Infusing Autopoietic and Cognitive Behaviors into Digital Automata to Improve Their Sentience, Resilience, and Intelligence

Round 1

Reviewer 1 Report

The paper is an interesting look at applying biological concepts to computing problems and specifically managing IaaS and PaaS services in a cloud computing paradigm. I do, however, have two major concerns. Firstly, the paper needs a related work section. Managing resources in a cloud computing environments is a well studied problem and there is no mention of existing approaches. Examples include:

[1] Mao, H., Schwarzkopf, M., Venkatakrishnan, S.B., Meng, Z. and Alizadeh, M., 2019. Learning scheduling algorithms for data processing clusters. In Proceedings of the ACM Special Interest Group on Data Communication (pp. 270-288).

[2] Ghafouri, S., Saleh-Bigdeli, A.A. and Doyle, J., 2020, October. Consolidation of Services in Mobile Edge Clouds using a Learning-based Framework. In 2020 IEEE World Congress on Services (SERVICES) (pp. 116-121). IEEE.

[3] Brandherm, F., Wang, L. and Mühlhäuser, M., 2019, March. A learning-based framework for optimizing service migration in mobile edge clouds. In Proceedings of the 2nd International Workshop on Edge Systems, Analytics and Networking (pp. 12-17).

The authors should discuss these works and how it relates to their proposal. Secondly, there is no evaluation of their approach against existing techniques. It is therefore difficult to evaluate the effectiveness of the proposal and the merit of the work.

The following are some minor points that should also be examined:

1. The authors state that Time  Dependence  &  History  of  Events is a  limitation of Deep Learning systems.  Deep learning systems possess this component as the training stage is essentially creating a history state. I think you need to clarify your point here.
2. The authors state that Knowledge Composition and Transfer Learning is a limitation. Transfer learning allows the modification of model for different applications see Torrey, L. and Shavlik, J., 2010. Transfer learning. In Handbook of research on machine learning applications and trends: algorithms, methods, and techniques (pp. 242-264). IGI global. Further discussion here to clarify your point would be useful.
   
   
3. The authors state that Learning algorithms have no hierarchical structures as a limitation. There are hierarchical learning schemes see Barto, A.G. and Mahadevan, S., 2003. Recent advances in hierarchical reinforcement learning. Discrete event dynamic systems, 13(1), pp.41-77. Further discussion about this to clarify your point would be useful.

Author Response

I rewrote extensively to address your valuable comments. Response is attached.

Thank you

Author Response File: Author Response.pdf

Reviewer 2 Report

The topic is interesting and has many merits. But I have following major concerns:-

1. The paper is presents like a story. So, please improve its presentation. Arrange carefully the second section.
2. Author has mentioned limitations of current methods, but has not presented any comparative analysis.
3. Quality of diagrams should be improved or if it is due to embedding in the source format then high quality figures should be supplied separately.
4. Fonts of figures and text is significantly different. Do make it consistent.
5. Explain the significance of Figure 3.
6. Some experimental or theoretical analysis should be discussed.
7. Conclusion is seem to be summary, so add the conclusion section summary separately.
8. There are some ambiguous lines too, please take care.
9. any attention to 32 it….?
10. Contributions should be clearly defined.

 

Author Response

Thank you for your valuable comments.  Rewrote significant portions based on reviewer comments two reviewers.

Result I believe is an improved version.

Thanks again.

 

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The author has done an excellent job of addressing my concerns. 

Author Response

Did comprehensive revision including grammar and spelling check using Grammarly and Writer.

put effort to improve clarity and precision.

Reviewer 2 Report

Authors should strictly follow the ethics of publications in the MDPI journal

Author Response

Made comprehensive revision to improve grammar and English along with clarity. Used Grammarly and Riter.

Added Author contribution and clarified what author's contribution is.

As far material from other papers, all material is referenced.