[1]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.[doi:10.11992/tis.202403038]
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.[doi:10.11992/tis.202403038]
点击复制
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.[doi:10.11992/tis.202403038]
一种注意力机制LSTM的5G网络地铁节电方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1309-1318
栏目:
人工智能院长论坛
出版日期:
2024-09-05
- Title:
- 5G network subway power-saving method based on attention mechanism LSTM
- Keywords:
- attention mechanism; 5G network power saving; LSTM; power-saving strategy; 5G power loss; subway power-saving; subway power utilization; 5G power utilization
- 分类号:
- TP311.13
- 文献标志码:
- 2024-08-29
- 摘要:
- 随着5G网络的规模化建设应用，5G基站设备的大功耗及高能耗成为运营商急需解决的成本问题。针对该问题，提出了一种基于注意力机制LSTM的5G网络地铁节电方法，该方法首先根据地铁特殊业务场景通过特征工程建立了与5G业务场景相关联的业务关键特征，为了尽可能挖掘长时序特征，建立了基于注意力机制的LSTM时序预测模型，实现了小时粒度5G基站业务量的精确预测；其次基于多项式回归模型建立了5G地铁业务量与基站配置量的函数模型，形成节电策略。最后，实现5G基站节电效能的有效评估，通过建立5G基站用电量与基站设备BBU、HUB、RRU等硬件设备功耗函数模型，实现节电策略实施后节电效能的有效评估。实验结果表明，对比传统的5G电力供应模型，该方法能够节省43%的电能。
- Abstract:
- The large-scale construction and application of the 5G network have made the large power consumption of 5G base station equipment an urgent cost problem for operators. A 5G network subway power-saving method based on attention mechanism LSTM is proposed in this study to address this problem. First, business-critical features related to 5G business scenarios are established by means of feature engineering based on unique subway operating scenarios. An attention mechanism-based LSTM time-series prediction model is established to realize an accurate forecast of hourly base station traffic volume for exploiting long time-order features as far as possible. Then, a function model for the relationship between 5G subway traffic volume and base station configuration is established based on a polynomial regression model to establish power-saving strategies. Finally, the power-saving efficiency of the 5G base station is evaluated by establishing function models for the power consumption of the 5G base station and base station equipment, such as BBU, HUB, and RRU, after implementing power-saving strategies. Experimental results show that the proposed method can achieve a 43% improvement in power-saving efficiency compared with the traditional 5G power supply model.
- 参考文献/References:
-
[1] FOURATI H, MAALOUL R, TRABELSI N, et al. An efficient energy saving scheme using reinforcement learning for 5G and beyond in H-CRAN[J]. Ad hoc networks, 2024, 155: 103406.
[2] 蒙占杰, 周丽丽, 李季. 4G/5G网络低碳发展思考[J]. 通信世界, 2022(13): 41-43.
MENG Zhanjie, ZHOU Lili, LI Ji. Thinking on low-carbon development of 4G/5G network[J]. Communications world, 2022(13): 41-43.
[3] 官磊, 丁洋, 李锐杰, 等. 面向“双碳” 的5G网络节能技术[J]. 电信科学, 2022, 38(4): 167-174.
GUAN Lei, DING Yang, LI Ruijie, et al. Network energy saving technologies for green 5G[J]. Telecommunications science, 2022, 38(4): 167-174.
[4] 徐丹, 曾宇, 孟维业, 等. AI使能的5G节能技术[J]. 电信科学, 2021, 37(5): 32-41.
XU Dan, ZENG Yu, MENG Weiye, et al. AI-enabled 5G energy-saving technology[J]. Telecommunications science, 2021, 37(5): 32-41.
[5] 苗晓春, 陈旭黎. 基于AI的5G基站节能应用[J]. 长江信息通信, 2024, 37(5): 152-154.
MIAO Xiaochun, CHEN Xuli. Application of energy saving solution for 5G base station based on AI[J]. Changjiang information & communications, 2024, 37(5): 152-154.
[6] 王素英, 贾海蓉, 申陈宁, 等. 改进GAN模型在基站流量预测及5G节能中的应用[J]. 太原理工大学学报, 2024, 55(4): 743-750.
WANG Suying, JIA Hairong, SHEN Chenning, et al. Application of GAN model with DE-GWO optimized LSTM for 5G energy consumption control[J]. Journal of Taiyuan University of technology, 2024, 55(4): 743-750.
[7] ZHENG Jiahuan, XIANG Yong. 5G base station energy saving method based on personalized scenarios[J]. Mobile communication, 2021, 45(03): 91-96.
[8] 翟敏, 宋耀宁. 5G移动通信网络智能节能应用方案[J]. 长江信息通信, 2023, 36(5): 221-224.
ZHAI Min, SONG Yaoning. Intelligent energy-saving application scheme for 5G mobile communication network[J]. Changjiang information & communications, 2023, 36(5): 221-224.
[9] PUTHENPURA S. Demonstrates SMaRT-5GTM open source energy savings platform at Fyuz[EB/OL]. (2023-10-04)[2024-3-14]. https://opennetworking.org/wp-content/uploads/2023/10/Fyuz-Webinar-Slides.pdf.
[10] 刘亮亮. “双碳” 视角下的5G全生命周期网络节能分析[J]. 数字通信世界, 2024(4): 67-69.
LIU Liangliang. Energy saving analysis of 5G full lifecycle network from the perspective of “dual carbon”[J]. Digital communication world, 2024(4): 67-69.
[11] FOURATI H, MAALOUL R, CHAARI L. A survey of 5G network systems: challenges and machine learning approaches[J]. International journal of machine learning and cybernetics, 2021, 12(2): 385-431.
[12] MALATHY S, JAYARAJAN P, OJUKWU H, et al. A review on energy management issues for future 5G and beyond network[J]. Wireless networks, 2021, 27(4): 2691-2718.
[13] 卜寅, 孙宏, 周瑜, 等. 基于AI+大数据的4G/5G无线基站智能协同节能系统的研究和应用[J]. 邮电设计技术, 2023(1): 1-6.
BU Yin, SUN Hong, ZHOU Yu, et al. Research and application of 4G/5G wireless base station intelligent cooperative energy saving system based on AI+Big data[J]. Designing techniques of posts and telecommunications, 2023(1): 1-6.
[14] POST B, BORST S, van den Berg H. A self-organizing base station sleeping and user association strategy for dense cellular networks[J]. Wireless networks, 2021, 27(1): 307-322.
[15] IQBAL A, THAM M L, CHANG Y C. Double deep Q-network-based energy-efficient resource allocation in cloud radio access network[J]. IEEE access, 2021, 9: 20440-20449.
[16] 罗新军, 许步扬. 面向广电的5G网络节能技术方案[J]. 电信工程技术与标准化, 2022, 35(1): 10-13.
LUO Xinjun, XU Buyang. Energy-saving technology solutions for 5G of China Broadcasting Network[J]. Telecom engineering technics and standardization, 2022, 35(1): 10-13.
[17] 王建斌, 王淑春, 廖尚金, 等. 基于DCNN-LSTM负荷预测算法的5G基站节能系统研究[J]. 电信科学, 2023, 39(4): 133-141.
WANG Jianbin, WANG Shuchun, LIAO Shangjin, et al. Research on 5G base station energy saving system based on DCNN-LSTM load prediction algorithm[J]. Telecommunications science, 2023, 39(4): 133-141.
[18] 高珍, 靳剑东, 李志强, 等. 基于AI的4G/5G基站协同节电方法研究与应用[J]. 电信工程技术与标准化, 2022, 35(9): 11-17.
GAO Zhen, JIN Jiandong, LI Zhiqiang, et al. Research and application of power saving solution for 4G/5G base station collaborative based on AI[J]. Telecom engineering technics and standardization, 2022, 35(9): 11-17.
[19] 魏云良, 张颖聪. 浅谈基于5G网络的端到端节能部署策略[J]. 江苏通信, 2023, 39(1): 19-22.
WEI Yunliang, ZHANG Yingcong. Discussion on end-to-end energy-saving deployment strategy based on 5G network[J]. Jiangsu communication, 2023, 39(1): 19-22.
[20] 梁祖坤, 易小明. 制造企业节电增效的技术与管理协同推进机制[J]. 上海节能, 2023(12): 1788-1798.
LIANG Zukun, YI Xiaoming. Collaborative promotion mechanism of technology and management for energy saving and efficiency improvement in manufacturing enterprises[J]. Shanghai energy saving, 2023(12): 1788-1798.
[21] KALITA P, SELVAMUTHU D. Stochastic modeling for energy efficiency in modified directional discontinuous reception for LTE-5G networks[J]. International journal of communication systems, 2023, 36(6): e5434.
[22] S S, MISHRA S, HOTA C. Joint QoS and energy-efficient resource allocation and scheduling in 5G Network Slicing[J]. Computer communications, 2023, 202: 110-123.
[23] Khan W U, Li X, Ihsan A, et al. Energy efficiency maximization for beyond 5G NOMA-enabled heterogeneous networks[J]. Peer-to-peer networking and applications, 2021, 14(5): 3250-3264.
[24] Shuvo M S A, Munna M A R, Sarker S, et al. Energy-efficient scheduling of small cells in 5G: A meta-heuristic approach[J]. Journal of network and computer applications, 2021, 178: 102986.
[25] 田四梅, 沈卫红, 杨嬛. 基于差异化场景的5G智能节电技术研究[J]. 通信与信息技术, 2023(S1): 86-89.
TIAN Simei, SHEN Weihong, YANG Xuan. Research on energy saving rechnology of 5G base station based on differentiated scenarios[J]. Communication & information technology, 2023(S1): 86-89.
[26] 赖琮霖, 李力卡, 曾焕浩. 5G基站智能硬关断节能实施方案与应用[J]. 电信工程技术与标准化, 2023, 36(S1): 96-100.
LAI Conglin, LI Lika, ZENG Huanhao. Implementation method and application of smart hardware shutdown energy saving for 5G base stations[J]. Telecom engineering technics and standardization, 2023, 36(S1): 96-100.
[27] 曾碧卿, 韩旭丽, 王盛玉, 等. 层次化双注意力神经网络模型的情感分析研究[J]. 智能系统学报, 2020, 15(3): 460.
ZENG Biqing, HAN Xuli, WANG Shengyu, et al. Hierarchical double-attention neural networks for sentiment classification[J]. CAAI transactions on intelligent systems, 2020, 15(3): 460.
[28] 黄文科. 面向5G的无线网络节能技术研究[J]. 长江信息通信, 2022, 35(10): 6-8.
HUANG Wenke. Research on energy saving technology for 5G-oriented wireless network[J]. Changjiang information & communications, 2022, 35(10): 6-8.
[29] GUO Wanying, KOO J, SIDDIQUI I F, et al. QoS-aware energy-efficient MicroBase Station deployment for 5G-enabled HetNets[J]. Journal of king Saud University - computer and information sciences, 2022, 34(10): 10487-10495.
- 相似文献/References:
-
[1]申凯,王晓峰,杨亚东.基于双向消息链路卷积网络的显著性物体检测[J].智能系统学报,2019,14(6):1152.[doi:10.11992/tis.201812003]
SHEN Kai,WANG Xiaofeng,YANG Yadong.Salient object detection based on bidirectional message link convolution neural network[J].CAAI Transactions on Intelligent Systems,2019,14():1152.[doi:10.11992/tis.201812003]
[2]赵文清,程幸福,赵振兵,等.注意力机制和Faster RCNN相结合的绝缘子识别[J].智能系统学报,2020,15(1):92.[doi:10.11992/tis.201907023]
ZHAO Wenqing,CHENG Xingfu,ZHAO Zhenbing,et al.Insulator recognition based on attention mechanism and Faster RCNN[J].CAAI Transactions on Intelligent Systems,2020,15():92.[doi:10.11992/tis.201907023]
[3]申翔翔,侯新文,尹传环.深度强化学习中状态注意力机制的研究[J].智能系统学报,2020,15(2):317.[doi:10.11992/tis.201809033]
SHEN Xiangxiang,HOU Xinwen,YIN Chuanhuan.State attention in deep reinforcement learning[J].CAAI Transactions on Intelligent Systems,2020,15():317.[doi:10.11992/tis.201809033]
[4]曾碧卿,韩旭丽,王盛玉,等.层次化双注意力神经网络模型的情感分析研究[J].智能系统学报,2020,15(3):460.[doi:10.11992/tis.201812017]
ZENG Biqing,HAN Xuli,WANG Shengyu,et al.Hierarchical double-attention neural networks for sentiment classification[J].CAAI Transactions on Intelligent Systems,2020,15():460.[doi:10.11992/tis.201812017]
[5]莫宏伟,田朋.基于注意力融合的图像描述生成方法[J].智能系统学报,2020,15(4):740.[doi:10.11992/tis.201910039]
MO Hongwei,TIAN Peng.An image caption generation method based on attention fusion[J].CAAI Transactions on Intelligent Systems,2020,15():740.[doi:10.11992/tis.201910039]
[6]鲍维克,袁春.面向推荐系统的分期序列自注意力网络[J].智能系统学报,2021,16(2):353.[doi:10.11992/tis.202005028]
BAO Weike,YUAN Chun.Recommendation system with long-term and short-term sequential self-attention network[J].CAAI Transactions on Intelligent Systems,2021,16():353.[doi:10.11992/tis.202005028]
[7]洪恺临,曹江涛,姬晓飞.改进Center-Net网络的自主喷涂机器人室内窗户检测[J].智能系统学报,2021,16(3):425.[doi:10.11992/tis.202005016]
HONG Kailin,CAO Jiangtao,JI Xiaofei.Indoor window detection of autonomous spraying robot based on improved CenterNet network[J].CAAI Transactions on Intelligent Systems,2021,16():425.[doi:10.11992/tis.202005016]
[8]张勇,高大林,巩敦卫,等.用于关系抽取的注意力图长短时记忆神经网络[J].智能系统学报,2021,16(3):518.[doi:10.11992/tis.202008036]
ZHANG Yong,GAO Dalin,GONG Dunwei,et al.Attention graph long short-term memory neural network for relation extraction[J].CAAI Transactions on Intelligent Systems,2021,16():518.[doi:10.11992/tis.202008036]
[9]陈新元,谢晟祎,陈庆强,等.结合卷积特征提取和路径语义的知识推理[J].智能系统学报,2021,16(4):729.[doi:10.11992/tis.202008007]
CHEN Xinyuan,XIE Shengyi,CHEN Qingqiang,et al.Knowledge-based inference on convolutional feature extraction and path semantics[J].CAAI Transactions on Intelligent Systems,2021,16():729.[doi:10.11992/tis.202008007]
[10]张恒,何文玢,何军,等.医学知识增强的肿瘤分期多任务学习模型[J].智能系统学报,2021,16(4):739.[doi:10.11992/tis.202010005]
ZHANG Heng,HE Wenbin,HE Jun,et al.Multi-task tumor stage learning model with medical knowledge enhancement[J].CAAI Transactions on Intelligent Systems,2021,16():739.[doi:10.11992/tis.202010005]
备注/Memo
收稿日期:2024-3-14。
基金项目:2023年度山西省高等学校科技创新项目(2023L517).
作者简介:邓翠艳，讲师，主要研究方向为数据挖掘、大数据与人工智能。主持省教育规划课题2项，授权发明专利2项，发表学术论文5篇。E-mail：13434146632@139.com;齐小刚，教授，博士生导师，博士，主要研究方向为复杂系统建模与仿真、网络算法设计与应用。主持国家自然科学基金项目、十三五预研项目等国家和省部级项目20余项。授权发明专利19项，软件著作权4项，发表学术论文100余篇。 E-mail： xgqi@xidian.edu.cn。
通讯作者:邓翠艳. E-mail：13934146632@139.com
更新日期/Last Update:
2024-09-05