Real-Time Awareness Scheduling for Multimedia Big Data Oriented In-Memory Computing
Real-Time Awareness Scheduling for Multimedia Big Data Oriented In-Memory Computing
复制标题
DOI：
10.1109/jiot.2018.2802913
复制
发表时间：
2018-02
影响因子：
10.6
通讯作者：
Jianwen Xu;K. Ota;M. Dong
中科院分区：
文献类型：
--
作者：
Jianwen Xu;K. Ota;M. Dong
作为学术界和工业界最引人注目的研究热点之一，物联网（IoT）正在不断改变我们的日常生活，它将我们几乎可以想象的一切联系在一起。从家居、车辆到城市设施，所有这些智能事物都需要强大的管理和处理能力来处理大量不同内容形式的多媒体数据，如图像、音频和视频。如今，由于摩尔定律不再适用，传统的思维方式可能不足以面对爆炸式增长的数据量。因此，在本文中，我们采用内存处理的思想来解决物联网中实时多媒体大数据计算问题。我们在调度方法设计中应用闭环反馈，将所有设备的内存存储集成在一个三层网络结构中。此外，我们还考虑了不同实时需求层次和内容形式的各自条件。分析结果表明，与现有的调度方法相比，我们的调度方法可以实现更好的工作负载分配和更小的延迟。
As one of the most striking research hotspots in both academia and industry, Internet of Things (IoT) has been constantly changing our daily life by joining together nearly all we can imagine. From home furnishings and vehicles to urban facilities, all these smart things need powerful managing and processing capabilities to deal with mass multimedia data in different content forms such as images, audios, and videos. Nowadays, since Moore’s Law is no longer applicable, conventional thinking may not be adequate in facing the explosive growing amount of data. Hence, in this paper, we adopt the idea of in-memory processing to solve the problem of real-time multimedia big data computing in IoT. We apply closed-loop feedback in the scheduling method design to integrate in-memory storages of all devices within a 3-tier network structure. In addition, we consider the respective conditions of different real-time required levels and content forms. The analysis results show that our scheduling method can achieve better workload allocation with less latency in comparison of existing methods.