This paper describes a new approach to online forecasting of power production from PV systems. The method is suited to online forecasting in many applications and in this paper it is used to predict hourly values of solar power for horizons of up to 36 h. The data used is 15-min observations of solar power from 21 PV systems located on rooftops in a small village in Denmark. The suggested method is a two-stage method where first a statistical normalization of the solar power is obtained using a clear sky model. The clear sky model is found using statistical smoothing techniques. Then forecasts of the normalized solar power are calculated using adaptive linear time series models. Both autoregressive (AR) and AR with exogenous input (ARX) models are evaluated, where the latter takes numerical weather predictions (NWPs) as input. The results indicate that for forecasts up to 2 h ahead the most important input is the available observations of solar power, while for longer horizons NWPs are the most important input. A root mean square error improvement of around 35% is achieved by the ARX model compared to a proposed reference model.

/pdf/online-short-term-solar-power-forecasting-1ljgpbshkb.pdf

Online Short-term Solar Power Forecasting

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.

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

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts. We then demonstrate how such theoretical concepts are applied in a variety of real-life contexts. 
We do not claim that this review is an exhaustive list of methods and applications. However, we wish that our encyclopedic presentation will offer a point of reference for the rich work that has been undertaken over the last decades, with some key insights for the future of forecasting theory and practice. Given its encyclopedic nature, the intended mode of reading is non-linear. We offer cross-references to allow the readers to navigate through the various topics. We complement the theoretical concepts and applications covered by large lists of free or open-source software implementations and publicly-available databases.

Forecasting: theory and practice

With the fast expansion of renewable energy system installed capacity in recent years, the availability, stability, and quality of smart grids have become increasingly important. The renewable energy output forecasting applications have also been developing rapidly in recent years, and such techniques have particularly been applied in the fields of wind and solar photovoltaic (PV). In the case of solar PV output forecasting, many applications have been performed with machine learning and hybrid techniques. In this paper, we propose a high-precision deep neural network model named PVPNet to forecast PV system output power. The methodology behind the proposed model is based on deep neural networks, and the model is able to generate a 24-h probabilistic and deterministic forecasting of PV power output based on meteorological information, such as temperature, solar radiation, and historical PV system output data. The forecasting accuracy of PVPNet is determined by the mean absolute error (MAE) and root mean square error (RMSE) values. The results from the experiments show that the MAE and RMSE of the proposed algorithm are 109.4845 and 163.1513, respectively. The results prove that the prediction accuracy of the PVPNet outperforms other benchmark models, and the algorithm also effectively predicts complex time series with a high degree of volatility and irregularity.

/pdf/multiple-input-deep-convolutional-neural-network-model-for-cbk75harhe.pdf

Multiple-Input Deep Convolutional Neural Network Model for Short-Term Photovoltaic Power Forecasting

Forecasting is a crucial task for successfully integrating photovoltaic (PV) output power into the grid. The design of accurate photovoltaic output forecasters remains a challenging issue, particularly for multistep-ahead prediction. Accurate PV output power forecasting is critical in a number of applications, such as micro-grids (MGs), energy optimization and management, PV integrated in smart buildings, and electrical vehicle chartering. Over the last decade, a vast literature has been produced on this topic, investigating numerical and probabilistic methods, physical models, and artificial intelligence (AI) techniques. This paper aims at providing a complete and critical review on the recent applications of AI techniques; we will focus particularly on machine learning (ML), deep learning (DL), and hybrid methods, as these branches of AI are becoming increasingly attractive. Special attention will be paid to the recent development of the application of DL, as well as to the future trends in this topic.

/pdf/advanced-methods-for-photovoltaic-output-power-forecasting-a-bcritwifhb.pdf

Advanced Methods for Photovoltaic Output Power Forecasting: A Review

We compare the 24-hour ahead forecasting performance of two methods commonly used for the prediction of the power output of photovoltaic systems. Both methods are based on Artificial Neural Networks (ANN), which have been trained on the same dataset, thus enabling a much-needed homogeneous comparison currently lacking in the available literature. The dataset consists of an hourly series of simultaneous climatic and PV system parameters covering an entire year, and has been clustered to distinguish sunny from cloudy days and separately train the ANN. One forecasting method feeds only on the available dataset, while the other is a hybrid method as it relies upon the daily weather forecast. For sunny days, the first method shows a very good and stable prediction performance, with an almost constant Normalized Mean Absolute Error, NMAE%, in all cases (1% 2% and up to 5.3% for all the other cases). For cloudy days, the forecasting performance of both methods typically drops; the performance is rather stable for the method that does not use weather forecasts, while for the hybrid method it varies significantly for the days considered in the analysis.

Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques

Machine Learning techniques for solar irradiation nowcasting: Cloud type classification forecast through satellite data and imagery

Forecasting the power production from renewable energy sources (RESs) has become fundamental in microgrid applications to optimize scheduling and dispatching of the available assets. In this article, a methodology to provide the 24 h ahead Photovoltaic (PV) power forecast based on a Physical Hybrid Artificial Neural Network (PHANN) for microgrids is presented. The goal of this paper is to provide a robust methodology to forecast 24 h in advance the PV power production in a microgrid, addressing the specific criticalities of this environment. The proposed approach has to validate measured data properly, through an effective algorithm and further refine the power forecast when newer data are available. The procedure is fully implemented in a facility of the Multi-Good Microgrid Laboratory (MG L a b 2 ) of the Politecnico di Milano, Milan, Italy, where new Energy Management Systems (EMSs) are studied. Reported results validate the proposed approach as a robust and accurate procedure for microgrid applications.

/pdf/robust-24-hours-ahead-forecast-in-a-microgrid-a-real-case-5c6rutolcq.pdf

Robust 24 Hours ahead Forecast in a Microgrid: A Real Case Study

The penetration of nonprogrammable renewable energy sources, namely wind and solar technology, has greatly increased in the last decades and nowadays the shift toward green energy sources represents a priority worldwide. The high variability of the primary source challenges the grid operators in ensuring the stability and reliability of the electric grid. Machine learning algorithms, and in particular artificial neural networks, are one of the most reliable methods for photovoltaic (PV) energy production forecast. This article proposes a new ensemble method based on the probabilistic distribution of the trials, the probabilistic ensemble method (PEM). The proposed method has been tested on a three-years real case study, where the available days have been clustered according to the solar irradiation forecast. The days where the worst performance, in terms of nRMSE, was recorded mostly belonged to the totally cloudy days class, that has been therefore selected for the analysis. The PEM has been compared with the ensemble based on the mean value, achieving an improvement in the nRMSE metric up to 4.79% in 2017 in the totally cloudy days class.

A New Probabilistic Ensemble Method for an Enhanced Day-Ahead PV Power Forecast

Application of Machine Learning in forecasting renewable energy sources (RES) is increasing: in particular, several neural networks have been employed to perform the day-ahead photo-voltaic output power forecast. The aim of this paper is to consider different training approaches in order to improve the accuracy of the PV power prediction, with particular attention to day-ahead and intra-day forecasts. Additionally, novel error metrics, specifically proposed for the defined task, are compared with traditional ones, showing the best approach for the different considered cases. The results will be validated over a 1-year time range of experimentally measured data, for a PV module installed in the Solar Tech Lab in the department of Energy at Politecnico di Milano.

Alfredo Nespoli

Papers

Day-Ahead Photovoltaic Forecasting: A Comparison of the Most Effective Techniques

Machine Learning techniques for solar irradiation nowcasting: Cloud type classification forecast through satellite data and imagery

Robust 24 Hours ahead Forecast in a Microgrid: A Real Case Study

A New Probabilistic Ensemble Method for an Enhanced Day-Ahead PV Power Forecast

Validation of ANN Training Approaches for Day-Ahead Photovoltaic Forecasts