The accurate short-term forecasting (PV) of power is crucial for grid stability control, energy trading optimization, and renewable energy integration in smart grids. However, PV generation is extremely variable and non-linear due to environmental fluctuations, which challenge the conventional forecasting models. This study proposes a hybrid deep learning architecture, Wavelet Transform–Transformer–Temporal Convolutional Network–Efficient Channel Attention Network–Gated Recurrent Unit (WT–Transformer–TCN–ECANet–GRU), to capture the overall temporal complexity of PV data through integrating signal decomposition, global attention, local convolutional features, and temporal memory. The model begins by employing the Wavelet Transform (WT) to decompose the raw PV time series into multi-frequency components, thereby enhancing feature extraction and denoising. Long-term temporal dependencies are captured in a Transformer encoder, and a Temporal Convolutional Network (TCN) detects local features. Features are then adaptively recalibrated by an Efficient Channel Attention (ECANet) module and passed to a Gated Recurrent Unit (GRU) for sequence modeling. Multiscale learning, attention-driven robust filtering, and efficient encoding of temporality are enabled with the modular pipeline. We validate the model on a real-world, high-resolution dataset of a Moroccan university building comprising 95,885 five-min PV generation records. The model yielded the lowest error metrics among benchmark architectures with an MAE of 209.36, RMSE of 616.53, and an R² of 0.96884, outperforming LSTM, GRU, CNN-LSTM, and other hybrid deep learning models. These results suggest improved predictive accuracy and potential applicability for real-time grid operation integration, supporting applications such as energy dispatching, reserve management, and short-term load balancing.

Since the PVSYST simulator is the most well-known software among researchers and PV experts, we chose to compare its results to those of the manual method. Thus, the objective of the article was to obtain the degree of similarity between the results of the PVSYST simulation and the manual calculation of the same parameters, based on the study of the photovoltaic systems of the University Ibn Tofail. Those installations are installed in the Faculty of Letters, Science, the Presidency and CFC. The later used in our study, have different parameters. Hence, to collect these parameters and their distinct data we used multiple sources. The datasheets of each components of the PV system contains the parameters that distinguish the devices therefore it was mandatory to look for that information, since it will facilitate our study. The meteorological database PVGIS, was our reference for the temperature and irradiation data. What’s more is the PVSYST software that helps in the simulation of the PV system and thus having a detailed report with massive information. All this collection of data was aiming to help us comparing the results of yields and other parameters by manual calculation versus simulation in PVSYST. Morocco has demonstrated a strong commitment to combat climate change by embracing renewable energy, particularly photovoltaic systems. In this pursuit, universities like Ibn Tofail University (UIT) play a crucial role in addressing climate challenges and developing research solutions for mitigation. UIT actively participates in projects related to environmental protection and sustainable development, contributing to Morocco’s growth and higher education advancement. As part of its efforts, UIT has been involved in implementing sustainable green projects and promoting renewable energy technologies. A specific study at UIT aimed to compare PVSYST simulation results with manual calculations for four PV systems on campus, considering parameters such as orientation, electrical installation, and panel types. The International Energy Agency (IEA) Photovoltaic Systems Program has established standards and a key concept, the yield factor, measuring the net energy production over a facility’s lifetime compared to the energy used for construction, operation, and supply. By evaluating the accuracy and efficiency of PVSYST, researchers sought to advance the use of PV systems and contribute to Morocco’s renewable energy goals. Such research not only aids in the progression of renewable energy technology but also aligns with Morocco’s vision for sustainable development and environmental protection.

Water and energy are strongly intertwined, especially in wastewater treatment plants (WWTPs) whose electrical loads can strain local grids. This work evaluates the technical, economic, and environmental feasibility of powering the WWTP attached to the smart building of Ibn Tofail University (Morocco) with building-integrated photovoltaics (PV) and a complementary wind turbine. Using the HOMER Pro optimizer, two configurations were compared: (i) stand-alone PV and (ii) a hybrid PV/wind system. The hybrid design raises the renewable energy fraction from 8.5% to 17.9%, cutting annual grid purchases by 8% and avoiding 47.9 t CO₂ yr⁻¹. The levelized cost of electricity decreases from 1.08 to 0.97 MAD kWh⁻¹ (≈0.11 to 0.10 USD kWh⁻¹), while the net present cost drops by 6%. Sensitivity analyses confirm robustness under grid electricity tariff and load-growth uncertainties. These results demonstrate that modest wind additions can double the renewable share and improve economics, offering a replicable pathway for WWTPs and smart buildings across the MENA region.