|
|
Frontiers of Information Technology & Electronic Engineering
ISSN 2095-9184 (print), ISSN 2095-9230 (online)
2024 Vol.25 No.5 P.664-684
A cloud-edge-device collaborative offloading scheme with heterogeneous tasks and its performance evaluation
Abstract: How to collaboratively offload tasks between user devices, edge networks (ENs), and cloud data centers is an interesting and challenging research topic. In this paper, we investigate the offloading decision, analytical modeling, and system parameter optimization problem in a collaborative cloud-edge-device environment, aiming to trade off different performance measures. According to the differentiated delay requirements of tasks, we classify the tasks into delay-sensitive and delay-tolerant tasks. To meet the delay requirements of delay-sensitive tasks and process as many delay-tolerant tasks as possible, we propose a cloud-edge-device collaborative task offloading scheme, in which delay-sensitive and delay-tolerant tasks follow the access threshold policy and the loss policy, respectively. We establish a four-dimensional continuous-time Markov chain as the system model. By using the Gauss-Seidel method, we derive the stationary probability distribution of the system model. Accordingly, we present the blocking rate of delay-sensitive tasks and the average delay of these two types of tasks. Numerical experiments are conducted and analyzed to evaluate the system performance, and numerical simulations are presented to evaluate and validate the effectiveness of the proposed task offloading scheme. Finally, we optimize the access threshold in the EN buffer to obtain the minimum system cost with different proportions of delay-sensitive tasks.
Key words: Edge computing; Offloading scheme; Cloud-edge-device collaboration; Markov chain; Cost function
Chinese Summary <1> 基于学习的四足机器人通用技能控制方法
机构：1浙江大学，交叉力学中心，中国杭州，310027；2浙江大学，杭州国际科创中心，中国杭州，311200；3浙江大学，流体动力与机电系统国家重点实验室，中国杭州，310058；4浙江大学，应用力学研究所，中国杭州，310027
目的：控制四足机器人实现连续、可控的多种运动。
创新点：1.将动作生成与基于动作模仿的强化学习方法结合，使用同一个控制器，跟踪不同运动学轨迹，在实物机器人上实现步态切换、高抬腿和跳跃等不同动作。2.提出参考轨迹可预测性的概念，强化学习控制器具备挖掘参考轨迹内在关联性的能力，揭示动作模仿中控制器输入的参考轨迹长度对控制器性能的影响机理。
方法：1.通过动作捕获、草绘与轨迹优化等方法，建立运动轨迹数据库。2.通过基于动作模仿的强化方法，在仿真环境中训练控制器模仿数据库中的动作。3.基于控制器设计动作状态机，根据用户指令实时生成可控的运动轨迹，作为控制器的输入，实现对实物机器人的控制。4.提出参考轨迹可预测性的概念，分析参考轨迹长度对控制器性能的影响。
结论：1.本文所提出的控制方法可以在实物机器人上实现对多种技能的控制。2.参考轨迹长度对控制器性能的影响是通过可预测性实现的；对于可预测性低的运动，可以通过补充参考轨迹长度提高控制器性能。
关键词组：
References:
[1]Ai LH, Tan B, Zhang JD, et al., 2023. Dynamic offloading strategy for delay-sensitive task in mobile-edge computing networks. IEEE Int Things J, 10(1):526-538.
[2]Akhlaqi MY, Hanapi ZM, 2023. Task offloading paradigm in mobile edge computing—current issues, adopted approaches, and future directions. J Netw Comput Appl, 212:103568.
[3]Bai XJ, Jin SF, 2022. Performance analysis of an energy-saving strategy in cloud data centers based on a MMAP[K]/M[K]/N1+N2 non-preemptive priority queue. Fut Gener Comput Syst, 136:205-220.
[4]Chahoud M, Otoum S, Mourad A, 2023. On the feasibility of federated learning towards on-demand client deployment at the edge. Inform Process Manag, 60(1):103150.
[5]Djigal H, Xu J, Liu LF, et al., 2022. Machine and deep learning for resource allocation in multi-access edge computing: a survey. IEEE Commun Surv Tutor, 24(4):2449-2494.
[6]Feng C, Han PC, Zhang X, et al., 2022. Computation offloading in mobile edge computing networks: a survey. J Netw Comput Appl, 202:103366.
[7]Gholami A, Baras JS, 2021. Collaborative cloud-edge-local computation offloading for multi-component applications. Proc IEEE/ACM Symp on Edge Computing, p.361-365.
[8]Guo M, Wang W, Huang X, et al., 2022. Lyapunov-based partial computation offloading for multiple mobile devices enabled by harvested energy in MEC. IEEE Int Things J, 9(11):9025-9035.
[9]Guo XB, Du ZL, Jin SF, 2022. Nash equilibrium and social optimization of a task offloading strategy with real-time virtual machine repair in an edge computing system. Clust Comput, 25(6):3785-3797.
[10]Hao YX, Jiang YY, Chen T, et al., 2019. iTaskOffloading: intelligent task offloading for a cloud-edge collaborative system. IEEE Netw, 33(5):82-88.
[11]He JY, Zhang D, Zhou YZ, et al., 2020. A truthful online mechanism for collaborative computation offloading in mobile edge computing. IEEE Trans Ind Inform, 16(7):4832-4841.
[12]He XQ, Shen YH, Ren J, et al., 2022. An online auction-based incentive mechanism for soft-deadline tasks in collaborative edge computing. Fut Gener Comput Syst, 137:1-13.
[13]Hossain D, Huynh LNT, Sultana T, et al., 2020. Collaborative task offloading for overloaded mobile edge computing in small-cell networks. Proc Int Conf on Information Networking, p.717-722.
[14]Islam A, Debnath A, Ghose M, et al., 2021. A survey on task offloading in multi-access edge computing. J Syst Archit, 118:102225.
[15]Jayanetti A, Halgamuge S, Buyya R, 2022. Deep reinforcement learning for energy and time optimized scheduling of precedence-constrained tasks in edge-cloud computing environments. Fut Gener Comput Syst, 137:14-30.
[16]Kim C, Dudin A, Dudin S, et al., 2021. Mathematical model of operation of a cell of a mobile communication network with adaptive modulation schemes and handover of mobile users. IEEE Access, 9:106933-106946.
[17]Li W, Jin SF, 2021. Performance evaluation and optimization of a task offloading strategy on the mobile edge computing with edge heterogeneity. J Supercomput, 77(11):12486-12507.
[18]Li YZ, Qi F, Wang ZL, et al., 2020. Distributed edge computing offloading algorithm based on deep reinforcement learning. IEEE Access, 8:85204-85215.
[19]Liao HL, Li XY, Guo DK, et al., 2022. Dependency-aware application assigning and scheduling in edge computing. IEEE Int Things J, 9(6):4451-4463.
[20]Luo ZY, Huang A, 2021. Joint game theory and greedy optimization scheme of computation offloading for UAV-aided network. Proc 31st Int Telecommunication Networks and Applications Conf, p.198-203.
[21]Ma X, Wang SG, Zhang S, et al., 2021. Cost-efficient resource provisioning for dynamic requests in cloud assisted mobile edge computing. IEEE Trans Cloud Comput, 9(3):968-980.
[22]Mao YY, 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.
[23]Mao YY, You CS, Zhang J, et al., 2017. A survey on mobile edge computing: the communication perspective. IEEE Commun Surv Tutor, 19(4):2322-2358.
[24]Muniswamaiah M, Agerwala T, Tappert CC, 2021. A survey on cloudlets, mobile edge, and fog computing. Proc 8th IEEE Int Conf on Cyber Security and Cloud Computing/7th IEEE Int Conf on Edge Computing and Scalable Cloud, p.139-142.
[25]Ranganath S, 2022. Edge computing: types and attributes. Adv Comput, 127:35-62.
[26]Saeik F, Avgeris M, Spatharakis D, et al., 2021. Task offloading in edge and cloud computing: a survey on mathematical, artificial intelligence and control theory solutions. Comput Netw, 195:108177.
[27]Song SN, Fang ZY, Jiang JY, 2022. Fast-DRD: fast decentralized reinforcement distillation for deadline-aware edge computing. Inform Process Manag, 59(2):102850.
[28]Stoyanova M, Nikoloudakis Y, Panagiotakis S, et al., 2020. A survey on the Internet of Things (IoT) forensics: challenges, approaches, and open issues. IEEE Commun Surv Tutor, 22(2):1191-1221.
[29]Su X, An L, Cheng Z, et al., 2023. Cloud-edge collaboration-based bi-level optimal scheduling for intelligent healthcare systems. Fut Gener Comput Syst, 141:28-39.
[30]Tan L, Kuang ZF, Zhao L, et al., 2022. Energy-efficient joint task offloading and resource allocation in OFDMA-based collaborative edge computing. IEEE Trans Wirel Commun, 21(3):1960-1972.
[31]Thai MT, Lin YD, Lai YC, et al., 2020. Workload and capacity optimization for cloud-edge computing systems with vertical and horizontal offloading. IEEE Trans Netw Serv Manag, 17(1):227-238.
[32]Tong Z, Deng XM, Ye F, et al., 2020. Adaptive computation offloading and resource allocation strategy in a mobile edge computing environment. Inform Sci, 537:116-131.
[33]Vhora F, Gandhi J, 2020. A comprehensive survey on mobile edge computing: challenges, tools, applications. Proc 4th Int Conf on Computing Methodologies and Communication, p.49-55.
[34]Wang YZ, Yu JQ, Yu ZB, 2023. Resource scheduling techniques in cloud from a view of coordination: a holistic survey. Front Inform Technol Electron Eng, 24(1):1-40.
[35]Wang ZY, Zhu Q, 2020. Partial task offloading strategy based on deep reinforcement learning. Proc IEEE 6th Int Conf on Computer and Communications, p.1516-1521.
[36]Wu JZ, Cao ZY, Zhang YJ, et al., 2019. Edge-cloud collaborative computation offloading model based on improved partical swarm optimization in MEC. Proc IEEE 25th Int Conf on Parallel and Distributed Systems, p.959-962.
[37]Xia SC, Wen XX, Yao ZX, et al., 2020. Dynamic task offloading and resource allocation for heterogeneous MEC-enable IoT. Proc IEEE/CIC Int Conf on Communications in China, p.847-852.
[38]Yang WY, Liu W, Wei XS, et al., 2021. EdgeKeeper: a trusted edge computing framework for ubiquitous power Internet of Things. Front Inform Technol Electron Eng, 22(3):374-399.
[39]Zhan WH, Luo CB, Min GY, et al., 2020. Mobility-aware multi-user offloading optimization for mobile edge computing. IEEE Trans Veh Technol, 69(3):3341-3356.
[40]Zhang JY, Yu P, Zhou FQ, et al., 2022. Resource and delay aware fine-grained service offloading in collaborative edge computing. Comput Netw, 218:109383.
[41]Zhang MJ, Cao JN, Yang L, et al., 2022. ENTS: an edge-native task scheduling system for collaborative edge computing. Proc IEEE/ACM 7th Symp on Edge Computing, p.149-161.
[42]Zhao H, Geng JW, Jin SF, 2023. Performance research on a task offloading strategy in a two-tier edge structure-based MEC system. J Supercomput, 79(9):10139-10177.
[43]Zheng T, Wan J, Zhang JL, et al., 2020. A survey of computation offloading in edge computing. Proc Int Conf on Computer, Information and Telecommunication Systems, p.1-6.
[44]Zhou WC, Fang WW, Li YY, et al., 2019. Markov approximation for task offloading and computation scaling in mobile edge computing. Mob Inform Syst, 2019:8172698.
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/FITEE.2300128
CLC number:
TP393
Download Full Text:
Downloaded:
428
Download summary:
<Click Here>Downloaded:
46Clicked:
520
Cited:
0
On-line Access:
2024-06-04
Received:
2023-02-28
Revision Accepted:
2024-06-04
Crosschecked:
2023-08-06
Tel: +86-571-87952276; Fax: +86-571-87952331; E-mail: jzus@zju.edu.cn
Copyright © 2000~ Journal of Zhejiang University-SCIENCE