Power flow analysis using adaptive neuro-fuzzy inference systems

Electric power systems expansion has involved the privatization and the restructuration of some power grids; this puts the power system operators in a competitive electricity market. In the other hand, the development of computer systems and software leads to new concepts such us smart grids, therefore the conventional power flow (PF) program need to be enhanced to become optimal power flow (OPF) taking into consideration some uncertainties. To solve power flow problem, two different approaches are used, the traditional and the intelligent one; artificial intelligence systems have proved their efficiency in power system analysis. Adaptive neuro-fuzzy inference systems (ANFIS) are a combination of two intelligent techniques: neural networks and fuzzy logic. This paper presents power flow solution using adaptive neuro-fuzzy inference systems (ANFIS) of IEEE 39 bus system. The training of our ANFIS is taken from power flow results using `power world simulator´ software. Power flow using ANFIS showed a clear improvement in terms of rapidity and feasibility.