MapReduce and Its Applications, Challenges, and Architecture: a Comprehensive Review and Directions for Future Research

Khezr, Seyednima; Navimipour, Nima Jafari

doi:10.1007/s10723-017-9408-0

Cited by 66 publications

(32 citation statements)

References 119 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are various field of researches that use MapReduce to enhance their performance, for example survey research in health care [14,29], government [6], sentiment analysis [19], set operations [15], or real-time data analytic [37]. There are researches that focus on state-of-the-art of MapReduce and its applications [20,24].…”

Section: Apriori Algorithms: Background and Remarksmentioning

confidence: 99%

On using MapReduce to scale algorithms for Big Data analytics: a case study

2019

View full text Add to dashboard Cite

Scale adds cost. It also adds complexity and can make even the simplest computing infeasible. Many data analytics algorithms are originally designed for in-memory data. When facing with huge volume of data, these algorithms fail to scale due to limitation of processing capacity, storage capacity and operations on a single machine. Thus, to improve scalability and efficiency, parallel and distributed algorithms are developed to

show abstract

Section: Apriori Algorithms: Background and Remarksmentioning

confidence: 99%

On using MapReduce to scale algorithms for Big Data analytics: a case study

2019

View full text Add to dashboard Cite

show abstract

“…As we know, relying on the current technologies such as grid and CC is not an effective way to mention the necessities of big data management. Hence, the reduction of complexity, the improvement of management, and the promotion of big data require new technologies . Preprocessing of raw sensory data is effective in reducing the load of the big data in computing environments.…”

Section: Review Of the State‐of‐the‐art Papersmentioning

confidence: 99%

“…Hence, the reduction of complexity, the improvement of management, and the promotion of big data require new technologies. 36 Preprocessing of raw sensory data is effective in reducing the load of the big data in computing environments. The raw and passive data generated by the networks' sensors have been designed again to be self-managed.…”

Section: Data Management Strategiesmentioning

confidence: 99%

A comprehensive study on managing strategies in the fog environments

Wang

Panpan

Batiha

2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Although cloud computing application is rising, some unanswered problems still exist because of its inner issues like untrustworthy inactivity, the absence of movement backing, and place awareness. Therefore, fog computing has appeared as a hopeful infrastructure to supply flexible resources at the edge of the network. Fog supplies processing, data, storing, and application amenities to ultimate operators. The management strategies have a great impact on fog computing, such as monitoring and optimizing, the correlated components for improving the performance, availability, security, and any fundamental operational requirement. However, as far as we know, no organized study exists about analyzing their importance in fog environments. This paper provides a detailed survey for covering the current state‐of‐the‐art in fog management. This paper classifies the management strategies into three main categories: data management, energy, and resource. We also presented a few prospects and problems like the suggestions for the upcoming studies in the associated methods requiring to be investigated in fog computing. Moreover, a new paradigm has been ensured by increasing fog functionality and resource consumption. In general, fog management strategies in computing environments still need improvements in the variety of its setting to convert to an on‐request method, decrease the associated overhead, and improve the performance. Therefore, proper management can maintain the least resource consumption, which will finish the extra decrease in energy usage. Therefore, we contribute to provide strong suggestions for future fog computing studies. This paper can handle the pace of publications and propose the outcomes of study and practice as an upcoming route for decision makers in healthcare. In principle, the increase of researchers, scientists and managers' awareness level would increase the managers' good and knowingly behavioral conduct on managing fog environments.

show abstract

“…5,6 To be specific, instead of sending all data collected to the cloud, FC suggests to processing data at the edges. FC can be used in several related domains, including big data analytics, 7,8 Internet of Things (IoT), 9,10 wireless sensor networks, [11][12][13] smart homes, 14 smart cities, 15 health care, 16 and mobile/wearable computing. 17,18 The benefits of FC are increasing throughput, reducing latency, saving energy, consolidating resources, and enhancing privacy and security.…”

Section: Introductionmentioning

confidence: 99%

Quality of service‐aware approaches in fog computing

Kashani

Rahmani

Navimipour

2020

Int J Communication

Self Cite

View full text Add to dashboard Cite

Summary In recent years, fog computing, a novel paradigm, has emerged for location and latency‐sensitive applications. It is a powerful complement for cloud computing that enables provisioning services and resources outside the cloud near the end devices. In a fog system, the existence of several nonhomogenous devices, which are potentially mobile, led to quality of service (QoS) worries. QoS‐aware approaches are presented in various parts of the fog system, and several different QoS factors are taken into account. In spite of the importance of QoS in fog computing, no comprehensive study on QoS‐aware approaches exists in fog computing. Hence, this paper reviews the current research used to guarantee QoS in fog computing. This paper investigates the QoS‐ensuring techniques that fall into three categories: service/resource management, communication management, and application management (published between 2013 and October 2018). Regarding the selected approaches, this paper represents merits, demerits, tools, evaluation types, and QoS factors. Finally, on the basis of the reviewed studies, we suggest some open issues and challenges which are worth further studying and researching in QoS‐aware approaches in fog computing.

show abstract

MapReduce and Its Applications, Challenges, and Architecture: a Comprehensive Review and Directions for Future Research

Cited by 66 publications

References 119 publications

On using MapReduce to scale algorithms for Big Data analytics: a case study

On using MapReduce to scale algorithms for Big Data analytics: a case study

A comprehensive study on managing strategies in the fog environments

Quality of service‐aware approaches in fog computing

Contact Info

Product

Resources

About