Abstract
This paper introduces a framework of device-to-device edge computing and networks (D2D-ECN), a new paradigm for computation offloading and data processing with a group of resource-rich devices towards collaborative optimization between communication and computation. However, the computation process of task intensive applications would be interrupted when capacity-limited battery energy run out. In order to tackle this issue, the D2D-ECN with energy harvesting technology is applied to provide a green computation network and guarantee service continuity. Specifically, we design a reinforcement learning framework in a point-to-point offloading system to overcome challenges of the dynamic nature and uncertainty of renewable energy, channel state and task generation rates. Furthermore, to cope with high-dimensionality and continuous-valued action of the offloading system with multiple cooperating devices, we propose an online approach based on Lyapunov optimization for computation offloading and resource management without priori energy and network information. Numerical results demonstrate that our proposed scheme can reduce system operation cost with low task execution time in D2D-ECN.
Similar content being viewed by others
References
Gubbi J, Buyya R, Marusic S, Palaniswami M (2013) Internet of things (IoT): a vision, architectural elements, and future directions. Future Generat Comput Syst 29(7):1645–1660
ETSI ISG (2015) Mobile edge computing a key technology towards 5G. White Paper 11:1–16
Pu L, Chen C, Xu J, Fu X (2016) D2D fogging: an energy-efficient and incentive-aware task offloading framework via network-assisted D2D collaboration. IEEE J Sel Areas Commun 34(12):3887–3901
Liu F et al (2013) Gearing resource-poor mobile devices with powerful clouds: architectures, challenges, and applications. IEEE Wireless Commun 20(3):14–22
Zhang K et al (2016) Energy-ffficient offloading for mobile edge computing in 5G heterogeneous networks. IEEE Access 4:5896–5907
Shih Y-Y, Chung W-H, Pang A-C, Chiu T-C, Wei H-Y (2017) Enabling low-latency applications in fog-radio access networks. IEEE Netw 31(1):52–58
Zhang K, Mao Y, Leng S, He Y, Zhang Y (2017) Mobile-edge computing for vehicular networks: a promising network paradigm with predictive off-loading. IEEE Vehi Tech Maga 12(2):36–44
Wang X, Leng S, Yang K (2017) Social-aware edge caching in fog radio access networks. IEEE Access 5:8492–8501
Chen X, Pu L, Gao L, Wu W, Wu D (2017) Exploiting massive D2D collaboration for energy-efficient mobile edge computing. IEEE Commun Mag 24(4):64–71
Ti N, Le L (2017) Computation offloading leveraging computing resources from edge cloud and mobile peers. In: Proceedings of the IEEE Int. Commun. Confe (ICC)
Meng X, Wang W, Zhang Z (2017) Delay-constrained hybrid computation offloading with cloud and fog computing. IEEE Access 5:21355–21367
Garlatova M, Wallwater A, Zussman G (2011) Networking low-power energy harvesting devices: measurements and algorithms. In: Proceedings of the IEEE Conf. Comput. Commun. (INFOCOM), pp 1602–1610
Dhillon H, Li Y, Nuggehalli P, Pi Z, Andrews J (2014) Fundamentals of heterogeneous cellular networks with energy harvesting. IEEE Trans Wireless Commun 13(5):2782–2797
Mao Y, Zhang J, Letaief KB (2016) Dynamic computation offloading for Mobile-Edge computing with energy harvesting devices. IEEE J Sel Areas Commun 34(12):3590–3605
Fan B, Leng S, Yang K (2016) A dynamic bandwidth allocation algorithm in mobile networks with big data of users and networks. IEEE Netw Maga 30(1):6–10
Mastronarde N, Schaar M (2011) Fast reinforcement learning for energy-efficient wireless communication. IEEE Trans Sig Process 50(12):6262–6266
Wei Y, Yu FR, Song M, Han Z (2017) User scheduling and resource allocation in HetNets with hybrid energy supply: an actor-critic reinforcement learning approach. IEEE Trans Wire Commun 17(1):680–692
Xu J, Chen L, Ren S (2017) Online learning for offloading and autoscaling in energy harvesting mobile edge computing. IEEE Trans Cogn Commun Netw 3(3):361–373
Mao Y, You C, Zhang J, Huang K, Letaief KB (2017) A servey on mobile edge computing: the communication perspective. IEEE Commun Survey Tuts 19(4):2322–2358
Miettinen AP, Nurminen JK (2010) Energy efficiency of mobile clients in cloud computing. In: Proceedings of the USENIX Conf. Hot Topics Cloud Comput. (HotCloud), Boston, MA, USA, pp 1–7
Wang Q, Leng S, Fu H, Zhang Y (2012) An IEEE 802.11p-based multichannle MAC scheme with channel coordination for vehicular Ad Hoc networks. IEEE Trans Intell Trans Sys 13(2):449–458
Rajan D, Sabharwal A, Aazhang B (2004) Delay-bounded packet scheduling of bursty traffic over wireless channels. IEEE Trans Inform Theory 50(1):125–144
Burd TD, Brodersen RW (1996) Processor design for portable systems. Kluwer J VLSI Signal Process Syst 13(2):203–221
Altman E (1999) Constrained Markov Decision Process Chapman and Hall/CRC
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge
Salodkar N, Bhorkar A, Karandikar A, Borkar VS (2008) An on-line learning algorithm for energy efficient delay constrained scheduling over a fading channel. IEEE J Sel Areas Commun 26(4):732–742
Neely MJ (2010) Stochastic network optimization with application to communication and queueing systems, San rafael, CA USA: Morgan claypool
Gibilisco P, Hiai F, Petz D (2009) Quantum covariance, quantum fisher information, and the uncertainty relations. IEEE Trans Inform Theory 55(1):439–443
Gorlatova M, Wallwater A, Zussma G (2012) Networking low-power energy harvesting devices: Measurements and algorithms. IEEE Trans Mobile Comput 12(9):1853–1865
Mitchell TM (1997) Machine learning McGraw-Hill
Acknowledgments
This work is supported by the joint fund of the Ministry of Education of China and China Mobile (MCM 20160304), the Fundamental Research Funds for the Central Universities, China (ZYGX2016Z011), and EU H2020 Project COSAFE (MSCA-RISE-2018-824019).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix: Convergence and optimality analysis of algorithm 1
Given the Lagrange multiplier η, Algorithm 1 can converge to an optimal state-action value (e.g, Q(t), to approximate Q∗) after finite number of iterations as it satisfies following conditions [30]: i) the state transition \(p(\left . {s^{\prime }} \right |s,a)\) in Eq. 10 is stationary under any observed state s ∈ S with the corresponding action a ∈ A; ii) the Lagrange function ρ in Eq. 13 is bounded, that is the unconstrained cost satisfies \(\left | \rho (s,a)\right | < \rho _{max}\) for each possible state-action pair (s,a), and ρmax is a constant; (iii) each state s and Lagrange function could be infinitely explored at the each episode. As a consequence, the Qη converges to the optimal Q∗η with probability 1. Moreover, it is worth mentioning that the executive time conducted by interactions between agent and external network environment have considerable impact on the feasibility and efficiency of Q-learning algorithm.
On the other hand, we impose the following additional conditions on the learning rate α(t) and β(t) to guarantee convergence of Theorem 1 [26],
Consequently, Eq. 19 can ensure to obtain optimal policy in finite iterations. ■
Appendix B: Proof for theorem 1
Based on the inequality \(\max {[x,0]^{2}} \le {x^{2}}\), the battery energy state transition can be reformulated as
Then, substituting the Lyapunov function (23) and the above inequality (29) into the Lyapunov drift function (24), we obtain
Taking the renewable energy arrival rate and energy utilization to hold for the inequalities \(\left | {e(t)} \right | \le {e_{\max }}\) and \(\left | {g(t)} \right | \le {g_{\max }}\), we define the following equation
Therefore, adding the \(\pi E\left \{ {c(t)} \right \}\) into each side of the inequality (30), which can be rewritten as the Eq. 26. ■
Rights and permissions
About this article
Cite this article
Qiao, G., Leng, S. & Zhang, Y. Online Learning and Optimization for Computation Offloading in D2D Edge Computing and Networks. Mobile Netw Appl 27, 1111–1122 (2022). https://doi.org/10.1007/s11036-018-1176-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11036-018-1176-y