Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems

Chaabene, Maher; Ammar, Mohsen Ben

doi:10.1016/j.renene.2007.10.004

Cited by 75 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, one can remark that Tassadducq et al [17] used in 2002 a backpropagation neural network to forecast the temperature at a given hour of the next day, only using the temperature at the same hour of the present day. In 2008, Chaabene and Ben Ammar [18] introduced a new methodology for dynamic forecasting of meteorological parameters. An ANFIS [19][20][21] neuro-fuzzy system offered daily time distribution of irradiance and ambient temperature relying on the meteorological behavior during the days before.…”

Section: Figure 1 Diagram Of the Optienr Project In Red The Forecamentioning

confidence: 99%

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

Eynard

Grieu

Polit

2011

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

To cite this version:Julien Eynard, Stéphane Grieu, Monique Polit. Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption. Engineering Applications of Artificial Intelligence, Elsevier, 2011, 24 (3) Domitia, 52 Av. Paul Alduy, 66860, Perpignan, Abstract: as part of the OptiEnR research project, the present paper deals with outdoor temperature and thermal power consumption forecasting. This project focuses on optimizing the functioning of a multi-energy district boiler (La Rochelle, west coast of France), adding to the plant a thermal storage unit and implementing a model-based predictive controller. The proposed short-term forecast method is based on the concept of time series and uses both a wavelet-based multi-resolution analysis and multi-layer artificial neural networks. One could speak of "MRA-ANN" methodology. The discrete wavelet transform allows decomposing sequences of past data in subsequences (named coefficients) according to different frequency domains, while preserving their temporal characteristics. From these coefficients, multi-layer Perceptrons are used to estimate future subsequences of 4 hours and 30 minutes. Future values of outdoor temperature and thermal power consumption are then obtained by simply summing up the estimated coefficients. Substituting the prediction task of an original time series of high variability by the estimation of its wavelet coefficients on different levels of lower variability is the main idea of the present work. In addition, the sequences of past data are completed, for each of their components, by both the minute of the day and the day of the year to place the developed model in time. The present paper mainly focuses on the impact on forecast accuracy of various parameters, related with the discrete wavelet transform, such as both the wavelet order and the decomposition level, and the topology of the neural networks used. The number of past sequences to take into account and the chosen time step were also major concerns. The optimal configuration for the tools used leads to very good forecasting results and validates the proposed MRA-ANN methodology.

show abstract

Section: Figure 1 Diagram Of the Optienr Project In Red The Forecamentioning

confidence: 99%

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

Eynard

Grieu

Polit

2011

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The views of theresults presented here,theirinvestigationlooks promising. Finally, forhorizonsh+24 and m+5, there are stilltoo few studiesusing theMLP.HoweverasMellitandPavan [27] andChaabeneandBen Ammar [57]we believeandhave shown that theMLPwereadapted to thesesituations. In addition,our approachwith the use oftime index appears to be efficient.…”

Section: Resultsmentioning

confidence: 99%

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

Voyant

Paoli

Muselli

et al. 2013

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

a b s t r a c tConsidering 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.

show abstract

“…However, as in most of the similar works, the energy model assumes that short term energy replenishment schedule for nodes is known. While there are studies on prediction of solar irradiation such as [20], [21] and [22]; few have used Kalman filtering techniques, and none of them combines online proportional time fair resource allocation algorithm with such a predictor.…”

Section: Related Workmentioning

confidence: 99%

Kalman prediction based proportional fair resource allocation for a solar powered base station

Tekbiyik-Ersoy

Uysal-Biyikoğlu

Leblebi̇ci̇oğlu

et al. 2013

2013 21st Signal Processing and Communications Applications Conference (SIU)

View full text Add to dashboard Cite

Optimization of a Wireless Sensor Network (WSN) downlink with an energy harvesting transmitter (base station) is considered. The base station (BS), which is attached to the central controller of the network, sends control information to the gateways of individual WSNs in the downlink. This paper specifically addresses the case where the BS is supplied with solar energy. Leveraging the daily periodicity inherent in solar energy harvesting, the schedule for delivery of maintenance messages from the BS to the nodes of a distributed network is optimized. Differences in channel gain from the BS to sensor nodes make it a challenge to provide service to each of them while efficiently spending the harvested energy. Based on PTF (Power-Time-Fair), a close-to-optimal solution for fair allocation of harvested energy in a wireless downlink proposed in previous work, we develop an online algorithm, PTF-On, that operates two algorithms in tandem: A prediction algorithm based on a Kalman filter that operates on solar irradiation measurements, and a modified version of PTF. PTF-On can predict the energy arrival profile throughout the day and schedule transmission to nodes to maximize total throughput in a proportionally fair way.

show abstract

Neuro-fuzzy dynamic model with Kalman filter to forecast irradiance and temperature for solar energy systems

Cited by 75 publications

References 11 publications

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

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

Kalman prediction based proportional fair resource allocation for a solar powered base station

Contact Info

Product

Resources

About