TY  - EJOU
AU  - Ma, Huan 
AU  - Ma, Linlin 
AU  - Wang, Zengwei 
AU  - Li, Zhendong 
AU  - Zhu, Yuanzhen 
AU  - Liu, Yutian 

TI  - Multi-Lever Early Warning for Wind and Photovoltaic Power Ramp Events Based on Neural Network and Fuzzy Logic
T2  - Energy Engineering

PY  - 2024
VL  - 121
IS  - 11
SN  - 1546-0118

AB  - With the increasing penetration of renewable energy in power system, renewable energy power ramp events (REPREs), dominated by wind power and photovoltaic power, pose significant threats to the secure and stable operation of power systems. This paper presents an early warning method for REPREs based on long short-term memory (LSTM) network and fuzzy logic. First, the warning levels of REPREs are defined by assessing the control costs of various power control measures. Then, the next 4-h power support capability of external grid is estimated by a tie line power prediction model, which is constructed based on the LSTM network. Finally, considering the risk attitudes of dispatchers, fuzzy rules are employed to address the boundary value attribution of the early warning interval, improving the rationality of power ramp event early warning. Simulation results demonstrate that the proposed method can generate reasonable early warning levels for REPREs, guiding decision-making for control strategy.
KW  - Early warning; machine learning; power system security; renewable energy power ramp event; smart grid

DO  - 10.32604/ee.2024.055051