A Bayesian Approach of the Availability Complementarity of Renewable Resources

The availability and the autonomy of local power systems supplied from renewable sources are the main subject of the paper. Due to pure random nature of solar and wind characteristics, the Bayes network methodology was selected to study the available generated power of given resources non-optimally located but near the load. The Bayes networks were generated from a large database. The corresponding information was recorded using a professional meteorological station while the Essential Graph Search was the algorithm to generate the final Bayes network structure and parameters. The network allows for weather estimation also. The final results were validated by meteorological experts.

[1]  Florin Munteanu,et al.  Data - driven Bayesian networks for reliability of supply from renewable sources , 2017, 2017 International Conference on Optimization of Electrical and Electronic Equipment (OPTIM) & 2017 Intl Aegean Conference on Electrical Machines and Power Electronics (ACEMP).

[2]  Alexandra Ciobanu,et al.  Bayesian networks utilization for reliability evaluation of power systems , 2016, 2016 International Conference and Exposition on Electrical and Power Engineering (EPE).

[3]  Amin Shokri Gazafroudi.  Assessing the Impact of Load and Renewable Energies’ Uncertainty on a Hybrid System , 2016 .

[4]  Hazel E. Thornton,et al.  The climatological relationships between wind and solar energy supply in Britain , 2015, 1505.07071.

[5]  Ming-Chao Huang,et al.  Oscillation characteristic study of wind speed, global solar radiation and air temperature using wavelet analysis , 2017 .

[6]  Marek J. Druzdzel,et al.  A Hybrid Anytime Algorithm for the Construction of Causal Models From Sparse Data , 1999, UAI.

[7]  M. D. Kock.  Weather Forecasting Using Dynamic Bayesian Networks Report on Dynamic Bayesian Network Learning , 2008 .

[8]  Bri-Mathias Hodge,et al.  Investigating the Correlation Between Wind and Solar Power Forecast Errors in the Western Interconnection , 2013 .

[10]  Jirí Vomlel,et al.  A reconstruction algorithm for the essential graph , 2009, Int. J. Approx. Reason..

[11]  R. G. Steadman,et al.  The Assessment of Sultriness. Part II: Effects of Wind, Extra Radiation and Barometric Pressure on Apparent Temperature , 1979 .

[12]  Lueder von Bremen,et al.  On the correlation of spatial wind speed and solar irradiance variability above the North Sea , 2016 .

[13]  J. A. Ruiz-Arias,et al.  Analysis of Spatiotemporal Balancing between Wind and Solar Energy Resources in the Southern Iberian Peninsula , 2012 .

[14]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine-mediated learning.

[15]  Goran Krajačić,et al.  LINEAR CORRELATION AND REGRESSION BETWEEN THE METEOROLOGICAL DATA AND THE ELECTRICITY DEMAND OF THE DUBROVNIK REGION IN A SHORT-TERM SCALE , 2016 .

[16]  José Manuel Gutiérrez,et al.  Bayesian Networks for Probabilistic Weather Prediction , 2002, ECAI.

[17]  Katalin Bódis,et al.  Assessing complementarity of wind and solar resources for energy production in Italy. A Monte Carlo approach , 2014 .