Marie Laure Nivet

Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation

We propose in this paper an original technique to predict global radiation using a hybrid ARMA/ANN model and data issued from a numerical weather prediction model (NWP). We particularly look at the multi-layer perceptron (MLP). After optimizing our architecture with NWP and endogenous data previously made stationary and using an innovative pre-input layer selection method, we combined it to an ARMA model from a rule based on the analysis of hourly data series. This model has been used to forecast the hourly global radiation for five places in Mediterranean area. Our technique outperforms classical models for all the places. The nRMSE for our hybrid model MLP/ARMA is 14.9% compared to 26.2% for the naive persistence predictor. Note that in the standalone ANN case the nRMSE is 18.4%. Finally, in order to discuss the reliability of the forecaster outputs, a complementary study concerning the confidence interval of each prediction is proposed.

Hybrid methodology for hourly global radiation forecasting in Mediterranean area

The renewable energies prediction and particularly global radiation forecasting is a challenge studied by a growing number of research teams. This paper proposes an original technique to model the insolation time series based on combining Artificial Neural Network (ANN) and Auto-Regressive and Moving Average (ARMA) model. While ANN by its non-linear nature is effective to predict cloudy days, ARMA techniques are more dedicated to sunny days without cloud occurrences. Thus, three hybrids models are suggested: the first proposes simply to use ARMA for 6 months in spring and summer and to use an optimized ANN for the other part of the year; the second model is equivalent to the first but with a seasonal learning; the last model depends on the error occurred the previous hour. These models were used to forecast the hourly global radiation for five places in Mediterranean area. The forecasting performance was compared among several models: the 3 above mentioned models, the best ANN and ARMA for each location. In the best configuration, the coupling of ANN and ARMA allows an improvement of more than 1%, with a maximum in autumn (3.4%) and a minimum in winter (0.9%) where ANN alone is the best.

Solar radiation forecasting using ad-hoc time series preprocessing and neural networks

In this paper, we present an application of neural networks in the renewable energy domain. We have developed a methodology for the daily prediction of global solar radiation on a horizontal surface. We use an ad-hoc time series preprocessing and a Multi-Layer Perceptron (MLP) in order to predict solar radiation at daily horizon. First results are promising with nRMSE < 21% and RMSE < 998 Wh/m2. Our optimized MLP presents prediction similar to or even better than conventional methods. Moreover we found that our data preprocessing approach can reduce significantly forecasting errors.

Numerical weather prediction or stochastic modelling: an objective criterion of choice for the global radiation forecasting

Numerous methods exist and were developed for global radiation forecasting. The two most popular types are the numerical weather predictions (NWP) and the predictions using stochastic approaches. We propose to compute a parameter noted constructed in part from the mutual information which is a quantity that measures the mutual dependence of two variables. Both of these are calculated with the objective to establish the more relevant method between NWP and stochastic models concerning the current problem.

Meteorological time series forecasting based on MLP modelling using heterogeneous transfer functions

In this paper, we propose to study four meteorological and seasonal time series coupled with a multi-layer perceptron (MLP) modeling. We chose to combine two transfer functions for the nodes of the hidden layer, and to use a temporal indicator (time index as input) in order to take into account the seasonal aspect of the studied time series. The results of the prediction concern two years of measurements and the learning step, eight independent years. We show that this methodology can improve the accuracy of meteorological data estimation compared to a classical MLP modelling with a homogenous transfer function.

Use of exogenous data to improve an Artificial Neural Networks dedicated to daily global radiation forecasting

This paper presents an application of Artificial Neural Networks (ANNs) in the renewable energy domain and, more particularly, to predict solar energy. We 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. In previous studies, we have demonstrated that an optimized ANN with endogenous inputs can forecast the solar radiation on a horizontal surface with acceptable errors. Thus we propose to study the contribution of exogenous meteorological data to our optimized PMC and compare with different forecasting methods used previously: a naïve forecaster like persistence and an ANN with preprocessing using only endogenous inputs. Although intuitively the use of meteorological data may 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 two 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.

Short-term solar irradiance and irradiation forecasts via different time series techniques: A preliminary study

This communication is devoted to solar irradiance and irradiation short-term forecasts, which are useful for electricity production. Several different time series approaches are employed. Our results and the corresponding numerical simulations show that techniques which do not need a large amount of historical data behave better than those which need them, especially when those data are quite noisy.

Bounded global irradiation prediction based on multilayer perceptron and time series formalism

As global solar radiation forecasting is a very important challenge, several methods are devoted to this goal with different levels of accuracy and confidence. In this study we propose to better understand how the uncertainty is propagated in the context of global radiation time series forecasting using machine learning. Indeed we propose to decompose the error considering four kinds of uncertainties: the error due to the measurement, the variability of time series, the machine learning uncertainty and the error related to the horizon. All these components of the error allow to determinate a global uncertainty generating a prediction bands related to the prediction efficiency. We also have defined a reliability index which could be very interesting for the grid manager in order to estimate the validity of predictions. We have experimented this method on a multilayer perceptron which is a popular machine learning technique. We have shown that the global error and its components are essentials to quantify in order to estimate the reliability of the model outputs. The described method has been successfully applied to four meteorological stations in Mediterranean area.

Urban Ozone Concentration Forecasting with Artificial Neural Network in Corsica

Abstract Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France), needs to develop a short-term prediction model to lead its mission of information towards the public. Various deterministic models exist for local forecasting, but need important computing resources, a good knowledge of atmospheric processes and can be inaccurate because of local climatical or geographical particularities, as observed in Corsica, a mountainous island located in the Mediterranean Sea. As a result, we focus in this study on statistical models, and particularly Artificial Neural Networks (ANNs) that have shown good results in the prediction of ozone concentration one hour ahead with data measured locally. The purpose of this study is to build a predictor realizing predictions of ozone 24 hours ahead in Corsica in order to be able to anticipate pollution peaks formation and to take appropriate preventive measures. Specific meteorological conditions are known to lead to particular pollution event in Corsica (e.g. Saharan dust events). Therefore, an ANN model will be used with pollutant and meteorological data for operational forecasting. Index of agreement of this model was calculated with a one year test dataset and reached 0.88.