Issue
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Optimized BiLSTM-Dense Model for Ultra-Short-Term PV Power Forecasting
Corresponding Author(s) : Prihatin Oktivasari
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control,
Vol. 10, No. 2, May 2025
Abstract
The growing integration of photovoltaic (PV) systems into power grids poses challenges due to the inherent variability in PV output, particularly during rapid weather changes. While existing forecasting methods often struggle to capture these fluctuations, accurate ultra-short-term PV power prediction is critical for grid stability. The study aims to develop an optimized BiLSTM-Dense model that enhances forecasting accuracy by incorporating an additional dense layer. The model is designed to improve forecasting performance over a 30-second horizon. It utilizes a dataset of solar irradiance, PV output power, surface temperature, ambient temperature, humidity, and wind speed, collected in late 2023. Data preprocessing involved normalization and smoothing techniques to enhance robustness. Hyperparameter optimization was performed using grid search. Evaluation results demonstrate the superiority of the proposed model, achieving an MAE of 0.00271 and an RMSE of 0.00806 when paired with the Adam optimizer and Swish activation function. Compared to standard BiLSTM, the BiLSTM-Dense achieved MAE and RMSE improvements of 0.52% and 2.19%, respectively. It also outperformed the LSTM model with reductions of 4.00% in MAE and 2.65% in RMSE, and significantly surpassed ARIMA, reducing MAE by 98.87% and RMSE by 97.21%. These findings highlight the model’s ability to capture complex, non-linear dependencies in PV output data, outperforming conventional approaches like ARIMA, which rely on linear assumptions, and simpler architectures like LSTM, which lack bidirectional context integration.
Keywords
Download Citation
Endnote/Zotero/Mendeley (RIS)BibTeX
- T. K. Abdus Salam Howlader, Md Humaun Kabir, S M Shafkat Newaz, “INTEGRATING SOLAR POWER WITH EXISTING GRIDS: STRATEGIES, TECHNOLOGIES, AND CHALLENGES – A REVIEW,” Glob. MAINSTREAM J., vol. 1, no. 2, pp. 48–62, May 2024, doi: 10.62304/ijse.v1i2.142.
- Q. Hassan et al., “Enhancing smart grid integrated renewable distributed generation capacities: Implications for sustainable energy transformation,” Sustain. Energy Technol. Assessments, vol. 66, p. 103793, Jun. 2024, doi: 10.1016/j.seta.2024.103793.
- D. Díaz-Bedoya, M. González-Rodríguez, J.-M. Clairand, X. Serrano-Guerrero, and G. Escrivá-Escrivá, “Forecasting Univariate Solar Irradiance using Machine learning models: A case study of two Andean Cities,” Energy Convers. Manag., vol. 296, p. 117618, Nov. 2023, doi: 10.1016/j.enconman.2023.117618.
- Wisdom Samuel Udo, Jephta Mensah Kwakye, Darlington Eze Ekechukwu, and Olorunshogo Benjamin Ogundipe, “PREDICTIVE ANALYTICS FOR ENHANCING SOLAR ENERGY FORECASTING AND GRID INTEGRATION,” Eng. Sci. Technol. J., vol. 4, no. 6, pp. 589–602, Dec. 2023, doi: 10.51594/estj.v4i6.1394.
- K. Hu, Z. Fu, C. Lang, W. Li, Q. Tao, and B. Wang, “Short-Term Photovoltaic Power Generation Prediction Based on Copula Function and CNN-CosAttention-Transformer,” Sustainability, vol. 16, no. 14, p. 5940, Jul. 2024, doi: 10.3390/su16145940.
- F.-F. Liu, S.-C. Chu, C.-C. Hu, J. Watada, and J.-S. Pan, “An effective QUATRE algorithm based on reorganized mechanism and its application for parameter estimation in improved photovoltaic module,” Heliyon, vol. 9, no. 6, p. e16468, Jun. 2023, doi: 10.1016/j.heliyon.2023.e16468.
- O. Doelle, N. Klinkenberg, A. Amthor, and C. Ament, “Probabilistic Intraday PV Power Forecast Using Ensembles of Deep Gaussian Mixture Density Networks,” Energies, vol. 16, no. 2, p. 646, Jan. 2023, doi: 10.3390/en16020646.
- J. Gaboitaolelwe, A. M. Zungeru, A. Yahya, C. K. Lebekwe, D. N. Vinod, and A. O. Salau, “Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison,” IEEE Access, vol. 11, pp. 40820–40845, 2023, doi: 10.1109/ACCESS.2023.3270041.
- A. Abdellatif et al., “Forecasting Photovoltaic Power Generation with a Stacking Ensemble Model,” Sustainability, vol. 14, no. 17, p. 11083, Sep. 2022, doi: 10.3390/su141711083.
- A. F. Amiri, A. Chouder, H. Oudira, S. Silvestre, and S. Kichou, “Improving Photovoltaic Power Prediction: Insights through Computational Modeling and Feature Selection,” Energies , vol. 17, no. 13, p. 3078, Jun. 2024, doi: 10.3390/en17133078.
- M. M. Taye, “Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions,” Computers, vol. 12, no. 5, p. 91, Apr. 2023, doi: 10.3390/computers12050091.
- H. Agarwal, G. Mahajan, A. Shrotriya, and D. Shekhawat, “Predictive Data Analysis: Leveraging RNN and LSTM Techniques for Time Series Dataset,” Procedia Comput. Sci., vol. 235, pp. 979–989, 2024, doi: 10.1016/j.procs.2024.04.093.
- L. Uma Maheshwari, G. Vallathan, K. Govindharaju, and D. . Geriyaashakthi, “Forecasting and Analysis of IoT Data by Employing Long Short-Term Memory (LSTM) Networks,” in 2023 International Conference on Emerging Research in Computational Science (ICERCS), IEEE, Dec. 2023, pp. 1–7. doi: 10.1109/ICERCS57948.2023.10434142.
- H. Yadav and A. Thakkar, “NOA-LSTM: An efficient LSTM cell architecture for time series forecasting,” Expert Syst. Appl., vol. 238, p. 122333, Mar. 2024, doi: 10.1016/j.eswa.2023.122333.
- Q. Kang, D. Yu, K. H. Cheong, and Z. Wang, “Deterministic convergence analysis for regularized long short-term memory and its application to regression and multi-classification problems,” Eng. Appl. Artif. Intell., vol. 133, p. 108444, Jul. 2024, doi: 10.1016/j.engappai.2024.108444.
- C. Qin, L. Chen, Z. Cai, M. Liu, and L. Jin, “Long short-term memory with activation on gradient,” Neural Networks, vol. 164, pp. 135–145, Jul. 2023, doi: 10.1016/j.neunet.2023.04.026.
- B. He, L. Li, Y. Bo, and J. Zhou, “Bi-directional LSTM-GRU Based Time Series Forecasting Approach,” Int. J. Comput. Sci. Inf. Technol., vol. 3, no. 2, pp. 222–231, Jul. 2024, doi: 10.62051/ijcsit.v3n2.26.
- Y. Fan, Q. Tang, Y. Guo, and Y. Wei, “BiLSTM-MLAM: A Multi-Scale Time Series Prediction Model for Sensor Data Based on Bi-LSTM and Local Attention Mechanisms,” Sensors, vol. 24, no. 12, p. 3962, Jun. 2024, doi: 10.3390/s24123962.
- L. Wencheng and M. Zhizhong, “Short-Term Photovoltaic Power Forecasting Using Enhanced Bidirectional Long Short-Term Memory Networks,” in 2024 36th Chinese Control and Decision Conference (CCDC), IEEE, May 2024, pp. 3308–3312. doi: 10.1109/ccdc62350.2024.10587916.
- T. Anu Shalini and B. Sri Revathi, “Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems,” Automatika, vol. 64, no. 1, pp. 127–144, Jan. 2023, doi: 10.1080/00051144.2022.2118101.
- N. Sutarna, C. Tjahyadi, P. Oktivasari, M. Dwiyaniti, and Tohazen, “Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting,” J. Robot. Control, vol. 5, no. 3, pp. 677–693, Mar. 2024, doi: 10.18196/jrc.v5i3.21120.
- 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.
- 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.
- 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), IEEE, Sep. 2023, pp. 221–225. doi: 10.1109/IC2IE60547.2023.10330942.
- D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, Jul. 2021, doi: 10.7717/peerj-cs.623.
- D. S. K. Karunasingha, “Root mean square error or mean absolute error? Use their ratio as well,” Inf. Sci. (Ny)., vol. 585, pp. 609–629, Mar. 2022, doi: 10.1016/j.ins.2021.11.036.
- D. G. Taslim and I. M. Murwantara, “Comparative analysis of ARIMA and LSTM for predicting fluctuating time series data,” Bull. Electr. Eng. Informatics, vol. 13, no. 3, pp. 1943–1951, Jun. 2024, doi: 10.11591/eei.v13i3.6034.
References
T. K. Abdus Salam Howlader, Md Humaun Kabir, S M Shafkat Newaz, “INTEGRATING SOLAR POWER WITH EXISTING GRIDS: STRATEGIES, TECHNOLOGIES, AND CHALLENGES – A REVIEW,” Glob. MAINSTREAM J., vol. 1, no. 2, pp. 48–62, May 2024, doi: 10.62304/ijse.v1i2.142.
Q. Hassan et al., “Enhancing smart grid integrated renewable distributed generation capacities: Implications for sustainable energy transformation,” Sustain. Energy Technol. Assessments, vol. 66, p. 103793, Jun. 2024, doi: 10.1016/j.seta.2024.103793.
D. Díaz-Bedoya, M. González-Rodríguez, J.-M. Clairand, X. Serrano-Guerrero, and G. Escrivá-Escrivá, “Forecasting Univariate Solar Irradiance using Machine learning models: A case study of two Andean Cities,” Energy Convers. Manag., vol. 296, p. 117618, Nov. 2023, doi: 10.1016/j.enconman.2023.117618.
Wisdom Samuel Udo, Jephta Mensah Kwakye, Darlington Eze Ekechukwu, and Olorunshogo Benjamin Ogundipe, “PREDICTIVE ANALYTICS FOR ENHANCING SOLAR ENERGY FORECASTING AND GRID INTEGRATION,” Eng. Sci. Technol. J., vol. 4, no. 6, pp. 589–602, Dec. 2023, doi: 10.51594/estj.v4i6.1394.
K. Hu, Z. Fu, C. Lang, W. Li, Q. Tao, and B. Wang, “Short-Term Photovoltaic Power Generation Prediction Based on Copula Function and CNN-CosAttention-Transformer,” Sustainability, vol. 16, no. 14, p. 5940, Jul. 2024, doi: 10.3390/su16145940.
F.-F. Liu, S.-C. Chu, C.-C. Hu, J. Watada, and J.-S. Pan, “An effective QUATRE algorithm based on reorganized mechanism and its application for parameter estimation in improved photovoltaic module,” Heliyon, vol. 9, no. 6, p. e16468, Jun. 2023, doi: 10.1016/j.heliyon.2023.e16468.
O. Doelle, N. Klinkenberg, A. Amthor, and C. Ament, “Probabilistic Intraday PV Power Forecast Using Ensembles of Deep Gaussian Mixture Density Networks,” Energies, vol. 16, no. 2, p. 646, Jan. 2023, doi: 10.3390/en16020646.
J. Gaboitaolelwe, A. M. Zungeru, A. Yahya, C. K. Lebekwe, D. N. Vinod, and A. O. Salau, “Machine Learning Based Solar Photovoltaic Power Forecasting: A Review and Comparison,” IEEE Access, vol. 11, pp. 40820–40845, 2023, doi: 10.1109/ACCESS.2023.3270041.
A. Abdellatif et al., “Forecasting Photovoltaic Power Generation with a Stacking Ensemble Model,” Sustainability, vol. 14, no. 17, p. 11083, Sep. 2022, doi: 10.3390/su141711083.
A. F. Amiri, A. Chouder, H. Oudira, S. Silvestre, and S. Kichou, “Improving Photovoltaic Power Prediction: Insights through Computational Modeling and Feature Selection,” Energies , vol. 17, no. 13, p. 3078, Jun. 2024, doi: 10.3390/en17133078.
M. M. Taye, “Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions,” Computers, vol. 12, no. 5, p. 91, Apr. 2023, doi: 10.3390/computers12050091.
H. Agarwal, G. Mahajan, A. Shrotriya, and D. Shekhawat, “Predictive Data Analysis: Leveraging RNN and LSTM Techniques for Time Series Dataset,” Procedia Comput. Sci., vol. 235, pp. 979–989, 2024, doi: 10.1016/j.procs.2024.04.093.
L. Uma Maheshwari, G. Vallathan, K. Govindharaju, and D. . Geriyaashakthi, “Forecasting and Analysis of IoT Data by Employing Long Short-Term Memory (LSTM) Networks,” in 2023 International Conference on Emerging Research in Computational Science (ICERCS), IEEE, Dec. 2023, pp. 1–7. doi: 10.1109/ICERCS57948.2023.10434142.
H. Yadav and A. Thakkar, “NOA-LSTM: An efficient LSTM cell architecture for time series forecasting,” Expert Syst. Appl., vol. 238, p. 122333, Mar. 2024, doi: 10.1016/j.eswa.2023.122333.
Q. Kang, D. Yu, K. H. Cheong, and Z. Wang, “Deterministic convergence analysis for regularized long short-term memory and its application to regression and multi-classification problems,” Eng. Appl. Artif. Intell., vol. 133, p. 108444, Jul. 2024, doi: 10.1016/j.engappai.2024.108444.
C. Qin, L. Chen, Z. Cai, M. Liu, and L. Jin, “Long short-term memory with activation on gradient,” Neural Networks, vol. 164, pp. 135–145, Jul. 2023, doi: 10.1016/j.neunet.2023.04.026.
B. He, L. Li, Y. Bo, and J. Zhou, “Bi-directional LSTM-GRU Based Time Series Forecasting Approach,” Int. J. Comput. Sci. Inf. Technol., vol. 3, no. 2, pp. 222–231, Jul. 2024, doi: 10.62051/ijcsit.v3n2.26.
Y. Fan, Q. Tang, Y. Guo, and Y. Wei, “BiLSTM-MLAM: A Multi-Scale Time Series Prediction Model for Sensor Data Based on Bi-LSTM and Local Attention Mechanisms,” Sensors, vol. 24, no. 12, p. 3962, Jun. 2024, doi: 10.3390/s24123962.
L. Wencheng and M. Zhizhong, “Short-Term Photovoltaic Power Forecasting Using Enhanced Bidirectional Long Short-Term Memory Networks,” in 2024 36th Chinese Control and Decision Conference (CCDC), IEEE, May 2024, pp. 3308–3312. doi: 10.1109/ccdc62350.2024.10587916.
T. Anu Shalini and B. Sri Revathi, “Hybrid power generation forecasting using CNN based BILSTM method for renewable energy systems,” Automatika, vol. 64, no. 1, pp. 127–144, Jan. 2023, doi: 10.1080/00051144.2022.2118101.
N. Sutarna, C. Tjahyadi, P. Oktivasari, M. Dwiyaniti, and Tohazen, “Hyperparameter Tuning Impact on Deep Learning Bi-LSTM for Photovoltaic Power Forecasting,” J. Robot. Control, vol. 5, no. 3, pp. 677–693, Mar. 2024, doi: 10.18196/jrc.v5i3.21120.
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.
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.
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), IEEE, Sep. 2023, pp. 221–225. doi: 10.1109/IC2IE60547.2023.10330942.
D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, p. e623, Jul. 2021, doi: 10.7717/peerj-cs.623.
D. S. K. Karunasingha, “Root mean square error or mean absolute error? Use their ratio as well,” Inf. Sci. (Ny)., vol. 585, pp. 609–629, Mar. 2022, doi: 10.1016/j.ins.2021.11.036.
D. G. Taslim and I. M. Murwantara, “Comparative analysis of ARIMA and LSTM for predicting fluctuating time series data,” Bull. Electr. Eng. Informatics, vol. 13, no. 3, pp. 1943–1951, Jun. 2024, doi: 10.11591/eei.v13i3.6034.