Accurate extraction of single-diode photovoltaic (PV) model parameters is essential for reliable performance prediction and diagnostics, yet five-parameter identification from I-V data is ill-posed and computationally expensive. To develop and validate a hybrid analytical–metaheuristic approach that derives the diode ideality factor, saturation current, and photocurrent analytically while optimizing only series and shunt resistances, thereby reducing computational cost without sacrificing accuracy. I-V datasets were collected from a 9.54 kW grid-connected PV installation in Algiers, Algeria (15 operating points; 747–815 W m⁻²; 25.4–28.4 °C). Nine metaheuristics—Stellar Oscillation Optimizer, Enzyme Action Optimization, Grey Wolf Optimizer, Whale Optimization Algorithm, Cuckoo Search, Owl Search Algorithm, Improved War Strategy Optimization, Rüppell’s Fox Optimizer, and Artificial Bee Colony—were benchmarked against full five-parameter optimization and a Newton–Raphson baseline, using root-mean-squared error (RMSE) as the objective and wall-time as the efficiency metric. The hybrid scheme reduced the decision space from five to two parameters and lowered computational cost by ≈60–70% relative to full-parameter optimization while closely reproducing measured I-V/P-V curves. Across datasets, algorithms achieved RMSE ≈ 2.49 × 10⁻² − 2.78 × 10⁻². Rüppell’s Fox Optimizer offered the best overall trade-off (lowest average RMSE and fastest runtime), with Whale Optimization Algorithm a strong alternative (typical runtimes ≈ 107–112 s). Partitioning identification between closed-form physics and light-weight optimization yields robust, accurate, and efficient PV parameter estimation suitable for time-sensitive or embedded applications. Dynamic validation using 1498 real-world measurements across clear-sky and cloudy conditions demonstrates excellent performance: current prediction $R^2=0.9882$, power estimation $R^2=0.9730$, and voltage tracking $R^2=0.9613$. Comprehensive environmental analysis across a 39.2 °C temperature range and diverse irradiance conditions ($0\text{–}1014 \mathrm{W}/{\mathrm{m}}^2$) validates the method’s robustness for practical PV monitoring applications.

Grid-connected photovoltaic (PV) systems integrated into industrial and institutional buildings are critical components of sustainable built environments, where accurate real-time power estimation underpins smart energy management, demand–supply balancing, and reduced dependence on the utility grid. This study develops and validates an Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting of the flexible power point (FPP) in a 117.76 kWp rooftop PV plant serving a technical workshop facility in northwestern Algeria. The proposed model uses environmental inputs (solar irradiance, ambient temperature, module temperature) and electrical inputs (load power, grid power) acquired from a supervisory monitoring infrastructure to predict the PV system’s FPP under real operating conditions in the built environment. A dataset of 24,479 valid samples spanning 85 distinct calendar days (1 May to 24 July 2025) was collected and preprocessed through cleaning, filtering, and feature-specific normalization. To ensure rigorous out-of-sample evaluation, three complementary validation strategies were implemented: (S1) a random day-based split (60 train/11 test days), (S2) a strictly chronological 70/15/15% split (50/11/10 days), and (S3) an external 14-day hold-out (11–24 July 2025) excised before any training, tuning or model selection step. Statistical analysis reveals strong nonlinear dependence of PV power on solar irradiance and module temperature, with correlations $r\approx 0.93$ between irradiance and module temperature, $r\approx 0.82$ between irradiance and PV power, and $r\approx 0.95$ between load and grid power, highlighting the importance of accurate predicting for facility-level energy management. The ANFIS model achieves $R^2=0.9992$, RMSE $=653.62$ W and MAE $=276.90$ W on the random-split test set; $R^2=0.9998$, RMSE $=325.40$ W and MAE $=119.17$ W on the chronological test set and $R^2=0.9997$–$0.9998$, RMSE $=363.45$–$408.50$ W on the external 14-day hold-out that was never seen during training. Comparative experiments with k-Nearest Neighbors, Decision Tree, Random Forest, Support Vector Machine, and a Deep Neural Network show that ANFIS is the only model maintaining sub-700 W RMSE on every split, whereas all five benchmarks degrade sharply under chronological and external evaluation (e.g., SVM 2225 → 5198 W; Decision Tree 7440 → 8058 W; DNN 1576 → 2576 W). The persistence of test/external RMSE below the training RMSE on data never used during model construction empirically rules out data leakage as a cause of the high accuracy. These results demonstrate that the proposed, interpretable neuro-fuzzy framework offers a robust and accurate tool for PV power estimation in building-integrated systems, supporting smart energy management and improved performance of energy-intensive built environments.