###
计算机系统应用:2019,28(3):28-35
本文二维码信息
码上扫一扫!
基于ESN和改进RBFNN的城市燃气负荷预测
(上海师范大学 信息与机电工程学院, 上海 201400)
City Gas Load Forecasting Based on ESN and Improved RBFNN
(College of Information and Mechanical Engineering, Shanghai Normal University, Shanghai 201400, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 121次   下载 127
投稿时间:2018-09-01    修订日期:2018-09-26
中文摘要: 城市燃气负荷预测是城市燃气管网系统运行调度中的重要内容.针对燃气负荷数据的周期性和非线性特点,以及单一模型存在的局限性,本文提出一种ESN和改进RBF神经网络的组合预测模型.首先用核Fisher线性判别对原始数据进行降维,其次用ESN模型进行初步预测,然后将ESN的预测结果作为RBF神经网络的输入来构建组合模型,并将差分进化算法和梯度下降算法结合,对RBF神经网络的结构和参数同时进行训练和优化,以增强算法的局部搜索能力,加快收敛速度.实验结果表明,本文模型比原组合模型的预测精度更高.
Abstract:City gas load forecasting is significant to the operation of city gas networks. In consideration of the periodicity and nonlinearity of gas load data and the shortcomings of a single model, a hybrid model of Echo State Network (ESN) and improved RBF Neural Network (RBFNN) is put forward. First of all, kernel Fisher linear discriminant is utilized for dimension reduction. Secondly, we adopt ESN to do a preliminary prediction. Then, differential evolution integrated with gradient descent by encoding is used to learn and optimize the structure and parameters of RBFNN. Last but not least, the produced result of ESN is the input of RBFNN. It is validated that the proposed model has a higher precision and convergence rate compared with the initial combinational model.
文章编号:     中图分类号:    文献标志码:
基金项目:上海市科委项目(11510502400)
引用文本:
徐玚,徐晓钟.基于ESN和改进RBFNN的城市燃气负荷预测.计算机系统应用,2019,28(3):28-35
XU Yang,XU Xiao-Zhong.City Gas Load Forecasting Based on ESN and Improved RBFNN.COMPUTER SYSTEMS APPLICATIONS,2019,28(3):28-35

用微信扫一扫

用微信扫一扫