兰州大学机构库 >数学与统计学院
基于EEMD和布谷鸟优化T-S模糊神经网络模型的风电场短期风速预测
Alternative TitleThe Short-Term Wind Speed Forecasting Based on EEMD and CS Optimizing T-S Fuzzy Neural Network Model
韩博惠
Thesis Advisor王建州
2014-05-22
Degree Grantor兰州大学
Place of Conferral兰州
Degree Name学士
KeywordEEMD数据预处理 T-S模糊神经网络 布谷鸟优化 风速预测
Abstract   随着科技的日益发展,能源的过度消耗已成为当今世界所面临的几大难题之一,提高绿色能源的利用率逐渐成为人们所关注的焦点。目前,风能发电是最具前景的可再生能源之一。但是由于风速具有很强的随机性和间歇性,导致风功率具有较强的波动性和不可控性,并网后甚至会严重影响发电设备和电能质量,因此,对风速的准确预测在风电行业的发展中显得尤为重要。    本文通过建立混合预测模型提高了单一预测模型在风电场短期风速预测的精度。模型主要通过总体平均经验模态分解(EEMD)对原始风电场风速数据进行了预处理,处理过的数据作为样本数据,训练经布谷鸟智能优化后的T-S模糊神经网络模型函数,从而使得预测精度更高。    仿真测试及结果显示,与单一的预测模型或人工优化后的模型相比,运用该混合预测模型在不同样本时间段的预测结果精度都要远远的高于其它模型,本文误差检测有平均误差、平均绝对误差,均方误差和平均绝对百分比误差(MAPE)对预测结果进行检测,其中测得MAPE误差为6%左右(小于10%)。说明了该预测模型的有效性和适用性,对风电场运营商在风场短期风速预测方面具有一定的参考价值。
Other Abstract    With the increasing development of technology, excessive consumption of energy has become one of the major challenges facing the world today , and to improve the utilization of green energy has become the focus of public concern.Currently, wind power is one of the most promising renewable energy sources . However, because of the strong natures of randomness and intermittence in wind speed , wind power has a strong lead to volatility and uncontrollable , even may seriously affect the power generation and power quality after the grid . Therefore, accurate prediction of the wind speed in the development of the wind power industry is particularly important.     In this paper, we improve the forecasting precision of short-term wind speed through the establishment of a hybrid forecasting model compared with the single forecast model in wind farm. Model mainly pretreated the original wind speed data through Ensemble Empirical Mode Decomposition (EEMD), and the processed data are used as the sample data training the T-S fuzzy neural network model function whose parameters have been intelligently optimized by the CS , thus making the prediction precision higher.     Testing and simulation results show that, compared with the single predictive model or artificial optimized models, the precision of using the hybrid prediction model in accuracy prediction of different sample or different periods are far higher than that of other models. The Mean Absolute Percentage Error (MAPE) detection showed the measured error is less than 10%, illustrating the validity and applicability of the prediction model, which also have some reference value in the short-term wind forecasting for wind farm operators .
URL查看原文
Language中文
Document Type学位论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/225244
Collection数学与统计学院
Recommended Citation
GB/T 7714
韩博惠. 基于EEMD和布谷鸟优化T-S模糊神经网络模型的风电场短期风速预测[D]. 兰州. 兰州大学,2014.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[韩博惠]'s Articles
Baidu academic
Similar articles in Baidu academic
[韩博惠]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[韩博惠]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.