Performance Evaluation of ANN-based MPPT included in Grid Feeding Inverter

Performance Evaluation of ANN-based MPPT included in Grid Feeding Inverter

1. IC3ECSBHI 2025 IEEE International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics PAPER TITLE: Performance Evaluation of ANN-based MPPT included in Grid Feeding Inverter PAPER ID: 1416 ORGANIZED BY: School Of Engineering, Gautam Buddha University, Gr. Noida, India Presenter/ Author(s) : Dr. Farhad Ilahi Bakhsh Affiliation : National Institute of Technology Srinagar

2. CONTENTS IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025)

3. INTRODUCTION & BRIEF REVIEW IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025)

4. Objectives IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025)

5. METHODOLOGY || DESIGNING OF GRID-INTEGRATED SYSTEM IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) The system integrates PV with the grid using DC-DC and DC-AC converters and ANN-based MPPT for optimal performance. The LCL filter ensures smooth grid integration. System Design Developed a 4.5kV single phase transformer-less grid interconnected PV system. Components used in the methodology are as follows. PV array : Converts solar energy into DC power (4.5kW) DC-DC boost converter : Boosts voltage to match grid needs. DC-AC inverter : Converts DC to AC for grid compatibility ANN Based controller : Optimize power extraction dynamically. Figure 1 . Schematic structure of grid connected system

6. METHODOLOGY || DESIGNING OF GRID-INTEGRATED SYSTEM IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) 2.1 Photovoltaic Array A photovoltaic array is a group of modules linked in series or parallel to supply the necessary power, whereas a solar panel is a collection of cells tied in series and parallel to provide the needed capacity. Maximum power rating , P m 249.86 Open circuit voltage, V oc 37.6 Short circuit current, I sc 8.55 Current at Maximum power, I m 8.06 Voltage at Maximum power, V m 31 Current temperature coefficient, K T 0.06 Voltage temperature coefficient, K V -0.35 Configuration : 2 parallel and 8 series panels Table 1 Specification of PV module

7. METHODOLOGY || DESIGNING OF GRID-INTEGRATED SYSTEM IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) 2.2 DC-DC Converter DC-DC Boost converter is introduced between the PV module and load point to obtain a regulated and desirable output. The duty cycle that is supplied to the boost converter allows it to function. The duty cycle was calculated using the MPPT approach, taking into account PV output. The inductor current, = 13.8 mH The capacitor voltage, = 200 μ F  

8. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) The ANN-based MPPT surpasses traditional P&O by offering higher precision and faster tracking. It efficiently adapts to dynamic weather conditions. MPPT Technique Perturb and Observe (P&O); Simple iterative approach with oscillations near MPP. Slower response under dynamic condition Artificial Neural Network (ANN) Two-layer feedforward neural network trained using Bayesian Regularization. Inputs: Irradiation and temperature. Outputs: Optimal voltage ( Vmpp ) and current ( Impp ). Maximum Power Point Tracking Figure 3. Basic structure of two-layer ANN

9. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Maximum Power Point Tracking Figure 4 . Regression Plot of ANN Model Figure 6 . Performance Evaluation of ANN technique Figure 5 . Histogram of Energy generation of ANN model Figure 7 . Training state plot of ANN model

10. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Simulation Results | MPPT Performance Figure 12 . DC Power at the converter respective with ideal maximum power Figure 11 . Duty cycle variation respective to irradiation Figure 10 . Output Current at Converter Figure 9 . DC Voltage at Converter

11. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Simulation Results | MPPT Performance   Irradiance Maximum Power (Pm) (W) Output Power (Pout) (W) Input Power (Pin) (W) Efficiency ( η ) (%) Output Voltage Ripple (%) Output Current Ripple (%) P&O ANN P&O ANN P&O ANN P&O ANN P&O ANN 1000W/m2 4497 4301 4325 4413 4431 97.46 97.61 0.54 0.51 0.53 0.45 800W/m2 3600 3253 3519 3355 3595 96.95 97.88 0.53 0.32 0.63 0.33 600W/m2 2696 1859 2612 1924 2657 96.62 98.31 0.52 0.29 0.58 0.37 400W/m2 1785 831 1490 860.4 1509 96.61 98.72 0.58 0.14 0.55 0.19 200W/m2 873.5 208.9 448.8 216.5 452.1 96.50 99.21 0.61 0.10 0.56 0.16 Figure 13 . Actual Efficiency at varying irradiance condition Table 2 Comparative parameters of P&O and ANN MPPT

12. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Simulation Results | ANN Grid integration Figure 14 . DC Link Voltage and Power Figure 15 . Generated PWM signal for VSI Figure 16 . Inverter end Voltage Figure 17 . Grid Voltage Figure 18 . Grid Current Figure 19 . Phasor Active and Reactive Power

13. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Simulation Results | ANN Grid integration Figure 20 . THD examination at grid current

14. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) Conclusion

15. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) References [1] Rezvani , Alireza, et al. “Investigation of ANN-GA and Modified Perturb and Observe MPPT Techniques for Photovoltaic System in the Grid Connected Mode.” Indian Journal of Science and Technology, vol. 8, no. 1, Jan. 2015, p. 87, doi:10.17485/ ijst /2015/v8i1/54277. [2] Izadbakhsh M, Gandomkar M, Rezvani A, Ahmadi A. Short-term resource scheduling of a renewable energy based micro grid. Renew Energ . 2015; 75:598–606. [3] Salas V, Olias E, Barrado A, Lazaro A. Review of the maximum power point tracking algorithms for stand-alone photovoltaic systems. Sol Energ Mater Sol Cell. 2006; 90(11):1555–78. [4] N. Karami, N. Moubayed , and R. Outbib , ‘‘General review and classification of different MPPT techniques,’’ Renew. Sustain. Energy Rev., vol. 68, pp. 1–18, Feb. 2017, doi : 10.1016/j.rser.2016.09.132. [5] C. H. Basha and C. Rani, ‘‘Different conventional and soft computing MPPT techniques for solar PV systems with high step-up boost converters: A comprehensive analysis,’’ Energies, vol. 13, no. 2, p. 371, Jan. 2020.

16. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) References [6] F. Khan and A. Tariq, "Comparative Analysis Of Solar Fed DC-DC Converter Controlled With Different Types Of MPPT Algorithm," 2023 International Conference on Power, Instrumentation, Energy and Control (PIECON), Aligarh, India, 2023, pp. 1-6, doi : 10.1109/PIECON56912.2023.10085886. [7] L. Chen and X. Wang, ‘‘Enhanced MPPT method based on ANN-assisted sequential Monte–Carlo and quickest change detection,’’ IET Smart Grid, vol. 2, no. 4, pp. 635–644, Dec. 2019. [8 ] K. K. Mohammed, S. Buyamin , I. Shams, and S. Mekhilef , ‘‘Maximum power point tracking based on adaptive neuro-fuzzy inference systems for a photovoltaic system with fast varying load conditions,’’ Int. Trans. Electr . Energy Syst., vol. 31, no. 6, 2021, Art. no. e12904. [9] A. A. Aldair, A. A. Obed, and A. F. Halihal , ‘‘Design and implementation of ANFIS-reference model controller based MPPT using FPGA for photovoltaic system,’’ Renew. Sustain. Energy Rev., vol. 82, pp. 2202– 2217, Feb. 2018. [10]K. Mohammad, M. F. Rashid, H. Rahat, F. Khan and K. Rahman, "Detailed Analysis of DC-DC Converters Fed with Solar-PV System with MPPT," 2022 International Conference for Advancement in Technology (ICONAT), Goa, India, 2022, pp. 1-6, doi : 10.1109/ICONAT53423.2022.9725881.

17. IEEE INTERNATIONAL CONFERENCE ON COGNITIVE COMPUTING IN ENGINEERING, COMMUNICATIONS, SCIENCES AND BIOMEDICAL HEALTH INFORMATICS (IC3ECSBHI-2025) References