Neural network fusion optimization for photovoltaic power forecasting

This paper aims to establish a comprehensive photovoltaic power generation prediction model. By collecting photovoltaic power generation data and weather data for a year, we analyzed the photovoltaic output characteristics in different seasons and found that the output characteristics in different seasons are also different. This article uses three neural network models, Long Short Term Memory Network, Recurrent Neural Network, and Dense Neural Network, to analyze the output characteristics of different seasons. Training, prediction, and prediction error analysis found that different models have different prediction accuracy in different seasons. Therefore, this paper proposes a weighted ensemble model add weights model based on the Nelder-Mead method to train and predict different seasons respectively. By analyzing the prediction error, the prediction accuracy needs to be better than a single model. We add noise to the data set to simulate unstable lighting conditions such as rainy days, and train and predict the data set after adding noise. The prediction results show that the comprehensive model has higher prediction accuracy than a single model in extreme weather. In order to verify the reliability of the model, this article uses a sliding window to extract the confidence interval of the prediction results, and uses the Bootstrap method to calculate the confidence interval. By analyzing and comparing each model’s Average Coverage, Root Mean Squared Length, and Mean Width, the prediction accuracy and reliability of add weights model are better than those of a single model.

1. Qazi A., Hussain F., Rahim N.A.B.D., Hardaker G., Alghazzawi D, Shaban K., et al. Towards sustainable energy: a systematic review of renewable energy sources, technologies, and public opinions. IEEE Access. 2019;7:63837-63851. https://doi.org/10.1109/ACCESS.2019.2906402.

2. Hassan Q., Algburi S., Sameen A.Z., Salman H.M., Jaszczur M. A review of hybrid renewable energy systems: solar and wind-powered solutions: challenges, opportunities, and policy implications. Results in Engineering. 2023;20:101621. https://doi.org/10.1016/j.rineng.2023.101621.

3. Said D. Intelligent photovoltaic power forecasting methods for a sustainable electricity market of smart micro-grid. IEEE Communications Magazine. 2021;59(7):122-128. https://doi.org/10.1109/MCOM.001.2001140.

4. Li Qing, Zhang Xinyan, Ma Tianjiao, Jiao Chunlei, Wang Heng, Hu Wei. A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine. Energy. 2021;224:120094. https://doi.org/10.1016/j.energy.2021.120094.

5. Wang Kejun, Qi Xiaoxia, Liu Hongda. A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network. Applied Energy. 2019;251:113315. https://doi.org/10.1016/j.apenergy.2019.113315.

6. Mayer M.J., Gróf G. Extensive comparison of physical models for photovoltaic power forecasting. Applied Energy. 2021;283:116239. https://doi.org/10.1016/j.apenergy.2020.116239.

7. De Giorgi M.G., Congedo P.M., Malvoni M. Photovoltaic power forecasting using statistical methods: impact of weather data. IET Science, Measurement & Technology. 2014;8:90-97. https://doi.org/10.1049/iet-smt.2013.0135.

8. Markovics D., Mayer M.J. Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction. Renewable and Sustainable Energy Reviews. 2022;161:112364. https://doi.org/10.1016/j. rser.2022.112364.

9. Liu Ling, Liu Fang, Zheng Yuling. A novel ultra-short-term pv power forecasting method based on DBN-based TakagiSugeno fuzzy model. Energies. 2021;14(20):6447. https://doi.org/10.3390/en14206447.

10. Tai Bin, Yu Lei, Huang Yangjue, Wang Jinfeng, Wang Yin, Zhu Yuanzhe, et al. Power prediction of photovoltaic power generation based on LSTM model with additive attention mechanism. In: 7th International Conference on Smart Grid and Smart Cities. 22–24 September 2023, Lanzhou. Lanzhou; 2023, р. 474-480. https://doi.org/10.1109/ ICGSC59580.2023.10319231.

11. Wang X., Zhou X., Xing J., Yang J. A prediction method of PV output power based on the combination of improved grey back propagation neural network. Journal of Solar Energy. 2021;7:81-87. https://doi.org/10.7667/PSPC151675.

12. Liu Fang, Li Ranran, Li Yong, Yan Ruifeng, Saha Tapan. Takagi–Sugeno fuzzy model‐based approach considering multiple weather factors for the photovoltaic power short‐term forecasting. IET Renewable Power Generation. 2017;11:1281- 1287. https://doi.org/10.1049/iet-rpg.2016.1036.

13. Hossain M.S., Mahmood Н. Short-term photovoltaic power forecasting using an LSTM neural network and synthetic weather forecast. IEEE Access. 2020;8:172524-172533. https://doi.org/10.1109/ACCESS.2020.3024901.

14. Dolara A., Grimaccia F., Leva S., Mussetta M., Ogliari E. Comparison of training approaches for photovoltaic forecasts by means of machine learning. Applied Sciences. 2018;8(2):228. https://doi.org/10.3390/app8020228.

15. Ozaki Yо., Yano M., Onishi M. Effective hyperparameter optimization using Nelder-Mead method in deep learning. IPSJ Transactions on Computer Vision and Applications. 2017;9(20):1-12. https://doi.org/10.1186/s41074-017-0030-7.

16. Sherstinsky А. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena. 2020;404:132306. https://doi.org/10.1016/j.physd.2019.132306.

17. Muhuri P.S., Chatterjee P., Yuan Xiaohong, Roy K., Esterline А. Using a long short-term memory recurrent neural network (LSTM-RNN) to classify network attacks. Information. 2020;11(5):243. https://doi.org/10.3390/info11050243.

18. Lee Donghun, Kim Kwanho. Recurrent neural network-based hourly prediction of photovoltaic power output using meteorological information. Energies. 2019;12(2):215. https://doi.org/10.3390/en12020215.

19. Vivas E., Allende-Cid H., Salas R. A systematic review of statistical and machine learning methods for electrical power forecasting with reported mape score. Entropy. 2020;22(12):1412. https://doi.org/10.3390/e22121412.

20. Al-Dahidi S., Ayadi O., Alrbai M., Adeeb J. Ensemble approach of optimized artificial neural networks for solar photovoltaic power prediction. IEEE Access. 2019;7:81741-81758. https://doi.org/10.1109/ACCESS.2019.2923905.