|本期目录/Table of Contents|

[1]林麒麟,包广清.基于MEA-Elman神经网络的电力日负荷预测[J].工业仪表与自动化装置,2017,(03):7-10.
　BAO Guangqing,LIN Qilin.Daily power load forecasting based on MEA-Elman Neural-network model[J].Industrial Instrumentation & Automation,2017,(03):7-10.
点击复制

基于MEA-Elman神经网络的电力日负荷预测

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2017年03期
页码:
7-10
栏目:
出版日期:
2017-06-15

文章信息/Info

Title:
Daily power load forecasting based on MEA-Elman Neural-network model
文章编号:
1000-0682（2017）03-0000-00
作者:
林麒麟; 包广清
(兰州理工大学电气工程与信息工程学院，兰州730050)
Author(s):
BAO Guangqing;  LIN Qilin
(College of Electrical Engineering and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China)
关键词:
日负荷预测; MEA; 优化; MEA-Elman神经网络
Keywords:
Daily Power Load Forecasting; Mind Evolutionary Algorithm; optimization;  MEA-Elman Net
分类号:
TM715
DOI:
-
文献标志码:
A
摘要:
Elman神经网络是一种动态反馈网络，对历史状态敏感，具有短期记忆功能和处理动态信息的能力，可以建立动态、非线性电力负荷预测模型。由于Elman神经网络采用BP算法，容易陷入局部极小解，迭代次数多且学习效率低，该文利用思维进化算法(MEA)优化Elman神经网络的方法，提出基于MEA-Elman神经网络的电力负荷预测模型。实验表明，该方法能够避免不成熟收敛问题，减少迭代次数，有效提高了配电网短期负荷的预测精度，对电力系统合理调度与规划具有重要意义。
Abstract:
Elman Neural Network is a dynamic recurrent neural-network which is sensitive to historical state and has the abilities of short-term memory and dealing with dynamic information. So we can establish a dynamic nonlinear model for power load forecasting. However, When adopting the BP algorithm, the Elman network has such problems as being apt to fall into local optima, many iterations and low efficiency. To overcome these drawbacks, this paper uses Mind Evolutionary Algorithm optimize the Elman Net, then comes up with a MEA-Elman Net model to carry out the power load forecasting. The simulation results indicate the MEA-Elman model can avoid the flaw of premature convergence, reduce the number of iterations and improve the prediction accuracy. It is significant for the reasonable scheduling and planning of power system .

参考文献/References:

[1] 何耀耀, 许启发, 杨善林, 等. 基于RBF神经网络分位数回归的电力负荷概率密度预测方法[J].中国电机工程学报, 2013, 31(1): 93-98.

[2] Hobbs B F，Helman U，Jitprapaikulsarn S et al. Artificial neural networks for short-term energy forecasting: Accuracy and economic value[J].Neurocomputing，1998，23(1)：71-84.
[3] 黄大伟.带扩展记忆的粒子群优化算法及其在电力系统短期负荷预测中应用[D]. 重庆: 重庆大学, 2011.
[4] Qi Wu. A hybrid-forecasting model based on Gaussian support vector machine and chaotic particle swarm optimization[J].Expert Systems with Applications, 2010,37(3): 2388-2394.
[5] 陈刚, 周杰, 张雪君, 等. 基于BP与RBF级联神经网络的日负荷预测[J]. 电网技术, 2009, 33(12): 101-105.
[6] 郭红戈. 思维进化算法的转移概率分析及几乎处处收敛性证明[J]. 控制与决策, 2014, 39(12): 2201-2206.
[7] 李根，李文辉. 基于思维进化算法的人脸特征点跟踪[J]. 吉林大学学报(工学报), 2015, 45(2):606-612.
[8] 李鹏华, 柴毅, 熊庆宇. 量子门Elman神经网络及其梯度扩展的量子反向传播学习算法[J]. 自动化学报, 2013, 39(9): 1511-1522
[9] http://neuron.tuke.sk/competition/index. php
[10] 高莹莹, 朱维彬. 深层神经网络中间层可见化建模[J]. 自动化学报, 2015, 41(9):1627-1637.
[11] Hasan Hüseyin .evik, Mehmet ,unka. Short-term load forecasting using fuzzy logic and ANFIS. Neural Computing and Applications. 2015, 26(6): 1355-1367.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：2016-12-21
作者简介：林麒麟(1989)，男，硕士研究生，主要研究方向为电力负荷预测。
更新日期/Last Update: 1900-01-01