Next Article in Journal
Energy Enhancement and Energy Spread Compression of Electron Beams in a Hybrid Laser-Plasma Wakefield Accelerator
Next Article in Special Issue
Latency-Classification-Based Deadline-Aware Task Offloading Algorithm in Mobile Edge Computing Environments
Previous Article in Journal
Efficient Weights Quantization of Convolutional Neural Networks Using Kernel Density Estimation based Non-uniform Quantizer
Previous Article in Special Issue
A Smart System for Text-Lifelog Generation from Wearable Cameras in Smart Environment Using Concept-Augmented Image Captioning with Modified Beam Search Strategy
Open AccessArticle
Peer-Review Record

EDCrammer: An Efficient Caching Rate-Control Algorithm for Streaming Data on Resource-Limited Edge Nodes

Appl. Sci. 2019, 9(12), 2560;
Reviewer 1: Yao-Te Tsai
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Appl. Sci. 2019, 9(12), 2560;
Received: 3 May 2019 / Revised: 14 June 2019 / Accepted: 20 June 2019 / Published: 23 June 2019
(This article belongs to the Special Issue Edge Computing Applications in IoT)

Round 1

Reviewer 1 Report

1. Introduction: You have mentioned the advantages and limitations of caching techniques and edge nodes. I doubt that there is no references in this section. You also indicated that "Instead, it has studied to apply relatively heavy tasks, such as machine learning and video encoding, to edge nodes. Furthermore, existing research has focused on pre-deploying data to an edge node without fully considering the dynamic scale-up and -down of the cache, which are related to the pay-as-you-go pricing policy of cloud computing." Where is the proof? At the end of the section, you wrote ", the caching could be useful to better meet the Quality of Service (QoS)". How could it be better meet the Quality of Service (QoS). I strongly encourage you to write research objectives to make everything clear. 

2. Literature Review: I think you should rewrite this section. In my opinion, It looks like piece by piece instead of a systematic review.

3.Can you please explain why your proposed method performed worse than the existing method in  Scenarios 1 and 2?

Author Response

Dear reviewer 1,

I really appreciate you to give me the beneficial comments. Thanks to your comments, the paper has been improved to be more systematic and clear, and easier to understand.

The point-by-point response and the revised paper are attached.

Author Response File: Author Response.pdf

Reviewer 2 Report

Basically, this paper is well organized, and enough background information is provided. In addition, the evaluation methodology has been presented in details. Overall, I think this paper is qualified to be published after a few minor revision. My comments are listed below:

The English writing can be further improved. For example, on page 3, the authors use "seem to" a couple of times, which is not proper in a research paper. Some abbreviations are not explained in the paper, e.g., PID, etc.

What's the difference between data and service data in Figure 2?

On page 6, the authors mentioned that the message broker could mitigate latency and load congestion. The reason is not explained. 

Similarly, the authors said their DMQTT can minimize the traffic, but the reason is not given in details.

On page 11, the authors did each experiment 30 times. Why did they set 30 times?

PID controller has many different types. The authors only evaluated their design based on one type of it. It will be beneficial if the authors can offer multiple designs and then evaluate them to determine the optimal design. 

Author Response

Dear reviewer 2,

I really appreciate you to give me the beneficial comments. Thanks to the detailed comments, the lack of clarity and ambiguity in the paper have been secured and made easier to understand.

The point-by-point response and the revised paper are attached.

Author Response File: Author Response.pdf

Reviewer 3 Report

The authors in this paper have proposed an efficient caching algorithm for streaming data on resource-limited edge nodes. The work is interesting, however, the authors need to justify the following:

1. The abstract is huge and very long. Needs to be rewritten.

2. What is the difference between Algo. 1 and 2?

3. What is the inputs and outputs of your algorithms?

4. IN between the abstract and introduction, I have missed the following:

- Paper motivation?

- Paper main contributions

- The technology used to deliver your solution

4. Related work and Introduction are mixed and confusing. Much related work in terms of data and management are missing. I recommend the following work:

- Al Ridhawi, Ismaeel, et al. "A collaborative mobile edge computing and user solution for service composition in 5G systems." Transactions on Emerging Telecommunications Technologies 29.11 (2018): e3446.

Al Ridhawi, Ismaeel, et al. "Data caching and selection in 5G networks using F2F communication." 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC). IEEE, 2017.

** You may discuss how your solution can fit within congestion crowded environments:

- Aloqaily, Moayad, et al. "Congestion mitigation in densely crowded environments for augmenting qos in vehicular clouds." Proceedings of the 8th ACM Symposium on Design and Analysis of Intelligent Vehicular Networks and Applications. ACM, 2018.

- M. Aloqaily, I. Al Ridhawi, H. B. Salameh, Y. Jararweh, Data and service management in densely crowded environments: Challenges, opportunities, and recent developments, IEEE Communications Magazine.

5. You need also to summarize the challenges and open issues in a section before the conclusion. Issues related to Trust, security, and privacy are important. The solution in the emerging domains of AI and ML is also important for the readers. As such, I recommend the following:

- S. Otoum, B. Kantarci, and H. Mouftah, "Adaptively supervised and intrusion-aware data aggregation for wireless sensor clusters in critical infrastructures " 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, 2018, pp. 1-6.

- S. Otoum, B. Kantarci and H. T. Mouftah, "Detection of Known and Unknown Intrusive Sensor Behavior in Critical Applications," in IEEE Sensors Letters, vol. 1, no. 5, pp. 1-4, Oct. 2017, Art no. 7500804.

- Otoum, Safa, Burak Kantarci, and Hussein T. Mouftah. "Mitigating False Negative intruder decisions in WSN-based Smart Grid monitoring." 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC). IEEE, 2017.

- S. Otoum, B. Kantarci and H. T. Mouftah, "On the Feasibility of Deep Learning in Sensor Network Intrusion Detection," in IEEE Networking Letters.

6. I will visit the results section in the revised version.

Author Response

Dear reviewer 3,

I really appreciate your beneficial comments. I have described the point-by-point response in a word file. You can find it in the attached file.

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

The authors have answered to all my comments. I believe the paper is in very good shape for publication.

Back to TopTop