风电的波动性和随机性,尤其是功率爬坡事件严重威胁着电网运行的安全和稳定。功率爬坡是极端天气影响下产生的,属于小概率事件。其极低的发生概率导致历史爬坡样本数量严重不足,并制约了传统功率预测模型的预测精度。针对此类问题,提出一种基于生成对抗网络的风电爬坡功率预测方案。将历史爬坡数据和模拟特征量作为输入,通过生成器和判别器的对抗训练,生成大量与历史爬坡数据特征相似的模拟爬坡数据,实现爬坡数据集的扩充。再将扩充后的爬坡数据集输入给长短期记忆神经网络算法,进行风电爬坡功率预测。通过仿真测试,验证了该方法在历史爬坡数据匮乏情况下风电爬坡功率预测的有效性。并与传统预测方法进行了对比,证明了其预测的精确性。
Abstract
Volatility and randomness of wind power, especially power ramping events, seriously threaten the sound and stable operation of the power grid. Ramping events, which accidentally, are generated under the influence of extreme weather. It’s extremely low probability of occurrence leads to a huge shortage of historical data, restricting the prediction accuracy of traditional power prediction models. To handle such problems, a wind power ramping prediction model based on generative adversarial network is proposed. Taking historical ramping data and simulated feature quantities as input, through the adversarial training of the generator and discriminator, a large number of simulated data with similar characteristics to the historical samples are generated to realize the expansion of the ramping data set. Then the expanded data set is used as input to the long and short-term memory neural network algorithm to predict ramping power. The simulation results show that the method is effective in predicting wind power climbing power in the case of lack of historical climbing data. And compared with the traditional prediction method, the accuracy of the prediction is proved.
关键词
风电功率预测 /
神经网络 /
生成对抗网络 /
功率爬坡事件
Key words
wind power forecast /
neural network /
generative adversarial network /
power ramping events
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 钱政, 裴岩, 曹利宵, 等. 风电功率预测方法综述[J]. 高电压技术, 2016, 42(4): 1047-1060.
QIAN Z, PEI Y, CAO L X, et al.Review of wind power forecasting method[J]. High voltage engineering, 2016, 42(4): 1047-1060.
[2] 张东英, 代悦, 张旭, 等. 风电爬坡事件研究综述及展望[J]. 电网技术, 2018, 42(6): 1783-1792.
ZHANG D Y, DAI Y, ZHANG X, et al.Review and prospect of research on wind power ramp events[J]. Power system technology, 2018, 42(6): 1783-1792.
[3] CULTER N, KAY M, JACKA K, et al.Detecting, categorizing and forecasting large ramps in wind farm power output using meteorological observations and WPPT[J]. Wind energy, 2007, 10(5): 453-470.
[4] ZHENG H, KUSIAK A.Prediction of wind farm power ramp rates: a data-mining approach[J]. Journal of solar energy engineering, 2009, 131(3): 031011-031018.
[5] ZACK J W, YOUNG S, COTE M, et al.Development and testing of an innovative short-term large wind ramp forecasting system[C]//Proceedings of the European Wind Energy Conference and Exhibition(EWEC 2010), Warsaw, Poland, 2010: 20-23.
[6] 戚永志, 刘玉田. 基于竞争博弈的风电爬坡协同控制策略[J]. 中国电机工程学报, 2014, 34(25): 4341-4349.
QI Y Z, LIU Y T.Ramping coordination control of wind generation based on competitive game theory[J]. Proceedings of the CSEE, 2014, 34(25): 4341-4349.
[7] 甘迪, 柯德平, 孙元章, 等. 基于突变理论的风电爬坡多步预测[J]. 现代电力, 2016, 33(3): 14-21.
GAN D, KE D P, SUN Y Z, et al.Multi-step wind power ramp forecasting based on catastrophe theory[J]. Modern electric power, 2016, 33(3): 14-21.
[8] 何成明, 王洪涛, 王春义, 等. 风电功率爬坡事件作用下考虑时序特性的系统风险评估[J]. 电力自动化设备, 2016, 36(1): 35-41.
HE C M, WANG H T, WANG C Y, et al.Risk assessment considering time-sequence characteristics for power system with wind power ramp event[J]. Electric power automation equipment, 2016, 36(1): 35-41.
[9] 景惠甜, 韩丽, 高志宇. 基于卷积神经网络特征提取的风电功率爬坡预测[J]. 电力系统自动化, 2021, 45(4): 98-105.
JING H T, HAN L, GAO Z Y, et al.Wind power ramp forecast based on feature extraction using convolutional neural network[J]. Automation of electric power systems, 2021, 45(4): 98-105.
[10] 杨茂, 马剑, 李大勇, 等. 超短期风电功率爬坡事件检测和统计分析[J]. 电力系统保护与控制, 2018, 46(6): 62-68.
YANG M, MA J, LI D Y, et al.Ultra-short-term wind power climbing event detection and statistical analysis[J]. Power system protection and control, 2018,46(6): 62-68.
[11] 叶林, 路朋, 滕景竹, 等. 考虑风电功率爬坡的功率预测——校正模型[J]. 电力系统自动化, 2019, 43(6): 49-58.
YE L, LU P, TENG J Z, et al.Power prediction and correction model considering wind power ramping events[J]. Automation of electric power systems, 2019, 43(6): 49-58.
[12] 屈尹鹏, 徐箭, 姜尚光, 等. 基于频繁模式挖掘的风电爬坡事件统计特性建模及预测[J]. 电力系统自动化, 2021, 45(1): 36-43.
QU Y P, XU J, JIANG S G, et al.Frequent pattern mining based modeling and forecasting for statistical characteristics of wind power ramp events[J]. Automation of electric power systems, 2021, 45(1): 36-43.
[13] 崔明建, 孙元章, 柯德平. 基于原子稀疏分解和BP神经网络的风电功率爬坡事件预测[J]. 电力系统自动化, 2014, 38(12): 6-11, 26.
CUI M J, SUN Y Z, KE D P, et al.A capacity optimization method of hybrid energy storage system for optimizing tie-line power in microgrids[J]. Automation of electric power systems, 2014, 38(12): 6-11,26.
[14] 朱刘柱, 王绪利, 马静, 等. 基于小波包分解与循环神经网络的综合能源系统短期负荷预测[J]. 电力建设, 2020, 41(12): 131-138.
ZHU L Z, WANG X L, MA J, et al.Short-term load forecast of integrated energy system based on wavelet packet decomposition and recurrent neural network[J]. Electric power construction, 2020, 41(12): 131-138.
[15] 庄家懿, 杨国华, 郑豪丰, 等. 并行多模型融合的混合神经网络超短期负荷预测[J]. 电力建设, 2020, 41(10): 1-8.
ZHUANG J Y, YANG G H, ZHENG H F, et al.Ultra-short-term load forecasting using hybrid neural network based on parallel multi-model combination[J]. Electric power construction, 2020, 41(10): 1-8.
基金
宁波职业技术学院青年课题《一种基于RNN网络端到端预测算法研究》（NZ23Q01）
PDF(1600 KB)
