skip to main content
research-article

EECDN: Energy-efficient Cooperative DNN Edge Inference in Wireless Sensor Networks

Authors Info & Claims
Published:14 November 2022Publication History
Skip Abstract Section

Abstract

Multi-access edge computing (MEC) is emerging to improve the quality of experience of mobile devices including internet of things sensors by offloading computing intensive tasks to MEC servers. Existing MEC-enabled cooperative computation offloading works focus on the optimization of total energy consumption but fail to exploit multi-relay diversity and min-max fairness of energy consumption on participated sensors. We explore a typical wireless sensor network with multi-source, multi-relay, and one edge server, where relay nodes can provide both cooperative communication and computation services. We divide the energy efficiency optimization problem into two sub-problems: One is to minimize the weighted average total energy consumption per time slot, and the other is to minimize the maximum weighted energy consumption. For the first sub-problem, we propose an optimal algorithm named as optimal weighted average total energy consumption algorithm (OTCA) based on bipartite matching. For the second sub-problem, greedy algorithm for fairness guarantee (GAF) is proposed with an approximation ratio of (1 + ε), where ε is a small positive constant. Extensive numerical results show that OTCA outperforms the baseline algorithms by 26.7–77.4% on the average total weighted energy consumption while GAF outperforms benchmark algorithms by 30.7–84.4%. NS-3 simulation experiments comply with numerical results.

REFERENCES

  1. [1] Alkhayyat Ahmed and Sadkhan Sattar B.. 2018. Bandwidth efficiency analysis of cooperative communication with reactive relay selection. In Proceedings of the International Conference on Engineering Technology and their Applications. IEEE, 7780.Google ScholarGoogle ScholarCross RefCross Ref
  2. [2] Andrews Matthew, Borst Sem, Lee Jeongran, Martin-Lopez Enrique, and Palyutina Karina. 2020. Tracking the state of large dynamic networks via reinforcement learning. In Proceedings of the IEEE Conference on Computer Communications. 416425.Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. [3] Björnson Emil, Özdogan Özgecan, and Larsson Erik G.. 2019. Intelligent reflecting surface versus decode-and-forward: How large surfaces are needed to beat relaying? IEEE Wireless Commun. Lett. 9, 2 (2019), 244248.Google ScholarGoogle ScholarCross RefCross Ref
  4. [4] Boyd Stephen and Vandenberghe Lieven. 2004. Convex Optimization. Cambridge University Press.Google ScholarGoogle ScholarDigital LibraryDigital Library
  5. [5] Cao Xiaowen, Wang Feng, Xu Jie, Zhang Rui, and Cui Shuguang. 2018. Joint computation and communication cooperation for energy-efficient mobile edge computing. IEEE IoT J. 6, 3 (2018), 41884200.Google ScholarGoogle Scholar
  6. [6] Chen Long, Wu Jigang, Zhang Jun, Dai Hong-Ning, Long Xin, and Yao Mianyang. 2020. Dependency-aware computation offloading for mobile edge computing with edge-cloud cooperation. IEEE Trans. Cloud Comput. (2020), 118. DOI:Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] Chen Meng-Hsi, Dong Min, and Liang Ben. 2018. Resource sharing of a computing access point for multi-user mobile cloud offloading with delay constraints. IEEE Trans. Mobile Comput. 17, 12 (2018), 28682881.Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. [8] Chen Ying, Zhang Ning, Zhang Yongchao, Chen Xin, Wu Wen, and Shen Xuemin Sherman. 2021. TOFFEE: Task offloading and frequency scaling for energy efficiency of mobile devices in mobile edge computing. IEEE Trans. Cloud Comput. 9, 4 (2021), 16341644.Google ScholarGoogle ScholarCross RefCross Ref
  9. [9] Cho Hewon, Cui Ying, and Lee Jemin. 2020. Energy-efficient computation task splitting for edge computing-enabled vehicular networks. In Proceedings of the IEEE International Conference on Communications Workshops. 16.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Dai Yueyue, Xu Du, Maharjan Sabita, and Zhang Yan. 2018. Joint computation offloading and user association in multi-task mobile edge computing. IEEE Trans. Vehic. Technol. 67, 12 (2018), 1231312325.Google ScholarGoogle ScholarCross RefCross Ref
  11. [11] Dao Nhu-Ngoc, Vu Duc-Nghia, Lee Yunseong, Cho Sungrae, Cho Chihyun, and Kim Hyunbum. 2018. Pattern-identified online task scheduling in multitier edge computing for industrial IoT services. Mobile Inf. Syst. (2018), 110.Google ScholarGoogle Scholar
  12. [12] Donahue Jeffrey, Anne Hendricks Lisa, Guadarrama Sergio, Rohrbach Marcus, Venugopalan Subhashini, Saenko Kate, and Darrell Trevor. 2015. Long-term recurrent convolutional networks for visual recognition and description. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 26252634.Google ScholarGoogle ScholarCross RefCross Ref
  13. [13] Fang He, Xu Li, Zou Yulong, Wang Xianbin, and Choo Kim-Kwang Raymond. 2018. Three-stage stackelberg game for defending against full-duplex active eavesdropping attacks in cooperative communication. IEEE Trans. Vehic. Technol. 67, 11 (2018), 1078810799.Google ScholarGoogle ScholarCross RefCross Ref
  14. [14] Gao Lianli, Guo Zhao, Zhang Hanwang, Xu Xing, and Shen Heng Tao. 2017. Video captioning with attention-based LSTM and semantic consistency. IEEE Trans. Multimedia 19, 9 (2017), 20452055.Google ScholarGoogle ScholarDigital LibraryDigital Library
  15. [15] Gupta Nishant, Agarwal Satyam, and Mishra Deepak. 2021. UAV deployment for throughput maximization in a UAV-Assisted cellular communications. In Proceedings of the 2021 IEEE 32nd Annual International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC’21). IEEE, 10551060.Google ScholarGoogle ScholarCross RefCross Ref
  16. [16] Huang Shanfeng, Wang Shuai, Wang Rui, Wen Miaowen, and Huang Kaibin. 2021. Reconfigurable intelligent surface assisted mobile edge computing with heterogeneous learning tasks. IEEE Trans. Cogn. Commun. Netw. 7, 2 (2021), 369382.Google ScholarGoogle ScholarCross RefCross Ref
  17. [17] Kang Yiping, Hauswald Johann, Gao Cao, Rovinski Austin, Mudge Trevor, Mars Jason, and Tang Lingjia. 2017. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge. In Proceedings of the 22nd International Conference on Architectural Support for Programming Languages and Operating Systems. 615629.Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Kim Hokeun, Kang Eunsuk, Broman David, and Lee Edward A.. 2020. Resilient authentication and authorization for the internet of things (IoT) using edge computing. ACM Trans. IoT 1, 1 (2020), 127.Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. [19] Krizhevsky Alex, Sutskever Ilya, and Hinton Geoffrey E.. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (2017), 8490.Google ScholarGoogle ScholarDigital LibraryDigital Library
  20. [20] Kuhn Harold W.. 2005. The Hungarian method for the assignment problem. Nav. Res. Logist. 52, 1 (2005), 721.Google ScholarGoogle ScholarCross RefCross Ref
  21. [21] Li En, Zeng Liekang, Zhou Zhi, and Chen Xu. 2020. Edge AI: On-demand accelerating deep neural network inference via edge computing. IEEE Trans. Wireless Commun. 19, 1 (2020), 447457.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Li Huilin, Xu Haitao, Zhou Chengcheng, Lü Xing, and Han Zhu. 2020. Joint optimization strategy of computation offloading and resource allocation in multi-access edge computing environment. IEEE Trans. Vehic. Technol. 69, 9 (2020), 1021410226.Google ScholarGoogle ScholarCross RefCross Ref
  23. [23] Li Lingxiang, Siew Marie, and Quek Tony Q. S.. 2019. Learning-based pricing for privacy-preserving job offloading in mobile edge computing. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’19). 47844788.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Li Yang, Xu Gaochao, Yang Kun, Ge Jiaqi, Liu Peng, and Jin Zhenjun. 2020. Energy efficient relay selection and resource allocation in D2D-enabled mobile edge computing. IEEE Trans. Vehic. Technol. 69, 12 (2020), 1580015814.Google ScholarGoogle ScholarCross RefCross Ref
  25. [25] Liao Haijun, Zhou Zhenyu, Zhao Xiongwen, and Wang Yang. 2021. Learning-based queue-aware task offloading and resource allocation for space-air-ground-integrated power IoT. IEEE IoT J. 8, 7 (2021), 52505263.Google ScholarGoogle Scholar
  26. [26] Luo Guiyang, Zhou Haibo, Cheng Nan, Yuan Quan, Li Jinglin, Yang Fangchun, and Shen Xuemin. 2021. Software-defined cooperative data sharing in edge computing assisted 5G-VANET. IEEE Trans. Mobile Comput. 20, 3 (2021), 12121229.Google ScholarGoogle ScholarCross RefCross Ref
  27. [27] Luo Jie, Deng Xiaoheng, Zhang Honggang, and Qi Huamei. 2019. QoE-driven computation offloading for edge computing. J. Syst. Arch. 97 (2019), 3439.Google ScholarGoogle ScholarDigital LibraryDigital Library
  28. [28] Lyu X., Tian H., Ni W., Zhang Y., Zhang P., and Liu R. P.. 2018. Energy-efficient admission of delay-sensitive tasks for mobile edge computing. IEEE Trans. Commun. 66, 6 (2018), 26032616.Google ScholarGoogle ScholarCross RefCross Ref
  29. [29] Mei Lifan, Hu Runchen, Cao Houwei, Liu Yong, Han Zifan, Li Feng, and Li Jin. 2020. Realtime mobile bandwidth prediction using LSTM neural network and Bayesian fusion. Comput. Netw. 182 (2020), 107515.Google ScholarGoogle ScholarCross RefCross Ref
  30. [30] Mianyang Yao, Long Chen, Zhang Jun, Jiale Huang, and Wu Jigang. 2022. Loading cost-aware model caching and request routing for cooperative edge inference. In Proceedings of the International Conference on Communications. IEEE, 16.Google ScholarGoogle Scholar
  31. [31] Miettinen Antti P. and Nurminen Jukka K.. 2010. Energy efficiency of mobile clients in cloud computing. In Proceedings of the USENIX Conference on Hot Topics in Cloud Computing (HotCloud’10). 4 pages. .Google ScholarGoogle ScholarDigital LibraryDigital Library
  32. [32] Munkres James. 1957. Algorithms for the assignment and transportation problems. J. Soc. Industr. Appl. Math. 5, 1 (1957), 3238.Google ScholarGoogle ScholarCross RefCross Ref
  33. [33] Qian Li Ping, Zhu Zhengying, Yu Ningning, and Wu Yuan. 2019. Joint minimization of transmission energy and computation energy for MEC-aware NOMA NB-IoT networks. In Proceedings of the IEEE Global Communications Conference. 17.Google ScholarGoogle ScholarDigital LibraryDigital Library
  34. [34] Qiao Guanhua, Leng Supeng, and Zhang Yan. 2019. Online learning and optimization for computation offloading in D2D edge computing and networks. Mobile Netw. Appl. (2019), 112.Google ScholarGoogle Scholar
  35. [35] Ross Philipp and Luckow Andre. 2019. EdgeInsight: Characterizing and modeling the performance of machine learning inference on the edge and cloud. In Proceedings of the IEEE International Conference on Big Data. 18971906.Google ScholarGoogle ScholarCross RefCross Ref
  36. [36] Shannon Claude Elwood. 1998. Communication in the presence of noise. Proc. IEEE 86, 2 (1998), 447457.Google ScholarGoogle ScholarDigital LibraryDigital Library
  37. [37] Sharma Neha and Panwar Deepak. 2020. Green IoT: Advancements and sustainability with environment by 2050. In Proceedings of the International Conference on Reliability, Infocom Technologies and Optimization. 11271132.Google ScholarGoogle ScholarCross RefCross Ref
  38. [38] Xu Ding, Li Qun, and Zhu Hongbo. 2019. Energy-saving computation offloading by joint data compression and resource allocation for mobile-edge computing. IEEE Commun. Lett. 23, 4 (2019), 704707.Google ScholarGoogle Scholar
  39. [39] Xu Hongli, Huang Liusheng, Qiao Chunming, Zhang Yindong, and Sun Quan. 2012. Bandwidth-power aware cooperative multipath routing for wireless multimedia sensor networks. IEEE Trans. Wireless Commun. 11, 4 (2012), 15321543.Google ScholarGoogle ScholarCross RefCross Ref
  40. [40] Xu Jie and Yao Jianping. 2019. Exploiting physical-layer security for multiuser multicarrier computation offloading. IEEE Wireless Commun. Lett. 8, 1 (2019), 912.Google ScholarGoogle ScholarCross RefCross Ref
  41. [41] Xu Zichuan, Zhang Zhiheng, Lui John C. S., Liang Weifa, Xia Qiufen, Zhou Pan, Xu Wenzheng, and Wu Guowei. 2021. Affinity-aware VNF placement in mobile edge clouds via leveraging GPUs. IEEE Trans. Comput. 70, 12 (2021), 22342248.Google ScholarGoogle ScholarDigital LibraryDigital Library
  42. [42] Yao Mianyang. 2022. Source Code to Evaluate the Energy Consumption. Retrieved from https://github.com/mycano/eecdn.git.Google ScholarGoogle Scholar
  43. [43] Yao Shuochao, Li Jinyang, Liu Dongxin, Wang Tianshi, Liu Shengzhong, Shao Huajie, and Abdelzaher Tarek. 2020. Deep compressive offloading: Speeding up neural network inference by trading edge computation for network latency. In Proceedings of the 18th Conference on Embedded Networked Sensor Systems. 476488.Google ScholarGoogle ScholarDigital LibraryDigital Library
  44. [44] Yao Shuochao, Li Jinyang, Liu Dongxin, Wang Tianshi, Liu Shengzhong, Shao Huajie, and Abdelzaher Tarek. 2021. Deep compressive offloading: Speeding up edge offloading for AI services. Mobile Comput. Commun. 25, 1 (2021), 3942.Google ScholarGoogle ScholarDigital LibraryDigital Library
  45. [45] Yu Shuai, Wang Xin, and Langar Rami. 2017. Computation offloading for mobile edge computing: A deep learning approach. In Proceedings of the IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communications. 16.Google ScholarGoogle ScholarDigital LibraryDigital Library
  46. [46] Yuan Quan, Li Jinglin, Zhou Haibo, Lin Tao, Luo Guiyang, and Shen Xuemin. 2020. A joint service migration and mobility optimization approach for vehicular edge computing. IEEE Trans. Vehic. Technol. 69, 8 (2020), 90419052.Google ScholarGoogle ScholarCross RefCross Ref
  47. [47] Zhang Guanglin, Zhang Wenqian, Cao Yu, Li Demin, and Wang Lin. 2018. Energy-delay tradeoff for dynamic offloading in mobile-edge computing system with energy harvesting devices. IEEE Trans. Industr. Inf. 14, 10 (2018), 46424655.Google ScholarGoogle ScholarCross RefCross Ref
  48. [48] Zhang Jiao, Hu Xiping, Ning Zhaolong, Ngai Edith C.-H., Zhou Li, Wei Jibo, Cheng Jun, and Hu Bin. 2018. Energy-latency tradeoff for energy-aware offloading in mobile edge computing networks. IEEE IoT J. 5, 4 (2018), 26332645.Google ScholarGoogle Scholar
  49. [49] Zhang Tiankui, Xu Yu, Loo Jonathan, Yang Dingcheng, and Xiao Lin. 2020. Joint computation and communication design for UAV-assisted mobile edge computing in IoT. IEEE Trans. Industr. Inf. 16, 8 (2020), 55055516.Google ScholarGoogle ScholarCross RefCross Ref
  50. [50] Zhao Liang, Yang Kaiqi, Tan Zhiyuan, Li Xianwei, Sharma Suraj, and Liu Zhi. 2021. A novel cost optimization strategy for SDN-enabled UAV-assisted vehicular computation offloading. IEEE Trans. Intell. Transport. Syst. 22, 6 (2021), 36643674.Google ScholarGoogle ScholarCross RefCross Ref
  51. [51] Zhou Guangli, Wang Tao, Wu Yating, Zheng Guoxin, and Yang Guangli. 2016. Energy-efficient power allocation for decode-and-forward OFDM relay links. In Mobile and Wireless Technologies. Lecture Notes in Electrical Engineering, vol. 391. Springer, Singapore. Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. EECDN: Energy-efficient Cooperative DNN Edge Inference in Wireless Sensor Networks

      Recommendations

      Comments

      Login options

      Check if you have access through your login credentials or your institution to get full access on this article.

      Sign in

      Full Access

      • Published in

        cover image ACM Transactions on Internet Technology
        ACM Transactions on Internet Technology  Volume 22, Issue 4
        November 2022
        642 pages
        ISSN:1533-5399
        EISSN:1557-6051
        DOI:10.1145/3561988
        Issue’s Table of Contents

        Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

        Publisher

        Association for Computing Machinery

        New York, NY, United States

        Publication History

        • Published: 14 November 2022
        • Online AM: 23 June 2022
        • Accepted: 14 June 2022
        • Revised: 3 April 2022
        • Received: 3 July 2021
        Published in toit Volume 22, Issue 4

        Permissions

        Request permissions about this article.

        Request Permissions

        Check for updates

        Qualifiers

        • research-article
        • Refereed

      PDF Format

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Full Text

      View this article in Full Text.

      View Full Text

      HTML Format

      View this article in HTML Format .

      View HTML Format
      About Cookies On This Site

      We use cookies to ensure that we give you the best experience on our website.

      Learn more

      Got it!