A Bayesian Network Approach to Estimating Software Reliability of RSG-GAS Reactor Protection System

S. Santoso, S. Bakhri, J. Situmorang


Reliability represents one of the most important attributes of software quality. Assessing the reliability of software embedded in the safety of highlycritical systems is essential. Unfortunately, there are many factors influencing software reliability that cannot be measured directly. Furthermore, the existing models and approaches for assessing software reliability have assumptions and limitations which are not directly acceptable for all systems, such as reactor protection systems. This paper presents the result of a study which aims to conduct quantitative assessment of the software reliability at the reactor protection system (RPS) of RSG-GAS based on software development life cycle. A Bayesian network (BN) is applied in this research and used to predict the software defect in the operation which represents the software reliability. The availability of operation failure data, characteristics of the RPS components and their operation features, prior knowledge on the software development and system reliability, as well as relevant finding from references were considered in the assessment and the construction of nodes on causal network model. The structure of causal model consists of eight nodes including design quality, problem complexity, and defect inserted in the software. The calculation result using Agenarisk software revealed that software defect in the operation of RPS follows binomial statistic distribution with the mean of 1.393. This number indicated the high software maturity level and high capability of the organization. The improvement of software defect concentration range on the posterior distribution compared with the prior’s is also identified. The result achieved is valuable for furtherreliability estimation by introducingnew evidence and experience data, and by setting up an appropriate plan in order to enhance software reliability in the RPS.


Reliability; Software; RSG-GAS; Bayesian network; Protection system

Full Text:


DOI: https://doi.org/10.17146/aij.2019.775

Copyright (c) 2019 Atom Indonesia

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.