A review and evaluation of the state-of-the-art in PV solar power forecasting: Techniques and optimization

• Published in: Renewable & sustainable energy reviews Vol. 124; p. 109792
• Main Authors: Ahmed, R., Sreeram, V., Mishra, Y., Arif, M.D.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.05.2020
• Subjects: Deep convolutional neural network; Forecast accuracy; Forecasting technique; Long short term memory; Optimization; Solar power; Wavelet transform; Wavelet transform; Forecasting technique; Solar power; Forecast accuracy; Deep convolutional neural network; Long short term memory; Optimization
• ISSN: 1364-0321; 1879-0690
• DOI: 10.1016/j.rser.2020.109792

Integration of photovoltaics into power grids is difficult as solar energy is highly dependent on climate and geography; often fluctuating erratically. This causes penetrations and voltage surges, system instability, inefficient utilities planning and financial loss. Forecast models can help; however, time stamp, forecast horizon, input correlation analysis, data pre and post-processing, weather classification, network optimization, uncertainty quantification and performance evaluations need consideration. Thus, contemporary forecasting techniques are reviewed and evaluated. Input correlational analyses reveal that solar irradiance is most correlated with Photovoltaic output, and so, weather classification and cloud motion study are crucial. Moreover, the best data cleansing processes: normalization and wavelet transforms, and augmentation using generative adversarial network are recommended for network training and forecasting. Furthermore, optimization of inputs and network parameters, using genetic algorithm and particle swarm optimization, is emphasized. Next, established performance evaluation metrics MAE, RMSE and MAPE are discussed, with suggestions for including economic utility metrics. Subsequently, modelling approaches are critiqued, objectively compared and categorized into physical, statistical, artificial intelligence, ensemble and hybrid approaches. It is determined that ensembles of artificial neural networks are best for forecasting short term photovoltaic power forecast and online sequential extreme learning machine superb for adaptive networks; while Bootstrap technique optimum for estimating uncertainty. Additionally, convolutional neural network is found to excel in eliciting a model's deep underlying non-linear input-output relationships. The conclusions drawn impart fresh insights in photovoltaic power forecast initiatives, especially in the use of hybrid artificial neural networks and evolutionary algorithms. •Critical review on the versatility of LSTM and DCNN in predicting short temporal horizon PV output.•Discussion on the importance of input data optimization using coupled evolutionary algorithms.•Standardizing comparison of different forecast models by focusing on data length, quality and resolution.•Research directions on optimization of NN architecture, data pre-processing and uncertainty quantification.