Spatio-Temporal Forecasting of Global Horizontal Irradiance Using Bayesian Inference
Round 1
Reviewer 1 Report
Unfortunately, this paper does not make any new contribution, and difficult to perceive the goals of this study. Therefore, this study is not acceptable to me in its present form. Specific points are given below:
- The novelty of this research is not clear and not enough for publication. Only proposes/considers a few models based on traditional approaches. Therefore, this study does not present any novel idea. Moreover, few models/techniques are employed for comparison.
- The literature review is incomplete and ignores the latest research works.
- Flowchart demonstrating models development is missing and makes this study hard to understand
- Discussion on the results is missing, i.e., why one model is superior to the other? A thorough analysis/discussion of the results is needed.
- English writing needs to be improved.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 2 Report
The paper proposes two hybrid prediction modes for daily GHI. The work quality is good, though there are some aspects that can be improved:
- The authors claim that they compared their model to the benchmarking model and the benchmarking model is still better than them? The only novel idea is using the data from multi cites?
- It is worth to add a section to highlight the novelty of your work.
- The literature review could be improved and be more critical.
- It is better to make the dataset publicly available as a service to the research community.
- The authors didn't cite the most recent works on GPR forecast models as follows:
Fatemeh Najibi, Dimitra Apostolopoulou, Eduardo Alonso, Enhanced performance Gaussian process regression for probabilistic short-term solar output forecast,International Journal of Electrical Power & Energy Systems,
Volume 130,2021,106916,ISSN 0142-0615,
https://doi.org/10.1016/j.ijepes.2021.106916.(https://www.sciencedirect.com/science/article/pii/S0142061521001563)
F. Najibi, D. Apostolopoulou and E. Alonso, "Clustering Sensitivity Analysis for Gaussian Process Regression Based Solar Output Forecast," 2021 IEEE Madrid PowerTech, 2021, pp. 1-6, doi: 10.1109/PowerTech46648.2021.9495007.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper is generally well-written and structured. However, in my opinion, the paper has some shortcomings
1) Please focus on the abstract, In particular, the authors should point out their quantitative improvements, based on all the used evaluation metrics.
2) Needs clarity on choosing 8 different locations.
3) The proposed model needs a more critical review by comparing it with the latest research papers.
4) GHI forecasting is popular research, but the references are not enough. please add references.
5) Is the forecasting accuracy improved by choosing the significant predictor variables? please justify.
6) Compare the proposed model accuracy with different forecasting horizons.
7) Provide the time convergence and time complexity of the model?
Author Response
Please see the attachement
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
The authors have carefully addressed all my concerns.
Reviewer 3 Report
The authors have addressed the questions and incorporated the suggestions.