數(shù)字孿生邊緣網(wǎng)絡(luò)端到端時(shí)延優(yōu)化的任務(wù)卸載與資源分配方法

李松; 李順; 王博文; 孫彥景

doi:10.11999/JEIT240344

數(shù)字孿生邊緣網(wǎng)絡(luò)端到端時(shí)延優(yōu)化的任務(wù)卸載與資源分配方法

doi: 10.11999/JEIT240344

李松^{1, 2, ,},
李順¹,
王博文¹,
孫彥景^{1, 2}

1.
中國(guó)礦業(yè)大學(xué)信息與控制工程學(xué)院徐州 221116
2.
徐州市智能安全與應(yīng)急協(xié)同工程研究中心徐州 221116

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(62071472, 62101556)，江蘇省自然科學(xué)基金(BK20210489)，中央高?；究蒲袠I(yè)務(wù)費(fèi)項(xiàng)目(2020ZDPYMS26)，江蘇省研究生科研與實(shí)踐創(chuàng)新計(jì)劃項(xiàng)目(KYCX24_2763)，中國(guó)礦業(yè)大學(xué)研究生創(chuàng)新計(jì)劃項(xiàng)目(2024WLJCRCZL133)，西安市網(wǎng)絡(luò)融合通信重點(diǎn)實(shí)驗(yàn)室開放基金項(xiàng)目(2022NCC-N103)，海南省省屬科研院所技術(shù)創(chuàng)新項(xiàng)目(KYYSGY2024-005)，工信部項(xiàng)目(CBG01N23-01-04)

詳細(xì)信息

作者簡(jiǎn)介:
李松：男，副教授，研究方向?yàn)楣I(yè)物聯(lián)網(wǎng)、邊緣計(jì)算等

李順：男，碩士生，研究方向?yàn)橐苿?dòng)邊緣計(jì)算、數(shù)字孿生等

王博文：男，副教授，研究方向?yàn)楣I(yè)物聯(lián)網(wǎng)、社交物聯(lián)網(wǎng)等

孫彥景：男，教授，研究方向?yàn)楣I(yè)物聯(lián)網(wǎng)、無線資源分配等

通訊作者:
李松　lisong@cumt.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問數(shù): 125
- HTML全文瀏覽量: 64
- PDF下載量: 6
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2024-04-29
- 修回日期: 2025-02-12
- 網(wǎng)絡(luò)出版日期: 2025-02-20

Task Offloading and Resource Allocation Method for End-to-End Delay Optimization in Digital Twin Edge Networks

LI Song^{1, 2
, ,},
LI Shun¹,
WANG Bowen¹,
SUN Yanjing^{1, 2}

1.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China
2.
Xuzhou Engineering Research Center of Intelligent Industry Safety and Emergency Collaboration, Xuzhou 221116, China

Funds: The National Natural Science Foundation of China (62071472, 62101556), Natural Science Foundation of Jiangsu Province of China (BK20210489), The Fundamental Research Funds for the Central Universities (2020ZDPYMS26), Funded by the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX24_2763), Funded by the Graduate Innovation Program of China University of Mining and Technology (2024WLJCRCZL133), The Xi’an Key Laboratory of Network Convergence Communication (2022NCC-N103), Project of Technical Innovation of Hainan Scientific Research Institutes (KYYSGY2024-005), The Ministry of Industry and Information Technology (CBG01N23-01-04)

摘要

摘要: 針對(duì)移動(dòng)邊緣計(jì)算(MEC)場(chǎng)景中任務(wù)卸載、計(jì)算和結(jié)果反饋全過程時(shí)延優(yōu)化問題，該文提出了一種數(shù)字孿生(DT)輔助的聯(lián)合MEC任務(wù)卸載、設(shè)備關(guān)聯(lián)與資源分配的端到端時(shí)延優(yōu)化方法。首先，在數(shù)字孿生邊緣網(wǎng)絡(luò)(DITEN)框架下，為包含傳感器、邊緣服務(wù)器以及執(zhí)行器構(gòu)成的邊緣計(jì)算網(wǎng)絡(luò)建立了物理模型與數(shù)字孿生模型，以及全過程邊緣網(wǎng)絡(luò)任務(wù)模型并推導(dǎo)了任務(wù)端到端時(shí)延，進(jìn)而建立了時(shí)延、能耗等約束下的端到端時(shí)延優(yōu)化問題。其次，為解決所提出的混合整數(shù)非凸優(yōu)化問題，將原問題分解為4個(gè)子問題，并提出了一種基于內(nèi)部凸近似方法和匈牙利算法的交替優(yōu)化算法。在DT輔助下聯(lián)合優(yōu)化了設(shè)備關(guān)聯(lián)、卸載比例、發(fā)射功率、傳輸帶寬以及DT估計(jì)處理速率。最后，仿真結(jié)果表明，與其他基準(zhǔn)方案相比，所提聯(lián)合優(yōu)化方案顯著降低了端到端時(shí)延。
- 移動(dòng)邊緣計(jì)算 /
- 數(shù)字孿生 /
- 任務(wù)卸載 /
- 資源分配 /
- 交替優(yōu)化
Abstract: Objective The rapid development of wireless communication and the Internet of Things (IoT) has led to significant growth in compute-intensive and delay-sensitive applications, which impose stricter latency requirements. However, local devices often face challenges in meeting these demands due to limitations in storage, computing power, and battery life. Mobile Edge Computing (MEC) has emerged as a key technology to address these issues. Despite its potential, the dynamic and complex nature of edge networks presents significant challenges in task offloading and resource allocation. DIgital Twin Edge Networks (DITEN), which map digital twins to physical devices in real-time, offer a promising solution. By integrating MEC with Digital Twin (DT) technology, this approach not only alleviates resource limitations in devices but also optimizes resource allocation in the digital domain, minimizing physical resource waste. This paper tackles the End-to-End (E2E) optimization problem in the offloading, computation, and result feedback process within edge computing networks. A DT-assisted joint task offloading, device association, and resource allocation scheme is proposed for E2E delay optimization, providing theoretical support for improving resource utilization in edge networks. Methods The optimization problem in this paper involves a non-convex objective function with both binary and continuous constraints, making it a mixed integer non-convex problem. To address this, the original problem is decomposed into four subproblems: computation and communication resource optimization, device association optimization, offloading decision optimization, and transmission bandwidth optimization. Within the Alternating Optimization (AO) framework, the Internal Convex Approximation (ICA) method is applied to convert the non-convex problem into a convex one. Additionally, the many-to-one matching problem is transformed into a one-to-one matching problem, and the Hungarian Algorithm (HA) is employed to solve the device association subproblem. Finally, the ICA-HA-AO is proposed to address the E2E delay optimization problem effectively. Results and Discussions The ICA-HA-AO algorithm approximates non-convex constraints as convex ones through constraint transformation and iteratively solves the original problem, determining optimal strategies for task offloading, device association, and resource allocation. Simulation results show that the ICA-HA-AO algorithm achieves optimal performance across varying task resource requirements, bandwidth, edge processing rates, and task volumes. Compared to the worst-performing benchmark scheme, delays are reduced by approximately 0.8 s, 1.5 s, 0.5 s, and 1.2 s, respectively (Fig. 5–Fig. 8). As the DT deviation increases, the delay also increases more significantly, with a rise of about 0.12 s when the deviation increases from 0.01 to 0.02, emphasizing the importance of setting the DT deviation (Fig. 9). When the number of devices remains constant and the number of Access Points (APs) increases, the delay continues to decrease, highlighting the significance of AP deployment in practice. Additionally, when the number of APs remains fixed and the number of devices increases, the delay increases accordingly. However, the ICA-HA-AO algorithm effectively controls the rate of delay increase. For instance, when the number of devices is 10, 15, and 20, the delay increase is reduced from 0.39 s to 0.21 s (Fig. 10). These results demonstrate that the ICA-HA-AO algorithm can more efficiently utilize and schedule resources, achieving optimal resource allocation. Conclusions This paper investigates the joint optimization problem of task offloading, device association, and resource allocation in DITEN. Firstly, within the edge computing network, physical and DT models are established for a network comprising sensors, edge servers, and actuators. A comprehensive task model is developed, and the E2E delay for tasks is derived. The optimization problem for minimizing E2E delay is then formulated, subject to constraints such as power and energy consumption. Secondly, to solve the proposed mixed integer non-convex optimization problem, the original problem is decomposed into four subproblems. Based on the ICA and HA methods, an ICA-HA-AO algorithm is proposed to solve the problem iteratively. Finally, simulation results demonstrate that the proposed ICA-HA-AO algorithm significantly reduces E2E delay and outperforms benchmark schemes. Future work may explore integrating this method with techniques to improve spectrum utilization, thereby further enhancing spectrum efficiency and overall performance in DITEN systems.
- Mobile Edge Computing (MEC) /
- Digital Twin (DT) /
- Task offloading /
- Resource allocation /
- Alternating optimization

HTML全文

圖 1 數(shù)字孿生邊緣網(wǎng)絡(luò)(DITEN)系統(tǒng)模型

下載: 全尺寸圖片幻燈片

圖 2 全過程任務(wù)模型

下載: 全尺寸圖片幻燈片

圖 3 端到端時(shí)延示意圖

下載: 全尺寸圖片幻燈片

圖 4 基于加邊補(bǔ)零法的二分圖最優(yōu)匹配過程

下載: 全尺寸圖片幻燈片

圖 5 任務(wù)所需計(jì)算資源與端到端時(shí)延的關(guān)系

下載: 全尺寸圖片幻燈片

圖 6 傳輸帶寬與端到端時(shí)延的關(guān)系

下載: 全尺寸圖片幻燈片

圖 7 服務(wù)器處理速率與端到端時(shí)延的關(guān)系

下載: 全尺寸圖片幻燈片

圖 8 任務(wù)量與端到端時(shí)延的關(guān)系

下載: 全尺寸圖片幻燈片

圖 9 不同DT偏差對(duì)端到端時(shí)延的影響

下載: 全尺寸圖片幻燈片

圖 10 設(shè)備數(shù)量不同的端到端時(shí)延對(duì)比

下載: 全尺寸圖片幻燈片

1 基于內(nèi)部凸近似的計(jì)算與通信資源分配算法

輸入：卸載因子$ \alpha $，關(guān)聯(lián)變量$ \pi $，傳輸帶寬$ \bar b,\underline b $，發(fā)射功率$ p $以及　計(jì)算頻率$ {\mathbf{f}} $；
初始化：迭代次數(shù)$ i = 0 $，容忍值$ \varepsilon $，最大迭代次數(shù)$ {I_{\max }} $
輸出：最優(yōu)功率和計(jì)算頻率$ ({p^},{{\mathbf{f}}^}) $
(1) while 1 do
(2) 　　求解問題式(24)的可行解$ ({p^{(i + 1)}},{{\mathbf{f}}^{(i + 1)}}) $；
(3) 　　$ i = i + 1 $
(4) 　if 收斂or$ i \gt {I_{\max }} $ then
(5) 　　break；
(6) 　end if
(7) end while

下載: 導(dǎo)出CSV

2 基于匈牙利算法的傳感器與AP關(guān)聯(lián)優(yōu)化算法

輸入：卸載因子$ \alpha $，傳輸帶寬$ \bar b,\underline b $，發(fā)射功率$ p $以及計(jì)算頻率$ {\mathbf{f}} $；
輸出：最優(yōu)關(guān)聯(lián)策略$ ({\pi ^*}) $
(1)給定傳感器數(shù)量K，AP數(shù)量M，AP能夠服務(wù)傳感器的最大數(shù) 　量N；
(2)每個(gè)AP虛擬成N個(gè)，形成數(shù)量為NM的虛擬AP集合；
(3)if $ K \lt NM $ then
(4) 　加邊補(bǔ)零，增加$ NM - K $個(gè)虛擬傳感器；
(5)end if
(6)執(zhí)行匈牙利算法。

下載: 導(dǎo)出CSV

3 基于內(nèi)部凸近似方法和匈牙利算法的ICA-HA-AO算法

輸入：卸載因子$ {\alpha ^{(0)}} $，關(guān)聯(lián)變量$ {\pi ^{(0)}} $，帶寬$ {\bar b^{(0)}},\underline b^{(0)} $，發(fā)射功率$ {p^{(0)}} $，計(jì)算頻率$ {{\mathbf{f}}^{(0)}} $，設(shè)置迭代次數(shù)$ i = 0 $，容忍值$ \varepsilon $和最大迭代次數(shù)$ {I_{\max }} $；
輸出：最優(yōu)資源分配$ ({\alpha ^},{\pi ^},{\bar b^},{\underline ^},{p^},{{\mathbf{f}}^}) $
(1) while 1 do
(2) 　給定$ ({\alpha ^{(i)}},{\pi ^{(i)}},{\bar b^{(i)}},{\underline b} ^{(i)}) $，利用算法1求解子問題SP1，得到最優(yōu)傳感器計(jì)算頻率以及AP的計(jì)算頻率和發(fā)射功率$ ({p^{^{(i + 1)}}},{{\mathbf{f}}^{^{(i + 1)}}}) $；
(3) 　給定$ ({{\mathbf{f}}^{(i + 1)}},{p^{(i + 1)}},{\alpha ^{(i)}},{\bar b^{(i)}},\underline b^{(i)}) $，利用算法2求解子問題SP2，得到最優(yōu)傳感器與AP關(guān)聯(lián)策略$ ({\pi ^{^{(i + 1)}}}) $；
(4) 　給定$ ({{\mathbf{f}}^{(i + 1)}},{p^{(i + 1)}},{\pi ^{(i + 1)}},{\bar b^{(i)}},{\underline b ^{(i)}}) $，利用內(nèi)點(diǎn)法求解子問題SP3，得到最優(yōu)卸載決策$ ({\alpha ^{^{(i + 1)}}}) $；
(5) 　給定$ ({{\mathbf{f}}^{(i + 1)}},{p^{(i + 1)}},{\pi ^{(i + 1)}},{\alpha ^{(i)}}) $，利用內(nèi)點(diǎn)法求解子問題SP4，得到最優(yōu)上下行帶寬$ ({\bar b^{(i + 1)}},{\underline b^{(i + 1)}}) $；
(6) 　$ i = i + 1 $
(7) 　　if 收斂 or $ i \gt {I_{\max }} $ then
(8) 　　　break;
(9) 　　end if
(10) end while

下載: 導(dǎo)出CSV

表 1 仿真參數(shù)

參數(shù)名	參數(shù)值	參數(shù)名	參數(shù)值
傳感器發(fā)射功率$ {\bar p_k} $	10 dBm^[8]	傳感器最大計(jì)算頻率$ F_{\max }^{\rm{se} } $	3 GHz^[7]
AP最大發(fā)射功率$ {P_{\max }} $	40 dBm^[18]	AP最大計(jì)算頻率$ F_{\max }^{\rm{AP} } $	10 GHz^[7]
輸入任務(wù)量$ {I_k} $	100 Mbit^[18]	路徑損耗$ {\beta _0} $	–30 dB^[14]
任務(wù)所需計(jì)算資源$ {C_k} $	960×10⁶ cycle^[7]	參考距離$ {d_0} $	10 m^[9]
傳輸總帶寬$ B $	20 MHz^[18]	噪聲功率$ {N_0} $	–174 dBm/Hz^[18]
最大時(shí)延與能耗$ {T_{\max }},{E_{\max }} $	2 s, 1.5 J	有效交換電容系數(shù)$ \xi $	10^–28[9]

下載: 導(dǎo)出CSV

參考文獻(xiàn)(19)

[1]	DJIGAL H, XU Jia, LIU Linfeng, et al. Machine and deep learning for resource allocation in multi-access edge computing: A survey[J]. IEEE Communications Surveys & Tutorials, 2022, 24(4): 2449–2494. doi: 10.1109/COMST.2022.3199544.
[2]	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.
[3]	WANG Zhiying, SUN Gang, SU Hanyue, et al. Low-latency scheduling approach for dependent tasks in MEC-enabled 5G vehicular networks[J]. IEEE Internet of Things Journal, 2024, 11(4): 6278–6289. doi: 10.1109/JIOT.2023.3309940.
[4]	DENG Xiaoheng, YIN Jian, GUAN Peiyuan, et al. Intelligent delay-aware partial computing task offloading for multiuser industrial internet of things through edge computing[J]. IEEE Internet of Things Journal, 2023, 10(4): 2954–2966. doi: 10.1109/JIOT.2021.3123406.
[5]	MEI Jing, TONG Zhao, LI Kenli, et al. Energy-efficient heuristic computation offloading with delay constraints in mobile edge computing[J]. IEEE Transactions on Services Computing, 2023, 16(6): 4404–4417. doi: 10.1109/TSC.2023.3324604.
[6]	ZHANG Haibo, LIU Xiangyu, XU, Yongjun, et al. Partial offloading and resource allocation for MEC-assisted vehicular networks[J]. IEEE Transactions on Vehicular Technology, 2024, 73(1): 1276–1288. doi: 10.1109/TVT.2023.3306939.
[7]	VAN HUYNH D, NGUYEN V D, KHOSRAVIRAD S R, et al. URLLC edge networks with joint optimal user association, task offloading and resource allocation: A digital twin approach[J]. IEEE Transactions on Communications, 2022, 70(11): 7669–7682. doi: 10.1109/TCOMM.2022.3205692.
[8]	VAN HUYNH D, NGUYEN V D, CHATZINOTAS S, et al. Joint communication and computation offloading for ultra-reliable and low-latency with multi-tier computing[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(2): 521–537. doi: 10.1109/JSAC.2022.3227088.
[9]	LI Song, SUN Weibin, SUN Yanjing, et al. Energy-efficient task offloading using dynamic voltage scaling in mobile edge computing[J]. IEEE Transactions on Network Science and Engineering, 2021, 8(1): 588–598. doi: 10.1109/TNSE.2020.3046014.
[10]	ZHANG Yongchao, HU Jia, and MIN Geyong. Digital twin-driven intelligent task offloading for collaborative mobile edge computing[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(10): 3034–3045. doi: 10.1109/JSAC.2023.3310058.
[11]	唐倫, 單貞貞, 文明艷, 等. 工業(yè)物聯(lián)網(wǎng)中數(shù)字孿生輔助任務(wù)卸載算法[J]. 電子與信息學(xué)報(bào), 2024, 46(4): 1296–1305. doi: 10.11999/JEIT230317. TANG Lun, SHAN Zhenzhen, WEN Mingyan, et al. Digital twin-assisted task offloading algorithms for the industrial internet of things[J]. Journal of Electronics & Information Technology, 2024, 46(4): 1296–1305. doi: 10.11999/JEIT230317.
[12]	TANG Fengxiao, CHEN Xuehan, RODRIGUES T K, et al. Survey on digital twin edge networks (DITEN) toward 6G[J]. IEEE Open Journal of the Communications Society, 2022, 3: 1360–1381. doi: 10.1109/OJCOMS.2022.3197811.
[13]	張彥, 盧云龍. 數(shù)字孿生邊緣網(wǎng)絡(luò)[J]. 中興通訊技術(shù), 2023, 29(3): 21–25. doi: 10.12142/ZTETJ.202303005. ZHANG Yan and LU Yunlong. Digital twin edge networks[J]. ZTE Technology Journal, 2023, 29(3): 21–25. doi: 10.12142/ZTETJ.202303005.
[14]	蘇健, 錢震, 李斌. 數(shù)字孿生使能的智能超表面邊緣計(jì)算網(wǎng)絡(luò)任務(wù)卸載[J]. 電子與信息學(xué)報(bào), 2022, 44(7): 2416–2424. doi: 10.11999/JEIT220180. SU Jian, QIAN Zhen, and LI Bin. Digital twin empowered task offloading for RIS-assisted edge computing networks[J]. Journal of Electronics & Information Technology, 2022, 44(7): 2416–2424. doi: 10.11999/JEIT220180.
[15]	DAI Yueyue, ZHANG Ke, MAHARJAN S, et al. Deep reinforcement learning for stochastic computation offloading in digital twin networks[J]. IEEE Transactions on Industrial Informatics, 2021, 17(7): 4968–4977. doi: 10.1109/TII.2020.3016320.
[16]	LU Yunlong, MAHARJAN S, and ZHANG Yan. Adaptive edge association for wireless digital twin networks in 6G[J]. IEEE Internet of Things Journal, 2021, 8(22): 16219–16230. doi: 10.1109/JIOT.2021.3098508.
[17]	SUN Wen, ZHANG Haibin, WANG Rong, et al. Reducing offloading latency for digital twin edge networks in 6G[J]. IEEE Transactions on Vehicular Technology, 2020, 69(10): 12240–12251. doi: 10.1109/TVT.2020.3018817.
[18]	SUN Yaping, XU Jie, and CUI Shuguang. Joint user association and resource allocation optimization for MEC-enabled IoT networks[C]. Proceedings of the ICC 2022 - IEEE International Conference on Communications, Seoul, Korea, 2022: 4884–4889. doi: 10.1109/ICC45855.2022.9839276.
[19]	DONG Rui, SHE Changyang, HARDJAWANA W, et al. Deep learning for hybrid 5G services in mobile edge computing systems: Learn from a digital twin[J]. IEEE Transactions on Wireless Communications, 2019, 18(10): 4692–4707. doi: 10.1109/TWC.2019.2927312.