A Survey on Sustainable Surrogate-Based Optimisation

Round 1

Reviewer 1 Report

In this paper, authors defined sustainable SBO, which consists of three aspects: applying SBO to a sustainable application, reducing the number of expensive function evaluations, and considering the computational effort of the machine learning and optimisation parts of SBO. This paper investigates an interesting problem, and the structure is relative good. However, a major revision is needed before the acceptance.

1. Some details of the off-the-shelf SBO algorithms can be presented in the main text to make the paper more meaningful and significant.
2. The math equations can be described for each typical SBO algorithm.
3. If could, authors can introduce the performance evaluation comparisons, including how to build the testing platform.
4. Please go through the paper carefully and double check whether the right template are used. Correct some errors and formatting issues (e.g., “Definition 2. SBO for Sustainability” -> “Definition 2. SBO for sustainability”?).
5. The abbreviation table can be present in to the main body.
6. Some references lack the necessary information (e.g., [1]), please provide all information according to the right template.
7. As a survey paper, the references are inadequate. Make the References more comprehensive, besides expensive optimisation problems, some other promising scenarios (e.g., Big data, other IoT systems) can be covered in this work. If the above related work can be discussed, it can strongly improve the research significance. For the improvement, the following papers can be considered to make the references more comprehensive.

Cen Chen, Kenli Li, Sin G. Teo, Xiaofeng Zou, Keqin Li, Zeng Zeng: Citywide Traffic Flow Prediction Based on Multiple Gated Spatio-temporal Convolutional Neural Networks. ACM Trans. Knowl. Discov. Data 14(4): 42:1-42:23 (2020)

S. Zhou , L. Chen, V. Sugumaran: Hidden Two-Stream Collaborative Learning Network for Action Recognition. Computers, Materials and Continua, 2020, 63(3):1545-1561.

Bin Pu, Kenli Li, Shengli Li, Ningbo Zhu: Automatic Fetal Ultrasound Standard Plane Recognition Based on Deep Learning and IIoT. IEEE Trans. Ind. Informatics 17(11): 7771-7780 (2021)

W. Wang, Y. Yang, J. Li, Y. Hu, Y. Luo, X. Wang: Woodland Labeling in Chenzhou, China, via Deep Learning Approach. Int. J. Comput. Intell. Syst. 13(1): 1393-1403 (2020)

J. Wang, Y. Yang, T. Wang, R. Sherratt, J. Zhang. Big Data Service Architecture: A Survey. Journal of Internet Technology, 2020, 21(2): 393-405

Mingxing Duan, Kenli Li, Xiangke Liao, Keqin Li: A Parallel Multiclassification Algorithm for Big Data Using an Extreme Learning Machine. IEEE Trans. Neural Networks Learn. Syst. 29(6): 2337-2351 (2018)

J. Zhang, S. Zhong, T. Wang, H.-C. Chao, J. Wang. Blockchain-Based Systems and Applications: A Survey. Journal of Internet Technology, 2020, 21(1): 1-14

R. U. Maheswari and R. Umamaheswari, “Wind turbine drivetrain expert fault detection system: multivariate empirical mode decomposition based multi-sensor fusion with bayesian learning classification,” Intelligent Automation & Soft Computing, vol. 26, no.3, pp. 479–488, 2020.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

In this manuscript, the sustainable surrogate-based optimisation (SBO) algorithm is defined, and it consists of three aspects: applying SBO to a sustainable application, reducing the number of expensive function evaluations, and considering the computational effort of the machine learning and optimisation parts of SBO. In addition, this manuscript presents the sustainable applications applied SBO, and analyses the used framework, type of surrogate used, sustainable SBO aspects, and open questions. This paper provides the recommendations for researchers working on sustainability-related applications who want to apply SBO, as well as recommendations for SBO researchers.

The author can provide some schematic diagrams in this paper for readers to easily read and understand.

Author Response

I would like to thank the reviewer for taking the time to read the paper and for the valuable feedback. It has lead to significant improvements of this paper. Section 2 and Section 3 now both contain schematic diagrams to explain the SBO concepts. Together with the points raised by Reviewer 1, this should make the concept of SBO easier to understand.

Round 2

Reviewer 1 Report

Revised paper is much better and can be accepted.