Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting

Nana Sutarna, Christianto Tjahyadi, Prihatin Oktivasari, Murie Dwiyaniti, Tohazen Tohazen

Abstract


Solar energy is one of the most promising renewable energy sources that can reduce greenhouse gas emissions and fossil fuel dependence. However, solar energy production is highly variable and uncertain due to the influence of weather conditions and environmental factors. Accurate forecasting of photovoltaic (PV) power output is essential for optimal planning and operation of PV systems, as well as for integrating them into the power grid. This study develops a deep learning model based on Bidirectional Long Short-Term Memory (Bi-LSTM) to predict short-term PV power output. The main objective is to examine the effect of hyperparameter tuning on the forecasting accuracy and the actual PV output power. The main contribution is identifying the optimal combination of hyperparameters, namely the optimizer, the learning rate, and the activation function, for the PV output. The dataset consists of 143786 observations from sensors measuring solar irradiation, PV surface temperature, ambient temperature, ambient humidity, wind speed, and PV power output for 50 days in Bandung, Indonesia. The data is preprocessed by smoothing and splitting into training (70%, 35 days), validation (15%, 7.5 days), and testing (15%, 7.5 days) sets. The Bi-LSTM model is trained and tested with two optimizers: Adam and RMSprop, and three activation functions: Tanh, ReLU, and Swish, with different learning rates. The results indicate that the optimal performance is obtained by the Bi-LSTM model with Adam optimizer, learning rate of 〖1e〗^(-4), and Tanh activation function. This model has the lowest MAE of 0.002931070979684591, the lowest RMSE of 0.008483537231080387, and the highest R-squared of 0.9988813964105624 when tested with the validation dataset and requires 93 epochs to build. The model also performs well on the test dataset, with the lowest MAE of 0.002717077964916825, the lowest RMSE of 0.007629486798682186, and the highest R-squared of 0.9992563395109665. This study concludes that hyperparameter tuning is a vital step in developing the Bi-LSTM model to improve the accuracy of PV output power prediction.

Keywords


Photovoltaic; Hyperparameter; Deep Learning; Bi-LSTM; PV Power Forecasting.

Full Text:

PDF

References


A. O. M. Maka and J. M. Alabid, “Solar energy technology and its roles in sustainable development,” Clean Energy, vol. 6, no. 3, pp. 476–483, Jun. 2022, doi: 10.1093/ce/zkac023.

D. Palmer, R. Gottschalg, and T. Betts, “The future scope of large-scale solar in the UK: Site suitability and target analysis,” Renew Energy, pp. 1136–1146, Apr. 2019, doi: 10.1016/j.renene.2018.08.109.

G. Rausser, G. Chebotareva, L. Smutka, W. Strielkowski, and J. Shiryaeva, “Future Development of Renewable Energy in Russia: A Case of Solar Power,” Front Energy Res, vol. 10, Mar. 2022, doi: 10.3389/fenrg.2022.862201.

M. Izanloo, Y. Noorollahi, and A. Aslani, “Future energy planning to maximize renewable energy share for the south Caspian Sea climate,” Renew Energy, vol. 175, pp. 660–675, Sep. 2021, doi: 10.1016/j.renene.2021.05.008.

J. Jurasz, F. A. Canales, A. Kies, M. Guezgouz, and A. Beluco, “A review on the complementarity of renewable energy sources: Concept, metrics, application and future research directions,” Solar Energy, vol. 195. pp. 703–724, 2020, doi: 10.1016/j.solener.2019.11.087.

Š. Bojnec, “Electricity Markets, Electricity Prices and Green Energy Transition,” Energies, vol. 16, no. 2, 2023, doi: 10.3390/en16020873.

S. Ambec and C. Crampes, “Real-time electricity pricing to balance green energy intermittency,” Energy Econ., vol. 94, 2021, doi: 10.1016/j.eneco.2020.105074.

A. V. Rodrigues, D. A. R. de Souza, F. D. R. Garcia, and S. J. L. Ribeiro, “Renewable energy for a green future: Electricity produced from efficient luminescent solar concentrators,” Solar Energy Advances, vol. 2, p. 100013, 2022, doi: 10.1016/j.seja.2022.100013.

M. Izanloo, Y. Noorollahi, and A. Aslani, “Future energy planning to maximize renewable energy share for the south Caspian Sea climate,” Renew Energy, vol. 175, pp. 660–675, Sep. 2021, doi: 10.1016/j.renene.2021.05.008.

D. Yang, “The future of solar forecasting in China,” Journal of Renewable and Sustainable Energy, vol. 15, no. 5, Sep. 2023, doi: 10.1063/5.0172315.

P. Piotrowski, M. Parol, P. Kapler, and B. Fetliński, “Advanced Forecasting Methods of 5-Minute Power Generation in a PV System for Microgrid Operation Control,” Energies, vol. 15, no. 7, Apr. 2022, doi: 10.3390/en15072645.

L. D. Riihimaki, X. Li, Z. Hou, and L. K. Berg, “Improving prediction of surface solar irradiance variability by integrating observed cloud characteristics and machine learning,” Solar Energy, vol. 225, pp. 275–285, Sep. 2021, doi: 10.1016/j.solener.2021.07.047.

Q. Paletta, G. Arbod, and J. Lasenby, “Benchmarking of deep learning irradiance forecasting models from sky images – An in-depth analysis,” Solar Energy, vol. 224, pp. 855–867, Aug. 2021, doi: 10.1016/j.solener.2021.05.056.

J. Ramirez-Vergara, L. B. Bosman, W. D. Leon-Salas, and E. Wollega, “Ambient temperature and solar irradiance forecasting prediction horizon sensitivity analysis,” Machine Learning with Applications, vol. 6, p. 100128, Dec. 2021, doi: 10.1016/j.mlwa.2021.100128.

V. Sansine, P. Ortega, D. Hissel, and M. Hopuare, “Solar Irradiance Probabilistic Forecasting Using Machine Learning, Metaheuristic Models and Numerical Weather Predictions,” Sustainability, vol. 14, no. 22, Nov. 2022, doi: 10.3390/su142215260.

J. A. Bellido-Jiménez, J. Estévez Gualda, and A. P. García-Marín, “Assessing new intra-daily temperature-based machine learning models to outperform solar radiation predictions in different conditions,” Appl. Energy, vol. 298, Sep. 2021, doi: 10.1016/j.apenergy.2021.117211.

Y. Feng, D. Gong, Q. Zhang, S. Jiang, L. Zhao, and N. Cui, “Evaluation of temperature-based machine learning and empirical models for predicting daily global solar radiation,” Energy Convers. Manag., vol. 198, Oct. 2019, doi: 10.1016/j.enconman.2019.111780.

M. Borunda, A. Ramírez, R. Garduno, G. Ruíz, S. Hernandez, and O. A. Jaramillo, “Photovoltaic Power Generation Forecasting for Regional Assessment Using Machine Learning,” Energies, vol. 15, no. 23, Dec. 2022, doi: 10.3390/en15238895.

A. M. A. Malkawi, A. Odat, and A. Bashaireh, “A Novel PV Maximum Power Point Tracking Based on Solar Irradiance and Circuit Parameters Estimation,” Sustainability, vol. 14, no. 13, Jul. 2022, doi: 10.3390/su14137699.

M. Seapan, Y. Hishikawa, M. Yoshita, and K. Okajima, “Temperature and irradiance dependences of the current and voltage at maximum power of crystalline silicon PV devices,” Solar Energy, vol. 204, pp. 459–465, Jul. 2020, doi: 10.1016/j.solener.2020.05.019.

A. J. P. Aparicio, M. C. Gallego, M. Antón, and J. M. Vaquero, “Relationship between solar activity and direct solar irradiance in Madrid (1910–1929),” Atmos. Res., vol. 235, 2020, doi: 10.1016/j.atmosres.2019.104766.

M. Bhavani, K. Vijaybhaskar Reddy, K. Mahesh, and S. Saravanan, “Impact of variation of solar irradiance and temperature on the inverter output for grid connected photo voltaic (PV) system at different climate conditions,” Mater. Today Proc., vol. 80, pp. 2101–2108, Jan. 2023, doi: 10.1016/j.matpr.2021.06.120.

M. Alaraj, I. Alsaidan, A. Kumar, M. Rizwan, and M. Jamil, “Advanced Intelligent Approach for Solar PV Power Forecasting Using Meteorological Parameters for Qassim Region, Saudi Arabia,” Sustainability, vol. 15, no. 12, Jun. 2023, doi: 10.3390/su15129234.

C. Roh, “Deep-Learning Algorithmic-Based Improved Maximum Power Point-Tracking Algorithms Using Irradiance Forecast,” Processes, vol. 10, no. 11, 2022, doi: 10.3390/pr10112201.

M. Gao, J. Li, F. Hong, and D. Long, “Day-ahead power forecasting in a large-scale photovoltaic plant based on weather classification using LSTM,” Energy, vol. 187, p. 115838, 2019.

O. Jogunola et al., “CBLSTM-AE: A Hybrid Deep Learning Framework for Predicting Energy Consumption,” Energies, vol. 15, no. 3, Feb. 2022, doi: 10.3390/en15030810.

M. Alrashidi and S. Rahman, “Short-term photovoltaic power production forecasting based on novel hybrid data-driven models,” J. Big Data, vol. 10, no. 1, Dec. 2023, doi: 10.1186/s40537-023-00706-7.

K. J. Iheanetu, “Solar Photovoltaic Power Forecasting: A Review,” Sustainability, vol. 14, no. 24, 2022, doi: 10.3390/su142417005.

M. Z. A. Pon and K. P. KK, “Hyperparameter tuning of deep learning models in keras,” Sparklinglight Transactions on Artificial Intelligence and Quantum Computing (STAIQC), vol. 1, no. 1, pp. 36-40, 2021.

H. Dhake, Y. Kashyap, and P. Kosmopoulos, “Algorithms for Hyperparameter Tuning of LSTMs for Time Series Forecasting,” Remote Sens., vol. 15, no. 8, Apr. 2023, doi: 10.3390/rs15082076.

K. E. Hoque and H. Aljamaan, “Impact of hyperparameter tuning on machine learning models in stock price forecasting,” IEEE Access, vol. 9, pp. 163815–163830, 2021, doi: 10.1109/ACCESS.2021.3134138.

C. Stoean et al., “Metaheuristic-Based Hyperparameter Tuning for Recurrent Deep Learning: Application to the Prediction of Solar Energy Generation,” Axioms, vol. 12, no. 3, Mar. 2023, doi: 10.3390/axioms12030266.

S. Wang and J. Ma, “A novel GBDT-BiLSTM hybrid model on improving day-ahead photovoltaic prediction,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-42153-7.

R. Guanoluisa, D. Arcos-Aviles, M. Flores-Calero, W. Martinez, and F. Guinjoan, “Photovoltaic Power Forecast Using Deep Learning Techniques with Hyperparameters Based on Bayesian Optimization: A Case Study in the Galapagos Islands,” Sustainability, vol. 15, no. 16, Aug. 2023, doi: 10.3390/su151612151.

R. Herrera-Casanova, A. Conde, and C. Santos-Pérez, “Hour-Ahead Photovoltaic Power Prediction Combining BiLSTM and Bayesian Optimization Algorithm, with Bootstrap Resampling for Interval Predictions,” Sensors, vol. 24, no. 3, p. 882, Jan. 2024, doi: 10.3390/s24030882.

A. Salam, A. El Hibaoui, and A. Saif, “A comparison of activation functions in multilayer neural network for predicting the production and consumption of electricity power,” International Journal of Electrical and Computer Engineering, vol. 11, no. 1, pp. 163–170, Feb. 2021, doi: 10.11591/ijece.v11i1.pp163-170.

M. Zulfiqar, K. A. A. Gamage, M. Kamran, and M. B. Rasheed, “Hyperparameter Optimization of Bayesian Neural Network Using Bayesian Optimization and Intelligent Feature Engineering for Load Forecasting,” Sensors, vol. 22, no. 12, Jun. 2022, doi: 10.3390/s22124446.

H. F. Mateo Romero et al., “Applications of Artificial Intelligence to Photovoltaic Systems: A Review,” Applied Sciences (Switzerland), vol. 12, no. 19, 2022, doi: 10.3390/app121910056.

V. Suresh, P. Janik, J. Rezmer, and Z. Leonowicz, “Forecasting solar PV output using convolutional neural networks with a sliding window algorithm,” Energies, vol. 13, no. 3, 2020, doi: 10.3390/en13030723.

M. Cordeiro-Costas, D. Villanueva, P. Eguía-Oller, and E. Granada-Álvarez, “Machine Learning and Deep Learning Models Applied to Photovoltaic Production Forecasting,” Applied Sciences, vol. 12, no. 17, Sep. 2022, doi: 10.3390/app12178769.

M. Tovar, M. Robles, and F. Rashid, “PV power prediction, using CNN-LSTM hybrid neural network model. Case of study: Temixco-Morelos, México,” Energies, vol. 13, no. 24, Dec. 2020, doi: 10.3390/en13246512.

L. Liu et al., “A Photovoltaic Power Prediction Approach Based on Data Decomposition and Stacked Deep Learning Model,” Electronics, vol. 12, no. 13, Jul. 2023, doi: 10.3390/electronics12132764.

B. Brahma and R. Wadhvani, “Solar irradiance forecasting based on deep learning methodologies and multi-site data,” Symmetry, vol. 12, no. 11, pp. 1–20, Nov. 2020, doi: 10.3390/sym12111830.

N. Khortsriwong et al., “Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant,” Energies, vol. 16, no. 5, Mar. 2023, doi: 10.3390/en16052119.

J. Dumas, C. Cointe, X. Fettweis, and B. Cornélusse, “Deep learning-based multi-output quantile forecasting of PV generation,” 2021 IEEE Madrid PowerTech, pp. 1-6, 2021, doi: 10.1109/PowerTech46648.2021.9494976.

D. Van Tai, “Solar photovoltaic power output forecasting using machine learning technique,” in Journal of Physics: Conference Series, vol. 1327, no. 1, p. 012051, 2019, doi: 10.1088/1742-6596/1327/1/012051.

L. Wen, X. Ye, and L. Gao, “A new automatic machine learning based hyperparameter optimization for workpiece quality prediction,” Measurement and Control, vol. 53, no. 7–8, pp. 1088–1098, Aug. 2020, doi: 10.1177/0020294020932347.

S. Choi and J. Hur, “An ensemble learner-based bagging model using past output data for photovoltaic forecasting,” Energies, vol. 13, no. 6, 2020, doi: 10.3390/en13061438.

Y. Zhou, Y. Liu, D. Wang, X. Liu, and Y. Wang, “A review on global solar radiation prediction with machine learning models in a comprehensive perspective,” Energy Conversion and Management, vol. 235, 2021, doi: 10.1016/j.enconman.2021.113960.

C. Singh and A. R. Garg, “Machine Learning Approach for Output Power Forecasting of Grid Connected Solar PV Plant in Madurai,” International Journal on Electrical Engineering and Informatics, vol. 15, no. 3, pp. 416–434, Sep. 2023, doi: 10.15676/ijeei.2023.15.3.4.

T. Handhayani, I. Lewenusa, D. E. Herwindiati, and J. Hendryli, "A Comparison of LSTM and BiLSTM for Forecasting the Air Pollution Index and Meteorological Conditions in Jakarta," 2022 5th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), pp. 334-339, 2022, doi: 10.1109/ISRITI56927.2022.10053078.

X. Huang, C. Zhang, Q. Li, Y. Tai, B. Gao, and J. Shi, “A Comparison of Hour-Ahead Solar Irradiance Forecasting Models Based on LSTM Network,” Math. Probl. Eng., vol. 2020, 2020, doi: 10.1155/2020/4251517.

S. Ghimire, R. C. Deo, N. Raj, and J. Mi, “Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms,” Appl. Energy, vol. 253, Nov. 2019, doi: 10.1016/j.apenergy.2019.113541.

M. A. Bou-Rabee, M. Y. Naz, I. E. D. Albalaa, and S. A. Sulaiman, “BiLSTM Network-Based Approach for Solar Irradiance Forecasting in Continental Climate Zones,” Energies, vol. 15, no. 6, pp. 1–12, May 2022.

N. Sutarna, C. Tjahyadi, P. Oktivasari, M. Dwiyaniti, and Tohazen, “Machine Learning Algorithm and Modeling in Solar Irradiance Forecasting,” in 2023 6th International Conference of Computer and Informatics Engineering (IC2IE), pp. 221–225, 2023, doi: 10.1109/IC2IE60547.2023.10330942.

P. Kumari and D. Toshniwal, “Deep learning models for solar irradiance forecasting: A comprehensive review,” Journal of Cleaner Production, vol. 318, 2021, doi: 10.1016/j.jclepro.2021.128566.

H. Jiang, N. Lu, J. Qin, W. Tang, and L. Yao, “A deep learning algorithm to estimate hourly global solar radiation from geostationary satellite data,” Renewable and Sustainable Energy Reviews, vol. 114, Oct. 2019, doi: 10.1016/j.rser.2019.109327.

M. N. Akhter et al., “An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants,” Energies, vol. 15, no. 6, Mar. 2022, doi: 10.3390/en15062243.

G. Li, H. Wang, S. Zhang, J. Xin, and H. Liu, “Recurrent neural networks based photovoltaic power forecasting approach,” Energies, vol. 12, no. 13, 2019, doi: 10.3390/en12132538.

H. K. Ahn and N. Park, “Deep rnn-based photovoltaic power short-term forecast using power iot sensors,” Energies, vol. 14, no. 2, May 2021, doi: 10.3390/en14020436.

C. Tao, J. Lu, J. Lang, X. Peng, K. Cheng, and S. Duan, “Short-term forecasting of photovoltaic power generation based on feature selection and bias compensation–lstm network,” Energies, vol. 14, no. 11, Jun. 2021, doi: 10.3390/en14113086.

V. H. Wentz, J. N. Maciel, J. J. G. Ledesma, and O. H. A. Junior, “Solar Irradiance Forecasting to Short-Term PV Power: Accuracy Comparison of ANN and LSTM Models,” Energies, vol. 15, no. 7, Apr. 2022, doi: 10.3390/en15072457.

S. Padhan and D. Tripathy, “Power Forecasting with Minimal Loss using LSTM and PV Model,” in ICPEE 2021 - 2021 1st International Conference on Power Electronics and Energy, 2021, doi: 10.1109/ICPEE50452.2021.9358565.

L. Y. P. C. Tan Jic Feng Dandan, “Very Short-Term Solar Generation Forecasting Based on LSTM with Temporal Attention Mechanism,” in Very Short-Term Solar Generation Forecasting Based on LSTM with Temporal Attention Mechanism, 2019 IEEE 5th International Conference on Computer and Communications, pp. 267–271, 2019.

G. Venitourakis et al., “Neural Network-Based Solar Irradiance Forecast for Edge Computing Devices,” Information, vol. 14, no. 11, p. 617, Nov. 2023, doi: 10.3390/info14110617.

M. Husein and I. Y. Chung, “Day-ahead solar irradiance forecasting for microgrids using a long short-term memory recurrent neural network: A deep learning approach,” Energies, vol. 12, no. 10, 2019, doi: 10.3390/en12101856.

M. Konstantinou, S. Peratikou, and A. G. Charalambides, “Solar photovoltaic forecasting of power output using lstm networks,” Atmosphere, vol. 12, no. 1, pp. 1–17, Jan. 2021, doi: 10.3390/atmos12010124.

J. Xie, B. Chen, X. Gu, F. Liang, and X. Xu, “Self-Attention-Based BiLSTM Model for Short Text Fine-Grained Sentiment Classification,” IEEE Access, vol. 7, pp. 180558–180570, 2019, doi: 10.1109/ACCESS.2019.2957510.

T. Peng, C. Zhang, J. Zhou, and M. S. Nazir, “An integrated framework of Bi-directional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting,” Energy, vol. 221, Apr. 2021, doi: 10.1016/j.energy.2021.119887.

F. R. Alharbi and D. Csala, “Wind speed and solar irradiance prediction using a bidirectional long short-term memory model based on neural networks,” Energies, vol. 14, no. 20, May 2021, doi: 10.3390/en14206501.

M. S. Hossain and 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.

L. Liu, J. Chen, X. Liu, and J. Yang, “An Improved Method for Photovoltaic Forecasting Model Training Based on Similarity,” Electronics, vol. 12, no. 9, May 2023, doi: 10.3390/electronics12092119.

M. Imani and H. R. Arabnia, “Hyperparameter Optimization and Combined Data Sampling Techniques in Machine Learning for Customer Churn Prediction: A Comparative Analysis,” Technologies, vol. 11, no. 6, p. 167, Nov. 2023, doi: 10.3390/technologies11060167.

A. Hussain, Z. A. Khan, T. Hussain, F. U. M. Ullah, S. Rho, and S. W. Baik, “A Hybrid Deep Learning-Based Network for Photovoltaic Power Forecasting,” Complexity, vol. 2022, 2022, doi: 10.1155/2022/7040601.

X. Luo and D. Zhang, “An adaptive deep learning framework for day-ahead forecasting of photovoltaic power generation,” Sustainable Energy Technologies and Assessments, vol. 52, p. 102326, 2022.

S. C. Lim, J. H. Huh, S. H. Hong, C. Y. Park, and J. C. Kim, “Solar Power Forecasting Using CNN-LSTM Hybrid Model,” Energies, vol. 15, no. 21, Nov. 2022, doi: 10.3390/en15218233.

T. Limouni, R. Yaagoubi, K. Bouziane, K. Guissi, and E. H. Baali, “Univariate and Multivariate LSTM Models for One Step and Multistep PV Power Forecasting,” International Journal of Renewable Energy Development, vol. 11, no. 3, pp. 815–828, Aug. 2022, doi: 10.14710/ijred.2022.43953.

K. Albeladi, B. Zafar, and A. Mueen, “Time Series Forecasting using LSTM and ARIMA,” 2018 IEEE 17th International Conference on Machine Learning and Applications, pp. 313-320, 2018.

M. Abumohsen, A. Y. Owda, and M. Owda, “Electrical Load Forecasting Using LSTM, GRU, and RNN Algorithms,” Energies, vol. 16, no. 5, Mar. 2023, doi: 10.3390/en16052283.

G. Li, S. Xie, B. Wang, J. Xin, Y. Li, and S. Du, “Photovoltaic Power Forecasting With a Hybrid Deep Learning Approach,” IEEE Access, vol. 8, pp. 175871–175880, 2020, doi: 10.1109/ACCESS.2020.3025860.

M. A. Bou‐rabee, M. Y. Naz, I. E. D. Albalaa, and S. A. Sulaiman, “BiLSTM Network‐Based Approach for Solar Irradiance Forecasting in Continental Climate Zones,” Energies, vol. 15, no. 6, Mar. 2022, doi: 10.3390/en15062226.




DOI: https://doi.org/10.18196/jrc.v5i3.21120

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Nana Sutarna, Christianto Tjahyadi, Prihatin Oktivasari, Murie Dwiyaniti, Tohazen

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

 

Journal of Robotics and Control (JRC)

P-ISSN: 2715-5056 || E-ISSN: 2715-5072
Organized by Peneliti Teknologi Teknik Indonesia
Published by Universitas Muhammadiyah Yogyakarta in collaboration with Peneliti Teknologi Teknik Indonesia, Indonesia and the Department of Electrical Engineering
Website: http://journal.umy.ac.id/index.php/jrc
Email: jrcofumy@gmail.com

Kuliah Teknik Elektro Terbaik