.109128, Article 109128
• Main Authors: Zhao, Xian, Liu, Haoran, Wu, Yaguang, Qiu, Qingan
• Format: Article
• Language: English
• Subjects: Dynamic tasks; Mission abort; Mission reliability; System survivability; Warm standby
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2023.109128

•Designing mission abort policy for warm standby systems considering dynamic tasks.•Deriving mission reliability and system survivability analytically.•Constructing joint optimization models to determine the optimal solutions.•Comparing the cost performance of different policies. Mission abort has recently attracted considerable attention to enhance the safety of critical systems during the primary mission (PM). Most of the existing research focuses on mission abort policies for systems performing a deterministic PM, i.e., operating for a fixed mission duration or completing a specified amount of work. However, in practice, systems are commonly required to perform dynamic tasks. This paper first makes advancements by jointly optimizing condition-based mission abort policies and system structure for the l-out-of-n: G warm standby system, where the dynamic arrival of tasks with a random amount of work is considered. In such systems, some components are initially in active mode, and the remaining warm standby components provide fault tolerance. Two types of mission success criteria are considered and corresponding mission abort policies are proposed based on different decision criteria. Mission reliability (MR) and system survivability (SS) are derived using recursive methods, considering the random switching of the active, idle, and warm standby modes under dynamic arrival of tasks. Mission abort policies and system structure are jointly optimized to balance MR and SS with the objective of minimizing the expected total cost. An example of a multiprocessor system is presented to illustrate the proposed model.