An Improved ANN–BPN to Radial Distribution System Load Flow - Proceedings of All India Seminar on Biomedical Engineering 2012 (AISOBE-2012) - page 188

Fig. 5 The 33-bus radial
distribution system

1 : 0
1 : 0 þ e / v

½ Neuron Input ¼ ð 1 Þ

Here, a is the abruptness of the sigmoid activation function and v is the total
input to the neuron. Let the vector X represents an input layer as in Fig. 4 . The net
input at the hidden layers is computed by the matrix equation below:

V H ¼ WH ½ X ð 2 Þ

where WH ji denotes the weight between ith input layer node and jth hidden layer
node. The output of the hidden layer node is given by,

Y H ¼ / V ðÞ 3 Þ

here / is the appropriate activation function. In a similar manner the total input
at the output layer is given by the following equation:

V o ¼ WO ½ V H ð 4 Þ

The output of the output layer node is given by,

Y ¼ / V ðÞ 5 Þ