4.7 Article

Robust Design Problem for Multi-Source Multi-Sink Flow Networks Based on Genetic Algorithm Approach

期刊

MATHEMATICS
卷 11, 期 18, 页码 -

出版社

MDPI
DOI: 10.3390/math11183902

关键词

flow network; robust design; MMSFNs; reliability optimization; genetic algorithm

向作者/读者索取更多资源

This study addresses the robust design problem for multi-source multi-sink stochastic-flow networks (MMSFNs) using a two-step approach. It formulates the problem as an optimization problem and proposes a sub-optimal solution based on a genetic algorithm (GA) involving two components. Extensive experimentation on different networks shows that the proposed solution is efficient.
Robust design problems in flow networks involve determining the optimal capacity assignments that enable the network to operate effectively even in the case of events' occurrence such as arcs or nodes' failures. Multi-source multi-sink flow networks (MMSFNs) are frequent in many real-life systems such as computer and telecommunication, logistics and supply-chain, and urban traffic. Although numerous studies on the design of MMSFNs have been conducted, the robust design problem for multi-source multi-sink stochastic-flow networks (MMSFNs) remains unexplored. To contribute to this field, this study addresses the robust design problem for MMSFNs using an approach of two steps. First, the problem is mathematically formulated as an optimization problem and second, a sub-optimal solution is proposed based on a genetic algorithm (GA) involving two components. The first component, an outer genetic algorithm, is employed to search the optimal capacity assigned to the network components with minimum sum. The second component, an inner genetic algorithm, is used to find the optimal flow vectors that maximize the system's reliability. Through extensive experimentation on three different networks with different topologies, the proposed solution has been found to be efficient.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据