Estimation of 5G Core and RAN End-to-End Delay through Gaussian Mixture Models

Round 1

Reviewer 1 Report

 

This work investigates the accuracy and time complexity of estimating Gaussian Mixture Distributions to model the end-to-end (E2E) delay for standalone and non-standalone 5G architectures. Overall, the article is easy to follow except for Section 4, which can be presented more clearly. The work has merit and is technically sound. The study is interesting and sheds light on the stochastic characterization of the 5G System E2E delay. The weakest point of the article is its motivation, which needs to be further strengthened. Below are some comments with the hope that they will help to improve the quality of the manuscript.

 

1. The authors highlight the importance of data analytics and list some of their applications. Nonetheless, identifying and developing one or several use cases in which the proposed modeling approach is practical would help to strengthen the paper's motivation. 
2. In line with the above comment, to better define the application scope and further motivate the modeling approach covered in this work, the authors should include a comparison (pros and cons) of their proposal with other modeling approaches. The reference below includes in Section 2.2 a revision of the existing analytical models (based on queuing theory -QT- and network calculus -NC-) to estimate the E2E delay in the 5G system. What are the advantages and disadvantages of your proposal compared to QT and NC-based models?

 

Chinchilla-Romero, L.; Prados-Garzon, J.; Ameigeiras, P.; Muñoz, P.; Lopez-Soler, J.M. 5G Infrastructure Network Slicing: E2E Mean Delay Model and Effectiveness Assessment to Reduce Downtimes in Industry 4.0. Sensors 2022, 22, 229. https://doi.org/10.3390/s22010229

 

3. It would also be interesting to discuss the implications of practical aspects in estimating the packet delay distribution. For instance, if the delay samples are taken using timestamps from unsynchronized clocks.  
4. Carefully revise and improve the clarity of Section 4.
5. Besides the figures depicting the setup for collecting the dataset, a figure comparing standalone and non-standalone 5G architectures might help to understand these concepts.
6. Fix the issues with the references.
7. Please expand the acronyms the first time they appear in the main text, even though they were expanded in the abstract.
8. In Section 3.2, I would keep the number of iterations used as a parameter instead of using a fixed value (25000). Instead, I would include the specific value considered in the experimental setup.

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The research is timely and worthwhile. The authors provide fresh insight into the field.

The manuscript doesn't respect the MDPI format and Scientific Best Practice in terms of structure, which means the structure: Introduction – Methodology – Results – Discussion - Conclusions. The Scientific Best Practice also applies to review studies and other qualitative approaches. This is also one reason why the red line in the manuscript is missing.

The introduction must be given a general overview of the subject under review and the motivation for why the study is being performed as well as the detailed scope of the study.

For explanation: Just giving an overview on the subject is not a scientific motivation.

Thus, the main questions are:

·       What is the scientific motivation for performing the literature review?

·       Which scientific question shall be answered with this?

·       What are the scientific gaps that require a bibliometric analysis for that subject?

·       What scientific hypothesis you wish to answer with the literature review?

Putting the scientific motivation will also help you to identify the novelties that characterises a scientific publication.

Authors must correct citations of all references, e.g., “The work in [?]….” page 3, 100 line

Authors need to revise and check citations in the text and in the references section. I suggest you add these references:

·       K. Pandey, R. Arya, "Robust Distributed Power Control with Resource Allocation in D2D Communication Network for 5G-IoT Communication System", International Journal of Computer Network and Information Security(IJCNIS) 2022, Vol.14, No.5, 73-81. DOI:10.5815/ijcnis.2022.05.06

·       Pradeep, P., Sankar, J.,  Sekhar, C. Design and Analysis of an Elliptical Edge with Pentagon Slot Patch Antenna for 5G Applications. International Journal of Wireless and Microwave Technologies (IJWMT) 2022, Vol.12, No.5, 36-42. DOI:10.5815/ijwmt.2022.05.04

I strongly recommend adding these works to the list of references.

 Authors should discuss the results and how they can be interpreted from the perspective of previously published studies.

 

I also suggest a grammar and spelling review. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Accept in present form