Big-Data Platform for Performance Monitoring of Telecom-Service-Provider Networks

Round 1

Reviewer 1 Report

In this paper, a big data platform for performance monitoring of telecom service provider network is proposed. The proposed platform is capable to collect, store and process data from millions of devices. Generally the paper is easy to read and interesting.

The following comments should be considered to improve the paper.

1. Paper motivation can be further improved by adding an intuitive example from real world application.

2. The authors list 5 contributions in this paper, which are too many. Please merge them to make the contributions concise.

3. What are the possible limitations of the propsal in this paper if any? Please clarify them in detail one by one at end of the paper.

4. The performance monitoring issue focused in this paper has been studied by many researchers. Therefore, I suggest the authors to introduce the following related literatures in future revision: IoT-Based Data Logger for Weather Monitoring Using Arduino-Based Wireless Sensor Networks with Remote Graphical Application and Alerts; Trident: Efficient and Practical Software Network Monitoring; Intelligent Monitoring System for Biogas Detection Based on the Internet of Things: Mohammedia, Morocco City Landfill Case; Wireless recommendations for Internet of vehicles: Recent advances, challenges, and opportunities.

5. Proofread the whole paper and correct the existing spelling errors including grammar and syntax.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper addressed a key issue of data management in telecom network. The paper explains couple of challenges and technologies in detail and then proposed an approach to handle the big data , 

The paper has following issues

1. Introduction is too primitive with lots of repeated information so it requires an update

2. Literature Review address major issues related to cloud but lacks Literature related to proposed topic 

3. In objective sections , be specific than using word some 

4. Section 4.1 disussed the latency but doesn't specify what is set in telecom standard to have a clear distinction between your approach and industrial standards 

5.what is the retention policy and what is standard minimum policy 

6. What are the evaluation metric selected that you want to observe , is article [19] list metrics but there is no comparison in the paper after 

7. In terms of 5V challenges how this paper address veracity and value , if not add them to limitations 

8. What are the current solution used in telecom industry and are they not using BigData and cloud 

9. What are implementation parameters for your experiments, there is no clear detail on how the experiments were setup and conducted 

10. Why roundrobin approach is selected, provide a justification to text 

11. Why you are using IP address to distinguish the host to overcome the challenge you mentioned 

13. Provide a comparison of your approach of moving Macaddess compared to current approach other than query time and also mention which query is referred 

The paper can be summarised and be presented in well explained way such as adding a flow diagram, experimental setup, comparison with current telecom standard and effect of current approach

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

The topic is relevant and may be of interest to a broad range of the journal's readers. However, this reviewer has some major concerns about the paper.

Major Strengths: The major strengths of the research are:

The approach is actually applied in the real HFC network and is an effective tool.

Major Weaknesses: The major weaknesses of the research are:

- I'm not sure how this platform could be generalized also for different scenarios. A discussion about this is required.

- Related Works: Recently different challenges and research areas are addressing the problem of continuous and real-time processing of data. Among them, the most relevant challenges are the repairing of data in real-time (https://doi.org/10.1109/BigDataCongress.2017.24) and the extraction of metadata (https://doi.org/10.1109/TKDE.2020.2967722), and online data representation (https://doi.org/10.1007/978-3-031-01865-7_8).

- Section 4.2: Are BDPfPM challenges required? The authors discuss well-known challenges in the literature that were interesting 20 years ago.

- Figure 6 should be replaced with a plot or table. 

- The experimental evaluation is mainly focused on the performances of the platforms. However, it would be interesting to obtain feedback on the usability and effectiveness of such a platform and discuss these results.

Grammar and Readability:

The paper is well written and clear. I don't find any typos.

Specific Comments: My specific comments concerning this manuscript are:

I think that the paper is already ready for publishing, but it could be improved with the considerations I reported in the review.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors have improved the paper in detailed, the following points still need to be addressed still

Add a research article in which similar kind of approach is adapted

Conduct a benchmark comparison between the previous approach and your proposed approach, reference no 19 can provide number of research articles related to your research

Author Response

Please see the attachment.

Author Response File: Author Response.pdf