基于RNN信息累积的动态多目标优化算法  

Dynamic Multi-objective Optimization Algorithm Based on RNN Information Accumulation

作　　者：程雪峰 董明刚[1,2] CHENG Xuefeng;DONG Minggang(School of Information Science and Engineering,Guilin University of Technology,Guilin,Guangxi 541006,China;Guangxi Key Laboratory of Embedded Technology and Intelligent System,Guilin,Guangxi 541006,China)

机构地区：[1]桂林理工大学信息科学与工程学院,广西桂林541006 [2]广西嵌入式技术与智能系统重点实验室,广西桂林541006

出　　处：《计算机科学》2024年第8期333-344,共12页Computer Science

基　　金：国家自然科学基金(61563012)。

摘　　要：动态多目标优化问题广泛存在于现实生活中,在环境发生变化后,进化算法需具备快速收敛、快速追踪帕累托最优前沿和维持多样性的能力。对于环境变化程度严重且变化频繁的情况,传统的预测方法无法有效获得帕累托最优前沿解。针对该问题,提出了一种基于循环神经网络(Recurrent Neural Networks,RNN)信息累积的动态多目标优化算法(IA-RNN)。首先,提出了一种基于RNN信息累积的非线性预测方法,利用RNN递归进行信息累积,提高了历史信息利用率,增强了预测的能力。其次,设计了一种基于个体的线性预测方法,利用参数矩阵对个体线性变化进行预测。线性预测与RNN非线性预测协同进化,可快速追踪帕累托最优前沿。最后,设计了一种基于最小二乘法的参数修正策略,通过当前环境的近似帕累托最优前沿解反向指导参数修正,减小了误差堆积的影响。将IA-RNN与5种代表性动态多目标优化算法在14个DF基准测试问题上进行比较。实验证明,IA-RNN算法的收敛性和多样性更优。Dynamic multi-objective optimization problems exist widely in real life.After the environment changes,it is necessary for the evolutionary algorithm to have the abilities of fast convergence,fast tracking Pareto optimal frontier and maintaining diversity.For severe and frequent environmental changes,the traditional forecasting method can not effectively obtain Pareto optimal frontier solution.For this problem,a dynamic multi-objective optimization algorithm based on recurrent neural networks information accumulation(IA-RNN)is proposed.Firstly,a nonlinear prediction method based on RNN information accumulation is proposed,which uses RNN recursion for information accumulation,improves the utilization rate of historical information and enhances the ability of prediction.Secondly,a linear prediction method based on individual is designed,which uses parameter matrix to predict the linear changes of individual.Linear prediction and RNN nonlinear prediction co-evolve,which can quickly track the Pareto optimal frontier.Finally,a parameter correction strategy based on the least square method is designed to guide the parameter correction by the approximate Pareto optimal frontier solution in the current environment,which reduces the influence of error accumulation.IA-RNN is compared with five representative dynamic multi-objective optimization algorithms on 14 DF benchmark problems.Experiments show that the IA-RNN algorithm has better convergence and diversity.

关 键 词：动态多目标 进化算法 预测 循环神经网络 信息累积 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]