arXiv subjects

Cyril Voyant

Publications and source records attributed to Cyril Voyant.

28 records · Page 2Linked to original sources

arXiv2013

Time series modeling with pruned multi-layer perceptron and 2-stage damped least-squares method

A Multi-Layer Perceptron (MLP) defines a family of artificial neural networks often used in TS modeling and forecasting. Because of its "black box" aspect, many researchers refuse to use it. Moreover, the optimization (often based on the exhaustive approach where "all" configurations are tested) and learning phases of this artificial intelligence tool (often based on the Levenberg-Marquardt algorithm; LMA) are weaknesses of this approach (exhaustively and local minima). These two tasks must be repeated depending on the knowledge of each new problem studied, making the process, long, laborious and not systematically robust. In this paper a pruning process is proposed. This method allows, during the training phase, to carry out an inputs selecting method activating (or not) inter-nodes connections in order to verify if forecasting is improved. We propose to use iteratively the popular damped least-squares method to activate inputs and neurons. A first pass is applied to 10% of the learning sample to determine weights significantly different from 0 and delete other. Then a classical batch process based on LMA is used with the new MLP. The validation is done using 25 measured meteorological TS and cross-comparing the prediction results of the classical LMA and the 2-stage LMA.

cs.NE↗

arXiv2013

Multi-horizon solar radiation forecasting for Mediterranean locations using time series models

Considering the grid manager's point of view, needs in terms of prediction of intermittent energy like the photovoltaic resource can be distinguished according to the considered horizon: following days (d+1, d+2 and d+3), next day by hourly step (h+24), next hour (h+1) and next few minutes (m+5 e.g.). Through this work, we have identified methodologies using time series models for the prediction horizon of global radiation and photovoltaic power. What we present here is a comparison of different predictors developed and tested to propose a hierarchy. For horizons d+1 and h+1, without advanced ad hoc time series pre-processing (stationarity) we find it is not easy to differentiate between autoregressive moving average (ARMA) and multilayer perceptron (MLP). However we observed that using exogenous variables improves significantly the results for MLP . We have shown that the MLP were more adapted for horizons h+24 and m+5. In summary, our results are complementary and improve the existing prediction techniques with innovative tools: stationarity, numerical weather prediction combination, MLP and ARMA hybridization, multivariate analysis, time index, etc.

physics.ao-ph↗

arXiv2013

Urban ozone concentration forecasting with artificial neural network in Corsica

Atmospheric pollutants concentration forecasting is an important issue in air quality monitoring. Qualitair Corse, the organization responsible for monitoring air quality in Corsica (France) region, needs to develop a short-term prediction model to lead its mission of information towards the public. Various deterministic models exist for meso-scale or local forecasting, but need powerful large variable sets, 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 a Mediterranean Sea. As a result, we focus in this study on statistical models, and particularly Artificial Neural Networks (ANN) that have shown good results in the prediction of ozone concentration at horizon h+1 with data measured locally. The purpose of this study is to build a predictor to realize predictions of ozone and PM10 at horizon d+1 in Corsica in order to be able to anticipate pollution peak formation and to take appropriated prevention measures. Specific meteorological conditions are known to lead to particular pollution event in Corsica (e.g. Saharan dust event). Therefore, several ANN models will be used, for meteorological conditions clustering and for operational forecasting.

cs.NE↗

arXiv2012

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.

cs.NE↗

arXiv2012

A Bayesian Model Committee Approach to Forecasting Global Solar Radiation

This paper proposes to use a rather new modelling approach in the realm of solar radiation forecasting. In this work, two forecasting models: Autoregressive Moving Average (ARMA) and Neural Network (NN) models are combined to form a model committee. The Bayesian inference is used to affect a probability to each model in the committee. Hence, each model's predictions are weighted by their respective probability. The models are fitted to one year of hourly Global Horizontal Irradiance (GHI) measurements. Another year (the test set) is used for making genuine one hour ahead (h+1) out-of-sample forecast comparisons. The proposed approach is benchmarked against the persistence model. The very first results show an improvement brought by this approach.

stat.AP↗

arXiv2012

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 (ALADIN). We particularly look at the Multi-Layer Perceptron. After optimizing our architecture with ALADIN 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 ANN/ARMA is 14.9% compared to 26.2% for the naïve persistence predictor. Note that in the stand alone 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

cs.NE↗

arXiv2011

Dosimetric uncertainties related to the elasticity of bladder and rectal walls: Adenocarcinoma of the prostate

Purpose. - Radiotherapy is an important treatment for prostate cancer.During treatment sessions, bladder and rectal repletion is difficult to quantify and cannot be measured with a single and initial CT scan acquisition. Some methods, such as image-guided radiation therapy and dose-guided radiation therapy, aimto compensate thismissing information through periodic CT acquisitions. The aimis to adapt patient's position, beam configuration or prescribed dose for a dosimetric compliance. Methods. -We evaluated organmotion (and repletion) for 54 patients after having computed the original ballistic on a new CT scan acquisition. A new delineation was done on the prostate, bladder and rectum to determine the newdisplacements and define organ dosesmistakes (equivalent uniformdose, average dose and dose-volume histograms). Results. - The new CT acquisitions confirmed that bladder and rectal volumes were not constant during sessions. Some cases showed that previously validated treatment plan became unsuitable. A proposed solution is to correct dosimetries when bladder volume modifications are significant. The result is an improvement for the stability of bladder doses, D50 error is reduced by 25.3%, mean dose error by 5.1% and equivalent uniform dose error by 2.6%. For the rectum this method decreases errors by only 1%. This process can reduce the risk of mismatch between the initial scan and following treatment sessions. Conclusion. - For the proposedmethod, the cone-beamCT is necessary to properly position the isocenter and to quantify bladder and rectal volume variation and deposited doses. The dosimetries are performed in the event that bladder (or rectum) volume modification limits are exceeded. To identify these limits, we have calculated that a tolerance of 10% for the equivalent uniformdose (compared to the initial value of the first dosimetry), this represents 11% of obsolete dosimetries for the bladder, and 4% for the rectum.

physics.med-ph↗

arXiv2010

Predictability of PV power grid performance on insular sites without weather stations: use of artificial neural networks

The official meteorological network is poor on the island of Corsica: only three sites being about 50 km apart are equipped with pyranometers which enable measurements by hourly and daily step. These sites are Ajaccio (41\degree 55'N and 8\degree 48'E, seaside), Bastia (42\degree 33'N, 9\degree 29'E, seaside) and Corte (42\degree 30'N, 9\degree 15'E average altitude of 486 meters). This lack of weather station makes difficult the predictability of PV power grid performance. This work intends to study a methodology which can predict global solar irradiation using data available from another location for daily and hourly horizon. In order to achieve this prediction, we have used Artificial Neural Network which is a popular artificial intelligence technique in the forecasting domain. A simulator has been obtained using data available for the station of Ajaccio that is the only station for which we have a lot of data: 16 years from 1972 to 1987. Then we have tested the efficiency of this simulator in two places with different geographical features: Corte, a mountainous region and Bastia, a coastal region. On daily horizon, the relocation has implied fewer errors than a "naïve" prediction method based on the persistence (RMSE=1468 Vs 1383Wh/m^2 to Bastia and 1325 Vs 1213Wh/m^2 to Corte). On hourly case, the results were still satisfactory, and widely better than persistence (RMSE=138.8 Vs 109.3 Wh/m^2 to Bastia and 135.1 Vs 114.7 Wh/m^2 to Corte). The last experiment was to evaluate the accuracy of our simulator on a PV power grid localized at 10 km from the station of Ajaccio. We got errors very suitable (nRMSE=27.9%, RMSE=99.0 W.h) compared to those obtained with the persistence (nRMSE=42.2%, RMSE=149.7 W.h).

cs.NE↗

arXiv2009

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 such as ARIMA techniques, Bayesian inference, Markov chains and k-Nearest-Neighbors approximators. Moreover we found that our data preprocessing approach can reduce significantly forecasting errors.

cs.AI↗

arXiv2009

Predictability of PV power grid performance on insular sites without weather stations: use of artificial neural networks

The official meteorological network is poor on the island of Corsica: only three sites being about 50 km apart are equipped with pyranometers which enable measurements by hourly and daily step. These sites are Ajaccio (seaside), Bastia (seaside) and Corte (average altitude of 486 meters). This lack of weather station makes difficult the predictability of PV power grid performance. This work intends to study a methodology which can predict global solar irradiation using data available from another location for daily and hourly horizon. In order to achieve this prediction, we have used Artificial Neural Network which is a popular artificial intelligence technique in the forecasting domain. A simulator has been obtained using data available for the station of Ajaccio that is the only station for which we have a lot of data: 16 years from 1972 to 1987. Then we have tested the efficiency of this simulator in two places with different geographical features: Corte, a mountainous region and Bastia, a coastal region. On daily horizon, the relocation has implied fewer errors than a naive prediction method based on the persistence (RMSE=1468 Vs 1383Wh/m2 to Bastia and 1325 Vs 1213Wh/m2 to Corte). On hourly case, the results were still satisfactory, and widely better than persistence (RMSE=138.8 Vs 109.3 Wh/m2 to Bastia and 135.1 Vs 114.7 Wh/m2 to Corte). The last experiment was to evaluate the accuracy of our simulator on a PV power grid localized at 10 km from the station of Ajaccio. We got errors very suitable (nRMSE=27.9%, RMSE=99.0 W.h) compared to those obtained with the persistence (nRMSE=42.2%, RMSE=149.7 W.h).

cs.OH↗