TY - GEN
T1 - Forecasting the Electric Network Frequency Signals on Power Grid
AU - Bang, Woorim
AU - Yoon, Ji Won
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported under the framework of international cooperation program managed by National Research Foundation of Korea(No.2017K1A3A1A17092614).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - The power grid, which is one of the important infrastructures, has a very challenging issue to stably manage electric power. The Electrical Network Frequency (ENF) which is the supply frequency on the power grid, however, has small variations near a constant frequency over time. In this paper, we studied the feasibility of predicting ENF values to operate the power grid reliably. To forecast ENF values, we analyzed the ENF signals by using auto-correlation and correlation coefficient. Based on the analysis results, we employed two approaches to forecast ENF values using a kernel regression model with correlation coefficient and autoregressive moving average model. To evaluate the accuracy of the proposed prediction algorithm, we experimented ENF data for 29 days in three power grids of the United States; the Eastern, the Western, and the Texas power grid. The results of our suggested methods presented the remarkable performance in forecasting ENF signals.
AB - The power grid, which is one of the important infrastructures, has a very challenging issue to stably manage electric power. The Electrical Network Frequency (ENF) which is the supply frequency on the power grid, however, has small variations near a constant frequency over time. In this paper, we studied the feasibility of predicting ENF values to operate the power grid reliably. To forecast ENF values, we analyzed the ENF signals by using auto-correlation and correlation coefficient. Based on the analysis results, we employed two approaches to forecast ENF values using a kernel regression model with correlation coefficient and autoregressive moving average model. To evaluate the accuracy of the proposed prediction algorithm, we experimented ENF data for 29 days in three power grids of the United States; the Eastern, the Western, and the Texas power grid. The results of our suggested methods presented the remarkable performance in forecasting ENF signals.
KW - Data Mining
KW - Electric Network Frequency
KW - Prediction
UR - http://www.scopus.com/inward/record.url?scp=85078263493&partnerID=8YFLogxK
U2 - 10.1109/ICTC46691.2019.8939676
DO - 10.1109/ICTC46691.2019.8939676
M3 - Conference contribution
AN - SCOPUS:85078263493
T3 - ICTC 2019 - 10th International Conference on ICT Convergence: ICT Convergence Leading the Autonomous Future
SP - 1218
EP - 1223
BT - ICTC 2019 - 10th International Conference on ICT Convergence
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Information and Communication Technology Convergence, ICTC 2019
Y2 - 16 October 2019 through 18 October 2019
ER -