Multivariate Strategy Using Artificial Neural Networks for Seasonal Photovoltaic Generation Forecasting (original) (raw)
Related papers
Renewable and Sustainable Energy Reviews, 2020
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.
HAL (Le Centre pour la Communication Scientifique Directe), 2010
In this paper, we present an application of Artificial Neural Networks (ANNs) in the renewable energy domain. We particularly look at the Multi-Layer Perceptron (MLP) network which has been the most used of ANNs architectures both in the renewable energy domain and in the time series forecasting. We have used a MLP and an ad-hoc time series preprocessing to develop a methodology for the daily prediction of global solar radiation on a horizontal surface and a 1.175 kWp PV plant production. Different forecasting methods are compared: a naïve forecaster like persistence, an ANN with preprocessing using only endogenous inputs and an ANN with preprocessing using endogenous and exogenous inputs (like temperature, pressure, nebulosity, insulation, wind speed and direction etc.). The endogenous case is easily computed: the use of Partial Auto Correlation Factor (PACF) allows to optimize the number of lag time to consider. For the exogenous variables, we have applied a Pearson correlation coefficient method to optimize the number of considered input neurons. Although intuitively the use of meteorological data in the input layer of the MLP can only increase the quality of prediction, the obtained results are relatively mixed. The use of exogenous data generates a decrease of nRMSE between 0.5% and 1% for the both studied locations. The absolute error (RMSE) is decreased by 52 Wh/m²/day in the simple endogenous case and 335 Wh/m²/day for the persistence forecast. The results are similar to the concrete case of a tilted PV wall (1.175 kWp), endogenous and exogenous data ANN inputs allow decreasing the nRMSE by 1% on a 6 months-cloudy period for the DC power production (January-June). Moreover, the use of exogenous data shows an interest only in cloudy period (winter season). In summer, endogenous data as inputs on a preprocessed ANN are sufficient. By comparison to a naïve forecaster as persistence, an ANN with endo and exogenous data improves the DC electrical power energy prediction by 9% (nRMSE). Next step of this work will drive to shorter horizons; power predictor of meteorological data should have a greater impact.
A Review of Machine Learning-based Photovoltaic Output Power Forecasting: Nordic Context
IEEE Access
Motivated by factors such as the reduction in cost and the need for a shift towards achieving UN's Sustainable Development Goals, PV (Photovoltaic) power generation is getting more attention in the cold regions of the Nordic countries and Canada. The cold climate and the albedo effect of snow in these regions present favorable operating conditions for PV cells and an opportunity to realize the seasonal matching of generation and consumption respectively. However, the erratic nature of PV brings a threat to the operation of the grid. PV power forecasting has been used as an economical solution to minimize and even overcome this limitation. This paper is therefore a comprehensive review of machine learning-based PV output power forecasting models in the literature in the context of Nordic climate. The impact of meteorological parameters and the soiling effect due to snow, which is unique to this climate, on the performance of a prediction model is discussed. PV power forecasting models in the literature are systematically classified into multiple groups and each group is analyzed and important suggestions are made for choosing a better model for these regions. Ensemble methods, optimization algorithms, time-series decomposition, and weather clustering are identified as important techniques that can be used to enhance performance. And notably, this work proposed two conceptual approaches that can be used to incorporate the effect of snow on PV power forecasting. Future research needs to focus on this area, which is crucial for the development of PV in these regions.
Short-term photovoltaic power forecasting using Artificial Neural Networks and an Analog Ensemble
Renewable Energy
A methodology based on Artificial Neural Networks (ANN) and an Analog Ensemble (AnEn) is presented to generate 72-hour deterministic and probabilistic forecasts of power generated by photovoltaic (PV) power plants using input from a numerical weather prediction model and computed astronomical variables. ANN and AnEn are used individually and in combination to generate forecasts for three solar power plants located in Italy. The computational scalability of the proposed solution is tested using synthetic data simulating 4,450 PV power stations. The NCAR Yellowstone supercomputer is employed to test the parallel implementation of the proposed solution, ranging from 1 node (32 cores) to 4,450 nodes (141,140 cores). Results show that a combined AnEn + ANN solution yields best results, and that the proposed solution is well suited for massive scale computation.
Short-Term Forecasting Models for Photovoltaic Plants: Analytical versus Soft-Computing Techniques
Mathematical Problems in Engineering, 2013
We present and compare two short-term statistical forecasting models for hourly average electric power production forecasts of photovoltaic (PV) plants: the analytical PV power forecasting model (APVF) and the multiplayer perceptron PV forecasting model (MPVF). Both models use forecasts from numerical weather prediction (NWP) tools at the location of the PV plant as well as the past recorded values of PV hourly electric power production. The APVF model consists of an original modeling for adjusting irradiation data of clear sky by an irradiation attenuation index, combined with a PV power production attenuation index. The MPVF model consists of an artificial neural network based model (selected among a large set of ANN optimized with genetic algorithms, GAs). The two models use forecasts from the same NWP tool as inputs. The APVF and MPVF models have been applied to a real-life case study of a grid-connected PV plant using the same data. Despite the fact that both models are quite d...
Photovoltaic Power Prediction Using Artificial Neural Networks and Numerical Weather Data
Sustainability, 2020
The monitoring of power generation installations is key for modelling and predicting their future behaviour. Many renewable energy generation systems, such as photovoltaic panels and wind turbines, strongly depend on weather conditions. However, in situ measurements of relevant weather variables are not always taken into account when designing monitoring systems, and only power output is available. This paper aims to combine data from a Numerical Weather Prediction model with machine learning tools in order to accurately predict the power generation from a photovoltaic system. An Artificial Neural Network (ANN) model is used to predict power outputs from a real installation located in Puglia (southern Italy) using temperature and solar irradiation data taken from the Global Data Assimilation System (GDAS) sflux model outputs. Power outputs and weather monitoring data from the PV installation are used as a reference dataset. Three training and testing scenarios are designed. In the f...
The work presented in this paper is part of a project aimed to develop a prototype device (DSP) able to forecast with a day in advance the energy produced by PV plants. The energy forecast is required by the National Authority for the electricity in order to control the high instabilities of the electric grid induced by unpredictable energy sources such as photovoltaic. In the paper several models to forecast the hourly solar irradiance with a day in advance using Artificial Neural Network (ANN) techniques are described. Statistical (ST) models that use only local measured data and Hybrid model (HY) that also use Numerical Weather Prediction (NWP) data are tested for the University of Rome "Tor Vergata" site. The performance of ST, NWP and HY models, together with the Persistence model (PM), are compared. The ST models and the NWP model exhibit similar results improving the performance of the PM of around 20%. Nevertheless different sources of forecast errors between ST and NWP models are identified. The Hybrid models give the better performance, improving the forecast of approximately 39% with respect to the Persistence model.
Comparison of Training Approaches for Photovoltaic Forecasts by Means of Machine Learning
Applied Sciences, 2018
The relevance of forecasting in renewable energy sources (RES) applications is increasing, due to their intrinsic variability. In recent years, several machine learning and hybrid techniques have been employed to perform day-ahead photovoltaic (PV) output power forecasts. In this paper, the authors present a comparison of the artificial neural network's main characteristics used in a hybrid method, focusing in particular on the training approach. In particular, the influence of different data-set composition affecting the forecast outcome have been inspected by increasing the training dataset size and by varying the training and validation shares, in order to assess the most effective training method of this machine learning approach, based on commonly used and a newly-defined performance indexes for the prediction error. The results will be validated over a one-year time range of experimentally measured data. Novel error metrics are proposed and compared with traditional ones, showing the best approach for the different cases of either a newly deployed PV plant or an already-existing PV facility.
IET Renewable Power Generation
The modernisation of the world has significantly reduced the prime sources of energy such as coal, diesel and gas. Thus, alternative energy sources based on renewable energy have been a major focus nowadays to meet the world's energy demand and at the same time to reduce global warming. Among these energy sources, solar energy is a major source of alternative energy that is used to generate electricity through photovoltaic (PV) system. However, the performance of the power generated is highly sensitive on climate and seasonal factors. The unpredictable behaviour of the climate affects the power output and causes an unfavourable impact on the stability, reliability and operation of the grid. Thus an accurate forecasting of PV output is a crucial requirement to ensure the stability and reliability of the grid. This study provides a systematic and critical review on the methods used to forecast PV power output with main focus on the metaheuristic and machine learning methods. Advantages and disadvantages of each method are summarised, based on historical data along with forecasting horizons and input parameters. Finally, a comprehensive comparison between machine learning and metaheuristic methods is compiled to assist researchers in choosing the best forecasting technique for future research.
Forecasting solar power generated by grid connected PV systems using ensembles of neural networks
2015 International Joint Conference on Neural Networks (IJCNN), 2015
Forecasting solar power generated from photovoltaic systems at different time intervals is necessary for ensuring reliable and economic operation of the electricity grid. In this paper, we study the application of neural networks for predicting the next day photovoltaic power outputs in 30 minutes intervals from the previous values, without using any exogenous data. We propose three different approaches based on ensembles of neural networkstwo non-iterative and one iterative. We evaluate the performance of these approaches using four Australian solar datasets for one year. This includes assessing predictive accuracy, evaluating the benefit of using an ensemble, and comparing performance with two persistence models used as baselines and a prediction model based on support vector regression. The results show that among the three proposed approaches, the iterative approach was the most accurate and it also outperformed all other methods used for comparison.