| 引用本文: | 张志艳,兰 龙,白景升,等.小样本条件下风电功率预测方法的研究[J].电力系统保护与控制,2025,53(18):120-130.[点击复制] |
| ZHANG Zhiyan,LAN Long,BAI Jingsheng,et al.Research on wind power forecasting methods under small-sample conditions[J].Power System Protection and Control,2025,53(18):120-130[点击复制] |
|
| 摘要: |
| 针对风电功率预测通常需要大量历史数据和复杂模型支持的问题，提出了一种小样本条件下风电功率预测模型。首先，针对样本不足问题，提出基于时序马尔可夫链蒙特卡洛(time-Markov chain Monte Carlo, Time-MCMC)的数据扩充方法，采用统计、插值、拟合和自适应识别方法进行数据清洗，提升样本的多样性和质量。其次，融合多种优化策略，构建基于改进型混合天鹰优化与非洲秃鹫优化算法(improved hybrid aquila optimization and African vulture optimization algorithm, IHAOAVOA)的反向传播(backpropagation, BP)神经网络风电功率预测模型。最后，以实际算例验证了数据扩充方法的有效性，同时对扩充后的样本集分别采用BP神经网络、天鹰优化器(aquila optimizer, AO)优化BP神经网络、非洲秃鹫优化算法(African vultures optimization algorithm, AVOA)优化BP神经网络和IHAOAVOA-BP神经网络4种模型进行功率预测。预测结果表明，与AVOA-BP模型相比，所提模型平均绝对值误差(mean absolute error, MAE)和均方误差(mean squared error, MSE)分别至少降低了0.45 MW和21.48%。 |
| 关键词: 功率预测 小样本 BP神经网络 马尔可夫链蒙特卡洛 混合优化策略 |
| DOI：10.19783/j.cnki.pspc.241315 |
| 投稿时间：2024-09-28修订日期：2025-04-20 |
| 基金项目:河南省科技攻关项目资助(242102241030) |
|
| Research on wind power forecasting methods under small-sample conditions |
| ZHANG Zhiyan1,LAN Long1,BAI Jingsheng1,YANG Tangyige2,KONG Han1,LIU Hua3 |
| (1. College of Electrical and Information Engineering, Zhengzhou Light Industry University, Zhengzhou 450002, China;
2. Chaohu Guanhu Wind Farm, China General Nuclear New Energy, Chaohu 238007, China;
3. Construction Department of Henan Electric Power Company, Zhengzhou 450007, China) |
| Abstract: |
| To address the issue that wind power forecasting typically requires substantial historical data and support from complex models, a wind power forecasting model under small-sample conditions is proposed. First, aiming at the problem of insufficient samples, a data augmentation method based on time-Markov chain Monte Carlo (Time-MCMC) is developed. Statistical analysis, interpolation, fitting, and adaptive recognition methods are employed for data cleaning to improve the diversity and quality of the samples. Second, by integrating multiple optimization strategies, a wind power forecasting model is constructed, where the backpropagation (BP) neural network is optimized using the improved hybrid aquila optimization and African vulture optimization algorithm (IHAOAVOA). Finally, the effectiveness of the data augmentation method is verified using actual case studies. Meanwhile, power forecasting is conducted on the augmented sample set using four models: the BP neural network, the BP neural network optimized by the aquila optimizer (AO), the BP neural network optimized by the African vulture optimization algorithm (AVOA), and the IHAOAVOA-BP neural network. The forecasting results show that, compared with the AVOA-BP model, the mean absolute error (MAE) and mean squared error (MSE) of the proposed model are reduced by at least 0.45 MW and 21.48% respectively. |
| Key words: power forecasting small sample BP neural network Markov chain Monte Carlo hybrid optimization strategy |
