Isara Soisom
ABSTRACT
Thailand is a tropical country with high average solar power across the country. This makes Thailand a very suitable area for utilizing this kind of clean energy. However, not all areas in Thailand have high solar power all year round. This research is thus propose a cluster-based method to search for the area that produces high solar energy throughout the year. The proposed methodology is based on the clustering technique and the silhouette analysis is used to define the appropriate value of a k variable to be used in the k-means clustering algorithm. We divide the original solar energy data into several datasets on a monthly bases, that is based on the number of months. Then, intersect the grouping results to identify the areas with high solar energy throughout the year. The output of this methodology is the areas with the highest solar energy power. For the case study of Thailand, the analysis result can reveal high energy areas covering 29 provinces out of 77, which is approximately 7.52 percent of the total areas.
- Benmouiza, K. and Cheknane, A. (2013). Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models. Energy Conversion and Management, 75, 561-569.Google Scholar
Cross Ref
- BunNak, N. (2020). Sub-district-level solar radiation intensity data for Thailand from 2017. Open Government Data of Thailand. https://data.go.th/dataset/https-www-dede-go-th-more_news-php-cid-547-filename-indexGoogle Scholar
- Kanungo, T., Mount, D. M., Netanyahu, N. S., Piatko, C. D., Silverman, R., and Wu, A. Y. (2002). A local search approximation algorithm for k-means clustering. In: Proceedings of the Eighteenth Annual Symposium on Computational Geometry, pp. 10-18. https://doi.org/10.1145/513400.513402Google ScholarDigital Library
- Kodinariya, T. M. and Makwana, P. R. (2013). Review on determining number of cluster in k-means Clustering. International Journal of Advance Research in Computer Science and Management Studies, 1(6), 90-95.Google Scholar
- Li, S., Ma, H., and Li, W. (2017). Typical solar radiation year construction using k-means clustering and discrete-time Markov chain. Applied Energy, 205, 720-731.Google ScholarCross Ref
- Masoumi, M. (2021).Ocean data classification using unsupervised machine learning: planning for hybrid wave-wind offshore energy devices. Ocean Engineering, 219, 108387.Google ScholarCross Ref
- Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of Computational and Applied Mathematics, 20, 53–65.Google ScholarDigital Library
Index Terms
- The Search for Areas with High Solar Energy Based on Clustering Analysis
Recommendations
Ranking solar energy potential by class and country
MEDES: Proceedings of the 8th International Conference on Management of Digital EcoSystemsThe global ecosystem has been adversely affected by our over reliance on fossil fuels, nuclear energy and other forms which are less environmentally friendly. Of course, this is not the only reason for which advances are made into finding alternative ...
Evaluation of Electrical Generation Systems with Solar Energy and Wind Energy at Phu Laen Kha National Park of Chaiyaphum Province
IEEA '20: Proceedings of the 2020 The 9th International Conference on Informatics, Environment, Energy and ApplicationsThis research was to study the design of the electrical generation with solar energy and wind energy for National Park Protection Unit: PK. 2 (Pan Thong), National Park Protection Unit: PK. 3 (Pa Prong Phan Pi) and Pha Hua Nak Viewpoint of Phu Laen Kha ...
The Development of Wind-Solar Energy Systems in China
ICEET '09: Proceedings of the 2009 International Conference on Energy and Environment Technology - Volume 03China is the largest developing country in the world. At present, more and more energy demand gives immense pressure to Chinese government. The inappropriate energy structure must be improved by Chinese government in order to achieve the sustainable ...
Comments