Educational Tool for Optimizing Component Selection in Micro Hydroelectric Power Systems

Micro hydropower plants offer a low-impact solution for rural electrification; however, the preliminary selection of turbines and components requires calculations that often exceed students’ foundational training. This paper presents an open-source educational tool, executable on Google Colab, that automates this selection and visualizes its impact on generated power and energy in real-time. Developed in Python 3.12 using NumPy, pandas, IP widgets, and matplotlib, the application receives flow rate, net head, shaft speed, and efficiency margins as input, computes the specific speed (NSR), and recommends the appropriate turbine through a hybrid algorithm that combines heuristic rules with a decision tree trained on 60 documented micro hydropower configurations. Technical validation achieved a 90% match with reference turbines and a mean absolute error of 4.13 kW in electric power output. Visual outputs, including the power-head curve, energy time curve, and 3D power-efficiency surface, enhanced conceptual understanding. In a pre-and post-test with 22 students, the tool improved selection accuracy, reduced decision time, and yielded a Cronbach’s alpha of 0.88, with 95% or more positive responses. These results demonstrate that a lightweight, reproducible solution can enhance design precision and support active learning. Future work will incorporate seasonal flow variability and multi-objective cost-performance optimization.