Open Access
Subscription Access
Application of Artificial Intelligence in Power Management of Hybrid Renewable Power System
Abstract
This work looks at optimizing the performance of proton exchange membrane and solar hydrogen fuel cell in a hybrid system for efficient power generation using artificial intelligence. This kind of decentralized system is frequently located in remote and inaccessible areas with no access to electric grid. How to control and handle power is one key issue confronting hybrid renewable power generation system due to their unstable nature. Fuel cell is integrated with the photovoltaic as a means of support since the PV is not dependable during bad weather or at night. The data used for the study was obtained from the meteorological agency of selected areas. The hybrid system consisting of 60kW PV array and 40kW Proton Exchange Membrane Fuel Cell (PEMFC). The system is designed in MATLAB/Simulink software to meet a user load demand of 40kW. This study proposes an intelligent switching controller that can monitor the eratic weather condition and ensures a proper coordination between the solar PV and fuel cell generator at a minimum time via Fuzzy Logic control algorithm to ensure continuous supply and load demand consistency. The analysis of the system shows that perturb and observe local controller algorithm proves to be suitable in extracting maximum power from the PV panels with tracking efficiency greater than 94.5%. Also, the fuzzy logic controller was able to ensure proper regulation and coordination of the solar PV and fuel cell generator switching status with respect to changes in the external environment and in load demand. The results also proves that the proposed Hybrid System performs well under a range of operating conditions and maintained the electrolyser SOC at a reasonable level of 79% -98%. When the result was compared with IEEE 1547 and IEC 61727 international standards, it meets the requirements and so, can be effectively integrated into the national grid based on the IEEE 1547 and IEC 61727standard.
References
Caballero, F., Sauma, E. & Yanine, F. (2023). Business Optimal Design of a Grid-Connected Hybrid Photovoltaic-wind energy system. Journal of Energy, 6(1), 248-261.
Fadare, D. A. (2019). A Statistical analysis of wind energy potential in Ibadan, Nigeria, based on weibull distribution function, The pacific journal of science and technology, 9(1), 110–119.
González, A., Riba, J. R., Rius, A. & Puig, R. (2020) Optimal sizing of a hybrid grid-connected photovoltaic and wind power system. Applied Energy, 154, 752–762.
Liu, Z., Chen, Y., Luo, Y., Zhao, G. & Jin, X. (2021). Optimized planning of power source capacity in microgrid, considering combinations of energy storage devices. Applied Sciences (Switzerland), 6(12), 416.
Yang, H., Ma, T., Lu, L. & Peng, J. (2020). Optimal design of an autonomous solar-wind-pumped storage power supply system. Applied Energy, 160, 728–736.
Idoniboyeobu, D. C., Orike, S. & Biragbara, B. P. (2017). Optimization of a Grid Connected Photovoltaic System Using Fuzzy Logic Control. European Journal of Electrical and Computer Engineering, 1(2), 1-13.
Jadhav, H. T. & Roy, R. (2022). Stochastic optimal power flow incorporating offshore wind farm and electric vehicles. International Journal of Electrical Power & Energy Systems, 69, 173–187.
Chung, C. Y. Ke, D. & Sun, Y. (2018) A novel probabilistic optimal power flow model with uncertain wind power generation described by customized Gaussian mixture model. IEEE Transactions on Sustainable Energy, 7(1), 200–212.
Reynolds, P., Li, J., Wang, Y. & Wang, T. (2022). Evaluation of the optimal turbine pressure drop ratio for a solar chimney power plant. Energy Conversion and Management, 108, 14–22.
Jang, B., Krimb, F., Belmilia, H., Almia, M. F. & Bouloumaa, S. (2019). Advanced Fuzzy Maximum Power Point Tracking (MPPT) Controller for a stand-alone PV system. Solar Energy, 50(9), 383–392.
Refbacks
- There are currently no refbacks.