山东电力技术2018，Vol.45Issue(4)：24-30,7.
基于泄漏积分型回声状态网络的在线学习光伏功率短期预测
Online Learning PV Power Short Term Forecasting Based on Leaky-Integrator ESN
杨佳俊 1闫凯 1曹冉 1王志峰 1陈霖1
作者信息
- 1. 国网山东省电力公司莱芜供电公司,山东 莱芜 271100
- 折叠
摘要
Abstract
In order to enhance computing accuracy and universality of photovoltaic (PV) power forecasting, an online-learning method based on leaky-integrator echo state network (LIESN) is presented. Leaky-integrator neurons are introduced to plain ESN and the short-term memory ability is promoted. The impacts of parameters of LIESN on PV power forecasting performance are analyzed and an optimized model is obtained. The model is trained by least squares online learning algorithm and the final forecasting is obtained. By practical examples, complicated model can be established and applied to various weather conditions. The forecasting accuracy is superior to BP neural network and plain ESN.关键词
回声状态网络/泄漏积分/神经元/光伏功率预测/在线学习Key words
echo state network/leaky-integrator/neurons/photovoltaic power forecasting/online learning分类
信息技术与安全科学引用本文复制引用
杨佳俊,闫凯,曹冉,王志峰,陈霖..基于泄漏积分型回声状态网络的在线学习光伏功率短期预测[J].山东电力技术,2018,45(4):24-30,7.
