Josué Enmanuel Navarrete-Solano

Photovoltaic solar water pumping systems (PVSWPS) offer a sustainable solution for water access in remote rural areas, but their performance depends on tracking the maximum power point (MPP) of the photovoltaic (PV) array, which partial shading complicates by creating multiple local maxima in the power–voltage curve. This study presents the design and simulation in MATLAB/Simulink of a complete PVSWPS (PV array, Ćuk DC–DC converter, permanent magnet DC motor–centrifugal pump and hydraulic network) under partial shading scenarios representative of the Ecuadorian coast. Three MPPT strategies were compared: incremental conductance (IC-MPPT), particle swarm optimization exploiting empirically identified voltage clusters (PSO-MPPT), and an artificial neural network trained on the irradiance-to-MPP voltage relationship (ANN-MPPT). IC-MPPT converged to a local maximum in three of five scenarios, with a mean tracking error of 20.45%, whereas PSO-MPPT and ANN-MPPT reached 0.65% and 1.14%, increasing the pumped volume by approximately 6.5% and 7.0% in five stepped scenarios and by 3.9% and 4.6% in a 60 s continuous irradiance profile. This came with a lower converter efficiency (84.25% for IC-MPPT vs. 80.11% and 79.52%), a trade-off between tracking accuracy and efficiency. The net gain in delivered water supports intelligent MPPT for PV water pumping under frequent partial shading.

Photovoltaic solar water pumping systems (PVSWPS) offer a sustainable solution for water access in remote rural areas, but their performance strongly depends on accurately tracking the maximum power point (MPP) of the photovoltaic (PV) array, a task complicated by partial shading, which introduces multiple local maxima in the power–voltage characteristic. This study presents the design and simulation of a complete PVSWPS — comprising a PV array, a Ćuk DC–DC converter, a permanent magnet DC motor–centrifugal pump assembly, and a hydraulic network — modeled in MATLAB/Simulink and evaluated under partial shading scenarios representative of the Ecuadorian coast. Three MPPT strategies were implemented and compared: a conventional Incremental Conductance (IC-MPPT) algorithm, a Particle Swarm Optimization-based algorithm (PSO-MPPT) exploiting empirically identified voltage clusters, and an Artificial Neural Network-based algorithm (ANN-MPPT) trained on the irradiance-to-MPP voltage relationship. Results show that IC-MPPT converges to a local maximum in three of five evaluated scenarios, with a mean tracking error of 20.45%, whereas PSO-MPPT and ANN-MPPT maintain mean errors of 0.90% and 1.71%, respectively, increasing cumulative pumped water volume by approximately 5.7% and 5.1%. This gain came with a modest reduction in converter conversion efficiency, revealing a trade-off between tracking accuracy and efficiency that has received limited attention in the literature. These findings support the adoption of intelligent MPPT strategies for photovoltaic water pumping under frequent partial shading conditions.

Advances in machine learning have improved the ability to predict critical environmental conditions, including solar radiation levels that, while essential for life, can pose serious risks to human health. In Ecuador, due to its geographical location and altitude, UV radiation reaches extreme levels. This study presents the development of a chatbot system driven by a hybrid artificial intelligence model, combining Random Forest, CatBoost, Gradient Boosting, and a 1D Convolutional Neural Network. The model was trained with meteorological data, optimized using hyperparameters (iterations: 500–1500, depth: 4–8, learning rate: 0.01–0.3), and evaluated through MAE, MSE, R², and F1-Score. The hybrid model achieved superior accuracy (MAE = 13.77 W/m², MSE = 849.96, R² = 0.98), outperforming traditional methods. A 15% error margin was observed without significantly affecting classification. The chatbot, implemented via Telegram and hosted on Heroku, provided real-time personalized alerts, demonstrating an effective, accessible, and scalable solution for health safety and environmental awareness. Furthermore, it facilitates decision-making in the efficient generation of renewable energy and supports a more sustainable energy transition. It offers a tool that strengthens the relationship between artificial intelligence and sustainability by providing a practical instrument for integrating clean energy and mitigating climate change.