| Title |
Distribution System Voltage Control based on Forecast using Machine Learning to Increase the Hosting Capacity of Renewables |
| Authors |
원규현(Gyu-hyun Won) ; 정일엽(Il-Yop Chung) ; 강현구(Hyun-Koo Kang) |
| DOI |
https://doi.org/10.5370/KIEE.2020.69.8.1165 |
| Keywords |
Distributed energy resources; Feed forward neural network; Hosting capacity; On-load tap changer; Recurrent neural network; Renewable energy resources; Voltage control |
| Abstract |
The increase of renewable energy sources (RESs) interconnected to the distribution system can negatively affect the supply voltage regulations. This voltage problem eventually becomes an interconnection constraint for RESs. Therefore, to increase the interconnected capacity of RES stably, an appropriate voltage control which is capable of increasing the hosting capacity of the distribution system is needed. In order to solve this problem, in this paper, we proposed the voltage control method which is the OLTC (On-Load Tap Changer) tap position scheduling based on loads and RES’s generations forecast using machine learning method - feed forward neural network (FFNN), recurrent neural network (RNN), and long short term memory (LSTM) Additionally, to verify the forecasting based voltage control method proposed in this paper, the simulation result is shown the effect of increasing the hosting capacity of RESs depending on whether or not the voltage control method is applied. |