Computationally expedient Photovoltaic power Forecasting: A LSTM ensemble method augmented with adaptive weighting and data segmentation technique. (15th April 2022)

• Record Type: Journal Article
• Authors: Ahmed, Razin; Sreeram, Victor; Togneri, Roberto; Datta, Amitava; Arif, Muammer Din
• Is Part Of: Energy conversion and management. Volume 258(2022)
• Publication Date: 2022-04-15
• Subjects: AI Artificial intelligence -- ANN Artificial neural network -- ALSTM Attention long short term memory -- AE Auto encoder -- ARIMA Auto Regressive Integrated Moving Average -- ARMA Auto Regressive Moving Average -- BP Back-Propagation -- BR Bagged Regression Tree -- BiGRU Bidirectional Gated Recurrent Unit -- BiLSTM Bidirectional long short-term memory -- ConvLSTM Convolutional long short-term memory -- COV Coefficient of variation -- C-SALSTM/Conv-SA-LSTM Convolutional Self Attention long short-term memory -- CNN Convolutional neural network -- DBN Deep Belief Network -- DL Deep learning -- DKASC Desert Knowledge Australia Solar Centre -- GRU Gated Recurrent Unit -- GWp Gigawatts peak -- GHG Greenhouse gas -- IEA International Energy Agency -- LSTM Long short-term memory -- ML Machine Learning -- MLR Multiple Linear Regression -- MLP Multiple-layer Perceptron -- MLPNN Multiple-layer Perceptron Neural-Network -- NN Neural-Network -- NWP Numerical weather prediction -- OECD Organization for Economic Co-operation and Development -- PV Photovoltaic -- PVPF Photovoltaic power forecast -- RBF Radial basis function -- RNN Recurrent neural network -- RBM Restricted Boltzmann machine -- SARIMA Seasonal Auto Regressive Integrated Moving Average -- SVM Support Vector Machine -- SVR Support Vector Regression -- TWh Terawatt-hour -- DSS Data segmentation structure -- MAE Mean absolute error -- MAPE Mean absolute percentage error -- ME Mean error -- MSE Mean square error -- RMSE Root mean square error -- QNN Quantile Neural-Network; Solar Power -- Deep Learning -- Long Short Term Memory -- Ensemble Boosting Method -- Forecasting technique; Direct energy conversion -- Periodicals; Energy storage -- Periodicals; Energy transfer -- Periodicals; Énergie -- Conversion directe -- Périodiques; Direct energy conversion; Periodicals; 621.3105
• DOI: 10.1016/j.enconman.2022.115563
• Languages: English
• ISSNs: 0196-8904

Abstract

Highlights: Comparative analysis of data scaling parameters, input feature selection with univariate/multivariate preferences. Evaluation of the Long Short Term Memory model using Data Segmentation structures, varied time-horizons, and case studies. An ensemble boosting approach with an adjustable weighting mechanism is developed to optimize forecast accuracy. Runtime assessment and viability of the proposed approach. Abstract: Photovoltaics (PVs) hold the promise of sustainable electricity production. However, PV output is significantly influenced by variations in terrestrial solar radiation and other weather factors, causing problems in unit commitment, economic power dispatch and reliable electricity distribution from grid-connected, hybrid and off-grid PV plants. Thus, accurate and consistent PV output prediction is crucial for utilities companies and researchers. Current initiatives enlist a plethora of forecasting techniques, including: statistical models, physical models, artificial neural networks and deep learning algorithms. Nevertheless, most of these approaches suffer from computational costs, complex models and uncertainties. Hence, this research employed an ensemble-based Long Short-Term Memory (LSTM) algorithm comprising 10 component LSTM models. The method compares the effects of different data segmentations (three-months to one-day) and is based on varying time-horizons (14-days to 5-mins) in order to compare the effects of seasonal and periodic variations on time-series data and PV output forecast. The comparison is then used to minimise uncertainty by implementing grid search technique. Subsequently, the model's performance was evaluated using MAPE analysis for two cases involving erratic weather conditions and PV output in two specific days of the year 2020. From the evaluation, the best prediction was found to be for the two-week dataset with MAPE of 6.02. This approach combined with online data acquisition from the Yulara Solar System power plant in central Australia leads to a more practical, computationally economical and robust PV power generation forecasting technique.