Use of Optimised LSTM Neural Networks Pre-Trained With Synthetic Data to Estimate PV Generation.

Miguel Martínez Comesaña; Javier Martínez Torres; Pablo Eguía Oller; Javier López Gómez

doi:10.9781/ijimai.2023.11.002

Authors

Miguel Martínez Comesaña University of Vigo.
Javier Martínez Torres University of Vigo.
Pablo Eguía Oller University of Vigo.
Javier López Gómez University of Vigo.

DOI:

https://doi.org/10.9781/ijimai.2023.11.002

Keywords:

Genetic Algorithms, LSTM, Optimisation, Pre-Training, PV Power, Synthetic Datasets

Supporting Agencies

This research was supported by the Ministry of Science, Innovation and Universities of the Spanish government under the DEEPSMART project (PID2021-126739OB-C21). The authors also want to thank the Ministry of Science, Innovation and Universities for grant FPU19/01187. Funding for open access charge: Universidade de Vigo/CISUG.

Abstract

Optimising the use of the photovoltaic (PV) energy is essential to reduce fossil fuel emissions by increasing the use of solar power generation. In recent years, research has focused on physical simulations or artifical intelligence models attempting to increase the accuracy of PV generation predictions. The use of simulated data as pre-training for deep learning models has increased in different fields. The reasons are the higher efficiency in the subsequent training with real data and the possibility of not having real data available. This work presents a methodology, based on an deep learning model optimised with specific techniques and pre-trained with synthetic data, to estimate the generation of a PV system. A case study of a photovoltaic installation with 296 PV panels located in northwest Spain is presented. The results show that the model with proper pre-training trains six to seven times faster than a model without pre-training and three to four times faster than a model pre-trained with non-accurate simulated data. In terms of accuracy and considering a homogeneous training process, all models obtained average relative errors around 12%, except the model with incorrect pre-training which performs worse.

Downloads

Download data is not yet available.

References

A. Abdelkader, A. Rabeh, D. Mohamed Ali, J. Mohamed, “Multi-objective genetic algorithm based sizing optimization of a stand-alone wind/pv power supply system with enhanced battery/supercapacitor hybrid energy storage,” Energy, vol. 163, pp. 351–363, 2018, doi: https://doi.org/10.1016/j.energy.2018.08.135.

J. Munkhammar, J. D.K. Bishop, J. J. Sarralde, W. Tian, R. Choudhary, “Household electricity use, electric vehicle home-charging and distributed photovoltaic power production in the city of westminster,” Energy and Buildings, vol. 86, pp. 439–448, 2015, doi: https://doi.org/10.1016/j.enbuild.2014.10.006.

R. Fachrizal, M. Shepero, D. Van der Meer, J. Munkhammar, J. Widén, “Smart charging of electric vehicles considering photovoltaic power production and electricity consumption: A review,” eTransportation, vol. 4, p. 100056, 2020, doi: https://doi.org/10.1016/j.etran.2020.100056.

D. B. Richardson, “Electric vehicles and the electric grid: A review of modeling approaches, impacts, and renewable energy integration,” Renewable and Sustainable Energy Reviews, vol. 19, pp. 247–254, 2013, doi: https://doi.org/10.1016/j.rser.2012.11.042.

A. Anand, A. Shukla, H. Panchal, A. Sharma, “Thermal regulation of photovoltaic system for enhanced power production: A review,” Journal of Energy Storage, vol. 35, p. 102236, 2021, doi: https://doi.org/10.1016/j.est.2021.102236.

A. R. Jordehi, “Parameter estimation of solar photovoltaic (pv) cells: A review,” Renewable and Sustainable Energy Reviews, vol. 61, pp. 354–371, 2016, doi: https://doi.org/10.1016/j.rser.2016.03.049.

S. Theocharides, G. Makrides, A. Livera, M. Theristis, P. Kaimakis, G. E. Georghiou, “Day-ahead photovoltaic power production forecasting methodology based on machine learning and statistical post-processing,” Applied Energy, vol. 268, p. 115023, 2020, doi: https://doi.org/10.1016/j.apenergy.2020.115023.

S. Dwyer, S. Teske, “Renewables 2018 global status report,” Renewables 2018 Global Status Report, 2018.

I. Renewable Energy Statistics, “International renewable energy agency,” Renewable Energy Target Setting, Abu Dhabi, UAE, 2015.

E. Bueno, P. d. S. Vicente, T. C. Pimenta, E. R. Ribeiro, “Photovoltaic array reconfiguration strategy for maximization of energy production,” International Journal of Photoenergy, vol. 2015, p. 592383, 2015, doi: 10.1155/2015/592383.

L. Prado Osco, J. Marcato Junior, A. P. Marques Ramos, L. A. de Castro Jorge, S. Narges Fatholahi, J. de Andrade Silva, E. T. Matsubara, H. Pistori, W. N. Gonçalves, J. Li, “A review on deep learning in uav remote sensing,” International Journal of Applied Earth Observation and Geoinformation, vol. 102, p. 102456, 2021, doi: https://doi.org/10.1016/j.jag.2021.102456.

M. Martínez-Comesaña, L. Febrero-Garrido, E. Granada-Álvarez, J. Martínez-Torres, S. Martínez-Mariño, “Heat loss coefficient estimation applied to existing buildings through machine learning models,” Applied Sciences, vol. 10, no. 24, 2020, doi: 10.3390/app10248968.

M. Nabipour, P. Nayyeri, H. Jabani, S. S., A. Mosavi, “Predicting stock market trends using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis,” IEEE Access, vol. 8, pp. 150199–150212, 2020, doi: 10.1109/ACCESS.2020.3015966.

L. Mert, “Agnostic deep neural network approach to the estimation of hydrogen production for solar-powered systems,” International Journal of Hydrogen Energy, vol. 46, no. 9, pp. 6272–6285, 2021, doi: https://doi.org/10.1016/j.ijhydene.2020.11.161.

P. Dhanith, B. Surendiran, S. Raja, “A word embedding based approach for focused web crawling using the recurrent neural network,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 6, no. 6, pp. 122-132, 2021.

M. Martínez-Comesaña, L. Febrero-Garrido, F. Troncoso-Pastoriza, J. Martínez-Torres, “Prediction of building’s thermal performance using lstm and mlp neural networks,” Applied Sciences, vol. 10, no. 21, 2020, doi: 10.3390/app10217439.

R. R. Kumari, V. V. Kumar, K. R. Naidu, “Optimized dwt based digital image watermarking and extraction using rnn-lstm,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 7, no. 2, pp. 150-162, 2021.

X.-H. Le, H. V. Ho, G. Lee, S. Jung, “Application of long short-term memory (lstm) neural network for flood forecasting,” Water, vol. 11, no. 7, 2019, doi: 10.3390/w11071387.

M. Chai, F. Xia, S. Hao, D. Peng, C. Cui, W. Liu, “Pv power prediction based on lstm with adaptive hyperparameter adjustment,” IEEE Access, vol. 7, pp. 115473–115486, 2019, doi: 10.1109/ACCESS.2019.2936597.

M. Khodayar, M. E. Khodayar, S. Mohammad Jafar Jalali, “Deep learning for pattern recognition of photovoltaic energy generation,” The Electricity Journal, vol. 34, no. 1, p. 106882, 2021, doi: https://doi.org/10.1016/j.tej.2020.106882.

M. S. Hossain, H. Mahmood, “Short-term photovoltaic power forecasting using an lstm neural network and synthetic weather forecast,” IEEE Access, vol. 8, pp. 172524–172533, 2020, doi: 10.1109/ACCESS.2020.3024901.

M. Abdel-Nasser, K. Mahmoud, “Accurate photovoltaic power forecasting models using deep lstm-rnn,” Neural Computing and Applications, vol. 31, no. 7, pp. 2727–2740, 2019, doi: 10.1007/s00521-017-3225-z.

L. Yang, A. Shami, “On hyperparameter optimization of machine learning algorithms: Theory and practice,” Neurocomputing, vol. 415, pp. 295–316, 2020, doi: https://doi.org/10.1016/j.neucom.2020.07.061.

M. Martínez-Comesaña, P. Eguía-Oller, J. Martínez-Torres, L. Febrero-Garrido, E. Granada-Álvarez, “Optimisation of thermal comfort and indoor air quality estimations applied to in-use buildings combining nsga-iii and xgboost,” Sustainable Cities and Society, vol. 80, p. 103723, 2022, doi: https://doi.org/10.1016/j.scs.2022.103723.

Y. Yoo, “Hyperparameter optimization of deep neural network using univariate dynamic encoding algorithm for searches,” Knowledge-Based Systems, vol. 178, pp. 74–83, 2019, doi: https://doi.org/10.1016/j.knosys.2019.04.019.

Y. Novaria Kunang, S. Nurmaini, D. Stiawan, B. Yudho Suprapto, “Attack classification of an intrusion detection system using deep learning and hyperparameter optimization,” Journal of Information Security and Applications, vol. 58, p. 102804, 2021, doi: https://doi.org/10.1016/j.jisa.2021.102804.

Y. Guo, J.-Y. Li, Z.-H. Zhan, “Efficient hyperparameter optimization for convolution neural networks in deep learning: A distributed particle swarm optimization approach,” Cybernetics and Systems, vol. 52, no. 1, pp. 36–57, 2021, doi: 10.1080/01969722.2020.1827797.

S. Lee, J. Kim, H. Kang, D.-Y. Kang, J. Park, “Genetic algorithm based deep learning neural network structure and hyperparameter optimization,” Applied Sciences, vol. 11, no. 2, 2021, doi: 10.3390/app11020744.

H. Chung, K.-S. Shin, “Genetic algorithm-optimized multi-channelconvolutional neural network for stock market prediction,” Neural Computing and Applications, vol. 32, no. 12, pp. 7897–7914, 2020, doi: 10.1007/s00521-019-04236-3.

Á. A. Domingo, M. A. Ezquerra, “Gpgpu implementation of a geneticalgorithm for stereo refinement,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 3, no. 2, pp. 69–76, 2015.

M. Martínez-Comesaña, A. Ogando-Martínez, F. Troncoso-Pastoriza, J. López-Gómez, L. Febrero-Garrido, E. Granada-Álvarez, “Use of optimised mlp neural networks for spatiotemporal estimation of indoor environmental conditions of existing buildings,” Building and Environment, vol. 205, p. 108243, 2021, doi: https://doi.org/10.1016/j.buildenv.2021.108243.

R. Damaševičius, M. Gupta, N. Kumar, B. K. Singh, N. Gupta, “Nsga-iii-based deep-learning model for biomedical search engines,” Mathematical Problems in Engineering, vol. 2021, p. 9935862, 2021, doi: 10.1155/2021/9935862.

P. Trampert, D. Rubinstein, F. Boughorbel, C. Schlinkmann, M. Luschkova, P. Slusallek, T. Dahmen, S. Sandfeld, “Deep neural networks for analysis of microscopy images—synthetic data generation and adaptive sampling,” Crystals, vol. 11, no. 3, 2021, doi: 10.3390/cryst11030258.

J. Liu, J. Gu, H. Li, K. H. Carlson, “Machine learning and transport simulations for groundwater anomaly detection,” Journal of Computational and Applied Mathematics, vol. 380, p. 112982, 2020, doi: https://doi.org/10.1016/j.cam.2020.112982.

K. Antczak, “Deep recurrent neural networks for ecg signal denoising,” 2018. [Online]. Available: https://arxiv.org/abs/1807.11551, doi: 10.48550/ARXIV.1807.11551.

Q. Wang, J. Gao, W. Lin, Y. Yuan, “Learning from synthetic data for crowd counting in the wild,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.

J. C. Balloch, I. Agrawal, Varun Essa, S. Chernova, “Unbiasing semantic segmentation for robot perception using synthetic data feature transfer,” 2018. [Online]. Available: https://arxiv.org/abs/1809.03676, doi: 10.48550/ARXIV.1809.03676.

Y. Yu, X. Si, C. Hu, J. Zhang, “A review of recurrent neural networks: Lstm cells and network architectures,” Neural computation, vol. 31, no. 7, pp. 1235–1270, 2019.

A. Sherstinsky, “Fundamentals of recurrent neural network (rnn) and long short-term memory (lstm) network,” Physica D: Nonlinear Phenomena, vol. 404, p. 132306, 2020, doi: https://doi.org/10.1016/j.physd.2019.132306.

Y. Hu, A. E. G. Huber, J. Anumula, S. Chii Liu, “Overcoming the vanishing gradient problem in plain recurrent networks,” CoRR, vol. abs/1801.06105, 2018.

S. Jha, A. Dey, R. Kumar, V. Kumar, “A novel approach on visual question answering by parameter prediction using faster region based convolutional neural network,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 5, no. 5, pp. 30–37, 2019.

A. H. Elkasem, S. Kamel, A. Rashad, F. J. Melguizo, “Optimal performance of doubly fed induction generator wind farm using multi-objective genetic algorithm,” International Journal of Interactive Multimedia and Artificial Intelligence, vol. 5, no. 5, pp. 48–53, 2019.

S. Katoch, S. S. Chauhan, V. Kumar, “A review on genetic algorithm: past, present, and future,” Multimedia Tools and Applications, vol. 80, no. 5, pp. 8091–8126, 2021, doi: 10.1007/s11042-020-10139-6.

A. Vukadinović, J. Radosavljević, A. Ðorđević, M. Protić, N. Petrović, “Multi-objective optimization of energy performance for a detached residential building with a sunspace using the nsga-ii genetic algorithm,” Solar Energy, vol. 224, pp. 1426–1444, 2021, doi: https://doi.org/10.1016/j.solener.2021.06.082.

S. Wang, D. Zhao, J. Yuan, H. Li, Y. Gao, “Application of nsga-ii algorithm for fault diagnosis in power system,” Electric Power Systems Research, vol. 175, p. 105893, 2019, doi: https://doi.org/10.1016/j.epsr.2019.105893.

M. A. J. Idrissi, H. Ramchoun, Y. Ghanou, M. Ettaouil, “Genetic algorithm for neural network architecture optimization,” in 2016 3rd International Conference on Logistics Operations Management (GOL), 2016, pp. 1–4.

Y. Wu, J. Wei, W. Ying, Y. Lan, Z. Cui, Z. Wang, “A collaborative decomposition-based evolutionary algorithm integrating normal and penalty-based boundary intersection methods for many-objective optimization,” Information Sciences, vol. 616, pp. 505–525, 2022, doi: https://doi.org/10.1016/j.ins.2022.10.136.

S. Verma, M. Pant, V. Snasel, “A comprehensive review on nsga-ii for multi-objective combinatorial optimization problems,” IEEE Access, vol. 9, pp. 57757–57791, 2021, doi: 10.1109/ACCESS.2021.3070634.

F. Troncoso-Pastoriza, M. Martínez-Comesaña, A. Ogando-Martínez, J. López-Gómez, P. Eguía-Oller, L. Febrero-Garrido, “Iot-based platform for automated ieq spatio-temporal analysis in buildings using machine learning techniques,” Automation in Construction, vol. 139, p. 104261, 2022, doi: https://doi.org/10.1016/j.autcon.2022.104261.

Z. Pang, F. Niu, Z. O’Neill, “Solar radiation prediction using recurrent neural network and artificial neural network: A case study with comparisons,” Renewable Energy, vol. 156, pp. 279–289, 2020, doi: https://doi.org/10.1016/j.renene.2020.04.042.

U. O. W.-M. Solar Energy Laboratory, TRNSYS, a transient simulation program. Madison, Wis. : The Laboratory, 1975., 1975.

A. Remlaoui, D. Nehari, M. Laissaoui, A. M. Sandid, “Performanceevaluation of a solar thermal and photovoltaic hybrid system powering a direct contact membrane distillation: Trnsys simulation,” Desalin. Water Treat, vol. 194, pp. 37–51, 2020.

J. López Gómez, A. Ogando Martínez, F. Troncoso Pastoriza, L. Febrero Garrido, E. Granada Álvarez, J. A. Orosa García, “Photovoltaic power prediction using artificial neural networks and numerical weather data,” Sustainability, vol. 12, no. 24, 2020, doi: 10.3390/su122410295.

X. de Galicia, “Meteogalicia,” 2021. [Online]. Available: https://www.meteogalicia.gal/web/RSS/rssIndex.action, Last access: 12 September 2022.

NOAA, “The global forecast system (gfs) - global spectral model (gsm),” 2021. [Online]. Available: https://www.emc.ncep.noaa.gov/emc/pages/numerical_forecast_systems/gfs/documentation.php, Last access: 12 September 2022.

G. Van Rossum, F. L. Drake Jr, “Python/c api reference manual,” Python Software Foundation, 2002.

S. Martínez, E. Pérez, P. Eguía, A. Erkoreka, E. Granada, “Model calibration and exergoeconomic optimization with nsga-ii applied to a residential cogeneration,” Applied Thermal Engineering, vol. 169, p. 114916, 2020, doi: https://doi.org/10.1016/j.applthermaleng.2020.114916.

A. E. I. Brownlee, J. A. Wright, “Constrained, mixed-integer and multi-objective optimisation of building designs by nsga-ii with fitness approximation,” Applied Soft Computing, vol. 33, pp. 114–126, 2015, doi: https://doi.org/10.1016/j.asoc.2015.04.010.

M. K. Park, J. M. Lee, W. H. Kang, J. M. Choi, K. H. Lee, “Predictive model for pv power generation using rnn (lstm),” Journal of Mechanical Science and Technology, vol. 35, no. 2, pp. 795–803, 2021, doi: 10.1007/s12206-021-0140-0.

B. Kim, D. Suh, “Solar photovoltaic generation forecasting using machine learning methods,” The Journal of Contents Computing, vol. 2, no. 1, pp. 105–112, 2020.

B. Kim, D. Suh, “A hybrid spatio-temporal prediction model for solar photovoltaic generation using numerical weather data and satellite images,” Remote Sensing, vol. 12, no. 22, 2020, doi: 10.3390/rs12223706.

ANSI/ASHRAE, “Measurement of energy and demand savings,” in ASHRAE Guideline 14-2002, vol. 8400, 2002, p. 170.