Non-intrusive identification of residential customers

We present a new approach which identifies the number of customers within particular categories living in a chosen area of energy supply. This identification is made from total energy consumption measured at distribution feeders by applying characteristic patterns of energy use and nonlinear programming techniques. Customers were segmented into four main categories with six sub-groups in each category. A total pattern of energy use was obtained by summing for each sub-group the energy consumption which is based on the characteristic patterns of energy use for that sub-group and the number of customers in that sub-group. Simulations were carried out to verify different optimization procedures. Results show that a variable matrix optimization procedure can identify customers most accurately by minimizing the assumed objective function to a negligible value after 100 iterations.