Background:
The recent development of small-scale, decentralized generation from
renewable sources and the fall in the price of the equipment needed for this operation have given a
new role to the distribution networks, which is to collect the energy produced by the smallest generation
plants and deliver it to the end customers. However, the national Grid Codes present technical
requirements in terms of FRT and particularly LVRT and HVRT which are imposed on PV
plants connected to medium voltage distribution networks, to ensure the energy needed by the
loads connected to the network at the time of the failure and especially sensitive ones.
Methods:
In this paper, an intelligent neural network approach is applied to the DVR control circuit
to enable the requirements of the sensitive load connected near the PCC, and the system is
tested in the presence of a non-linear load to demonstrate its efficiency for all situations. The proposed
strategy is based on the implementation of an improved ANFIS and ANN control which are
compared to a tuned PI controller, the approach intends to meet the technical requirement of the
recently approved Grid Code in Morocco. The simulation is performed using MATLAB Simulink.
Results:
The proposed approach brings great improvement to the load side voltage waveforms,
and numerical experiment findings demonstrate that it can successfully guarantee the technical
requirements of the electrical grid code.
Conclusion:
The results obtained show better behavior of the system using ANFIS and ANN control
strategy in the presence of a nonlinear load and a significant improvement of the voltage
THD.