基于EPNET模型和多期预测的时间序列预测  

Time Series Forecasting Based on EPNET Model and Multiple-Step-Ahead

作　　者：汤九斌[1] 孙明明[1] 陆建峰[1] 杨静宇[1] 

机构地区：[1]南京理工大学计算机系,南京210094

出　　处：《计算机应用》2004年第4期54-57,共4页journal of Computer Applications

摘　　要：文中主要研究了基于EPNET(EvolutionaryProgrammingNet)的时间序列预测问题。EPNET是一种进化人工神经网络模型,它能够同时优化网络权值和网络结构。该模型没有采用遗传算法中的交叉算子,而是采用了五个变异算子来获得比较理想的进化效果。在此基础上,提出了基于该模型的时间序列预测算法,介绍了该算法实现时的有关问题。This paper mainly investigates the forecasting time series based on the EPNET (Evolutionary Programming Net). EPNET is an evolutionary model for Artificial Neural Network (ANN),which can evolve the connection weight and architectures simultaneously. In this model,the crossover operator of Genetic Algorithms (GAs) is not adopted. However,5 mutation operators are used instead to get a better result. The time series forecasting algorithm based on the model is proposed. It introduces the problems for implementation in detail.

关 键 词：EPNET 时间序列预测 多期预测 进化人工神经网络模型 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]