Parameter tuning for a cooperative parallel implementation of process-network synthesis algorithms

• Published in: Central European journal of operations research Vol. 27; no. 2; pp. 551 - 572
• Main Authors: Bartos, Aniko, Bertok, Botond
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 13.06.2019; Springer; Springer Nature B.V
• Subjects: Algorithms; Business and Management; Combinatorial analysis; Mathematical optimization; Methods; Multiprocessing; Network synthesis; Operations research; Operations Research/Decision Theory; Optimization; Original Paper; Parameters; Production engineering; Tuning; Hungary; Graph and tree search; Process network synthesis; Parallel programming; P-graph; Parameter tuning
• ISSN: 1435-246X; 1613-9178
• DOI: 10.1007/s10100-018-0576-1

Process-network synthesis is the determination of the optimal network structure of a process system together with optimal configurations and capacities of the operating units incorporated into the system. The aim of developing more and more sophisticated solver algorithms is to find the optimum as fast as possible and increase the circle of practically solvable process synthesis problems. The P-graph framework can effectively reduce the number of structures to be examined and accelerate the computation searching for the optimum due to the exploitation of combinatorial characteristics of candidate solution structures. A cooperative parallel implementation of P-graph algorithms have been published recently to exploit the capabilities of multi-core and multiprocessor systems (Bartos and Bertok in De Gruyter Ser Logic Appl 1:303–313, 2015 ). The parallel implementation has increased performance significantly but this can be further improved by fine tuning the parameters of the parallel algorithm. Outcomes of experiments on parameter optimization are to be presented herein.