A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power

Rajagukguk, Rial A.; Ramadhan, Raden A. A.; Lee, Hyun-Jin

doi:10.3390/en13246623

Cited by 150 publications

(91 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the forecast precision and compare the models, some validation metrics like Coefficient of determination (R 2 ), Root Mean Square Error (RMSE), mean absolute error (MAE), explained variance (EV), mean absolute percentage error (MAPE), Mean bias error (MBE), and Relative Mean bias error (rMBE) are used (Table II); where y t is concentration level of a pollutant,ŷ t is its corresponding forecasted values, and n is the number of data points [59], [60]. The more precise forecasting is, the lower RMSE, MAE, MBE and rMBE values and high R 2 , EV, and MAPE values are.…”

Section: Measurements Of Effectivenessmentioning

confidence: 99%

Integrated Multiple Directed Attention-Based Deep Learning for Improved Air Pollution Forecasting

Dairi

Harrou

Khadraoui

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

In recent years, human health across the world is becoming concerned by a constant threat of air pollution, which causes many chronic diseases and premature mortalities. Poor air quality does not have only serious adverse effects on human health and vegetation, but also some major negative political, societal, and economic impacts. Hence, it is essential investing more effort on accurate forecasting of ambient air pollution to provide practical and relevant solutions, achieve acceptable air quality, and plan for prevention. In this work, we propose a flexible and efficient deep learning-driven model to forecast concentrations of ambient pollutants. The paper introduces first the traditional Variational AutoEncoder (VAE) and the attention mechanism to develop the forecasting modeling strategy based on the innovative Integrated Multiple Directed Attention Deep Learning architecture (IMDA). To assess the performance of the proposed forecasting methodology, experimental validation is then performed using air pollution data from four US states. Six statistical indicators have been used to evaluate the forecasting accuracy. A discussion of the results obtained finally demonstrates the satisfying performance of IMDA-VAE methods to forecast different pollutants in different locations. Furthermore, results indicate that the proposed IMDA-VAE model can effectively improve air pollution forecasting performance and outperforms the deep learning models, namely VAE, Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), bidirectional LSTM, bidirectional GRU, and ConvLSTM. We also showed that the forecasting results of the proposed model surpass the performance of LSTM and GRU with the attention mechanism.

show abstract

Section: Measurements Of Effectivenessmentioning

confidence: 99%

Integrated Multiple Directed Attention-Based Deep Learning for Improved Air Pollution Forecasting

Dairi

Harrou

Khadraoui

et al. 2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…The performance of these methods depends on the precise task, the available data as well as the data resolution and prediction window. Typically, the forecasts are obtained using a number of external sources including solar irradiance, wind, humidity and atmospheric pressure [14,26]. Sky-image-based techniques have been employed for time horizons of under one hour, while satellite-image-based techniques were found to be more suitable for the prediction of several hours ahead [27].…”

Section: Photovoltaic (Pv) Power Predictionmentioning

confidence: 99%

“…In addition, many studies only focus on the prediction of solar irradiance, since it is highly correlated to PV power. A detailed review of these methods can be found in [26] which also provides guidance on the suitability of different methods depending on the time horizon and the prediction window.…”

Section: Photovoltaic (Pv) Power Predictionmentioning

confidence: 99%

Data-Driven Energy Storage Scheduling to Minimise Peak Demand on Distribution Systems with PV Generation

et al. 2021

View full text Add to dashboard Cite

The growing adoption of decentralised renewable energy generation (such as solar photovoltaic panels and wind turbines) and low-carbon technologies will increase the strain experienced by the distribution networks in the near future. In such a scenario, energy storage is becoming a key alternative to traditional expensive reinforcements to network infrastructure, due to its flexibility, decreasing costs and fast deployment capabilities. In this work, an end-to-end data-driven solution to optimally design the control of a battery unit with the aim of reducing the peak electricity demand is presented. The proposed solution uses state-of-the-art machine learning methods for forecasting electricity demand and PV generation, combined with an optimisation strategy to maximise the use of photovoltaic energy to charge the energy storage unit. To this end, historical demand, weather, and solar energy generation data collected at the Stentaway Primary substation near Plymouth, UK, and at other six locations were employed.

show abstract

“…Some studies conclude that statistical models outperform ML models [ 10 ] while others state the opposite [ 11 , 12 ]. However, this interpretation may appear to be fairly simplistic without taking into account the dataset size [ 13 ], the variable being forecast [ 14 ], the time horizon [ 15 ], or the computational load [ 16 ]. Although historically, the forecasts have been dominated by statistical methods, over the last decade there has been a significant shift toward ML strategies [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

“…The forecasting strategy developed in this paper, uses long short-term memory recurrent neural networks (LSTM-RNNs) and is based on an indirect approach in which the irradiance is forecasted first and the output power is calculated by using the PV model. LSTM-RNNs have been used in several works, achieving satisfactory results on account of their recurrent architecture, which includes memory units [ 16 ]. These allow the ANN to identify temporal patterns from the historical data of the forecast variable, thereby reducing the forecast error in comparison to other alternatives.…”

Section: Introductionmentioning

confidence: 99%

Intra-Day Solar Power Forecasting Strategy for Managing Virtual Power Plants

Moreno

Santos

Martín

et al. 2021

Sensors

View full text Add to dashboard Cite

Solar energy penetration has been on the rise worldwide during the past decade, attracting a growing interest in solar power forecasting over short time horizons. The increasing integration of these resources without accurate power forecasts hinders the grid operation and discourages the use of this renewable resource. To overcome this problem, Virtual Power Plants (VPPs) provide a solution to centralize the management of several installations to minimize the forecasting error. This paper introduces a method to efficiently produce intra-day accurate Photovoltaic (PV) power forecasts at different locations, by using free and available information. Prediction intervals, which are based on the Mean Absolute Error (MAE), account for the forecast uncertainty which provides additional information about the VPP node power generation. The performance of the forecasting strategy has been verified against the power generated by a real PV installation, and a set of ground-based meteorological stations in geographical proximity have been used to emulate a VPP. The forecasting approach is based on a Long Short-Term Memory (LSTM) network and shows similar errors to those obtained with other deep learning methods published in the literature, offering a MAE performance of 44.19 W/m2 under different lead times and launch times. By applying this technique to 8 VPP nodes, the global error is reduced by 12.37% in terms of the MAE, showing huge potential in this environment.

show abstract

A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power

Cited by 150 publications

References 60 publications

Integrated Multiple Directed Attention-Based Deep Learning for Improved Air Pollution Forecasting

Integrated Multiple Directed Attention-Based Deep Learning for Improved Air Pollution Forecasting

Data-Driven Energy Storage Scheduling to Minimise Peak Demand on Distribution Systems with PV Generation

Intra-Day Solar Power Forecasting Strategy for Managing Virtual Power Plants

Contact Info

Product

Resources

About