基于门控递归神经网络的电网日峰值负荷预测
    点此下载全文
引用本文:吴福疆?覮,范晟,王振达,王烁.基于门控递归神经网络的电网日峰值负荷预测[J].计算技术与自动化,2020,(4):20-26
摘要点击次数: 325
全文下载次数: 0
作者单位
吴福疆?覮,范晟,王振达,王烁 (广东电网有限责任公司 汕头供电局广东 汕头 515000) 
中文摘要:日峰值负荷作为非线性、非平稳且波动的时间序列,难以准确预测。提出了一种结合动态时间规整(DTW)的门控递归神经网络(GRNN)用于准确预测日峰值负荷。利用DTW距离用于匹配最相似的负荷曲线,可以捕捉负荷变化趋势。采用热编码方案对离散变量进行编码,扩展其特征从而表征对负荷曲线的影响。提出了一种基于DTW的门控递归单元(DTW-GRU)算法用于日峰值负荷预测,并在欧洲智能技术网络(EUNITE)数据集上进行了测试。仿真结果表明,与其他算法相比,该算法的MAPE仅为1.01%。
中文关键词:峰值负荷预测  动态时间规整  热编码  门控递归单元
 
Daily Peak Load Forecasting Based on Gating Recurrent Neural Network
Abstract:As a non-linear,non-stationary and fluctuating time series,daily peak load is difficult to predict accurately. A gated recurrent neural network (GRNN) combined with dynamic time warping (DTW) is proposed to predict daily peak load accurately. DTW distance is used to match the most similar load curve,which can capture the trend of load change. The thermal coding scheme is used to encode the discrete variables and extend their characteristics to represent the influence on the load curve. A DTW-GRU algorithm based on DTW is proposed for daily peak load forecasting,and it is tested on the European Intelligent Technology Network (EUNITE) dataset. Simulation results show that the MAPE of this algorithm is only 1.01% compared with other algorithms.
keywords:peak load forecasting  dynamic time regulation  thermal coding  gated recursive unit
查看全文   查看/发表评论   下载pdf阅读器