Privacy-Friendly Task Offloading for Smart Grid in 6G Satellite–Terrestrial Edge Computing Networksâ€
Round 1
Reviewer 1 Report
The paper is well written. However, for it to be accepted certain issues have to be addressed as follows:
1) The novelty of the work has been clearly stated but there is no critical evaluation of the literature to justify the present work. I suggest the authors add more literature to the introduction and carry out a much better critical review
2) Table 1 should be nomenclature and should come at the beginning of the paper before the introduction.
3) the quality of the figures is poor. I suggest the authors review them and improve their quality.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Authors can apply following comments in the main text to imporve the quality of the paper:
1- Please add some numerical results in the Abstract section for bandwidth, offloading cost and other factors.
2- Main contributions of the task offloading approach can be added in Section 1.
3- Following case studies can be discussed in Literature review as well:
- https://onlinelibrary.wiley.com/doi/10.1002/dac.5378
- https://www.sciencedirect.com/science/article/pii/S2542660523001555
- https://onlinelibrary.wiley.com/doi/10.1002/dac.5154
- https://ieeexplore.ieee.org/abstract/document/9990352
4- Please discuss on time complexity of Algorithm 1 as The DRTO Algorithm.
5- Please describe main details of the proposed method performance for evaluating Execution Latency.
Need a double check on grammar
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
In this manuscript, the authors present a method for task offloading in networks consisting of satellite and terrestrial edge computing nodes. In particular, they formulate the offloading cost minimization problem by consider a privacy preservation framework (confusing possible attackers by also including dummy tasks). Then, the authors also propose a DRL algorithm to solve the offloading problem, considering also the energy related to the transmission and computation functions. They verify their methodology through simulations, demonstrating that random dummy tasks effectively reduce the privacy leakage during offloading, while DRL algorithm exhibits a near-optimal offloading cost performance with much less runtime consumption. The presented work is interesting, the references are appropriate, and the investigated subject is very relevant to the topics of Electronics journal. A few minor comments:
- Minor typos and formatting problems (e.g., page 5, line 226)
- Except for the privacy problem during offloading, are there any extensions compared to the conference paper? I see that even result figures are the same. Please specifically state in the introduction what are the extensions, new simulation material, results, etc. compared to your conference paper.
- In future works, you may also consider the energy reduction associated with the transmission power as a joint energy-efficiency problem that can be solved with DRL. In this way, your mathematical modeling can be updated, or even make a 2-stage DRL algorithm. Relevant references for the joint energy-efficiency problem in wireless networks are:
1. AlQerm, Ismail, and Basem Shihada. "Energy-efficient power allocation in multitier 5G networks using enhanced online learning." IEEE Transactions on Vehicular Technology 66.12 (2017): 11086-11097.
2. Liu, Chi Harold, et al. "Energy-efficient UAV control for effective and fair communication coverage: A deep reinforcement learning approach." IEEE Journal on Selected Areas in Communications 36.9 (2018): 2059-2070.
3. Spantideas, Sotirios T., et al. "Joint energy-efficient and throughput-sufficient transmissions in 5G cells with deep Q-learning." 2021 IEEE International Mediterranean Conference on Communications and Networking (MeditCom). IEEE, 2021.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
No further comments
