[1]CHEN Zhixiong,XIE Yupeng,GUO Yihe.Prediction and reinforcement learning-based optimized resource allocation for 5G hybrid network slicing[J].CAAI Transactions on Intelligent Systems,2026,21(3):739-750.[doi:10.11992/tis.202506012]
Copy

Prediction and reinforcement learning-based optimized resource allocation for 5G hybrid network slicing

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 3 Page number: 739-750 Column: 学术论文—智能系统 Public date: 2026-05-05
Title:
Prediction and reinforcement learning-based optimized resource allocation for 5G hybrid network slicing
Author(s):
CHEN Zhixiong1; 2; 3;  XIE Yupeng1;  GUO Yihe1
1. Department of Electronic and Communication Engineering, North China Electric Power University, Baoding 071003, China;
2. Hebei Key Laboratory of Power Internet of Things Technology, North China Electric Power University, Baoding 071003, China;
3. Hebei Engineering Research Center of Intelligent Technology for Power Internet of Things, North China Electric Power University, Baoding 071003, China
Keywords:
5G hybrid scenarios; network slice; radio access resource allocation; service-level agreement; reinforcement learning; predictive; randomized initialization probabilistic threshold; learning frequency
CLC:
TP393；TN929.5
DOI:
10.11992/tis.202506012
Abstract:
To address the high learning frequency and high computational complexity of existing algorithms for rational slice resource allocation and service-level agreement (SLA) assurance, this paper proposes an intelligent time-frequency resource allocation strategy that integrates time series prediction with reinforcement learning. Under constraints on SLA violation probability and 5G resources, an optimization model for slice resource allocation in hybrid 5G scenarios is established, with the objective of minimizing the time-frequency resource usage. First, a stacked long short-term memory network is employed to predict key SLA indicators such as signal-to-noise ratio, queue buffer occupancy, latency, and the number of connected devices for enhanced mobile broadband, ultra-reliable low-latency communications, and massive machine-type communications scenarios. Next, the states, actions, and reward function of the Gaussian-kernel-based reinforcement learning algorithm are defined. The learning process is guided by the predicted SLA indicators and a randomly initialized probabilistic gating threshold to derive a near-optimal resource allocation policy. Simulation results demonstrate that, compared with existing algorithms, the proposed approach achieves better overall performance in prediction accuracy, convergence speed, and resource allocation efficiency while ensuring basic performance metrics such as SLA violation probability and resource usage. It also reduces the frequency and complexity of machine learning operations.
References:
[1] 殷珉, 沈航, 王天荆, 等. 基于分层联邦学习的无人机小基站RAN切片方法[J]. 电子学报, 2023, 51(7): 1774-1780 YIN Min, SHEN Hang, WANG Tianjing, et al. Hierarchical federated learning-based RAN slicing for drone-small-cells[J]. Acta electronica sinica, 2023, 51(7): 1774-1780
[2] GUNDALL M, STRUFE M, SCHOTTEN H D, et al. Introduction of a 5G-enabled architecture for the realization of industry 4.0 use cases[J]. IEEE access, 2021, 9: 25508-25521
[3] WANG Haozhe, WU Yulei, MIN Geyong, et al. A graph neural network-based digital twin for network slicing management[J]. IEEE transactions on industrial informatics, 2022, 18(2): 1367-1376
[4] MAHMOOD A, BELTRAMELLI L, FAKHRUL ABEDIN S, et al. Industrial IoT in 5G-and-beyond networks: vision, architecture, and design trends[J]. IEEE transactions on industrial informatics, 2022, 18(6): 4122-4137
[5] 王再见, 谷慧敏. 基于联合优化的网络切片资源分配策略[J]. 通信学报, 2023, 44(5): 234-245 WANG Zaijian, GU Huimin. Network slicing resource allocation strategy based on joint optimization[J]. Journal on communications, 2023, 44(5): 234-245
[6] THIRUVASAGAM P K, CHAKRABORTY A, MURTHY C S R. Resilient and latency-aware orchestration of network slices using multi-connectivity in MEC-enabled 5G networks[J]. IEEE transactions on network and service management, 2021, 18(3): 2502-2514
[7] DATAR M, ALTMAN E, LE CADRE H. Strategic resource pricing and allocation in a 5G network slicing Stackelberg game[J]. IEEE transactions on network and service management, 2023, 20(1): 502-520
[8] AYEPAH-MENSAH D, SUN Guolin, BOATENG G O, et al. Blockchain-enabled federated learning-based resource allocation and trading for network slicing in 5G[J]. IEEE/ACM transactions on networking, 2024, 32(1): 654-669
[9] AZIMI Y, YOUSEFI S, KALBKHANI H, et al. Applications of machine learning in resource management for RAN-slicing in 5G and beyond networks: a survey[J]. IEEE access, 2022, 10: 106581-106612
[10] 陈智雄, 詹学滋, 左嘉烁. 基于深度强化学习的电力线与无线双模通信MAC层接入算法[J]. 智能系统学报, 2025, 20(2): 344-354 CHEN Zhixiong, ZHAN Xuezi, ZUO Jiashuo. Adaptive MAC layer access algorithm for power line and wireless dualmode communication based on deep reinforcement learning[J]. CAAI transactions on intelligent systems, 2025, 20(2): 344-354
[11] YARKINA N, GAYDAMAKA A, MOLTCHANOV D, et al. Performance assessment of an ITU-T compliant machine learning enhancements for 5G RAN network slicing[J]. IEEE transactions on mobile computing, 2024, 23(1): 719-736
[12] DONG Tianjian, QI Qi, WANG Jingyu, et al. Standing on the shoulders of giants: cross-slice federated meta learning for resource orchestration to cold-start slice[J]. ACM transactions on networking, 2023, 31(2): 828-845
[13] HU Tianlun, LIAO Qi, LIU Qiang, et al. Information bottleneck-based domain adaptation for hybrid deep learning in scalable network slicing[J]. IEEE transactions on machine learning in communications and networking, 2024, 2: 1642-1660
[14] KRISHNA M B, LORENZ P. Deterministic network slice instance policy for intra and inter slice resource management in 5G[J]. IEEE transactions on vehicular technology, 2025, 74(3): 4904-4916
[15] ZHOU Hao, EROL-KANTARCI M, VINCENT POOR H. Learning from peers: deep transfer reinforcement learning for joint radio and cache resource allocation in 5G RAN slicing[J]. IEEE transactions on cognitive communications and networking, 2022, 8(4): 1925-1941
[16] CHANG Xiaolei, JI Tian, ZHU Runsu, et al. Toward an efficient and dynamic allocation of radio access network slicing resources for 5G era[J]. IEEE access, 2023, 11: 95037-95050
[17] 李冲冲. 基于模型的强化学习中随机算法研究[D]. 北京: 北京交通大学, 2024. LI Chongchong. Research on random algorithm in model-based reinforcement learning[D]. Beijing: Beijing Jiaotong University, 2024.
[18] ALCARAZ J J, LOSILLA F, ZANELLA A, et al. Model-based reinforcement learning with kernels for resource allocation in RAN slices[J]. IEEE transactions on wireless communications, 2023, 22(1): 486-501
[19] KATTEPUR A, DAVID S, MOHALIK S K. Model-based reinforcement learning for router port queue configurations[J]. Intelligent and converged networks, 2021, 2(3): 177-197
[20] CHEN Yuxuan, LI Rongpeng, YU Xiaoxue, et al. Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach[J]. Frontiers of information technology & electronic engineering, 2025, 26(2): 278-292
[21] 王迪, 张震, 王洋, 等. 一种基于模型可信度的强化学习方法[J/OL]. 控制工程, 1-9[2025-06-16]. WANG Di, ZHANG Zhen, WANG Yang, et al. A reinforcement learning method based on model credibility[J/OL]. Control engineering of China, 1-9[2025-06-16].
[22] YU Peng, YANG Mo, XIONG Ao, et al. Intelligent-driven green resource allocation for industrial Internet of Things in 5G heterogeneous networks[J]. IEEE transactions on industrial informatics, 2022, 18(1): 520-530
[23] FERREIRA D, BRAGA REIS A, SENNA C, et al. A forecasting approach to improve control and management for 5G networks[J]. IEEE transactions on network and service management, 2021, 18(2): 1817-1831
[24] 姜华, 杨家伟, 黄巍, 等. 基于深度强化学习的D2D辅助MEC网络资源分配算法[J]. 电力信息与通信技术, 2023, 21(7): 51-58 JIANG Hua, YANG Jiawei, HUANG Wei, et al. A D2D-assisted MEC network resource allocation algorithm based on deep reinforcement learning[J]. Electric power information and communication technology, 2023, 21(7): 51-58
[25] MARTIN-PEREZ J, KONDEPU K, DE VLEESCHAUWER D, et al. Dimensioning V2N services in 5G networks through forecast-based scaling[J]. IEEE access, 2022, 10: 9587-9602
[26] 陈志鹏, 张勇, 高海荣, 等. 隐私保护下融合联邦学习和LSTM的少数据综合能源多元负荷预测[J]. 智能系统学报, 2024, 19(3): 565-574 CHEN Zhipeng, ZHANG Yong, GAO Hairong, et al. Integrated energy multivariate load forecasting combining federated learning with LSTM in privacy-protected and low-data environments[J]. CAAI transactions on intelligent systems, 2024, 19(3): 565-574
[27] WU Qiong, CHEN Xu, ZHOU Zhi, et al. Deep reinforcement learning with spatio-temporal traffic forecasting for data-driven base station sleep control[J]. IEEE/ACM transactions on networking, 2021, 29(2): 935-948
[28] MENDOZA J, DE-LA-BANDERA I, PALACIOS D, et al. Forecasting framework for mobile networks based on automatic feature selection[J]. IEEE transactions on network and service management, 2023, 20(2): 974-984
[29] 赵晨, 张铖, 黄永明. 基于流量感知的无线接入网智能切片资源分配方法研究[J]. 信号处理, 2024(4): 719-732 ZHAO Chen, ZHANG Cheng, HUANG Yongming. Research on traffic-aware intelligent slicing resource allocation for radio access network[J]. Journal of signal processing, 2024(4): 719-732
[30] 邓翠艳, 齐小刚. 一种注意力机制LSTM的5G网络地铁节电方法[J]. 智能系统学报, 2024, 19(5): 1309-1318 DENG Cuiyan, QI Xiaogang. 5G network subway power-saving method based on attention mechanism LSTM[J]. CAAI transactions on intelligent systems, 2024, 19(5): 1309-1318
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems