- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 IEEE PES Innovative Smart Grid Technologies Conference - Latin America (ISGT Latin America) - Gramado, Brazil (2019.9.15-2019.9.18)] 2019 IEEE PES Innovative Smart Grid Technologies Conference - Latin America (ISGT Latin America) - Generation Planning Model Including Frequency Stability Constrains to Mitigate Large-Scale Integration of Photovoltaic Plants
摘要： In the last two decades, electricity systems have undergone structural changes due to the incorporation of large- scale variable generation technologies (VGTs). Some of the VGT such as photovoltaics (PV) and wind power produces undesirable effects in the system. In power systems, synchronous generators are the primary sources of inertia. During power imbalance, the inertia of the generators prevents frequency stability issues. The VGTs do not naturally provide inertia, so when their participation in the production matrix is high; the system loses robustness since the inertia is decreased. This paper proposes a generator-planning model that includes the effects of lower inertia due to the increase of VGTs. The objective is to obtain a limited frequency deviation during contingencies. The proposed model adds restrictions related to the frequency variation to the capacity of the units that are in fault. The simulations show that to comply with the specified frequency deviations, the model must oversize the park in the order of 13 % in small meshed systems, while in real size systems the oversize is in the order of 1 %.
关键词： Frequency regulation,inertial response,renewable energy sources,power generation planning
更新于2025-09-11 14:15:04
-
Integrating Grey Data Preprocessor and Deep Belief Network for Day-ahead PV Power Output Forecast
摘要： Generation output forecasting is a crucial task for planning and sizing of a photovoltaic (PV) power plant. The purpose of this paper is to present an effective model for day-ahead forecasting PV power output of a plant based on deep belief network (DBN) combined with grey theory-based data preprocessor (GT-DBN), where the DBN attempts to learn high-level abstractions in historical PV output data by utilizing hierarchical architectures. Test results obtained by the proposed model are compared with those obtained by other five forecasting methods including autoregressive integrated moving average model (ARIMA), back propagation neural network (BPNN), radial basis function neural network (RBFNN), support vector regression (SVR), and DBN alone. It shows that the proposed model is superior to other models in forecasting accuracy and is suitable for day-ahead PV power output prediction.
关键词： supervised learning,time series analysis,power generation planning,neural networks,Renewable energy
更新于2025-09-04 15:30:14