{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:05:08Z","timestamp":1780419908323,"version":"3.54.1"},"reference-count":48,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T00:00:00Z","timestamp":1677024000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Energies"],"abstract":"<jats:p>Recently, deep learning techniques have become popular and are widely employed in several research areas, such as optimization, pattern recognition, object identification, and forecasting, due to the advanced development of computer programming technologies. A significant number of renewable energy sources (RESs) as environmentally friendly sources, especially solar photovoltaic (PV) sources, have been integrated into modern power systems. However, the PV source is highly fluctuating and difficult to predict accurately for short-term PV output power generation, leading to ineffective system planning and affecting energy security. Compared to conventional predictive approaches, such as linear regression, predictive-based deep learning methods are promising in predicting short-term PV power generation with high accuracy. This paper investigates the performance of several well-known deep learning techniques to forecast short-term PV power generation in the real-site floating PV power plant of 1.5 MWp capacity at Suranaree University of Technology Hospital, Thailand. The considered deep learning techniques include single models (RNN, CNN, LSTM, GRU, BiLSTM, and BiGRU) and hybrid models (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Five-minute resolution data from the real floating PV power plant is used to train and test the deep learning models. Accuracy indices of MAE, MAPE, and RMSE are applied to quantify errors between actual and forecasted values obtained from the different deep learning techniques. The obtained results show that, with the same training dataset, the performance of the deep learning models differs when testing under different weather conditions and time horizons. The CNN-BiGRU model offers the best performance for one-day PV forecasting, while the BiLSTM model is the most preferable for one-week PV forecasting.<\/jats:p>","DOI":"10.3390\/en16052119","type":"journal-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T05:01:32Z","timestamp":1677042092000},"page":"2119","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant"],"prefix":"10.3390","volume":"16","author":[{"given":"Nonthawat","family":"Khortsriwong","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6255-0521","authenticated-orcid":false,"given":"Promphak","family":"Boonraksa","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Rajamangala University of Technology Suvarnabhumi, Nonthaburi 11000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0995-0980","authenticated-orcid":false,"given":"Terapong","family":"Boonraksa","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Rajamangala University of Technology Rattanakosin, Nakhon Pathom 73170, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thipwan","family":"Fangsuwannarak","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asada","family":"Boonsrirat","sequence":"additional","affiliation":[{"name":"Energy Solution Business, SCG Chemicals Public Co., Ltd., Bangsue, Bangkok 10800, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0976-5873","authenticated-orcid":false,"given":"Watcharakorn","family":"Pinthurat","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Telecommunications, The University of New South Wales, Sydney 2052, Australia"},{"name":"Department of Electrical Engineering, Rajamangala University of Technology Tawan-Ok, Chanthaburi 22210, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7086-2197","authenticated-orcid":false,"given":"Boonruang","family":"Marungsri","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108932","DOI":"10.1016\/j.epsr.2022.108932","article-title":"Techniques for compensation of unbalanced conditions in LV distribution networks with integrated renewable generation: An overview","volume":"214","author":"Pinthurat","year":"2023","journal-title":"Electr. Power Syst. Res."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wynn, S.L.L., Boonraksa, T., Boonraksa, P., Pinthurat, W., and Marungsri, B. (2023). Decentralized Energy Management System in Microgrid Considering Uncertainty and Demand Response. Electronics, 12.","DOI":"10.3390\/electronics12010237"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Williams, Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_5","unstructured":"J\u00fcrgen, S. (2022, June 12). First Very Deep Learning with Unsupervised Pre-Training. Available online: https:\/\/people.idsia.ch\/~juergen\/very-deep-learning-1991.html."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., and Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv.","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_9","unstructured":"Fukushima, K., and Miyake, S. (1982). Competition and Cooperation in Neural Nets, Springer."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"El Haj, Y., Milman, R., Kaplan, I., and Ashasi-Sorkhabi, A. (2021, January 12\u201315). Hybrid Algorithm Based on Machine Learning and Deep Learning to Identify Ceramic Insulators and Detect Physical Damages. Proceedings of the 2021 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP), Vancouver, BC, Canada.","DOI":"10.1109\/CEIDP50766.2021.9705342"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Long, G., Mu, H., Li, Y., Zhang, D., Ding, N., and Zhang, G. (2020, January 6\u201310). Fault Identification Technology of Series Arc Based on Deep Learning Algorithm. Proceedings of the 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), Beijing, China.","DOI":"10.1109\/ICHVE49031.2020.9279366"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ali, M., Mujeeb, A., Ullah, H., and Zeb, S. (2020, January 28\u201331). Reactive Power Optimization Using Feed Forward Neural Deep Reinforcement Learning Method: (Deep Reinforcement Learning DQN algorithm). Proceedings of the 2020 Asia Energy and Electrical Engineering Symposium (AEEES), Chengdu, China.","DOI":"10.1109\/AEEES48850.2020.9121492"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3270","DOI":"10.1109\/TPWRS.2020.2987292","article-title":"Real-Time Optimal Power Flow: A Lagrangian Based Deep Reinforcement Learning Approach","volume":"35","author":"Yan","year":"2020","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"127037","DOI":"10.1016\/j.jclepro.2021.127037","article-title":"PV-Net: An innovative deep learning approach for efficient forecasting of short-term photovoltaic energy production","volume":"303","author":"Hawash","year":"2021","journal-title":"J. Clean. Prod."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3282","DOI":"10.1109\/TIA.2021.3073652","article-title":"Frequency-domain decomposition and deep learning based solar PV power ultra-short-term forecasting model","volume":"57","author":"Yan","year":"2021","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Nana, H., Lei, D., Lijie, W., Ying, H., Zhongjian, D., and Bo, W. (2019, January 3\u20135). Short-term Wind Speed Prediction Based on CNN_GRU Model. Proceedings of the 2019 Chinese Control And Decision Conference (CCDC), Nanchang, China.","DOI":"10.1109\/CCDC.2019.8833472"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Gao, Z., Li, Z., Luo, J., and Li, X. (2022). Short Text Aspect-Based Sentiment Analysis Based on CNN+ BiGRU. Appl. Sci., 12.","DOI":"10.3390\/app12052707"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.eswa.2009.05.044","article-title":"An artificial neural network (p, d, q) model for timeseries forecasting","volume":"37","author":"Khashei","year":"2010","journal-title":"Expert Syst. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Cui, C., He, M., Di, F., Lu, Y., Dai, Y., and Lv, F. (2020, January 12\u201314). Research on Power Load Forecasting Method Based on LSTM Model. Proceedings of the 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC), Chongqing, China.","DOI":"10.1109\/ITOEC49072.2020.9141684"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Islam, M.R., Al Mamun, A., Sohel, M., Hossain, M.L., and Uddin, M.M. (2020, January 12\u201314). LSTM-Based Electrical Load Forecasting for Chattogram City of Bangladesh. Proceedings of the 2020 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India.","DOI":"10.1109\/ESCI48226.2020.9167536"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yahya, M.A., Hadi, S.P., and Putranto, L.M. (2018, January 7\u20138). Short-Term Electric Load Forecasting Using Recurrent Neural Network (Study Case of Load Forecasting in Central Java and Special Region of Yogyakarta). Proceedings of the 2018 4th International Conference on Science and Technology (ICST), Yogyakarta, Indonesia.","DOI":"10.1109\/ICSTC.2018.8528651"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Bui, V., Nguyen, V.H., Pham, T.L., Kim, J., and Jang, Y.M. (2020, January 19\u201321). RNN-based Deep Learning for One-hour ahead Load Forecasting. Proceedings of the 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Fukuoka, Japan.","DOI":"10.1109\/ICAIIC48513.2020.9065071"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"032054","DOI":"10.1088\/1742-6596\/1748\/3\/032054","article-title":"Sentiment analysis based on BiGRU information enhancement","volume":"1748","author":"Yin","year":"2021","journal-title":"Proc. J. Phys. Conf. Ser."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"73750","DOI":"10.1109\/ACCESS.2018.2882878","article-title":"Combining Convolution Neural Network and Bidirectional Gated Recurrent Unit for Sentence Semantic Classification","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xiuyun, G., Ying, W., Yang, G., Chengzhi, S., Wen, X., and Yimiao, Y. (2018, January 20\u201322). Short-term Load Forecasting Model of GRU Network Based on Deep Learning Framework. Proceedings of the 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), Beijing, China.","DOI":"10.1109\/EI2.2018.8582419"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kumar, S., Hussain, L., Banarjee, S., and Reza, M. (2018, January 12\u201313). Energy Load Forecasting using Deep Learning Approach-LSTM and GRU in Spark Cluster. Proceedings of the 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT), Kolkata, India.","DOI":"10.1109\/EAIT.2018.8470406"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Luo, S., Rao, Y., Chen, J., Wang, H., and Wang, Z. (2020, January 6\u201310). Short-Term Load Forecasting Model of Distribution Transformer Based on CNN and LSTM. Proceedings of the 2020 IEEE International Conference on High Voltage Engineering and Application (ICHVE), Beijing, China.","DOI":"10.1109\/ICHVE49031.2020.9279813"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"9085","DOI":"10.1109\/ACCESS.2022.3143653","article-title":"Market Making Strategy Optimization via Deep Reinforcement Learning","volume":"10","author":"Sun","year":"2022","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Waseem, M., Lin, Z., and Yang, L. (2019). Data-driven load forecasting of air conditioners for demand response using levenberg\u2013marquardt algorithm-based ANN. Big Data Cogn. Comput., 3.","DOI":"10.3390\/bdcc3030036"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"112142","DOI":"10.1016\/j.enbuild.2022.112142","article-title":"Review of global research advances towards net-zero emissions buildings","volume":"266","author":"Ohene","year":"2022","journal-title":"Energy Build."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Pinthurat, W., and Hredzak, B. (2021). Distributed Control Strategy of Single-Phase Battery Systems for Compensation of Unbalanced Active Powers in a Three-Phase Four-Wire Microgrid. Energies, 14.","DOI":"10.3390\/en14248287"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.2339\/politeknik.903989","article-title":"The experimental study of dust effect on solar panel efficiency","volume":"25","author":"Demir","year":"2022","journal-title":"Politek. Derg."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Dhanraj, J.A., Mostafaeipour, A., Velmurugan, K., Techato, K., Chaurasiya, P.K., Solomon, J.M., Gopalan, A., and Phoungthong, K. (2021). An effective evaluation on fault detection in solar panels. Energies, 14.","DOI":"10.3390\/en14227770"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gosumbonggot, J., and Fujita, G. (2019). Global maximum power point tracking under shading condition and hotspot detection algorithms for photovoltaic systems. Energies, 12.","DOI":"10.3390\/en12050882"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dawan, P., Sriprapha, K., Kittisontirak, S., Boonraksa, T., Junhuathon, N., Titiroongruang, W., and Niemcharoen, S. (2020). Comparison of power output forecasting on the photovoltaic system using adaptive neuro-fuzzy inference systems and particle swarm optimization-artificial neural network model. Energies, 13.","DOI":"10.3390\/en13020351"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Jeong, H.S., Choi, J., Lee, H.H., and Jo, H.S. (2020). A study on the power generation prediction model considering environmental characteristics of Floating Photovoltaic System. Appl. Sci., 10.","DOI":"10.3390\/app10134526"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"175871","DOI":"10.1109\/ACCESS.2020.3025860","article-title":"Photovoltaic Power Forecasting with a hybrid deep learning approach","volume":"8","author":"Li","year":"2020","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"113315","DOI":"10.1016\/j.apenergy.2019.113315","article-title":"A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network","volume":"251","author":"Wang","year":"2019","journal-title":"Appl. Energy"},{"key":"ref_39","first-page":"23","article-title":"Short-term forecasting of photovoltaic solar power production using variational auto-encoder driven deep learning approac","volume":"10","author":"Dairi","year":"2020","journal-title":"Appl. Energy"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kuo, W.C., Chen, C.H., Hua, S.H., and Wang, C.C. (2022). Assessment of different deep learning methods of power generation forecasting for solar PV system. Appl. Energy, 12.","DOI":"10.3390\/app12157529"},{"key":"ref_41","first-page":"485","article-title":"Significance of epochs on training a neural network","volume":"9","author":"Afaq","year":"2020","journal-title":"Int. J. Sci. Technol. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hameed, Z., Shapoval, S., Garcia-Zapirain, B., and Zorilla, A.M. (2020, January 9\u201311). Sentiment analysis using an ensemble approach of BiGRU model: A case study of AMIS tweets. Proceedings of the 2020 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Louisville, KY, USA.","DOI":"10.1109\/ISSPIT51521.2020.9408866"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Skansi, S. (2018). Introduction to Deep Learning: From lOgical Calculus to Artificial Intelligence, Springer.","DOI":"10.1007\/978-3-319-73004-2"},{"key":"ref_44","unstructured":"Lewis, N. (2016). Deep Time Series Forecasting with Python, Create Space Independent Publishing Platform."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"66965","DOI":"10.1109\/ACCESS.2021.3076313","article-title":"Short-Term Load Forecasting Based on Adabelief Optimized Temporal Convolutional Network and Gated Recurrent Unit Hybrid Neural Network","volume":"9","author":"Shi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"32436","DOI":"10.1109\/ACCESS.2021.3060654","article-title":"A Short-Term Load Forecasting Method Using Integrated CNN and LSTM Network","volume":"9","author":"Rafi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"e12637","DOI":"10.1002\/2050-7038.12637","article-title":"An attention-based CNN-LSTM-BiLSTM model for short-term electric load forecasting in integrated energy system","volume":"31","author":"Wu","year":"2021","journal-title":"Int. Trans. Electr. Energy Syst."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"143759","DOI":"10.1109\/ACCESS.2020.3009537","article-title":"A Novel CNN-GRU-Based Hybrid Approach for Short-Term Residential Load Forecasting","volume":"8","author":"Sajjad","year":"2020","journal-title":"IEEE Access"}],"container-title":["Energies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1073\/16\/5\/2119\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:39:11Z","timestamp":1760121551000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1073\/16\/5\/2119"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,22]]},"references-count":48,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["en16052119"],"URL":"https:\/\/doi.org\/10.3390\/en16052119","relation":{},"ISSN":["1996-1073"],"issn-type":[{"value":"1996-1073","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,22]]}}}