基于EEMD-ANN的自适应光伏日电量预测方法
Adaptive Photovoltaic Daily Power Forecasting Algorithm based on EEMD-ANN
黄娟 1赵鹏 2王聚博 2凌宇龙 2苏洋 2赵闻音2
作者信息
- 1. 国家电投集团江西电力有限公司,江西 南昌 330000
- 2. 国家电投集团科学技术研究院有限公司,北京 102200
- 折叠
摘要
随着清洁能源的持续发展,我国光伏电源装机规模不断增大.为了应对其随机性、波动性、不确定性等特点给电网安全运行带来的严峻挑战,研究中结合集合经验模态分解(EEMD)方法对原始时间序列进行处理,将其分解为有限且少量的振荡模式,形成更清晰的信号输入,再通过人工神经网络(ANN)实现历史数据的规律挖掘,构建了基于EEMD-ANN的自适应光伏日电量预测模型.以我国南方某光伏电站日电量过程为例的结果表明,该模型获得的预测结果具有较好的预测精度,是一种实用性较强的光伏电量预测方法.
Abstract
With the continuous development of clean energy,the installed capacity of photovoltaic power sources in China is constantly increasing.In order to cope with the severe challenges brought by its ran-domness,volatility,uncertainty and other characteristics to the safe operation of the power grid,the re-search combines the set empirical mode decomposition(EEMD)method to process the original time se-ries,decomposing it into limited and small oscillation modes to form clearer signal inputs.Then,artificial neural networks(ANN)are used to mine the patterns of historical data,and an adaptive photovoltaic dai-ly electricity prediction model based on EEMD-ANN is constructed.The results of taking the daily elec-tricity consumption process of a photovoltaic power station in southern China as an example show that the prediction results obtained by the model have good prediction accuracy and are a practical method for pre-dicting photovoltaic electricity consumption.
关键词
光伏发电/集合经验模态分解(EEMD)/人工神经网络(ANN)/非平稳/自适应预测Key words
photovoltaic/ensemble empirical mode decomposition/artificial neural network/non station-ary/adaptive prediction引用本文复制引用
出版年
2024
NETL
NSTL
万方数据