Solar photovoltaic (SPV) generators play a vital role in the global pursuit of sustainable energy. However, the intermittent nature of SPV generators poses a challenge to power system planning. Accurate long-term SPV power forecasting is essential, but obtaining high-quality training data for many years is cumbersome due to faults in sensors, communication, or databases, leading to missing values. This paper proposes an attention network (AN) for SPV power imputation to address missing historical data. In addition, the SPV power forecasting model using BDLSTM NN is proposed for forecasting the SPV power in the long-term horizon. During training, the weights and biases of the imputation and forecasting models are proposed to be optimized using the Aquila optimization algorithm (AOA). Training and testing results substantiate that the proposed imputation and forecasting models consistently attain superior accuracy with a reduction in training time regardless of the missing rates, climatic patterns, and seasons as compared to benchmark models.
Solar photovoltaic (SPV) technology is gaining prominence due to its sustainability and minimal carbon footprint. However, the intermittent nature of SPV systems poses a challenge to widespread adoption. Accurate forecasting of SPV power is essential, relying heavily on high-quality data. Meteorological parameters from the National Renewable Energy Laboratory (NREL) often contain missing values, impacting the reliability of power system planning. These missing values can stem from various issues such as sensor malfunctions, communication errors, or database issues. Therefore, this paper introduces a variational autoencoder technique to construct an SPV power imputation model, aiming to fill in gaps in unobserved data. Moreover, the filled SPV power data is used to train a gated recurrent unit neural network for forecasting the SPV power. The hyperparameters of the imputation and forecasting models are optimized using the hummingbird optimization algorithm. Furthermore, the NovoGrad optimizes the hyperparameters of the imputation and forecasting models during training, thereby enhancing their performance and convergence. Furthermore, the proposed imputation and forecasting models are tested for various missing patterns. The effectiveness of the proposed imputation and forecasting models is demonstrated with real-world SPV power data for imputation and forecasting tasks.