Abstract
Abstract:
To get the distribution network to operate at its optimum
performance in an automated distribution system reconfiguration
was been proposed and researched. Considering, however,
that optimum performance implies minimum loss, no overloading
of transformers and cables, correct voltage profile, and absence
of phase voltage and current imbalances, network reconfiguration
alone is insufficient. It has to be complemented with techniques for
phase rearrangement between the distribution transformer banks
and the specific primary feeder with a radial structure and dynamic
phase and load balancing along a feeder with a radial structure.
This paper contributes such a technique at the low-voltage
and medium-voltage levels of a distribution network simultaneously
with reconfiguration at both levels. While the neural network
is adopted for the network reconfiguration problem, this paper introduces
a heuristic method for the phase balancing/loss minimization
problem. A comparison of the heuristic algorithm with that of
the neural network shows the former to be more robust. The approach
proposed here, therefore for the combined problem, uses
the neural network in conjunction with a heuristic method which
enables different reconfiguration switches to be turned on/off and
connected consumers to be switched between different phases to
keep the phases balanced. An application example of the proposed
method using real data is presented