[1]陈馨凝,刘 辉,刘雨薇,等.基于改进磷虾群算法优化ESN的短期负荷预测[J].湖北工业大学学报,2020,(1):38-42.
 CHEN Xinning,LIU Hui,LIU Yuwei,et al.Short-term Load Forecasting of Echo State Network based on Improved Krill Herd Algorithm[J].,2020,(1):38-42.
点击复制

基于改进磷虾群算法优化ESN的短期负荷预测()
分享到:

《湖北工业大学学报》[ISSN:1003-4684/CN:42-1752/Z]

卷:
期数:
2020年第1期
页码:
38-42
栏目:
湖北工业大学学报
出版日期:
2020-02-28

文章信息/Info

Title:
Short-term Load Forecasting of Echo State Network based on Improved Krill Herd Algorithm
文章编号:
1003-4684(2020)01-0038-05
作者:
陈馨凝 刘 辉 刘雨薇 邹琪骁 李侯君
湖北工业大学电气与电子工程学院, 湖北 武汉 430068
Author(s):
CHEN Xinning LIU HuiLIU Yuwei ZOU QixiaoLI Houjun
School of Electrical and Electronic Engineering,Hubei Univ. of Tech .,Wuhan 430068,China
关键词:
短期负荷预测 回声状态网络 改进磷虾群算法
Keywords:
short-term load forecasting echo state network improved krill herd algorithm
分类号:
TM715.1
文献标志码:
A
摘要:
为提高负荷预测的精确度,本文提出了一种基于改进磷虾群算法优化ESN神经网络的负荷预测模型。首先采用核主成分分析法对河南某地区的实际电力负荷数据进行优选,再使用IKH-ESN模型对优选后的数据进行预测。同时建立传统BP、传统ESN、PSO-BP三种模型进行预测并对比分析。仿真结果证明本文所提出模型有效地克服了传统模型易陷入局部最小等问题,对于负荷预测更具有准确性与有效性。
Abstract:
In order to improve the accuracy of load forecasting, this paper proposes a load forecasting model based on improved krill herd algorithm to optimize echo state network. Firstly, the kernel principal component analysis method is used to optimize the actual power load data of a certain area in Henan Province, and then the IKH-ESN model is used to predict the preferred data. At the same time, three models of traditional BP, traditional ESN and PSO-BP were established for prediction and comparative analysis. The simulation results show that the proposed model could effectively overcome the problem that the traditional model is easy to fall into the local minimum, and it is more accurate and effective for load forecasting.

参考文献/References:

[1] 张智晟,于道林.考虑需求响应综合影响因素的RBF-NN短期负荷预测模型[J].中国电机工程学报,2018,38(06):1631-1638,1899. 
[2] 朱祥和.考虑气象因素的短期负荷预测模型研究[J].数学的实践与认识,2018,48(03):131-143. 
[3] 董浩,李明星,张淑清,等.基于核主成分分析和极限学习机的短期电力负荷预测[J].电子测量与仪器学报,2018,32(01):188-193. 
[4] 王帅哲,王金梅,王永奇,等.基于改进遗传算法的BP神经网络短期电力负荷预测[J].国外电子测量技术,2019,38(01):15-18. 
[5] 孙海蓉,谢碧霞,田瑶,等.基于数据的SecRPSO-SVM短期电力负荷预测[J].系统仿真学报,2017,29(08):1829-1836. 
[6] Gandomi A H , Alavi A H . Krill herd: A new bio-inspired optimization algorithm[J]. Communications in Nonlinear Science and Numerical Simulation, 2012, 17(12):4831-4845.
[7] Wang G G , Guo L , Gandomi A H , et al. Chaotic Krill Herd algorithm[J]. Information Sciences, 2014, 274:17-34.
[8] Abualigah L M, Khader A T, Hanandeh E S. Hybrid clustering analysis using improved krill herd algorithm[J]. Applied Intelligence, 2018, 48(5):1-25. 
[9] 刘唐,周炜,李志鹏,等.基于改进磷虾群算法的K-means算法[J].探测与控制学报,2019,41(01):76-81. 
[10] Yusoff M H , Chrol-Cannon J , Jin Y . Modeling neural plasticity in echo state networks for classification and regression[J]. Information Sciences, 2016, 364-365(C):184-196.
[11] Jaeger H. Echo state network[J]. Scholarpedia, 2007, 2(9):1479 - 1482. 
[12] 琚垚,祁林,刘帅.基于改进乌鸦算法和ESN神经网络的短期风电功率预测[J].电力系统保护与控制,2019,47(04):58-64. 
[13] 宋绍剑,王尧,林小峰.基于蚁群算法优化回声状态网络的研究[J].计算机工程与科学,2017,39(12):2326-2332. 
[14] 刘畅,刘天琪,陈振寰,等.基于KPCA和BP神经网络的短期负荷预测[J].电测与仪表,2016,53(10):57-61.

备注/Memo

备注/Memo:
[收稿日期] 2019-09-02
[基金项目] 国家自然科学基金(41601394)
[第一作者] 陈馨凝(1995-), 女, 河南信阳人,湖北工业大学硕士研究生,研究方向为电气工程
[通信作者] 刘   辉(1962-), 男,湖北武汉,理学博士,湖北工业大学教授,研究方向为电气工程
更新日期/Last Update: 2020-04-11