ABSTRACT
Monitoring of
Voltage Stability Margin (VSM) and stabilizing the voltage of the network in
the event of predicted voltage instability has been one of the challenges
facing the electrical power system in Nigeria. This thesis presents an
artificial neural network (ANN)-based approach for monitoring of the voltage
stability margin(VSM) and consequently stabilizing the voltage of the network
in the event of predicted voltage instability by compensating for the dip using
Static Var Compensators (SVC) in electric power system. To achieve this
objective, the first work done was to characterize and hence develop a model
for the station under study which was the 330/132/33kV New Haven, Enugu Transmission
Substation in Nigeria. Next, a load flow algorithm was developed for the
station under study and voltage stability margin (VSM) was determined. The VSM
was calculated by estimating the distance from the current operation state to
the maximum voltage stability limit point according to the system loading
parameter. The artificial neural network (ANN) was then modeled and trained.
Static var compensator (SVC) was then modeled and incorporated in the ANN and
the setup was simulated. The results obtained were then compared with those
gotten before the incorporation of ANN-SVC and improvements on voltage profile
of the load buses were observed. The main drawback on the previously published
works in the literature on voltage stability assessment (VSA) using neural
networks is that they need to train a new neural network when a change in the
power system topology occurs. Therefore, the possibility of employing a single
ANN for estimating the VSM and for controlling the switching of the SVC for the
330/132/33kV New Haven, Enugu Transmission Substation in Nigeria was
investigated in this thesis. The effectiveness of the proposed method is tested
on the dynamic model in the Power System Analysis Toolbox (PSAT) software. The
ANN network was designed in the MATLAB/SIMMULINK software and consequently
deployed into the system to control the SVC at the point with critical voltage
sensitivity. The results obtained indicate that the proposed scheme provides a
compact and efficient ANN model that can successfully and accurately estimate
the VSM with an accuracy of about 95% while controlling the SVC considering
different
system
configurations as well as operating conditions.
Get the Complete Project Material Now!!!
