Scholarlink

Transmission line capacity limitations have resulted in significant wind curtailment within wind farms, but the introduction of dynamic thermal rating (DTR) has enabled short-term increases in line capacity, offering a promising solution. Incorporating DTR into wind farms holds promise for increasing the penetration of renewable energy. Therefore, it is crucial to acknowledge tie-lines equipped with DTR alongside wind farms as a unified entity when predicting short-term transmission capacity. However, given the uncertainty arising from meteorological fluctuations affecting both wind turbines (WTs) and DTR, this paper proposed a data-driven model to short-term transmission capacity prediction. The model initially employs the Complementary Ensemble Empirical Mode Decomposition (CEEMD) method to decompose the feature quantities, reducing their complexity. Subsequently, it utilizes the Bi-directional Long Short-Term Memory (BiLSTM) network to forecast the decomposed Intrinsic Mode Function (IMF) components. To enhance the efficiency of the BiLSTM network and mitigate parameter influence, a new algorithm, i.e., Newton-Raphson-Based Optimizer (NRBO), is applied to optimize the parameters of the BiLSTM network. Finally, the prediction outcomes of IMF are aggregated to derive the short-term transmission capacity of the target under study. Case analyses demonstrate that this approach enhances prediction accuracy. Furthermore, integrating DTR into wind farms has the potential to mitigate wind curtailment and elevate the utilization of renewable energy sources.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Short-Term Forecasting of Wind Farm Output Considering Dynamic Thermal Rating of the Tie-Lines

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yi Su,
  • Mao Tan,
  • Lin Wang,
  • Changqing Chen

摘要

Transmission line capacity limitations have resulted in significant wind curtailment within wind farms, but the introduction of dynamic thermal rating (DTR) has enabled short-term increases in line capacity, offering a promising solution. Incorporating DTR into wind farms holds promise for increasing the penetration of renewable energy. Therefore, it is crucial to acknowledge tie-lines equipped with DTR alongside wind farms as a unified entity when predicting short-term transmission capacity. However, given the uncertainty arising from meteorological fluctuations affecting both wind turbines (WTs) and DTR, this paper proposed a data-driven model to short-term transmission capacity prediction. The model initially employs the Complementary Ensemble Empirical Mode Decomposition (CEEMD) method to decompose the feature quantities, reducing their complexity. Subsequently, it utilizes the Bi-directional Long Short-Term Memory (BiLSTM) network to forecast the decomposed Intrinsic Mode Function (IMF) components. To enhance the efficiency of the BiLSTM network and mitigate parameter influence, a new algorithm, i.e., Newton-Raphson-Based Optimizer (NRBO), is applied to optimize the parameters of the BiLSTM network. Finally, the prediction outcomes of IMF are aggregated to derive the short-term transmission capacity of the target under study. Case analyses demonstrate that this approach enhances prediction accuracy. Furthermore, integrating DTR into wind farms has the potential to mitigate wind curtailment and elevate the utilization of renewable energy sources.