Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm

Zhuge Bin; Cai Xiaodan; Pan Tingting; Xu Yunhan; Wang Zhengxian; Zhang Zitian; Dong Ligang; Jiang Xian; Yu Xiao

doi:10.11959/j.issn.1000-0801.DXKX250559

您当前的位置：

首页 >

文章列表页 >

Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm

Research and Development | 更新时间：2026-06-17

- Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm
- Telecommunications Science Vol. 42, Issue 5, Pages: 88-101(2026)
- 作者机构：
  
  1.浙江工商大学信息与电子工程学院（萨塞克斯人工智能学院），浙江杭州 310018
  2.浙江力积存储科技股份有限公司，浙江杭州 310018
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(W2421086;61871468);Project of Tongxiang General Artificial Intelligence Research Institute(TAGI2-B-2024-0014);Zhejiang Key Laboratory of New Network Standards and Application Technology(2013E10012);Key Science and Technology Innovation Project of Zhejiang Province(2023R5211);Key R&D Program of Zhejiang Province(2025C02038)
- DOI：10.11959/j.issn.1000-0801.DXKX250559
  CLC： TP393
- Received：18 September 2025，
  
  Revised：2026-01-09，
  
  Accepted：12 January 2026，
  
  Published：20 May 2026
- 稿件说明：
移动端阅览
诸葛斌,蔡晓丹,潘婷婷等.基于元启发式RIME算法的深度时间序列预测模型优化方法[J].电信科学,2026,42(05):88-101.

Zhuge Bin,Cai Xiaodan,Pan Tingting,et al.Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm[J].Telecommunications Science,2026,42(05):88-101.
诸葛斌,蔡晓丹,潘婷婷等.基于元启发式RIME算法的深度时间序列预测模型优化方法[J].电信科学,2026,42(05):88-101. DOI： 10.11959/j.issn.1000-0801.DXKX250559.

Zhuge Bin,Cai Xiaodan,Pan Tingting,et al.Optimization method of deep time series prediction model based on meta-heuristic RIME algorithm[J].Telecommunications Science,2026,42(05):88-101. DOI： 10.11959/j.issn.1000-0801.DXKX250559.

摘要

时间序列预测在金融、电力、网络等关键领域具有重要应用价值。深度学习模型在该任务中展现出强大的拟合能力，但其性能高度依赖结构设计与超参数选择。传统的调参方法（如网格搜索和人工经验）存在效率低、易陷入局部最优等问题。为此，构建了基于双向时间卷积网络和双向门控循环单元的注意力机制模型（bidirectional temporal convolutional network-bidirectional gated recurrent unit-attention，BiTCN-BiGRU-Attention）的深度时间序列预测模型，并引入新型元启发式优化算法——霜冰优化算法（RIME）对其进行优化。RIME算法模拟霜冰自然生长机制，结合软霜搜索策略、硬霜刺破机制与正贪婪选择策略，实现了全局探索与局部开发的有效平衡。实验在标准基准函数和多个真实数据集上对算法性能进行了全面评估。结果表明，RIME算法优化后的预测模型在精度、收敛速度与稳定性方面均优于未优化模型，为深度时序预测模型的高效自动化优化提供了新的思路与实践路径。

Abstract

Time series prediction was recognized as having significant application value in critical fields such as finance

power

and networks. Deep learning models were demonstrated to possess strong fitting capabilities for this task

but their performance was found to be heavily dependent on structural design and hyperparameter selection. Traditional parameter-tuning methods

such as grid search and manual experience

were criticized for their low efficiency and tendency to fall into local optima. To address these issues

a deep time series prediction model based on the BiTCN-BiGRU-Attention architecture was constructed

and a novel metaheuristic optimization algorithm

RIME

was introduced for optimization. The RIME was designed to simulate the natural growth mechanism of rime ice

combining soft rime search strategies

hard rime piercing mechanisms

and positive greedy selection strategies to achieve an effective balance between global exploration and local exploitation. In the experimental section

the algorithm’s performance was comprehensively evaluated on standard benchmark functions and multiple real-world datasets. The results show that the RIME-optimized prediction model was superior to the unoptimized model in terms of accuracy

convergence speed

and stability. New insights and practical pathways were provided for the efficient and automated optimization of deep time series prediction models.

关键词

Keywords

references

Williams B M , Hoel L A . Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: theoretical basis and empirical results [J ] . Journal of Transportation Engineering , 2003 , 129 ( 6 ): 664 - 672 .

何勇 , 李艳婷 . 基于向量自回归模型的移动通信基站流量预测 [J ] . 工业工程与管理 , 2017 , 22 ( 4 ): 79 - 84 .

He Y , Li Y T . Forecasting the traffic flow of base station based on vector auto-regression [J ] . Industrial Engineering and Management , 2017 , 22 ( 4 ): 79 - 84 .

孙红哲 , 王坚 , 王鹏 , 等 . 基于Attention-BiTCN的网络入侵检测方法 [J ] . 信息网络安全 , 2024 , 24 ( 2 ): 309 - 318 .

Sun H Z , Wang J , Wang P , et al . Network intrusion detection method based on attention-BiTCN [J ] . Netinfo Security , 2024 , 24 ( 2 ): 309 - 318 .

徐海兵 , 郭久明 . 基于双向GRU模型的网络流量预测的研究 [J ] . 电子技术应用 , 2022 , 48 ( 2 ): 19 - 22, 27 .

Xu H B , Guo J M . Research on network traffic prediction based on Bi-GRU model [J ] . Application of Electronic Technique , 2022 , 48 ( 2 ): 19 - 22, 27 .

尹春勇 , 曹儒商 , 王琪凯 . 基于TCN-BiGRU的网络异常检测研究 [J ] . 微电子学与计算机 , 2025 , 42 ( 8 ): 120 - 131 .

Yin C Y , Cao R S , Wang Q K . Research on network anomaly detection based on TCN-BiGRU [J ] . Microelectronics & Com-puter ， 2025 , 42 ( 8 ): 120 - 131 .

Morales-Hernández A , Van Nieuwenhuyse I , Rojas Gonzalez S . A survey on multi-objective hyperparameter optimization algorithms for machine learning [J ] . Artificial Intelligence Review , 2023 , 56 ( 8 ): 8043 - 8093 .

Snoek J , Larochelle H , Adams R P . Practical Bayesian optimization of machine learning algorithms [C ] // Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2 (NIPS' 12). 2012 : 2951 – 2959 .

路梦雨 , 毛经坤 , 赵洪阳 . 基于贝叶斯优化的CNN-LSTM-Attention的个性化商品推荐算法 [J ] . 天津理工大学学报 , 2024-04-30 .

Lu M Y , Mao J K , Zhao H Y . Personalized product recommendation algorithm based on Bayesian optimization of CNN-LSTM-Attention [J ] . Journal of Tianjin University of Technology , 2024-04-30 .

Fakhrmoosavi F , Kamjoo E , Kavianipour M , et al . A stochastic framework using Bayesian optimization algorithm to assess the network-level societal impacts of connected and autonomous vehicles [J ] . Transportation Research Part C: Emerging Technologies , 2022 , 139 : 103663 .

Kaveh M , Mesgari M S . Application of meta-heuristic algorithms for training neural networks and deep learning architectures: a comprehensive review [J ] . Neural Processing Letters , 2023 , 55 ( 4 ): 4519 - 4622 .

杜伟 , 王圣 , 李健 , 等 . 基于CNN-LSTM-AM模型的储能锂离子电池荷电状态预测 [J ] . 电工技术学报 , 2025 , 40 ( 9 ): 2982 - 2995 .

Du W , Wang S , Li J , et al . Prediction of state of charge for energy storage lithium-ion batteries based on CNN-LSTM-AM model [J ] . Transactions of China Electrotechnical Society , 2025 , 40 ( 9 ): 2982 - 2995 .

段宇 , 黄君 , 杨关友 , 等 . 基于RIME-VMD-SSA-LSTM法研究非生态因素影响的来水预报模型 [J ] . 云南水力发电 , 2024 , 40 ( 5 ): 44 - 50 .

Duan Y , Huang J , Yang G Y , et al . Research on inflow forecasting model of non-ecological factors based on RIME-VMD-SSA-LSTM method [J ] . Yunnan Water Power , 2024 , 40 ( 5 ): 44 - 50 .

Li W K , Yang X , Yin Y C , et al . A novel hybrid improved RIME algorithm for global optimization problems [J ] . Biomimetics , 2025 , 10 ( 1 ): 14 .

Su H , Zhao D , Heidari A A , et al . RIME: a physics-based optimization [J ] . Neurocomputing , 2023 , 532 : 183 - 214 .

蒋卓宇 , 关维维 , 孔祥力 , 等 . 基于IHOA-BiTCN-BiGRU-Attention的城市负荷信息聚合预测 [J ] . 电源学报 , 2025-04-15 .

Jiang Z Y , Guan W W , Kong X L , et al . Urban load information aggregation forecasting based on attention mechanisms [J ] . Journal of Power Supply , 2025-04-15 .

Wang J , Wang W C , Hu X X , et al . Black-winged kite algorithm: a nature-inspired meta-heuristic for solving benchmark functions and engineering problems [J ] . Artificial Intelligence Review , 2024 , 57 ( 4 ): 98 .

Abualigah L , Diabat A , Mirjalili S , et al . The arithmetic optimization algorithm [J ] . Computer Methods in Applied Mechanics and Engineering , 2021 , 376 : 113609 .

Mirjalili S , Mirjalili S M , Lewis A . Grey wolf optimizer [J ] . Advances in Engineering Software , 2014 , 69 : 46 - 61 .

Ren Q Y , Zhuge B , Zhang Z T , et al . Improved sparrow algorithm based virtual machine placement [J ] . Cluster Computing , 2024 , 27 ( 5 ): 6511 - 6525 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

GhostMamba-SAN: an efficient DDoS attack detection model

Research on log text fault association rule mining based on GPT network

Infrared image human vehicle detection algorithm based on SDL-YOLO

A review of physical layer technologies in underwater acoustic communications: from model-driven to data-driven

Deep learning-based compressed sensing impulsive noise suppression in NOMA systems

Related Author

Bao Xiaoan

Yang Fenghao

Fan Yunlong

Tu Xiaomei

Hu Tianbin

Wu Biao

LI Bing

YE Qingwei

Related Institution

School of Science, Zhejiang Sci-Tech University

School of Artificial Intelligence and Automation, Hohai University

School of Urban and Rural Construction, Zhejiang Guangsha Vocational and Technical University of Construction

School of Computer Science and Technology, Zhejiang Sci-Tech University

Faculty of Electrical Engineering and Computer Science, Ningbo University

⁰