Filters

2016 - 20173
Reset filters

Settings

Publisher: IeeeSubject: Big Data

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Conference Object
    Citation - WoS: 3
    Software Engineering Issues in Big Data Application Development
    (Ieee, 2017) Karakaya, Ziya
    Big Data has become one of the most important concepts that is being studied in Computer/Software Engineering. The data produced in recent years have increased rapidly and exponentially, necessitating the solution of major problems such as the collection, processing and storage of huge volume of data. Big Data Frameworks are developed specifically to solve these problems that facilitates application developers by providing opportunities to collect, process, manage, monitor and analyze these data. A few examples of these frameworks are Hadoop, Spark, Storm, and Flink, which are developed by Software Engineers as open source projects. Although the challenges raised from coordination of IT resources such as huge amounts of computation power, storage area, memory, and network bandwidth in a distributed manner solved by these frameworks, there still remains many Software Engineering problems in application development phase, even if they based on these frameworks. High scalability, fault tolerance, flexibility, reliability and testability can be listed as the main issues need to be carefully considered in terms of Software Engineering. In this paper, we first clarify the terms Framework-Application, and then the overview information about Big Data and related frameworks are given before emphasizing the problems arising in terms of Software Engineering. Nevertheless, we tried to provide guidance to the people who would develop software for Big Data and tried to give the further research guidance.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 28
    A Comparison of Stream Processing Frameworks
    (Ieee, 2017) Karakaya, Ziya; Yazici, Ali; Alayyoub, Mohammed
    This study compares the performance of Big Data Stream Processing frameworks including Apache Spark, Flink, and Storm. Also, it measures the resource usage and performance scalability of the frameworks against a varying number of cluster sizes. It has been observed that, Flink outperforms both Spark and Storm under equal constraints. However, Spark can be optimized to provide the higher throughput than Flink with the cost of higher latency.
  • Thumbnail Image
    Conference Object
    Systematic Mapping for Big Data Stream Processing Frameworks
    (Ieee, 2016) Alayyoub, Mohammed; Yazici, Ali; Karakaya, Ziya
    There has been lots of discussions about the choice of a stream processing framework (SPF) for Big Data. Each of the SPFs has different cutting edge technologies in their steps of processing the data in motion that gives them a better advantage over the others. Even though, the cutting edge technologies used in each stream processing framework might better them, it is still hard to say which framework bests the rest under different scenarios and conditions. in this study, we aim to show trends and differences about several SPFs for Big Data by using the Systematic Mapping (SM) approach. To achieve our objectives, we raise 6 research questions (RQs), in which 91 studies that conducted between 2010 and 2015 were evaluated. We present the trends by classifying the research on SPFs with respect to the proposed RQs which can help researchers to obtain an overview of the field.