Partially observable Markov decision processes for optimal operations of gas transmission networks. (July 2020)

• Record Type: Journal Article
• Authors: Compare, Michele; Baraldi, Piero; Marelli, Paolo; Zio, Enrico
• Is Part Of: Reliability engineering & system safety. Volume 199(2020)
• Publication Date: 2020-07
• Subjects: Partially observable Markov decision Processes -- Prognostics and health management -- Degradation state estimation errors -- Gas transmission network; Reliability (Engineering) -- Periodicals; System safety -- Periodicals; Industrial safety -- Periodicals; Fiabilité -- Périodiques; Sécurité des systèmes -- Périodiques; Sécurité du travail -- Périodiques; 620.00452
• DOI: 10.1016/j.ress.2020.106893
• Languages: English
• ISSNs: 0951-8320

Abstract

Highlights: We consider a Gas Transmission Networks (GTN) equipped with realistic PHM capabilities. PHM suffers from misclassification errors in the monitored equipment health states. GTN operation decisions depend on its health conditions and gas demand variation. GTN operation decisions are intertwined with maintenance decisions. The GTN O&M management is framed as a Sequential Decision Problem under uncertainty. Abstract: We develop a decision-support framework based on Partially Observable Markov Decision Processes (POMDPs) for the management of Gas Transmission Networks (GTNs) operations, encoding realistic degradation state estimations provided by Prognostics and Health Management (PHM) systems, while considering demand variations and the effects of the management decisions on the GTN degradation evolution. This Operation and Maintenance (O&M) framework allows optimally operating a GTN. Furthermore, the economic impact of using PHM systems with different accuracy levels can be estimated. The approach is shown with reference to a GTN of the literature.