By: Alexandra Ciobanu (Technical University of Iasi), Anders L. Madsen (HUGIN), and Thomas D. Nielsen (Aalborg University)
15 June 2016
We have developed a Bayesian network from a combination of expert knowledge, information from literature and a database of historical data. For the model development we have used a database that takes into account wind speed and solar radiation. With these we can calculate the power generated by each source of energy and we are able to compare it to the amount of energy required to the consumer.
This comparison is done by adding a Boolean function denoted loss of load probability (Lolp) that tells us if energy demand is met or not. The model has been evaluated on a holdout dataset to determine the performance of the model.
Useful references for those interested in BBN include:
Jensen, F. V. and Nielsen, T. D. (2007) Bayesian Networks and Decision Graphs. Springer, Second Edition.
Kjærulff, U. B. and Madsen, A. L. (2013) Bayesian Networks and Influence Diagrams: A Guide to Construction and Analysis. Springer, Second Edition.
For further details on the model: Alexandra Ciobanu
For further details on the use of Bayesian networks and web deployment of models contact: Anders L Madsen (alm(at)hugin(dot)com)