作者: Zhi-Zhong Liu , Quan Z. Sheng , Xiaofei Xu , DianHui Chu , Wei Emma Zhang
关键词:
摘要: Mobile edge computing (MEC) makes up for the disadvantages of cloud computing, and has gained a considerable momentum recently. However, dynamically changing QoS always results in failures QoS-ware recommendation composition MEC services, which significantly negates advantages MEC. To address this issue, considering user-related service-related contextual factors various services scheduling scenarios, we propose two context-aware prediction schemes services. The first scheme is designed situations when are scheduled real-time, contains real-time estimation methods. One can estimate multi-QoS other fitted second future. This includes predict Finally, adaptive strategies developed light characteristics proposed According to these strategies, most appropriate method could be adaptively. Extensive experiments conducted validate our approaches demonstrate their performance.