Big Data Analytics Based On Cloud Computing:A Systematic Literature Review

In the 21st century,many IT companies and organizations decided to grow up with next generation technology like computing.One of these is cloud computing and another is big data.Big data has become very important for innovation and growths on disruptive technologies such as cloud computing,internet of things and data analytics.Big data analytics(BDA)can help an organization to better understand the information contained within the data and also help identify the data that is most important knowledge that comes from analyzing the data.For the commercial market,big data analytics has proven its value and companies such as Facebook,Amazon,and Google have come to rely on big data analytics as part of their primary marketing schemes as well as a means of servicing their customers better.To analyze such large volumes of data,BDA is typically performed using specialized software tools and application for predictive analytics,data mining,text mining,forecasting and data optimization.It requires specialized capabilities,coinciding with the advanced technology that requires innovation of cloud computing.Cloud computing is a popular,efficient and prominent platform for service oriented computing in the last two decades.There is a relationship between cloud computing and big data-cloud computing resources are needed to support the storage projects that involved analysis of big data moving to cloud-based computing becomes a business case for big data.A systematic literature review(SLR)has been attracting wide attention in software engineering since 2004.Many researchers have reported their experiences in the application of systematic literature reviews in different areas of software enginering.However,in order to gain a deeper understanding of practitioners who have not attempted to explore the experience of any independent and systematic evaluation,the systematic evaluation is a new research method of software engineering.They claim that systematic literature review method requires the use of evidence-based knowledge systems in a systematic review.The objective of this research is to systematically investigate the existing research that is related to big data analytics on cloud computing,summarize the state-of-the-art research trends,categorize the technology used and relevant software as well as classify the research contents and the main research focuses.For conducting the investigation and presenting the analysis results,this research used the systematic review method based on the evidence-based software engineering paradigm.This thesis presents a systematic literature review(SLR)of published research articles concerning big data analytics in cloud computing.Based on a predefined search strategy,717 articles were identified,of which 57 were included in the review.The selected 57 articles were published between years 2010 and 2016.The thesis defines a review process by developing a review protocol and presenting the results of the review.Through reviewing and analyzing 57 articles,this study tries to answer the questions-5W+1H model(Who:authors/countries,Why:objective of research,What:research ideas,Where patterns of papers at different cloud service and types of publication venues,When article citation,How:article inter-relevance to develop).This paper finds that the deployment of big data on the cloud platform has some problems and challenges to be solved,such as data security,privacy protection and other issues.Although some researchers have proposed some coping methods,this systematic literature survey has found that this research is still in the early stage,so further research is still needed.The results are expected to provide researchers,software managers and software engineers with more information about the existing methods of big data analytics in cloud computing.We are focusing on,how we can put big data and cloud computing into one frame of development.Also,this paper has presented the list of selected papers about big data analytics based on cloud computing in a list with the summary for each of them.