AUTHOR=Sheikh Muhammad Saad , Enam Rabia Noor , Qureshi Rehan Inam 

TITLE=Machine learning-driven task scheduling with dynamic K-means based clustering algorithm using fuzzy logic in FOG environment

JOURNAL=Frontiers in Computer Science

VOLUME=Volume 5 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2023.1293209

DOI=10.3389/fcomp.2023.1293209

ISSN=2624-9898

ABSTRACT=Revise Sections 1.Updated in literature survey section.potential limitations of the proposed machine learning-based methodology that could be valuable for a more comprehensive evaluation.Updated in Conclusion section.The details of the algorithms compared with the DCNS Kmeans Clustering using fuzzy logic algorithm are not provided Updated in literature survey section.Why the response time of the proposed algorithm is increasing with the increasing number of simulation and execution time is decreasing while for the other algorithms it is almost comparable for each simulation.With an increasing number of tasks, the task scheduling problem becomes more complex. This is because the algorithm needs to consider more factors when scheduling tasks, such as the capabilities of each fog node, the requirements of each task which in our experiment is randomly assigned as shown in table 1,2,3 which I recently added. I have updated table 4 and added number of task content which make it clear that every time there is a variation in all the objective execution time, response time and bandwidth due to ambiguity in task requirement but this proposed algorithm works optimal from other compared algorithms. After updating table 4 there was no need of table 5 that's why I removed it.It is advisable to provide a more comprehensive and formal elaboration of the problem statement.Currently, the text repeats information from the introduction, and it might be beneficial to incorporate it into the section on the proposed algorithm.Updated in Introduction Section.The literature review focuses primarily on resource allocation and task scheduling. However, it would be better to expand the scope of the review to include research on the use of machine learning algorithms (ML) and their transformative potential in the area of task scheduling for Fog computing.Updated in literature survey section.