A Manufacturing SCOS Model (MSCOS) Based on the Similarity of Parameter Sequences Between Tasks and Service Composition

Abstract Service composition and optimal selection (SCOS) is a core issue in cloud manufacturing (CMfg) when integrating distributed services for complex tasks. Generally, set of recommended task parameter sequences (Tps) will be given publishing The similarity between the service sequence (SCps) Tps also reflects rationality composition. However, various evaluation models based on QoS have been proposed, ignoring SCps. Considering SCps an model, we propose SCOS framework called MSCOS. includes two parts: model algorithm both optimization selection. In numerical proximity geometric SCps, improving technique order preference by to ideal solution (TOPSIS) with grey correlation degree (GC), GC&TOPSIS (GTOPSIS). algorithm, improved flower pollination (IFPA) proposed achieve polyline characteristics fitness values population. Experiments show that MSCOS effect offer better performance than commonly used algorithms.