Towards Detection of Bottlenecks in Modular Systems
This work addresses system efficiency issues for engineers and managers, but it appears incremental as it reviews and applies existing heuristic methods without introducing new techniques.
The paper tackles the problem of detecting bottlenecks in modular systems by examining basic approaches such as Pareto chart methods, multicriteria analysis, and clique-based fusion, with numerical examples provided to illustrate these methods.
The paper describes some basic approaches to detection of bottlenecks in composite (modular) systems. The following basic system bottlenecks detection problems are examined: (1) traditional quality management approaches (Pareto chart based method, multicriteria analysis as selection of Pareto-efficient points, and/or multicriteria ranking), (2) selection of critical system elements (critical components/modules, critical component interconnection), (3) selection of interconnected system components as composite system faults (via clique-based fusion), (4) critical elements (e.g., nodes) in networks, and (5) predictive detection of system bottlenecks (detection of system components based on forecasting of their parameters). Here, heuristic solving schemes are used. Numerical examples illustrate the approaches.