A Review of Fog Computing and Machine Learning: Concepts, Applications, Challenges, and Open Issues

Karrar Hameed Abdulkareem, Mazin Abed Mohammed, Saraswathy Shamini Gunasekaran, Mohammed Nasser Al-Mhiqani, Ammar Awad Mutlag, Salama A. Mostafa, Nabeel Salih Ali, Dheyaa Ahmed Ibrahim

Research output: Contribution to journalReview articlepeer-review

144 Citations (Scopus)


Systems based on fog computing produce massive amounts of data; accordingly, an increasing number of fog computing apps and services are emerging. In addition, machine learning (ML), which is an essential area, has gained considerable progress in various research domains, including robotics, neuromorphic computing, computer graphics, natural language processing (NLP), decision-making, and speech recognition. Several researches have been proposed that study how to employ ML to settle fog computing problems. In recent years, an increasing trend has been observed in adopting ML to enhance fog computing applications and provide fog services, like efficient resource management, security, mitigating latency and energy consumption, and traffic modeling. Based on our understanding and knowledge, there is no study has yet investigated the role of ML in the fog computing paradigm. Accordingly, the current research shed light on presenting an overview of the ML functions in fog computing area. The ML application for fog computing become strong end-user and high layers services to gain profound analytics and more smart responses for needed tasks. We present a comprehensive review to underline the latest improvements in ML techniques that are associated with three aspects of fog computing: management of resource, accuracy, and security. The role of ML in edge computing is also highlighted. Moreover, other perspectives related to the ML domain, such as types of application support, technique, and dataset are provided. Lastly, research challenges and open issues are discussed.

Original languageEnglish
Article number8869895
Pages (from-to)153123-153140
Number of pages18
JournalIEEE Access
Early online date15 Oct 2019
Publication statusPublished - 31 Oct 2019
Externally publishedYes

Cite this