CAJ | 학술논문

针对传统间歇性能源海量数据处理技术的局限性，提出了基于MapReduce模型的间歇性能源海量数据处理技术，利用廉价的商用计算机组成集群，对海量数据进行并行处理，确保了海量数据处理的可靠性、低成本、高效能和扩展性，并对该技术的平台实现进行了论述。最后通过实验对比不同数据平台下海量数据处理的效率，验证了基于MapReduce模型的间歇性能源海量数据处理技术的高效性。
침대전통간헐성능원해량수거처리기술적국한성，제출료기우MapReduce모형적간헐성능원해량수거처리기술，이용렴개적상용계산궤조성집군，대해량수거진행병행처리，학보료해량수거처리적가고성、저성본、고효능화확전성，병대해기술적평태실현진행료논술。최후통과실험대비불동수거평태하해량수거처리적효솔，험증료기우MapReduce모형적간헐성능원해량수거처리기술적고효성。
To overcome the limitations of the traditional massive data processing technology of intermittent energy,this paper introduces a massive data processing technology of intermittent energy based on a MapReduce model.This is a method for processing large-scale data in-parallel on large clusters of cheap commercial computers to ensure the reliability,low cost,high efficiency and scalability of massive data processing.Then the technology platform of massive data processing is discussed. Finally,by a comparison of processing efficiency via different platforms,the high efficiency of the massive data processing technology of intermittent energy based on MapReduce model is proved.