Rousseaux, Patricia[Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Système et modélisation >]
Wehenkel, Louis[Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
2005
Proceedings of the 15th Power System Computation Conference (PSCC)
International
15th Power System computation conference (PSCC)
August 22-26
University of Liege
Liège
Belgium
[en] data mining ; power system planning ; probabilistic method ; random sampling ; Monte-Carlo ; real example
[en] This paper describes a methodology for the study of long-term network planning under uncertainties. In this approach the major external uncertainties during the planning horizon are modelled as macro-scenarios at different future time instants. The random nature of actual operating conditions is taken into account by using a probabilistic model of micro-scenarios based on past statistics. MonteCarlo simulations are used to generate and simulate a specified number of scenarios. Data mining techniques are then applied to the simulations results collected in a database, so as to extract information and to rank scenarios and network reinforcements according to different performance criteria. The paper describes the application of this approach on a real transmission planning problem faced by the Belgian transmission system operator.