arrow
Return

Dynamic Multiobjective Optimization Algorithm Guided by Recurrent Neural Network

delete2024-01-01
delete0
PRE
AI
Y
Yaru Hu
J
Junwei Ou
P
Ponnuthurai Nagaratnam Suganthan
W
Witold Pedrycz
王锐 cover
王锐 (Rui Wang)
郑
郑金华 (Jinhua Zheng)
邹
邹娟 (Juan Zou)
Y
Yanjie Song
DOI:10.1109/tevc.2024.3419892delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
In recent years, prediction-based algorithms have attracted much attention for solving dynamic multiobjective optimization (DMO) problems in the evolutionary computing community. However, this class of algorithms still has potential for further improvements by enhancing the historical information extraction approach to balance convergence and diversity. In this article, we propose a DMO algorithm based on a recurrent neural network (RNN) to balance the population’s convergence and diversity in dynamic environments. The RNN model in the proposed algorithm employs online learning in order to constantly improve according to the increasing evolutionary information. Meanwhile, differing from most existing prediction-based algorithms, the learning machine is not limited by assumptions, such as linear or nonlinear correlation, when it predicts new solutions for future evolutionary environments. Besides, an auxiliary strategy is performed, which adaptively introduces the random or mutated solutions according to the error losses between the prediction solutions and the optimal solutions in the whole optimization process. The experimental results show that the proposed algorithm is more effective for handling DMO problems than several recent algorithms.

Journal

IEEE Transactions on Evolutionary Computation cover
IEEE Transactions on Evolutionary Computation
IF:
12
Papers:
2.0K
Citations:
3.1W

Organization

Q
qatar university
Scholars:
675
Papers: 288
Citations: 7.3K
U
University of Alberta
Scholars:
2.7K
Papers: 1.2K
Citations: 3.2W
Xiangtan University cover
Xiangtan University
Scholars:
1.3K
Papers: 392
Citations: 6.3K
N
national university of defense technology
Scholars:
3.9K
Papers: 1.0K
Citations: 1.1K
researcher View more organizations
Cited Papers

Cited Papers

Solving Dynamic Multiobjective Problem via Autoencoding Evolutionary Search
err2022-05-01
err61
PREAI
errFeng, Liang; Zhou, Wei; Liu, Weichen; Ong, Yew-Soon; Tan, Kay Chen
errShare
errSave
Novel Prediction Strategies for Dynamic Multiobjective Optimization
err2020-04-01
err95
PREAI
errZhang, Qingyang; Yang, Shengxiang; Jiang, Shouyong; Wang, Ronggui; Li, Xiaoli
errShare
errSave
Time Series Recognition with Convolutional and Recursive Neural Networks in BSPM
err2023-05-03
err0
PREAI
errWójcik,Dariusz; Rymarczyk,Tomasz; Maciura,Łukasz; Oleszek,Michał; Adamkiewicz,Przemysław
errShare
errSave
Prediction-Based Population Re-initialization for Evolutionary Dynamic Multi-objective Optimization
err2024-09-05
err0
PREAI
errAimin Zhou; Yaochu Jin; Qingfu Zhang; Bernhard Sendhoff; Edward Tsang
errShare
errSave
errShare
errSave
researcher View more