An Hour-Ahead PV Power Forecasting Method Based on an RNN-LSTM Model for Three Different PV Plants

Abstract

Incorporating solar energy into a grid necessitates an accurate power production forecast for photovoltaic (PV) facilities. In this research, output PV power was predicted at an hour ahead on yearly basis for three different PV plants based on polycrystalline (p-si), monocrystalline (m-si), and thin-film (a-si) technologies over a four-year period. Wind speed, module temperature, ambiance, and solar irradiation were among the input characteristics taken into account. Each PV plant power output was the output parameter. A deep learning method (RNN-LSTM) was developed and evaluated against existing techniques to forecast the PV output power of the selected PV plant. The proposed technique was compared with regression (GPR, GPR (PCA)), hybrid ANFIS (grid partitioning, subtractive clustering and FCM) and machine learning (ANN, SVR, SVR (PCA)) methods. Furthermore, different LSTM structures were also investigated, with recurrent neural networks (RNN) based on 2019 data to determine the best structure. The following parameters of prediction accuracy measure were considered: RMSE, MSE, MAE, correlation (r) and determination (R2) coefficients. In comparison to all other approaches, RNN-LSTM had higher prediction accuracy on the basis of minimum (RMSE and MSE) and maximum (r and R2). The p-si, m-si and a-si PV plants showed the lowest RMSE values of 26.85 W/m2, 19.78 W/m2 and 39.2 W/m2 respectively. Moreover, the proposed method was found to be robust and flexible in forecasting the output power of the three considered different photovoltaic plants.

Variational mode decomposition combined fuzzy—Twin support vector machine model with deep learning for solar photovoltaic power forecasting

“…Elizabeth Michael et al (2022) developed a short-term solar irradiance prediction model called modified multi-step Convolutional Neural Network (CNN)-stacked Long-Short-Term-Memory network (LSTM) with drop-out [26]. developed a deep learning approach (RNN-LSTM) to forecast the PV output power of the considered solar farms [27]. performed a review of machine learning methods from different perspectives and provided a critical review of machine learning models for recent PV output power applications [28].…”

“…Among the machine learning models, few feed forward models and their variants, recurrent neural predictors and memory based models has been widely used [11][12][13][14][15][16][17][18]. Also, with the growth of deep learning based techniques, researchers has initiated in developing predictor models for solar PV output power forecasting using various deep learning models for the said application [1,14,19,20,26,27,43,47]. On this detailed review made on the different machine learning and deep learning models for PV output power forecasting of solar farms, they are prone to possess the disadvantages as listed below,…”

“…• Occurrences of global minima and stagnation issues [3][4][5][6][7] • Scalability problems on the normalization procedures adopted [2,8,[12][13][14][15][16][17] • Over-fitting and under-fitting issues [5, 6, 9-11, 23, 48, 51] • Dimensionality constraints of the solar farm data and data handling issues [18][19][20][21][22][23][24] • Elapsed training time [29,31,37] • Data extraction problems in regression based ML models [10][11][12][13][14][15] • Higher number of trainable parameters in DL models [1, 14, 19-20, 26, 27, 43, 47] • Repetitive training of deep neural networks [19,20,26,27] • High computational overhead due to repetitive process [29][30][31][32][33][34][35][36] • Few predictor models with high complexity and data redundancy [45][46][47]…”

“…For the two considered solar PV farms, the VMD-ALO-DLFTSVM model intended to attained better prediction accuracy and minimized value of mean square error during the training and testing process. Table 8 presents a comparative analysis of the proposed predictor with that of the prediction techniques from previous works [18,27,29,33,40,61]. For all these previous methods, the same datasets were presented as input and their MSE and prediction accuracy was attained.…”

Prediction of a Grid-Connected Photovoltaic Park’s Output with Artificial Neural Networks Trained by Actual Performance Data

“…The ANN-based model demonstrated a 2.107% MAE and 2.645% RMSE against 2.406% and 5.185%, respectively, for the persistence model [16]. Akhter et al proposed a model for an hour-ahead prediction on a yearly basis of three different PV plants, based on available data for wind speed, module, ambient temperature, and solar irradiation employing a long short-term memory (LSTM) recurrent neural network (RNN) with a deep learning method, with the results compared with regression, hybrid Adaptive neuro-fuzzy inference system (ANFIS), and machine learning methods [17]. Natarajan et al proposed a radial belied neural network (RBFN) with inputs from large-scale PV plants with evaluation metrics of RMSE, nRMSE, MBE, MAE, MaxAE, MAPE, and Kolmogorov-Smirnov test integral (KSI) and OVER metrics, skewness, and kurtosis and variability estimation [18].…”