Probabilistic assessment and preventive control of voltage security margins using artificial neural network

This paper describes a new technique for probabilistic assessment and preventive control of voltage security margins using artificial neural network. The probabilistic insecurity index (PISI) has been obtained for various operating conditions considering single and double line outages and accounting static voltage stability limit. Evaluated PISI has been obtained for various settings of reactive power control variables and loading conditions using cut-set method. These results have been used to train a multi layer feed forward network so as to assess the security on line. Further sensitivities of PISI have been evaluated based on trained network and have been used to control power system security. The algorithm has been implemented on a 6-bus, 7-line IEEE standard test system.