Forecasting solar still performance from conventional weather data variation by machine learning method
Wenjie Gao(高文杰)1, Leshan Shen(沈乐山)2,3, Senshan Sun(孙森山)1, Guilong Peng(彭桂龙)1, Zhen Shen(申震)2,3, Yunpeng Wang(王云鹏)1, AbdAllah Wagih Kandeal6, Zhouyang Luo(骆周扬)2,3, A. E. Kabeel7,8, Jianqun Zhang(张坚群)4,†, Hua Bao(鲍华)5,‡, and Nuo Yang(杨诺)1,§
1 State Key Laboratory of Coal Combustion, and School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China; 2 Zhejiang Baima Lake Laboratory Co., Ltd., Hangzhou 31121, China; 3 Zhejiang Energy Group R&D Institute, Co., Ltd., Hangzhou 311121, China; 4 Zhejiang Zheneng Yueqing Electric Power Generation Co., Ltd., Yueqing 325609, China; 5 University of Michigan-Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai 200240, China; 6 Mechanical Engineering Department, Faculty of Engineering, Kafrelsheikh University, Kafrelsheikh 33516, Egypt; 7 Mechanical Power Engineering Department, Faculty of Engineering, Tanta University, Tanta, Egypt; 8 Faculty of Engineering, Delta University for Science and Technology, Gamasa, Egypt
Abstract Solar stills are considered an effective method to solve the scarcity of drinkable water. However, it is still missing a way to forecast its production. Herein, it is proposed that a convenient forecasting model which just needs to input the conventional weather forecasting data. The model is established by using machine learning methods of random forest and optimized by Bayesian algorithm. The required data to train the model are obtained from daily measurements lasting 9 months. To validate the accuracy model, the determination coefficients of two types of solar stills are calculated as 0.935 and 0.929, respectively, which are much higher than the value of both multiple linear regression (0.767) and the traditional models (0.829 and 0.847). Moreover, by applying the model, we predicted the freshwater production of four cities in China. The predicted production is approved to be reliable by a high value of correlation (0.868) between the predicted production and the solar insolation. With the help of the forecasting model, it would greatly promote the global application of solar stills.
Fund: Project supported by the National Key Research and Development Program of China (Grant No. 2018YFE0127800), the Science, Technology & Innovation Funding Authority (STIFA), Egypt grant (Grant No. 40517), China Postdoctoral Science Foundation (Grant No. 2020M682411), and the Fundamental Research Funds for the Central Universities (Grant No. 2019kfyRCPY045).
Corresponding Authors:
Jianqun Zhang, Hua Bao, Nuo Yang
E-mail: zhangjianq888@163.com;hua.bao@sjtu.edu.cn;nuo@hust.edu.cn
Cite this article:
Wenjie Gao(高文杰), Leshan Shen(沈乐山), Senshan Sun(孙森山), Guilong Peng(彭桂龙), Zhen Shen(申震), Yunpeng Wang(王云鹏), AbdAllah Wagih Kandeal, Zhouyang Luo(骆周扬), A. E. Kabeel, Jianqun Zhang(张坚群), Hua Bao(鲍华), and Nuo Yang(杨诺) Forecasting solar still performance from conventional weather data variation by machine learning method 2023 Chin. Phys. B 32 048801
[1] El-Samadony Y and Kabeel A E 2014 Energy68 744 [2] Abujazar M S S, Fatihah S, Lotfy E R, Kabeel A E and Sharil S 2018 Desalination425 94 [3] Kabeel A E, Arunkumar T, Denkenberger D C and Sathyamurthy R 2017 Appl. Thermal Eng.114 815 [4] Katekar V P and Deshmukh S S 2020 Journal of Cleaner Production257 120544 [5] Elimelech M and Phillip W A 2011 Science333 712 [6] Peng G L, Sharshir S W, Wang Y P, An M, Ma D K, Zang J F, Kabeel A E and Yang N 2021 Journal of Cleaner Production311 127432 [7] Mekonnen M M and Hoekstra A Y 2016 Science Advances2 e1500323 [8] Sharshir S W, Peng G L, Elsheikh A H, et al. 2020 Journal of Cleaner Production248 119224 [9] Shalaby S M, Sharshir S W, Kabeel A E, Kandeal A W, Abosheiasha H F, Abdelgaied M, Hamed M H and Yang N 2022 Energy Conversion and Management251 114971 [10] Kandeal A W, El-Shafai N M, Abdo M R, Thakur A K and Sharshir S W 2021 Solar Energy224 1313 [11] Chen Q, Alrowais R, Burhan M, Ybyraiymkul D and Ng K C 2020 Energy205 118037 [12] Gao M, Zhu L, Peh C K and Ho G W 2019 Energy & Environmental Science 12 841 [13] Peng G L, Deng S C, Sharshir S W, Ma D, Kabeel A E and Yang N 2019 Int. J. Heat Mass Transfer147 118866 [14] Chen S, Zhao P, Xie G, Wei Y and Zhang T 2021 Desalination512 115133 [15] Rahmani A, Kemmar F and Saadi Z 2021 Desalination501 114914 [16] Guo Y H, Dundas C M, Zhou X Y, Johnston K P and Yu G H 2021 Advanced Materials33 2102994 [17] Sharshir S W, Peng G, Wu L, Yang N, Essa F A, Elsheikh A H, Mohamed S I T and Kabeel A E 2017 Appl. Thermal Eng.113 684 [18] Cheng D, Gong W and Li N 2016 Desalination394 108 [19] Dunkle R 1961 International Development in Heat Transfer5 895 [20] Kumar S and Tiwari G N 1996 Sol. Energy57 459 [21] Panchal H 2016 Technology and Economics of Smart Grids and Sustainable Energy1 1 [22] Elango C, Gunasekaran N and Sampathkumar K 2015 Renewable Sustainable Energy Rev.47 856 [23] Maddah H A, Bassyouni M, Abdel-Aziz M H, Zoromba M S and Al-Hossainy A F 2020 Renewable Energy162 489 [24] Mashaly A F and Alazba A A 2016 Computers and Electronics in Agriculture122 146 [25] Ren Y S, Lei L, Deng X, Zheng Y, Li Y, Li J and Mei Z N 2019 Sci. Rep.9 15442 [26] Pei J, Deng L, Song S, Zhao M, Zhang Y, Wu S, Xie Y and Shi L P 2019 Nature572 106 [27] Belmokre A, Mihoubi M K and Santillán D 2019 KSCE Journal of Civil Engineering23 4800 [28] Wang Y P, Kandeal A W, Swidan A, Sharshir S W, Abdelaziz G B, Halim M A, Kabeel A E and Yang N 2020 Appl. Thermal Eng.186 116233 [29] Svetnik V 2003 Journal of Chemical Information & Computer Sciences 43 1947 [30] Chan C W and Paelinckx D 2008 Remote Sensing of Environment112 2999 [31] Singh H N and Tiwari G N 2004 Desalination168 145 [32] Shi J, Luo X, Liu Z, Fan J and Bao H 2021 Cell Reports Physical Science2 100330
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
