Energy-optimal DNN model placement in UAV-enabled edge computing networks

Abstract

Unmanned aerial vehicle (UAV)-enabled edge computing is emerging as a potential enabler for Artificial Intelligence of Things (AIoT) in the forthcoming sixth-generation (6G) communication networks. With the use of flexible UAVs, massive sensing data is gathered and processed promptly without considering geographical locations. Deep neural networks (DNNs) are becoming a driving force to extract valuable information from sensing data. However, the lightweight servers installed on UAVs are not able to meet the extremely high requirements of inference tasks due to the limited battery capacities of UAVs. In this work, we investigate a DNN model placement problem for AIoT applications, where the trained DNN models are selected and placed on UAVs to execute inference tasks locally. It is impractical to obtain future DNN model request profiles and system operation states in UAV-enabled edge computing. The Lyapunov optimization technique is leveraged for the proposed DNN model placement problem. Based on the observed system overview, an advanced online placement (AOP) algorithm is developed to solve the transformed problem in each time slot, which can reduce DNN model transmission delay and disk I/O energy cost simultaneously while keeping the input data queues stable. Finally, extensive simulations are provided to depict the effectiveness of the AOP algorithm. The numerical results demonstrate that the AOP algorithm can reduce 18.14% of the model placement cost and 29.89% of the input data queue backlog on average by comparing it with benchmark algorithms.

Keywords

UAV-Enabled edge computing / DNN model Placement / 6G networks / Inference tasks

References

[1] W.Y.B. Lim, S. Garg, Z. Xiong, Y. Zhang, D. Niyato, C. Leung, C. Miao, Uav-assisted communication efficient federated learning in the era of the artificial intelligence of things, IEEE Network 35 (5) (2021) 188-195.

[2] D. Xu, T. Li, Y. Li, X. Su, S. Tarkoma, T. Jiang, J. Crowcroft, P. Hui, Edge intelligence: empowering intelligence to the edge of network, Proc. IEEE 109 (11)(2021) 1778-1837.

[3] J. Tang, J. Nie, J. Zhao, Y. Zhou, Z. Xiong, M. Guizani, Slicing-based software-defined mobile edge computing in the air, IEEE Wireless Commun. 29 (1) (2022) 119-125.

[4] J. Tang, J. Nie, Z. Xiong, J. Zhao, Y. Zhang, D. Niyato, Slicing-based reliable resource orchestration for secure software defined edge-cloud computing systems, IEEE Internet Things J. 9 (4) (2022) 2637-2648.

[5] B. Yang, X. Cao, K. Xiong, C. Yuen, Y.L. Guan, S. Leng, L. Qian, Z. Han, Edge intelligence for autonomous driving in 6G wireless system: design challenges and solutions, IEEE Wireless Commun. 28 (2) (2021) 40-47.

[6] S. Deng, H. Zhao, W. Fang, J. Yin, S. Dustdar, A.Y. Zomaya, Edge intelligence: the confluence of edge computing and artificial intelligence, IEEE Internet Things J. 7 (8) (2020) 7457-7469.

[7] D.C. Nguyen, M. Ding, Q.-V. Pham, P.N. Pathirana, L.B. Le, A. Seneviratne, J. Li, D. Niyato, H.V. Poor, Federated learning meets blockchain in edge computing: opportunities and challenges, IEEE Internet Things J. 8 (16) (2021) 12806-12825.

[8] K. Wang, Z. Hu, Q. Ai, Q. Liu, M. Chen, K. Liu, Y. Cong, Membership inference attack with multi-grade service models in edge intelligence, IEEE Network 35 (1)(2021) 184-189.

[9] Y. Xiao, G. Shi, Y. Li, W. Saad, H.V. Poor, Toward self-learning edge intelligence in 6G, IEEE Commun. Mag. 58 (12) (2020) 34-40.

[10] G. Manogaran, S. Mumtaz, C.X. Mavromoustakis, E. Pallis, G. Mastorakis, Artificial intelligence and blockchain-assisted offloading approach for data availability maximization in edge nodes, IEEE Trans. Veh. Technol. 70 (3) (2021) 2404-2412.

[11] W. Sun, J. Liu, Y. Yue, AI-enhanced offloading in edge computing: when machine learning meets industrial IoT, IEEE Network 33 (5) (2019) 68-74.

[12] B. Cao, L. Zhang, Y. Li, D. Feng, W. Cao, Intelligent offloading in multi-access edge computing: a state-of-the-art review and framework, IEEE Commun. Mag. 57 (3)(2019) 56-62.

[13] Z. Ning, K. Zhang, X. Wang, L. Guo, X. Hu, J. Huang, B. Hu, R.Y. Kwok, Intelligent edge computing in internet of vehicles: a joint computation offloading and caching solution, IEEE Trans. Intell. Transport. Syst. 22 (4) (2021) 2212-2225.

[14] G. Fragkos, N. Kemp, E.E. Tsiropoulou, S. Papavassiliou, Artificial intelligence empowered UAVs data offloading in mobile edge computing, in: Proceedings of the 2020 IEEE International Conference on Communications, IEEE, 2020, pp. 1-7.

[15] D. Wu, L. Zhou, Y. Cai, Y. Qian, Collaborative caching and matching for D2D content sharing, IEEE Wireless Commun. 25 (3) (2018) 43-49.

[16] X. Xia, F. Chen, Q. He, J. Grundy, M. Abdelrazek, H. Jin, Online collaborative data caching in edge computing, IEEE Trans. Parallel Distr. Syst. 32 (2) (2021) 281-294.

[17] X. Zhao, Q. Zhu, Collaborative online caching with freshness in the internet of things, in: Proceedings of the 2020 International Conference on Wireless Communications and Signal Processing (WCSP), IEEE, 2020, pp. 916-921.

[18] J. Liu, D. Li, Y. Xu, Collaborative online edge caching with bayesian clustering in wireless networks, IEEE Internet Things J. 7 (2) (2019) 1548-1560.

[19] G. Premsankar, B. Ghaddar, Energy-efficient service placement for latency-sensitive applications in edge computing, IEEE Internet Things J. 9 (18) (2022) 17926-17937.

[20] W. Zhang, D. Yang, H. Peng, W. Wu, W. Quan, H. Zhang, X. Shen, Deep reinforcement learning based resource management for DNN inference in industrial IoT, IEEE Trans. Veh. Technol. 70 (8) (2021) 7605-7618.

[21] G. Constantinou, C. Shahabi, S.H. Kim, Placement of DNN models on mobile edge devices for effective video analysis, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 207-218.

[22] P. Lin, Z. Shi, Z. Xiao, C. Chen, K. Li, Latency-driven model placement for efficient edge intelligence service, IEEE Transactions on Services Computing 15 (2) (2021) 591-601.

[23] U.U. Hafeez, X. Sun, A. Gandhi, Z. Liu, Towards optimal placement and scheduling of DNN operations with pesto, in: Proceedings of the 22nd International Middleware Conference, ACM, 2021, pp. 39-51.

[24] A.H. Arani, M.M. Azari, P. Hu, Y. Zhu, H. Yanikomeroglu, S. Safavi-Naeini, Reinforcement learning for energy-efficient trajectory design of UAVs, IEEE Internet Things J. 9 (11) (2021) 9060-9070.

[25] F. Xia, K. Sun, S. Yu, A. Aziz, L. Wan, S. Pan, H. Liu, Graph learning: a survey, IEEE Transactions on Artificial Intelligence 2 (2) (2021) 109-127.

[26] S. Wang, T. Tuor, T. Salonidis, K.K. Leung, C. Makaya, T. He, K. Chan, Adaptive federated learning in resource constrained edge computing systems, IEEE J. Sel. Area. Commun. 37 (6) (2019) 1205-1221.

[27] S. Sonkar, P. Kumar, R.C. George, T. Yuvaraj, D. Philip, A. Ghosh, Real-time object detection and recognition using fixed-wing LALE VTOL UAV, IEEE Sensor. J. 22 (21) (2022) 20738-20747.

[28] J. Kwak, Y. Kim, L.B. Le, S. Chong, Hybrid content caching in 5G wireless networks: cloud versus edge caching, IEEE Trans. Wireless Commun. 17 (5) (2018) 3030-3045.

[29] H. Li, D. Han, M. Tang, A privacy-preserving storage scheme for logistics data with assistance of blockchain, IEEE Internet Things J. 9 (6) (2021) 4704-4720.

[30] Y. Yin, Y. Li, B. Ye, T. Liang, Y. Li, A blockchain-based incremental update supported data storage system for intelligent vehicles, IEEE Trans. Veh. Technol. 70 (5) (2021) 4880-4893.

[31] Z. Zhou, M. Shojafar, J. Abawajy, H. Yin, H. Lu, ECMS: an edge intelligent energy efficient model in mobile edge computing, IEEE Transactions on Green Communications and Networking 6 (1) (2021) 238-247.

[32] O.M. Rosabal, O.L.A. López, D.E. Pérez, M. Shehab, H. Hilleshein, H. Alves, Minimization of the worst case average energy consumption in UAV-assisted IoT networks, IEEE Internet Things J. 9 (17) (2022) 15827-15838.

[33] S. Bi, L. Huang, H. Wang, Y.-J.A. Zhang, Lyapunov-guided deep reinforcement learning for stable online computation offloading in mobile-edge computing networks, IEEE Trans. Wireless Commun. 20 (11) (2021) 7519-7537.

[34] H. Zhang, K. Zeng, Communication-aware secret share placement in hierarchical edge computing, IEEE Internet Things J. 9 (5) (2021) 3717-3728.

[35] Z. Ma, S. Zhang, Z. Chen, T. Han, Z. Qian, M. Xiao, N. Chen, J. Wu, S. Lu, Towards revenue-driven multi-user online task offloading in edge computing, IEEE Trans. Parallel Distr. Syst. 33 (5) (2021) 1185-1198.

[36] B. Cao, Z. Sun, J. Zhang, Y. Gu, Resource allocation in 5G IoV architecture based on SDN and fog-cloud computing, IEEE Trans. Intell. Transport. Syst. 22 (6) (2021) 3832-3840.

[37] W. Wang, T. Chen, R. Ding, G. Seco-Granados, L. You, X. Gao, Location-based timing advance estimation for 5G integrated leo satellite communications, IEEE Trans. Veh. Technol. 70 (6) (2021) 6002-6017.

[38] W. Zhou, L. Xing, J. Xia, L. Fan, A. Nallanathan, Dynamic computation offloading for MIMO mobile edge computing systems with energy harvesting, IEEE Trans. Veh. Technol. 70 (5) (2021) 5172-5177.

[39] Q. Li, A. Nayak, X. Wang, D. Wang, F.R. Yu, A collaborative caching-transmission method for heterogeneous video services in cache-enabled terahertz heterogeneous networks, IEEE Trans. Veh. Technol. 71 (3) (2022) 3187-3200.

[40] S. Gu, X. Sun, Z. Yang, T. Huang, W. Xiang, K. Yu, Energy-aware coded caching strategy design with resource optimization for satellite-UAV-vehicle-integrated networks, IEEE Internet Things J. 9 (8) (2022) 5799-5811.

[41] B.F. Goldstein, V.C. Patil, V.C. Ferreira, A.S. Nery, F.M. França, S. Kundu, Preventing DNN model IP theft via hardware obfuscation, IEEE Journal on Emerging and Selected Topics in Circuits and Systems 11 (2) (2021) 267-277.