| 基于两阶段不确定性量化的光伏发电超短期功率预测 |
| |
| 引用本文： | 张家安,郝峰,董存,刘辉,李志军.基于两阶段不确定性量化的光伏发电超短期功率预测[J].太阳能学报,2023,44(1):69-77. |
| |
| 作者姓名： | 张家安 郝峰 董存 刘辉 李志军 |
| |
| 作者单位： | 1.省部共建电工装备可靠性与智能化国家重点实验室（河北工业大学）,天津 300401;2.河北工业大学人工智能与数据科学学院,天津 300401;3.国家电力调度控制中心,北京 100031;4.国网冀北电力有限公司电力科学研究院,北京 100045 |
| |
| 基金项目： | 河北省自然科学基金创新群体项目（E2020202142） |
| |
| 摘 要： | 针对光伏功率预测,提出一种光伏发电出力不确定性量化分析的两阶段模型。第1阶段,首先选取待预测日之前一段时间的光伏输出功率历史数据作为训练样本,引入模糊熵（FE）将不同天气类型量化并作为输入量;然后利用集成经验模态分解（EEMD）将光伏发电功率时间序列分解为多个模态分量,再利用Hurst指数分析将不同模态分量重构为中尺度和宏尺度2个子序列,基于双向长短期记忆神经网络并引入注意力机制对重构后的2个子序列分别进行预测;最后对中尺度子序列对应的误差序列进行修正,得到光伏发电出力的点预测结果。第2阶段,根据第1阶段点预测结果得到的误差统计,采用核密度估计（KDE）方法预测光伏发电出力的区间,分别获取在95%、90%、85%及80%置信水平下的区间覆盖率（PICP）。应用中国西北地区某光伏电站运行数据作为算例,验证了该文预测方法的有效性。
|
| 关 键 词： | 光伏发电 预测 神经网络 注意力机制 集成经验模态分解 误差校正 |
| 收稿时间： | 2021-07-28 |
ULTRA-SHORT-TERM POWER FORECASTING OF PHOTOVOLTAIC POWER GENERATION BASED ON TWO-STAGE UNCERTAINTY QUANTIZATION |
| |
| Zhang Jiaan,Hao Feng,Dong Cun,Liu Hui,Li Zhijun.ULTRA-SHORT-TERM POWER FORECASTING OF PHOTOVOLTAIC POWER GENERATION BASED ON TWO-STAGE UNCERTAINTY QUANTIZATION[J].Acta Energiae Solaris Sinica,2023,44(1):69-77. |
| |
| Authors: | Zhang Jiaan Hao Feng Dong Cun Liu Hui Li Zhijun |
| |
| Affiliation: | 1. State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300401, China;2. College of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300401, China;3. National Electric Power Dispatching and Control Center, Beijing 100031, China;4. State Grid Jibei Electric Power Co., Ltd., Research Institute, North China Electric Power Research Institute Co., Ltd., Beijing 100045, China |
| |
| Abstract: | A two-stage model for quantitative analysis of output uncertainty of photovoltaic power generation is proposed. In the first stage, the photovoltaic power for a period of time before the prediction day is used as the training sample, and the fuzzy entropy is introduced to quantify different weather types as the input. Then, based on the employing integrated empirical mode decomposition （EEMD）, the photovoltaic power time series is decomposed into multiple modal components, which are reconstructed into mesoscale and macro scale subsequences with Hurst index analysis. The BiLSTM based on attention mechanism （BiLSTM-Attention） is used to predict the two subsequences respectively. The error sequence corresponding to the mesoscale subsequence is corrected to obtain the point prediction results of photovoltaic power generation. In the second stage, the nuclear density estimation （KDE） method is used to predict the interval of photovoltaic power generation according to the error statistics obtained from the point prediction results in the first stage. The prediction interval coverage probability （PICP） at 95%, 90%, 85% and 80% confidence levels are obtained respectively. Taking the operation data of a photovoltaic power station in Northwest China as an example, the effectiveness of this method is verified. |
| |
| Keywords: | PV power generation forecasting neural networks attention mechanism EEMD error correction |
|
| 点击此处可从《太阳能学报》浏览原始摘要信息 |
|
点击此处可从《太阳能学报》下载全文 |
|
