異步移動(dòng)邊緣計(jì)算網(wǎng)絡(luò)中的聯(lián)合任務(wù)調(diào)度與計(jì)算資源分配優(yōu)化策略

王汝言; 楊安琪; 吳大鵬; 唐桐; 祝志遠(yuǎn)

doi:10.11999/JEIT240685

異步移動(dòng)邊緣計(jì)算網(wǎng)絡(luò)中的聯(lián)合任務(wù)調(diào)度與計(jì)算資源分配優(yōu)化策略

doi: 10.11999/JEIT240685 cstr: 32379.14.JEIT240685

1.
重慶郵電大學(xué)通信與信息工程學(xué)院重慶 400065
2.
先進(jìn)網(wǎng)絡(luò)與智能互聯(lián)技術(shù)重慶市高校重點(diǎn)實(shí)驗(yàn)室重慶 400065
3.
泛在感知與互聯(lián)重慶市重點(diǎn)實(shí)驗(yàn)室重慶 400065

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(62271096, U20A20157)，重慶市自然科學(xué)基金(CSTB2023NSCQ-LZX0134)，重慶市高校創(chuàng)新研究群體(CXQT20017)，重郵信通青創(chuàng)團(tuán)隊(duì)支持計(jì)劃(SCIE-QN-2022-04)，重慶市教委科學(xué)技術(shù)研究項(xiàng)目(KJQN202300632)，重慶市博士后特別資助項(xiàng)目(2022CQBSHTB2057)，重慶市研究生科研創(chuàng)新項(xiàng)目(CYB22250)

詳細(xì)信息

作者簡(jiǎn)介:
王汝言：男，教授，研究方向?yàn)榉涸诰W(wǎng)絡(luò)，多媒體信息處理等

楊安琪：女，碩士生，研究方向?yàn)橐苿?dòng)邊緣計(jì)算

吳大鵬：男，教授，研究方向?yàn)榉涸跓o(wú)線網(wǎng)絡(luò)、社會(huì)計(jì)算等

唐桐：男，講師，研究方向?yàn)橐曨l編碼傳輸?shù)?/p>
祝志遠(yuǎn)：男，講師，研究方向?yàn)榭尚胚吘売?jì)算等

通訊作者:
吳大鵬　wudp@cqupt.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問(wèn)數(shù): 441
- HTML全文瀏覽量: 177
- PDF下載量: 65
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-08-02
- 修回日期: 2025-01-25
- 網(wǎng)絡(luò)出版日期: 2025-02-15
- 刊出日期: 2025-02-28

Joint Task Scheduling and Computing Resource Allocation Optimization Strategy in Asynchronous Mobile Edge Computing Networks

1.
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
2.
Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China, Chongqing 400065, China
3.
Chongqing Key Laboratory of Ubiquitous Sensing and Networking, Chongqing 400065, China

Funds: The National Natural Science Foundation of China (62271096, U20A20157), The Natural Science Foundation of Chongqing(CSTB2023NSCQ-LZX0134), The University Innovation Research Group of Chongqing (CXQT20017), The Youth Innovation Group Support Program of ICE Discipline of CQUPT (SCIE-QN-2022-04), The Science and Technology Research Program of Chongqing Municipal Education Commission (KJQN202300632), Chongqing Postdoctoral Special Funding Project (2022CQBSHTB2057), Chongqing Postgraduate Research and Innovation Project (CYB22250)

摘要

摘要: 移動(dòng)邊緣計(jì)算(MEC)通過(guò)將密集型任務(wù)從傳感器卸載到附近邊緣服務(wù)器，來(lái)增強(qiáng)本地的計(jì)算能力，延長(zhǎng)其電池壽命。然而，在面向無(wú)線傳感器網(wǎng)等時(shí)變環(huán)境中，任務(wù)之間的異構(gòu)性可能會(huì)導(dǎo)致通信低效率、高時(shí)延等問(wèn)題。為此，該文提出一種異步移動(dòng)邊緣計(jì)算網(wǎng)絡(luò)中的聯(lián)合任務(wù)調(diào)度與計(jì)算資源分配優(yōu)化策略，該策略實(shí)時(shí)感知任務(wù)信息年齡和能耗，將異步邊緣卸載問(wèn)題數(shù)學(xué)建模為NP難(NP-hard problem)的混合整數(shù)規(guī)劃問(wèn)題，并提出基于混合動(dòng)作優(yōu)勢(shì)演員-評(píng)論家(HA2C)強(qiáng)化學(xué)習(xí)算法的任務(wù)調(diào)度和計(jì)算資源分配方案解決該問(wèn)題。仿真結(jié)果表明，該文方法能顯著降低異步卸載網(wǎng)絡(luò)的平均信息年齡和能耗，滿足無(wú)線傳感器網(wǎng)絡(luò)對(duì)任務(wù)時(shí)效性的要求。
- 異步移動(dòng)邊緣計(jì)算 /
- 無(wú)線傳感器網(wǎng)絡(luò) /
- 平均信息年齡 /
- 平均能耗 /
- 混合動(dòng)作強(qiáng)化學(xué)習(xí)
Abstract: Objective Mobile Edge Computing (MEC) is a key technology for addressing the limited computing capabilities and energy constraints of wireless devices. MEC improves local computing performance and extends battery life by offloading computationally intensive tasks from sensors to nearby edge servers. However, in dynamic environments such as anomaly detection, environmental monitoring, and vehicle positioning, task heterogeneity becomes a significant factor limiting performance. For example, the asynchrony of task generation times can result in issues such as low communication efficiency and increased latency. Furthermore, traditional latency measurement techniques often fail to accurately assess task timeliness. To address these challenges, this paper proposes a strategy for the joint optimization of task scheduling and computational resource allocation in asynchronous MEC networks. The proposed strategy adaptively optimizes task scheduling and resource allocation, minimizing the average information age and energy consumption, thereby enhancing overall system performance. Methods This paper focuses on age-aware asynchronous MEC offloading and resource allocation. Specifically, a mathematical model is formulated based on the First Come First Served (FCFS) queuing principle, considering the order of asynchronous task arrivals. This model optimizes task scheduling and computational resource allocation in asynchronous MEC offloading, with the goal of minimizing the Average Age of Information (AoI) and average energy consumption. In dynamic asynchronous MEC, optimization problems are inherently complex. When these tasks involve both binary offloading decisions and continuous resource allocation, the combination of actions further complicates problem-solving, transforming it into a non-convex optimization challenge. Additionally, the actor network of the Actor-Critic algorithm (A2C) adapts its output layer to either a Categorical or Gaussian distribution, depending on whether the action space is discrete or continuous. This paper proposes a Hybrid Advantage Actor-Critic (HA2C) Deep Reinforcement Learning (DRL) algorithm, which effectively optimizes dynamic task scheduling and computational resource allocation strategies as tasks are generated. Results and Discussions In the simulations, the performance of the algorithm is evaluated by comparing four different strategies: random strategy, DRL strategy, delay strategy, and synchronous strategy. The following conclusions are drawn: 1. Average AoI is more sensitive to task timeliness than latency metrics. It not only accounts for the time interval between task generation and reception but also considers the intervals between task generations, offering a better measure of task timeliness. Moreover, the HA2C algorithm effectively balances the timeliness of information and energy consumption, achieving optimal average AoI and energy consumption (Figure 4). 2. The hybrid action space of the HA2C algorithm is better suited for adapting to a growing number of devices. As the number of devices increases, HA2C significantly outperforms multi-agent algorithms and traditional A2C algorithms (Figure 5). This is because the number of actions in a discrete action space grows exponentially with the device count, ultimately leading to the curse of dimensionality, which degrades the performance of discrete DRL algorithms. 3. In the asynchronous MEC model, task generation occurs instantaneously and asynchronously. This setup allows a large amount of computational resources to be concentrated on tasks that arrive earlier, maximizing the utilization of MEC resources. As a result, asynchronous models outperform synchronous models in terms of both average AoI and average energy consumption (Figure 6). In conclusion, these experiments confirm that, compared to synchronous models, asynchronous models not only significantly improve computational efficiency but also effectively reduce energy consumption. Furthermore, the proposed HA2C algorithm proves to be highly effective in solving the asynchronous edge offloading and resource allocation problems, maintaining efficient performance even as the number of devices increases. Conclusions This paper leverages MEC to address the limited computational capacity and energy of wireless devices. Specifically, the paper considers scenarios where Wireless Sensor Network (WSN) edge computing systems continuously collect and process data to monitor real-time changes in the detection environment. In these contexts, the paper focuses on the heterogeneous generation times of sensor tasks deployed at different locations. The optimization goal is to minimize both average information age and energy consumption, achieved through task scheduling and adaptive resource allocation. The HA2C algorithm is designed to handle dynamic and unpredictable system changes while simultaneously managing both continuous and discrete actions. Simulation results demonstrate that the algorithm significantly reduces average information age and energy consumption in asynchronous offloading networks, while meeting the timeliness requirements of tasks in WSNs.
- Asynchronous Mobile Edge Computing (MEC) /
- Wireless Sensor Networks (WSNs) /
- Average Age of Information (AoI) /
- Average energy consumption /
- Hybrid action reinforcement learning

HTML全文

圖 1 異步MEC系統(tǒng)模型圖

下載: 全尺寸圖片幻燈片

圖 2 信息年齡隨時(shí)間變化

下載: 全尺寸圖片幻燈片

圖 3 HA2C強(qiáng)化學(xué)習(xí)

下載: 全尺寸圖片幻燈片

圖 4 傳感器數(shù)量為5，不同的MEC服務(wù)器計(jì)算能力的平均AoI和平均能耗的變化趨勢(shì)

下載: 全尺寸圖片幻燈片

圖 5 MEC服務(wù)器計(jì)算能力為20 GHz，不同傳感器數(shù)量對(duì)平均AoI和平均能耗的影響

下載: 全尺寸圖片幻燈片

圖 6 MEC服務(wù)器計(jì)算能力為20 GHz，不同傳感器數(shù)量下的同步卸載和異步卸載模型性能

下載: 全尺寸圖片幻燈片

參考文獻(xiàn)(19)

[1]	DEMEDEIROS K, HENDAWI A, and ALVAREZ M. A survey of AI-based anomaly detection in IoT and sensor networks[J]. Sensors, 2023, 23(3): 1352. doi: 10.3390/s23031352.
[2]	ZHANG Guangyang, SHEN Chao, SHI Qingjiang, et al. AoI minimization for WSN data collection with periodic updating scheme[J]. IEEE Transactions on Wireless Communications, 2023, 22(1): 32–46. doi: 10.1109/TWC.2022.3190986.
[3]	KANDRIS D, NAKAS C, VOMVAS D, et al. Applications of wireless sensor networks: An up-to-date survey[J]. Applied System Innovation, 2020, 3(1): 14. doi: 10.3390/asi3010014.
[4]	MACH P and BECVAR Z. Mobile edge computing: A survey on architecture and computation offloading[J]. IEEE Communications Surveys & Tutorials, 2017, 19(3): 1628–1656. doi: 10.1109/COMST.2017.2682318.
[5]	HORTELANO D, DE MIGUEL I, BARROSO R J D, et al. A comprehensive survey on reinforcement-learning-based computation offloading techniques in edge computing systems[J]. Journal of Network and Computer Applications, 2023, 216: 103669. doi: 10.1016/j.jnca.2023.103669.
[6]	HE Xingqiu, WANG Sheng, WANG Xiong, et al. Age-based scheduling for monitoring and control applications in mobile edge computing systems[C]. IEEE Conference on Computer Communications, London, UK, 2022: 1009–1018. doi: 10.1109/INFOCOM48880.2022.9796654.
[7]	QIN Xiaoqi, LI Yanlin, SONG Xianxin, et al. Timeliness of information for computation-intensive status updates in task-oriented communications[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(3): 623–638. doi: 10.1109/JSAC.2022.3229431.
[8]	YATES R D, SUN Yin, BROWN D R, et al. Age of information: An introduction and survey[J]. IEEE Journal on Selected Areas in Communications, 2021, 39(5): 1183–1210. doi: 10.1109/JSAC.2021.3065072.
[9]	LI Rui, MA Qian, GONG Jie, et al. Age of processing: Age-driven status sampling and processing offloading for edge-computing-enabled real-time IoT applications[J]. IEEE Internet of Things Journal, 2021, 8(19): 14471–14484. doi: 10.1109/JIOT.2021.3064055.
[10]	LIU Wentao, LI Dong, LIANG Tianhao, et al. Joint trajectory and scheduling optimization for age of synchronization minimization in UAV-assisted networks with random updates[J]. IEEE Transactions on Communications, 2023, 71(11): 6633–6646. doi: 10.1109/TCOMM.2023.3297198.
[11]	XIE Mangang, GONG Jie, and MA Xiao. Is the packetized transmission efficient? An age-energy perspective[C]. IEEE Conference on Computer Communications Workshops, Toronto, Canada, 2020: 329–333. doi: 10.1109/INFOCOMWKSHPS50562.2020.9162651.
[12]	YOU Changsheng, ZENG Yong, ZHANG Rui, et al. Asynchronous mobile-edge computation offloading: Energy-efficient resource management[J]. IEEE Transactions on Wireless Communications, 2018, 17(11): 7590–7605. doi: 10.1109/TWC.2018.2868710.
[13]	CANG Yihan, GAO Songtao, YU Yiming, et al. Joint user scheduling and resource optimization in MEC networks with asynchronous computing[C]. 2023 IEEE International Conference on Communications Workshops, Rome, Italy, 2023: 151–157. doi: 10.1109/ICCWorkshops57953.2023.10283775.
[14]	QIN Xiaoqi, LI Yanlin, MA Nan, et al. Timeliness-oriented asynchronous task offloading in UAV-edge-computing systems[J]. IEEE Transactions on Network Science and Engineering, 2024, 11(1): 900–912. doi: 10.1109/TNSE.2023.3310055.
[15]	TAN Lin, KUANG Zhufang, ZHAO Lian, et al. Energy-efficient joint task Offloading and resource allocation in OFDMA-based collaborative edge computing[J]. IEEE Transactions on Wireless Communications, 2022, 21(3): 1960–1972. doi: 10.1109/TWC.2021.3108641.
[16]	LI Ji, GAO Hui, LV Tiejun, et al. Deep reinforcement learning based computation offloading and resource allocation for MEC[C]. 2018 IEEE Wireless Communications and Networking Conference, Barcelona, Spain, 2018: 1–6. doi: 10.1109/WCNC.2018.8377343.
[17]	CHEN Xu, JIAO Lei, LI Wenzhong, et al. Efficient multi-user computation offloading for mobile-edge cloud computing[J]. IEEE/ACM Transactions on Networking, 2016, 24(5): 2795–2808. doi: 10.1109/TNET.2015.2487344.
[18]	LIU Wenshuai, LI Bin, XIE Wancheng, et al. Energy efficient computation offloading in aerial edge networks with multi-agent cooperation[J]. IEEE Transactions on Wireless Communications, 2023, 22(9): 5725–5739. doi: 10.1109/TWC.2023.3235997.
[19]	MNIH V, BADIA A P, MIRZA M, et al. Asynchronous methods for deep reinforcement learning[C]. The 33rd International Conference on Machine Learning, New York City, USA, 2016: 1928–1937.