摘要
为有效掌握电网风电场群的泛化能力,实现高精度、高效率的电网输配电,设计基于大数据模型的电网风电场群总功率预测模型。利用大数据建模条件,对电网风电场群的波动效果进行分类,并建立具有普遍性的一般波动属性条件,完成基于大数据模型的电网风电场群波动特性分析。利用上述分析结果,搭建标准的神经预测网络,并对风电场群总功率的汇聚层级别进行划分,再整合所有理论依据对预测规律进行总结,完成新型理论模型搭建,实现基于大数据模型的电网风电场群总功率预测。对比实验结果表明,与传统模型相比,应用新型总功率预测模型后,电网配电精度的平均值达到55%以上,单向输电效率最大值接近97%,电网风电场群的泛化能力得到良好控制。
In order to effectively grasp the generalization ability of wind farms in power grid and realize high-precision and high-efficiency transmission and distribution of power grid,a prediction model of total power of wind farms in power grid based on large data model is designed.Using the large data modeling conditions,the fluctuation effects of wind farms in power grid are classified,and the general fluctuation attribute conditions are established.The fluctuation characteristics of wind farms in power grid based on large data model are analyzed.Based on the above analysis results,a standard neural prediction network is built,and the aggregation level of the total power of wind farms is divided.Then,all theoretical basis is integrated to summarize the prediction rules,and a new theoretical model is built to realize the total power prediction of wind farms in power grid based on large data model.The experimental results show that,compared with the traditional model,the average distribution accuracy of the new total power prediction model is more than 55%,the maximum one-way transmission efficiency is close to 97%,and the generalization ability of the wind farm group is well controlled.
作者
魏梦飒
陆增洁
徐建清
李强
WEI Meng-sa;LU Zeng-jie;XU Jian-qing;LI Qiang(Songjiang Power Supply Company,State Grid Shanghai Municipal Electric Power Company,Shanghai 201600,China;Shibei Power Supply Company,State Grid Shanghai Municipal Electric Power Company,Shanghai 201900,China)
出处
《电子设计工程》
2019年第23期64-67,72,共5页
Electronic Design Engineering
基金
国家重点研究计划项目(2017YFA0700303)
关键词
大数据模型
电网风电场
功率预测
波动分类
属性条件
神经网络
汇聚层级
预测规律
large data model
grid wind farm
power prediction
wave classification
attribute conditions
neural network
convergence level
prediction law
