基于ConvLSTM的移动边缘计算服务器能耗模型

doi:10.3969/j.issn.0255-8297.2024.01.005

应用科学学报 ›› 2024, Vol. 42 ›› Issue (1): 53-66.doi: 10.3969/j.issn.0255-8297.2024.01.005

基于ConvLSTM的移动边缘计算服务器能耗模型

李小龙¹, 李曦², 杨凌峰¹, 黄华¹

1. 湖南工商大学计算机学院, 湖南长沙 410205;
2. 湖南工商大学前沿交叉学院, 湖南长沙 410205

收稿日期:2023-11-20 出版日期:2024-01-30 发布日期:2024-02-02
通信作者: 李小龙,教授,研究方向为人工智能、物联网。E-mail:lxl@hutb.edu.cn E-mail:lxl@hutb.edu.cn
基金资助:
国家自然科学基金（No. 61872140）；物联网智能感知湖南省普通高等学校科技创新团队支持项目；湖南省高新技术产业科技创新引领计划（科技攻关类）（No. 2020SK2026）资助

Server Energy Consumption Model Based on ConvLSTM in Mobile Edge Computing

LI Xiaolong¹, LI Xi², YANG Lingfeng¹, HUANG Hua¹

1. College of Computer Science, Hunan University of Technology and Business, Changsha 410205, Hunan, China;
2. College of Advanced Interdisciplinary Studies, Hunan University of Technology and Business, Changsha 410205, Hunan, China

Received:2023-11-20 Online:2024-01-30 Published:2024-02-02

摘要/Abstract

摘要： 针对现有能耗模型对动态工作负载波动具有低敏感性和低精度的问题，该文基于卷积长短期记忆（convolutional long short-term memory,ConvLSTM）神经网络，提出了用于移动边缘计算的服务器智能能耗模型（intelligence server energy consumption model,IECM），用于预测和优化服务器的能量消耗。通过收集服务器运行时间参数，使用熵值法筛选和保留显著影响服务器能耗的参数。基于选定的参数，利用ConvLSTM神经网络训练服务器能耗模型的深度网络。与现有的能耗模型相比，IECM在CPU密集型、I/O密集型、内存密集型和混合型任务上，能够适应服务器工作负载的动态变化，并在能耗预测上具有更好的准确性。

关键词: 卷积长短期记忆, 能耗预测, 智能功率模型, 功率建模

Abstract: To address the issue of low sensitivity and accuracy of existing energy consumption models in accommodating dynamic workload fluctuations, this paper proposes an intelligence server energy consumption model (IECM) based on the convolutional long short-term memory (ConvLSTM) neural network in mobile edge computing, which is used to predict and optimize energy consumption in servers. By collecting server runtime parameters and using the entropy method to filter and retain parameters significantly affecting server energy consumption, a deep network for training the server energy consumption model is constructed based on the selected parameters using the ConvLSTM neural network. Compared with existing energy consumption models, IECM exhibits superior adaptability to dynamic changes in server workload in CPU-intensive, I/O-intensive, memoryintensive, and mixed tasks, offering enhanced accuracy in energy consumption prediction.

Key words: convolutional long short-term memory (ConvLSTM), energy consumption prediction, intelligence power model, power modeling

中图分类号:

TP311

李小龙, 李曦, 杨凌峰, 黄华. 基于ConvLSTM的移动边缘计算服务器能耗模型[J]. 应用科学学报, 2024, 42(1): 53-66.

LI Xiaolong, LI Xi, YANG Lingfeng, HUANG Hua. Server Energy Consumption Model Based on ConvLSTM in Mobile Edge Computing[J]. Journal of Applied Sciences, 2024, 42(1): 53-66.

参考文献

[1] Goudarzi M, Wu H, Palaniswami M, et al. An application placement technique for concurrent IoT applications in edge and fog computing environments [J]. IEEE Transactions on Mobile Computing, 2020, 20(4): 1298-1311.
[2] Sachdeva I, Ramesh S, Chadha U, et al. Computational AI models in VAT photopolymerization: a review, current trends, open issues, and future opportunities [J]. Neural Computing and Applications, 2022, 34: 17207-17229.
[3] Palhares R M, Yuan Y, Wang Q. Artificial intelligence in industrial systems [J]. IEEE Transactions on Industrial Electronics, 2019, 66(12): 9636-9640.
[4] Tham J, Duin A H, Gee L, et al. Understanding virtual reality: presence, embodiment, and professional practice [J]. IEEE Transactions on Professional Communication, 2018, 61(2): 178-195.
[5] International Energy Agency. Digitalisation and energy [R]. 2017[2023-11-20]. https://www.iea.org/reports/digitalisation-and-energy.
[6] Koronen C, Ahman M, Nilsson L J. Data centres in future European energy systems— energy efficiency, integration and policy [J]. Energy Efficiency, 2020, 13(1): 129-144.
[7] Morlock F, Rolle B, Bauer M, et al. Forecasts of electric vehicle energy consumption based on characteristic speed profiles and real-time traffic data [J]. IEEE Transactions on Vehicular Technology, 2020, 69(2): 1404-1418.
[8] Zhang J, Wu Y L, Min G Y, et al. Balancing energy consumption and reputation gain of UAV scheduling in edge computing [J]. IEEE Transactions on Cognitive Communications and Networking, 2020, 6(4): 1204-1217.
[9] Ramsey D, Bouscayrol A, Boulon L, et al. Flexible simulation of an electric vehicle to estimate the impact of thermal comfort on the energy consumption [J]. IEEE Transactions on Transportation Electrification 2022, 8(2): 2288-2298.
[10] Worthington S. Chinese data centers use enough electricity for two countries [DB/OL]. 2016[2023-11-20]. https://www.datacenterdynamics.com/en/news/chinese-data-centers-use-enoughelectricity-for-two-countries/.
[11] Nadjahi C, Louahlia H, Lemasson S. A review of thermal management and innovative cooling strategies for data center [J]. Sustainable Computing: Informatics and Systems, 2018, 19(8): 14-28.
[12] Abdel-Basset M, Mohamed R, Elhoseny M, et al. Energy-aware marine predators algorithm for task scheduling in IoT-based fog computing applications [J]. IEEE Transactions on Industrial Informatics, 2021, 17(7): 5068-5076.
[13] El-taweel N A, Zidan A, Farag H E Z. Novel electric bus energy consumption model based on probabilistic synthetic speed profile integrated with HVAC [J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(3): 1517-1531.
[14] Zhou Z, Mohammad S, Mamoun A, et al. IECL: an intelligence energy consumption model for cloud manufacturing [J]. IEEE Transactions on Industral Informatics, 2022, 18(12)：8967-8976.
[15] Zhou Z, Abawaiy J H, Li F M, et al. Fine-grained energy consumption model of servers based on task characteristics in cloud data center [J]. IEEE Access, 2018, 6(1): 27080-27090.
[16] Park S M, Mun Y S, et al. Prediction method about power consumption by using utilization rate of resources in cloud computing environment [J].Journal of Internet Computing and Services, 2016, 17(1): 7-14.
[17] Duolikun D, Enokido T, Barolli L, et al. An energy consumption model of servers to make virtual machines migrate [C]//International Conference on Advanced Information Networking and Applications, 2022: 24-36.
[18] Chen C, Li K L, Wei W, et al. Hierarchical graph neural networks for few-shot learning [J].IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(1): 240-252.
[19] Cui K, Jing X. Research on prediction model of geotechnical parameters based on BP neural network [J]. Neural Computing and Applications, 2019, 31(12): 8205-8215.
[20] Nelega R, Greu D L, Jecan E, et al. Prediction of power generation of a photovoltaic power plant based on neural networks [J]. IEEE Access, 2023, 11: 20713-20724
[21] Zhou Z, Shojafar M, Abawajy J, et al. ECMS: an edge intelligent energy efficient model in mobile edge computing [J]. IEEE Transactions on Green Communications and Networking, 2022, 6(1): 238-247.
[22] Lin W W, Wu G X, Wang X Y, et al. An artificial neural network approach to power consumption model construction for servers in cloud data centers [J]. IEEE Transactions on Sustainable Computing, 2020, 5(3): 329-340.
[23] Wu W T, Lin W W, He L G, et al. A power consumption model for cloud servers based on Elman neural network [J]. IEEE Transactions on Cloud Computing, 2021, 9(4): 1268-1277.
[24] Li D Q, Wang M, Yan Q X. Research on prediction of power market credit system based on linear model and improved BP neural network [J]. Soft Computing, 2023, 27(11): 7591-7603.
[25] Liang Y, Hu Z G, Li K Q. Power consumption model based on feature selection and deep learning in cloud computing scenarios [J]. IET Communications, 2020, 14(10): 1610-1618.
[26] Zhou Z, Shojafar M, Alazab M, et al. IECL: an intelligent energy consumption model for cloud manufacturing [J]. IEEE Transactions on Industrial Informatics, 2022, 18(12): 8967-8976.
[27] Tang G M, Jiang W X, Xu Z F, et al. Zero-cost, fine-grained power monitoring of datacenters using non-intrusive power disaggregation [C]//The 16th Annual Middleware Conference, 2015: 271-282.
[28] Tang G M, Jiang W X, Xu Z F, et al. NIPD: non-intrusive power disaggregation in legacy datacenters [J]. IEEE Transactions on Computers, 2017, 66(2): 312-325.
[29] Hua Y N, Sevegnani M, Yi D W, et al. Fine-grained RNN with transfer learning for energy consumption estimation on EVs [J]. IEEE Transactions on Industrial Informatics, 2022, 18(11): 8182-8190.
[30] Zhao J C, Ji G X, Tian Y, et al. Environmental vulnerability assessment for mainland China based on entropy method [J]. Ecological Indicators, 2018, 91: 410-422.
[31] Hu W S, Li H C, Pan L, et al. Spatial-spectral feature extraction via deep ConvLSTM neural networks for hyperspectral image classification [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(6): 4237-4250.
[32] Zhou Z, Li Y F, Li F M, et al. An intelligence energy consumption model based on BP neural network in mobile edge Computing [J]. Journal of Parallel and Distributed Computing, 2022, 167(5): 211-220.
[33] Park K, Choi Y, Choi W J, et al. LSTM-based battery remaining useful life prediction with multi-channel charging profiles [J]. IEEE Access, 2020, 8(2): 20786-20798.
[34] Orru P F, Zoccheddu A, Sassu L, et al. Machine learning approach using MLP and SVM algorithms for the fault prediction of a centrifugal pump in the oil and gas industry [J]. Sustainability, 2020, 12(11): 4776.

基于ConvLSTM的移动边缘计算服务器能耗模型

Server Energy Consumption Model Based on ConvLSTM in Mobile Edge Computing

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价