A GRID SEARCH OPTIMIZED HYBRID MODEL FOR SOLAR IRRADIANCE FORECAST USING EMPIRICAL MODE DECOMPOSITION AND BIDIRECTIONAL GATED RECURRENT UNIT
DOI:
https://doi.org/10.55766/sujst6471Keywords:
Bidirectional Gated Recurrent Unit, Empirical Mode Decomposition, Grid Search, Long Short-Term Memory, Solar ForecastingAbstract
To ensure the reliable operation of the power grid, an accurate forecasting of solar irradiance (SI) is highly essential. Classical forecasting methods struggle to capture the fundamental nonlinearity of SI, resulting in low forecasting accuracy. A hybrid model based on deep learning (DL) technique called EMD-GS-BiGRU, which is the combination of empirical mode decomposition (EMD) with Bidirectional gated recurrent unit (BiGRU) predictor and grid search algorithm is proposed in this paper. The suggested EMD-GS-BiGRU model constructed and tested in two different Indian locations: Chennai and Jammu, for different popular models: artificial neural network (ANN), long short-term memory (LSTM), gated recurrent unit (GRU), and their EMD-based hybrid version i.e. EMD-GS-LSTM and EMD-GS-GRU. The evaluation of the performance of the proposed model is performed by statistical and graphical analysis of one hour ahead seasonal SI forecasts. According to the findings, the lower average root means square error (RMSE) of 64.39 W/m2-83.46 W/m2 is obtained by proposed model compared to contrast models. The proposed model also obtained higher yearly R2 value, 0.9366-0.955 compared to other models. Furthermore, the study found that the EMD with grid search optimized BiGRU enhanced the RMSE (39.23%-47.31%) and mean absolute percentage error (MAPE) (41.82%-52.31%) compared to other standalone contrast models.
References
Amer, H.N., Dahlan, N.Y., Azmi, A.M., Latip, M.F.A., Onn, M.S., and Tumian, A. (2023). Solar power prediction based on artificial neural network guided by feature selection for large-scale solar photovoltaic plant. Energy Reports, 9(Supplement 12):262-266. https://doi.org/10.1016/j.egyr.2023.09.141
Badoni, M., Singh, A., Singh, A.K., Saxena, H., and Kumar, R. (2023). Grid tied solar PV system with power quality enhancement using adaptive generalized maximum versoria criterion. CSEE Journal of Power and Energy Systems, 9(2):722-732.
Dhaked, D.K., Dadhich, S., and Birla, D. (2023). Power output forecasting of solar photovoltaic plant using LSTM. Green Energy and Intelligent Transportation, 2(5):100113. https://doi.org/10.1016/j.geits.2023.100113
Foo, Y.W., and Goh, C. (2021). Solar irradiance forecasting in tropical weather using an evolutionary lean neural network. In 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings (pp. 490-497). https://doi.org/10.1109/CEC45853.2021.9504875
Gayathry, V., Kaliyaperumal, D., and Salkuti, S.R. (2024). Seasonal solar irradiance forecasting using artificial intelligence techniques with uncertainty analysis. Scientific Reports, 14(1):1-19. https://doi.org/10.1038/s41598-024-68531-3
Gupta, A., Gupta, K., and Saroha, S. (2020). Solar irradiation forecasting technologies: A review. Strategic Planning for Energy and the Environment, 39(3-4):319-354.
Jailani, N.L.M., Dhanasegaran, J.K., Alkawsi, G., Alkahtani, A.A., Phing, C.C., Baashar, Y., Capretz, L.F., Al-Shetwi, A.Q., and Tiong, S.K. (2023). Investigating the power of LSTM-based models in solar energy forecasting. Processes, 11(5):1382. https://doi.org/10.3390/pr11051382
Jamei, M., Karbasi, M., Ali, M., Malik, A., Chu, X., and Yaseen, Z.M. (2023). A novel global solar exposure forecasting model based on air temperature: Designing a new multi-processing ensemble deep learning paradigm. Expert Systems with Applications, 222:119811. https://doi.org/10.1016/j.eswa.2023.119811
Kumar, R., Diwania, S., Khetrapal, P., and Singh, S. (2022a). Performance assessment of the two metaheuristic techniques and their hybrid for power system stability enhancement with PV-STATCOM. Neural Computing and Applications, 34(5):3723-3744. https://doi.org/10.1007/s00521-021-06637-9
Kumar, R., Diwania, S., Khetrapal, P., Singh, S., and Badoni, M. (2021). Multimachine stability enhancement with hybrid PSO-BFOA based PV-STATCOM. Sustainable Computing: Informatics and Systems, 32:100615. https://doi.org/10.1016/j.suscom.2021.100615
Kumar, R., Diwania, S., Singh, R., Ashfaq, H., Khetrapal, P., and Singh, S. (2022b). An intelligent hybrid wind-PV farm as a static compensator for overall stability and control of multimachine power system. ISA Transactions, 123:286-302. https://doi.org/10.1016/j.isatra.2021.05.014
Lai, C.S., Zhong, C., Pan, K., Ng, W.W.Y., and Lai, L.L. (2021). A deep learning-based hybrid method for hourly solar radiation forecasting. Expert Systems with Applications, 177:114941. https://doi.org/10.1016/j.eswa.2021.114941
Makade, R.G., Chakrabarti, S., and Jamil, B. (2021). Development of global solar radiation models: A comprehensive review and statistical analysis for Indian regions. Journal of Cleaner Production, 293:126208. https://doi.org/10.1016/j.jclepro.2021.126208
Obiora, C.N., Hasan, A.N., and Ali, A. (2023). Predicting solar irradiance at several time horizons using machine learning algorithms. Sustainability, 15(11):8927. https://doi.org/10.3390/su15118927
Qing, X., and Niu, Y. (2018). Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM. Energy, 148:461-468. https://doi.org/10.1016/j.energy.2018.01.177
Saroha, S., Zurek-Mortka, M., Szymanski, J.R., Shekher, V., and Singla, P. (2021). Forecasting of market clearing volume using wavelet packet-based neural networks with tracking signals. Energies, 14(19):6065. https://doi.org/10.3390/en14196065
Saxena, N., Kumar, R., Rao, Y.K.S.S., Mondloe, D.S., Dhapekar, N.K., Sharma, A., and Yadav, A.S. (2024). Hybrid KNN-SVM machine learning approach for solar power forecasting. Environmental Challenges, 14:100838. https://doi.org/10.1016/j.envc.2024.100838
Singh, S., Saini, S., Gupta, S.K., and Kumar, R. (2023). Solar-PV inverter for the overall stability of power systems with intelligent MPPT control of DC-link capacitor voltage. Protection and Control of Modern Power Systems, 8(1):15. https://doi.org/10.1186/s41601-023-00285-y
Singla, P., Duhan, M., and Saroha, S. (2021a). A comprehensive review and analysis of solar forecasting techniques. Frontiers in Energy, p. 1-37.
Singla, P., Duhan, M., and Saroha, S. (2021b). An ensemble method to forecast 24-h ahead solar irradiance using wavelet decomposition and BiLSTM deep learning network. Earth Science Informatics, 15(1):291-306. https://doi.org/10.1007/s12145-021-00723-1
Singla, P., Duhan, M., and Saroha, S. (2021c). Review of different error metrics: A case of solar forecasting. AIUB Journal of Science and Engineering (AJSE), 20(4):158-165. https://doi.org/10.53799/ajse.v20i4.212
Singla, P., Duhan, M., and Saroha, S. (2022a). A dual decomposition with error correction strategy based improved hybrid deep learning model to forecast solar irradiance, 44(1):1583-1607. https://doi.org/10.1080/15567036.2022.2056267
Singla, P., Duhan, M., and Saroha, S. (2022b). A hybrid solar irradiance forecasting using full wavelet packet decomposition and Bi-Directional Long Short-Term Memory (BiLSTM). Arabian Journal for Science and Engineering, 47(11):14211-14185. https://doi.org/10.1007/s13369-022-06655-2
Singla, P., Duhan, M., and Saroha, S. (2022c). An integrated framework of robust local mean decomposition and bidirectional long short-term memory to forecast solar irradiance. 20(10):1073-1085. https://doi.org/10.1080/15435075.2022.2143272
Singla, P., Duhan, M., and Saroha, S. (2022d). Different normalization techniques as data preprocessing for one step ahead forecasting of solar global horizontal irradiance. Artificial Intelligence for Renewable Energy Systems, p. 209-230. https://doi.org/10.1016/B978-0-323-90396-7.00004-3
Singla, P., Duhan, M., and Saroha, S. (2022e). Different optimizers-based gated recurrent unit network to forecast one step ahead solar irradiance. Lecture Notes in Electrical Engineering, 812:105-114. https://doi.org/10.1007/978-981-16-6970-5_9
Singla, P., Duhan, M., and Saroha, S. (2022f). One hour ahead solar irradiation forecast by deep learning network using meteorological variables. Lecture Notes in Electrical Engineering, 822:103-113. https://doi.org/10.1007/978-981-16-7664-2_9
Singla, P., Duhan, M., and Saroha, S. (2022g). Solar irradiation forecasting by long-short term memory using different training algorithms. p. 81-89. https://doi.org/10.1007/978-981-16-4663-8_7
Singla, P., Duhan, M., and Saroha, S. (2023a). A point and interval forecasting of solar irradiance using different decomposition based hybrid models. Earth Science Informatics, 16(3):2223-2240. https://doi.org/10.1007/s12145-023-01020-9
Singla, P., Duhan, M., and Saroha, S. (2023b). Performance evaluation of various solar forecasting models for structural & endogenous datasets. Distributed Generation & Alternative Energy Journal, 38(2):467-490. https://doi.org/10.13052/dgaej2156-3306.3825
Singla, P., Saroha, S., Duhan, M., Shekher, V., and Singh, K. (2024). A solar irradiance forecasting model using iterative filtering and bidirectional long short-term memory. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 46(1):8202-8222. https://doi.org/10.1080/15567036.2024.2370335
Wojtkiewicz, J., Hosseini, M., Gottumukkala, R., and Chambers, T.L. (2019). Hour-ahead solar irradiance forecasting using multivariate gated recurrent units. Energies, 12(21):4055. https://doi.org/10.3390/en12214055
