A solution framework for the long-term scheduling and inventory management of straight pipeline systems with multiple-sources. (March 2021)

• Record Type: Journal Article
• Authors: Tsunoda Meira, William Hitoshi; Magatão, Leandro; Neves Jr., Flávio; Arruda, Lúcia V.R.; Vaqueiro, Jonas Portugal; Relvas, Susana; Barbosa-Póvoa, Ana Paula
• Is Part Of: Computers & operations research. Volume 127(2021)
• Publication Date: 2021-03
• Subjects: Oil pipeline -- Scheduling -- Mixed integer linear programming -- Inventory management; Operations research -- Periodicals; Electronic digital computers -- Periodicals; 004.05
• DOI: 10.1016/j.cor.2020.105143
• Languages: English
• ISSNs: 0305-0548

Abstract

Highlights: A generic solution framework to solve multiple-sources straight pipeline systems. A rigorous inventory management for each product at each pipeline node. Precedence constraints as a novel strategy for the batch numbering and tracking. Pipeline and tank maintenance periods for the multiple-sources pipeline systems. Real-world straight pipeline instances with multiple-sources are addressed. Abstract: This paper addresses the long-term scheduling of pumping and delivery operations on straight multiproduct pipeline systems connecting multiple-sources to multiple-destinations. A generic solution framework is proposed, combining heuristic procedures and mixed integer linear programming (MILP) models. The pipeline scheduling problem is decomposed into two sub-problems: the allocation and sequencing of pumping operations of the initial source, and the scheduling of delivery operations and also pumping operations of the intermediate sources. An innovative execution procedure using a rolling horizon strategy is developed to solve both problems. We focus on a new discrete-time MILP model formulation, covering several operational aspects of real-world pipeline systems, such as rigorous treatment of forbidden sequences and preventive tank maintenance and pipeline maintenance periods, while considering rigorous inventory management during the scheduling horizon. The approach is validated by solving an illustrative example and two real-world based pipeline problems. Results show that the proposed framework is able to obtain solutions in reasonable run time with detailed inventory management and respecting several operational constraints of the system.