Abstract
Nowadays, various advanced techniques, like big data and deep learning, have been used in energy management systems for improving energy efficiency. Various research has been done on solar power generation prediction using multiple machine learning approaches. However, it is not easy to make exact predictions due to the alternative nature of solar energy. Therefore, this work aims to accurately implement and compare the neural network models to predict solar power generation. The models in this study are implemented using Python, TensorFlow, and Keras. The performance of the models is evaluated using 500 KWp grid-connected plant data. This work forecasted a solar power generation for 72 h using a time series dataset. Approximately, three years of the dataset are collected from January 2019 to October 2021 with hourly resolution from Airport Depot, Delhi, India. This paper compared the performance of the recurrent neural network (RNN) and long short-term memory (LSTM) in the form of accuracy. The three-year energy generation dataset is split into train and test data. The train data uses three years of energy generation data from January 2019 to September 2021, while the test data are used for October 2021. As a result, the determinant of coefficient (R \(^{2}\)) is a statistical error matrix representing the predicted values’ accuracy. The results show that the LSTM model predicts solar power generation with high accuracy (R \(^{2}\) = 0.92).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sweeney C, Bessa RJ, Browell J, Pinson P (2020) The future of forecasting for renewable energy. Wiley Interdisc Rev Energy Environ 9(2):e365
Ugurlu U, Oksuz I, Tas O (2018) Electricity price forecasting using recurrent neural networks. Energies 11(5)
Ahmed A, Khalid M (2019) A review on the selected applications of forecasting models in renewable power systems. Renew Sustain Energy Rev 100:9–21
Antonanzas J, Osorio N, Escobar R, Urraca R, de Pison FM, Antonanzas-Torres F (2016) Review of photovoltaic power forecasting. Solar Energy 136:78–111
Lotufo ADP (2020) Solar photovoltaic power forecasting. J Electr Comput Eng 020:8819925
Sobri S, Koohi-Kamali S, Rahim NA (2018) Solar photovoltaic generation forecasting methods: a review. Energy Convers Manage 156:459–497
Persson C, Bacher P, Shiga T, Madsen H (2017) Multi-site solar power forecasting using gradient boosted regression trees. Solar Energy 150:423–436
Kushwaha V, Pindoriya NM (2019) A sarima-rvfl hybrid model assisted by wavelet decomposition for very short-term solar pv power generation forecast. Renew Energy 140:124–139
Raza MQ, Mithulananthan N, Summerfield A (2018) Solar output power forecast using an ensemble framework with neural predictors and Bayesian adaptive combination. Solar Energy 166:226–241
Lin K-P, Pai P-F (2016) Solar power output forecasting using evolutionary seasonal decomposition least-square support vector regression. J Cleaner Prod 134:456–462
Chen Z, Chen Y, Wu L, Cheng S, Lin P, You L (2019) Accurate modeling of photovoltaic modules using a 1-d deep residual network based on i–v characteristics. Energy Convers Manage 186:168–187
Zheng J, Xu C, Zhang Z, Li X (2017) Electric load forecasting in smart grids using long-short-term-memory based recurrent neural network. In: 2017 51st Annual conference on information sciences and systems (CISS), pp 1–6
Ma J, Ma X (2018) A review of forecasting algorithms and energy management strategies for microgrids. Syst Sci Control Eng 6(1):237–248
Sun Y, Venugopal V, Brandt AR (2018) Convolutional neural network for short-term solar panel output prediction. IEEE, pp 2357–2361
Fan C, Wang J, Gang W, Li S (2019) Assessment of deep recurrent neural network-based strategies for short-term building energy predictions. Appl Energy 236:700–710
Mishra S, Palanisamy P (2018) Multi-time-horizon solar forecasting using recurrent neural network. In: 2018 IEEE energy conversion congress and exposition (ECCE). IEEE, pp 18–24
Xiaoqiao H, Zhang C, Li Q, Yonghang T, Gao B, Shi J (2020) A comparison of hour-ahead solar irradiance forecasting models based on lstm network. Math Probl Eng 2020:1–15
Srivastava S, Lessmann S (2018) A comparative study of lstm neural networks in forecasting day-ahead global horizontal irradiance with satellite data. Solar Energy 162:232–247
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Neeraj, Gupta, P., Tomar, A. (2022). A Comparison of Hourly Solar Energy Generation Forecasting Using RNN and LSTM Network. In: Tomar, A., Malik, H., Kumar, P., Iqbal, A. (eds) Proceedings of 3rd International Conference on Machine Learning, Advances in Computing, Renewable Energy and Communication. Lecture Notes in Electrical Engineering, vol 915. Springer, Singapore. https://doi.org/10.1007/978-981-19-2828-4_20
Download citation
DOI: https://doi.org/10.1007/978-981-19-2828-4_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2827-7
Online ISBN: 978-981-19-2828-4
eBook Packages: Computer ScienceComputer Science (R0)