会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 45. 发明专利
    • A System and A Method for Big And Stream Data Analytics using Incremental Mapreduce Framework for Smart City
    • AU2021102317A4
    • 2021-07-01
    • AU2021102317
    • 2021-05-01
    • DHANANI JENISHMEHTA RUPARANA DIPTITIDKE BHARAT
    • DHANANI JENISHMEHTA RUPARANA DIPTITIDKE BHARAT
    • G06F9/50G06F17/00G06F21/64G06Q50/26G16Y10/40G16Y10/50G16Y10/60
    • Abstract The present disclosure relates to a system and a method for big and stream data analytics using incremental MapReduce framework for smart city. Internet of Things helps to boost-up smart services from data generating, monitoring, and visualization for intelligent decision making. However, generated data is huge in the size, high in velocity and continuous. This disclosure presented the general smart city architecture having the capability of handling of batch data and stream data. The reference architecture exploited the MapReduce to handle the large volume of data in distributed environment. Due to high latency, MapReduce cannot utilize for the real-time analytics. This disclosure also presented the incremental MapReduce based modeling to process stream data for realtime analytics in smart city architecture. The proposed incremental MapReduce framework performs the in memory processing to reduce the latency and it utilizes the hash based grouping that reduces the CPU cycles and I/Os. InutData StemData Monute Storage Processing Module Unit Collector Unit 102 104 106 108 Figure1 olectingdata athighvelacityfrommanyapplicatisconsists awe bservices,1nternetofthings 2Q2 and various social networks. HandlinglargevalumefdatabydiAdingfileinttheblcksandtherebystedringveracluster of hardware with redundarcytachievefaulttlerancefor bath Map Reduce and incremental 204 MapReduce. Managingincomingcontinuousstream datafrom varioussourcsfor real-time analytics by 206 employirgastreamcollector. Dividingcollected stream data inta small blacs and thereafterallocating toan in put bufferaf 208 Mappersforincremental procssing. Minimizingthecentralprocessingunit[CPUcylesandinputsandoutputs[1/11jusingapair of 210 map pe rs. Performing mergeoperation for hash-based grupingofkey value pairs usinga pairofreducers 212 whichisfurtherstoredin adistributed filesystemand an outputcache. Figure 2