Journal of Solar Energy Research

Convolutional Neural Network–Long Short-Term Memory Based Intelligent Adaptive DSTATCOM Control for Enhanced Power Quality in Photovoltaic-Integrated Distribution Networks

Document Type : Research Article

Authors

1 Department of Electrical Engineering, Biju Pattnaik University of Technology, Rourkela, Odisha, India

2 School of Electrical Sciences, Odisha University of Technology and Research, Bhubaneswar, India

3 Department of Electrical and Electronics Engineering, Sreenidhi institute of science and Technology Hyderabad, India

10.22059/jser.2026.407530.1677

Abstract

This paper presents a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) based intelligent adaptive control strategy for a DSTATCOM to enhance power quality in photovoltaic (PV)-integrated distribution networks. The proposed controller exploits CNN-based spatial feature extraction of voltage–current waveforms and LSTM-based temporal learning to address nonlinear and time-varying disturbances. Simulation and real-time hardware-in-the-loop (HIL) validation using an OPAL-RT platform confirm superior performance under dynamic irradiance (200–1000 W/m²) and load variations (up to 50 kW). The DC-link voltage is tightly regulated within 758–764 V, with a maximum deviation below 3 V. Total Harmonic Distortion (THD) is reduced from 16.5–22.5% to 3.2–4.5%, achieving 79–82% harmonic suppression and compliance with IEEE-519 limits. The power factor improves from 0.78–0.84 to 0.97–0.99, approaching unity. The proposed controller exhibits a fast dynamic response of 3.8 ms, outperforming PI, Fuzzy-PID, ANN, CNN, and LSTM controllers. Reactive power tracking errors remain below 2.7%, demonstrating high robustness and real-time adaptability for smart PV-integrated grids.

Keywords

  1. Wu, G., Hu, D., Zhang, Y., Bao, G., & He, T. (2024). A convolutional neural network–long short-term memory–attention solar photovoltaic power prediction–correction model based on the division of twenty-four solar terms. Energies, 17(22), Article 5549. https://doi.org/10.3390/en17225549
  2. Hu, F., Zhang, L., & Wang, J. (2024). A hybrid convolutional–long short-term memory–attention framework for short-term photovoltaic power forecasting, incorporating data from neighboring stations. Applied Sciences, 14(12), Article 5189. https://doi.org/10.3390/app14125189
  3. Ledmaoui, Y., El Maghraoui, A., El Aroussi, M., & Saadane, R. (2024). Enhanced fault detection in photovoltaic panels using CNN-based classification with PyQt5 implementation. Sensors, 24(22), Article 7407. https://doi.org/10.3390/s24227407
  4. Chen, J.-H., Tan, K.-H., & Lee, Y.-D. (2022). Intelligent controlled DSTATCOM for power quality enhancement. Energies, 15(11), Article 4017. https://doi.org/10.3390/en15114017
  5. Alharkan, H., Habib, S., & Islam, M. (2023). Solar power prediction using dual stream CNN-LSTM architecture. Sensors, 23(2), Article 945. https://doi.org/10.3390/s23020945
  6. Vali, A. K., Varma, P. S., Reddy, C. R., Alanazi, A., & Elrashidi, A. (2025). Deep-learning-based controller for parallel DSTATCOM to improve power quality in distribution system. Energies, 18(18), Article 4902. https://doi.org/10.3390/en18184902
  7. Wang, J., Zhang, Z., Xu, W., Li, Y., & Niu, G. (2025). Short-term photovoltaic power forecasting using a Bi-LSTM neural network optimized by hybrid algorithms. Sustainability, 17(12), Article 5277. https://doi.org/10.3390/su17125277
  8. Kiasari, M., & Aly, H. (2025). AI-driven control strategies for FACTS devices in power quality management: A comprehensive review. Applied Sciences, 15(22), Article 12050. https://doi.org/10.3390/app152212050
  9. Ren, X., Zhang, F., Yan, J., & Liu, Y. (2024). A novel convolutional neural net architecture based on incorporating meteorological variable inputs into ultra-short-term photovoltaic power forecasting. Sustainability, 16(7), Article 2786. https://doi.org/10.3390/su16072786
  10. Garcia, C. I., et al. (2020). A comparison of power quality disturbance detection and classification methods using CNN, LSTM and CNN-LSTM. Applied Sciences, 10(19), Article 6755. https://doi.org/10.3390/app10196755
  11. Bui Duy, L., et al. (2024). Refining long short-term memory neural network input parameters for enhanced solar power forecasting. Energies, 17(16), Article 4174. https://doi.org/10.3390/en17164174
  12. Okwako, O. E., et al. (2022). Neural network controlled solar PV battery powered unified power quality conditioner for grid connected operation. Energies, 15(18), Article 6825. https://doi.org/10.3390/en15186825
  13. Lim, S.-C., Huh, J.-H., Hong, S.-H., Park, C.-Y., & Kim, J.-C. (2022). Solar power forecasting using CNN-LSTM hybrid model. Energies, 15(21), Article 8233. https://doi.org/10.3390/en15218233
  14. Shang, L., et al. (2023). CNN-LSTM hybrid model to promote signal processing of ultrasonic guided Lamb waves for damage detection in metallic pipelines. Sensors, 23(16), Article 7059. https://doi.org/10.3390/s23167059
  15. Kim, J. W., & Park, S. (2018). Magnetic flux leakage sensing and artificial neural network pattern recognition-based automated damage detection and quantification for wire rope non-destructive evaluation. Sensors, 18, Article 109. https://doi.org/10.3390/s18010109
  16. Bai, H., et al. (2025). Power quality disturbance classification strategy based on fast S-transform and an improved CNN-LSTM hybrid model. Processes, 13(3), Article 743. https://doi.org/10.3390/pr13030743
  17. Yang, L., Li, H., Zhang, H., Wu, Q., & Cao, X. (2024). Stochastic-distributionally robust frequency-constrained optimal planning for an isolated microgrid. IEEE Transactions on Sustainable Energy, 15, 2155–2169. https://doi.org/10.1016/j.ijepes.2025.110986
  18. Khetarpal, P., et al. (2023). Power quality disturbances detection and classification based on deep convolution auto-encoder networks. IEEE Access, 11, 46026–46038. doi: 10.1109/ACCESS.2023.3274732.
  19. Li, J., Lin, H., Liang, C., Teng, Z., & Cheng, D. (2019). Power quality disturbance detection method based on dual-resolution S-transform and learning vector quantization neural network. Transactions of China Electrotechnical Society, 34, 3453–3463. https://doi.org/10.32604/ee.2023.025900
  20. Zhang, L., Ding, Z., Xia, R., & Guo, F. (2023). Power quality data compression algorithm combining second-generation wavelet and fast Fourier transform. Southern Power System Technology, 7, (5). https://doi.org/10.3390/pr13030743
  21. Zhu, K., et al. (2024). Aiming to complex power quality disturbances: A novel decomposition and detection framework. IEEE Transactions on Industrial Informatics, 20, 4317–4326. DOI: 1049/gtd2.13200
  22. Karchi, N., et al. (2022). Adaptive least mean square controller for power quality enhancement in solar photovoltaic system. Energies, 15(23), Article 8909. https://doi.org/10.3390/en15238909
  23. Iweh, C. D., et al. (2021). Distributed generation and renewable energy integration into the grid: Prerequisites, push factors, practical options, issues and merits. Energies, 14, 5375. https://doi.org/10.3390/en14175375
  24. Patel, H., Gajjar, R., & Pandya, R. (2019). Artificial intelligence based MPPT techniques for solar PV system: A review. JETIR, 8, 1043–1059. https://ssrn.com/abstract=3708145
  25. Salem, E. Z. M., & Alranini, M. A. L. (2021). Review of maximum power point tracking algorithms of the PV system. Frontiers in Engineering and Built Environment, 1, 68–80. DOI: 1108/FEBE-03-2021-0019
  26. Pallavi, V., & Mahajan, P. (2020). Smooth LMS-based adaptive control of PV system tied to the grid for enhanced power quality. IET Power Electronics, 13, 3456–3466. https://doi.org/10.1049/iet-pel.2020.0134
  27. Avdhesh, K., & Garg, R. (2021). Control of grid integrated photovoltaic system using new variable step size least mean square adaptive filter. Electrical Engineering, 103, 2945–2959. https://doi.org/10.3390/en15238909
  28. Banik, A., et al. (2022). Design, modelling, and analysis of novel solar PV system using MATLAB. Materials Today: Proceedings, 51, 756–763. DOI: 1016/j.matpr.2021.06.226
  29. Jenisha, C. M. (2021). Decoupled control with constant DC link voltage for PV-fed single-phase grid connected systems. In Integration of renewable energy sources with smart grid (pp. 171–185). Hoboken, NJ, USA: Wiley. https://doi.org/10.3390/en15238909
  30. Babu, N. P. (2024). Adaptive grid-connected inverter control schemes for power quality enrichment in microgrid systems: Past, present, and future perspectives. Electric Power Systems Research, 230, 110288. https://doi.org/10.1016/j.epsr.2024.110288
  31. Ganthia, B. P., Mohanty, S., Rana, P. K., & Sahu, P. K. (2016). Compensation of voltage sag using DVR with PI controller. In Proceedings of ICEEOT (pp. 2138–2142). Chennai, India. doi: 10.1109/ICEEOT.2016.7755068.
  32. Rajendran, G., Raute, R., & Caruana, C. (2025). A comprehensive review of solar PV integration with smart-grids: Challenges, standards, and grid codes. Energies, 18(9), Article 2221. https://doi.org/10.3390/en18092221
  33. Li, P., & Huo, X. (2025). Simplified finite control set model predictive control for single-phase grid-tied inverters with twisted parameters. Electric Power Systems Research, 238, 111063. https://doi.org/10.3390/su17198729
  34. SivaramKrishnan, M., et al. (2025). Smart charging solution for electric vehicles: Leveraging grid connected solar PV with UPQC using HBA-MORARNN approach. Energy Reports, 13, 2454–2467. https://doi.org/10.1016/j.egyr.2025.02.004
  35. Ganthia, B. P., Pradhan, R., Das, S., & Ganthia, S. (2017). Analytical study of MPPT based PV system using fuzzy logic controller. In Proceedings of ICECDS (pp. 3266–3269). Chennai, India. doi: 10.1109/ICECDS.2017.8390063.
  36. Rubavathy, S. J., et al. (2021). Smart grid based multiagent system in transmission sector. In Proceedings of ICIRCA (pp. 1–5). Coimbatore, India. doi: 10.1109/ICIRCA51532.2021.9544644.
  37. Sahu, P. K., Mohanty, A., Ganthia, B. P., & Panda, A. K. (2016). A multiphase interleaved boost converter for grid-connected PV system. In Proceedings of MicroCom (pp. 1–6). Durgapur, India. doi: 10.1109/MicroCom.2016.7522539.
  38. Mohanty, M., Nayak, N., Ganthia, B. P., & Behera, M. K. (2023). Power smoothening of photovoltaic system using dynamic PSO with ESC under partial shading condition. In Proceedings of APSIT (pp. 675–680). Bhubaneswar, India. doi: 10.1109/APSIT58554.2023.10201763.
Journal of Solar Energy Research
Volume 11, Issue 1
January 2026
Pages 2780-2801