能量感知与注意力驱动的边端协同推理与资源分配

刘医铭; 田杰; 李腆腆; 周晓天; 张海霞

doi:10.11999/JEIT260086

能量感知与注意力驱动的边端协同推理与资源分配

doi: 10.11999/JEIT260086 cstr: 32379.14.JEIT260086

刘医铭^1,,
田杰^1, ,,
李腆腆¹,
周晓天^{2, 3},
张海霞^{2, 3}

1.
山东师范大学通信与电子工程学院济南 250358
2.
山东大学智能通信技术研究院济南 250100
3.
山东大学智能通信与感算融合重点实验室济南 250100

基金项目: 国家自然科学基金项目(62271295, U22A203, U24A20212)，山东省泰山学者计划项目(No.tsqn202408137)

详细信息

作者简介:
刘医铭：男，硕士生，研究方向为边缘计算、智能通信等，邮箱　1016969487@qq.com

田杰：女，教授，研究方向为智能通信与网络，无线资源管理，边缘智能计算等，邮箱tianjie@sdnu.edu.cn

李腆腆：女，副教授，研究方向为超可靠低时延通信、通信-感知-计算一体化设计等

周晓天：男，教授，研究方向为无线通信与网络、边缘计算与智能通信等

张海霞：女，教授，研究方向为无线通信与网络、无线资源管理、智能通信技术等

通讯作者:
田杰　tianjie@sdnu.edu.cn

中图分类号: TN929.5; TP18
计量
- 文章访问数: 22
- HTML全文浏览量: 5
- PDF下载量: 3
- 被引次数: 0
出版历程
- 收稿日期: 2026-01-23
- 修回日期: 2026-07-31
- 录用日期: 2026-08-10
- 网络出版日期: 2026-08-12

Energy-Aware and Attention-Driven Edge–End Collaborative Inference and Resource Allocation

LIU Yiming^1
,,
TIAN Jie^{1
, ,},
LI Tiantian¹,
ZHOU Xiaotian^{2, 3},
ZHANG Haixia^{2, 3}

1.
School of Communication and Electronic Engineering, Shandong Normal University, Jinan 250358, China
2.
Institute of Intelligent Communication Technologies, Shandong University, Jinan 250100, China
3.
Shandong Key Laboratory of Intelligent Communication and Sensing-Computing Integration, Jinan 250100, China

Funds: The National Natural Science Foundation of China(62271295, U22A203,U24A20212), Taishan Scholar Program of Shandong Province(No.tsqn202408137)

摘要

摘要: 针对移动边缘计算环境中计算密集型深度神经网络推理任务面临的通算资源受限与边缘服务器长期能耗约束等挑战，该文提出一种能量感知与注意力驱动的边端协同推理与资源分配方法，旨在最小化多用户推理任务的长期平均端到端处理时延。首先，基于李雅普诺夫优化理论构建边缘端虚拟能量赤字队列，量化能耗预算偏差，将长期能耗硬约束转化为单时隙内的动态惩罚权重，实现对模型分割点的实时能量感知调节。其次，设计基于键-值-查询范式的联合注意力机制，综合考量任务紧急度、剩余计算量及边缘端能量赤字状态，动态生成资源分配权重，实现上行带宽与边缘算力的快速协同分配。仿真实验表明，该方法能够在严格遵守长期能耗预算的前提下，提升通算资源利用效率，在不同负载场景下显著降低多用户推理任务的平均端到端时延。
- 移动边缘计算 /
- 长期能耗约束 /
- 协同推理 /
- 资源分配
Abstract: Objective The perception and decision-making capabilities of mobile intelligent applications have been significantly improved by the development of Deep Neural Networks (DNN). Nevertheless, these applications often have high computational loads, which greatly strain mobile terminals with constrained latency and energy consumption. Due to limited wireless bandwidth and edge computing power, severe resource contention is inevitable in multi-user concurrent scenarios, even though mobile edge computing (MEC) lowers latency pressure by moving tasks from the edge to the terminal. More importantly, because edge servers have limited resources, strict budget control of their long-term energy consumption is necessary to ensure the system's dependability and long-term operational efficiency.An energy-aware and attention-driven edge-to-edge collaborative inference and resource allocation technique is proposed in this paper. The majority of research ignores the system's long-term energy consumption limitations in favor of maximizing instantaneous performance. This approach greatly lowers the average end-to-end latency of multi-user inference tasks under various load scenarios and greatly increases the utilization efficiency of general computing resources while closely adhering to the long-term energy budget. Methods Based on the DNN collaborative inference model in an edge environment, this paper models the problem as minimizing the long-term average end-to-end processing latency of all user inference tasks, under the premise of satisfying the long-term energy consumption budget constraint of the ES system. This optimization problem and energy consumption constraint both involve long-term averages and stochasticity, and the DNN model partitioning and general computing resource allocation decisions are highly coupled. Therefore, this paper adopts Lyapunov optimization theory to transform this complex problem into a more manageable single-slot deterministic optimization problem. In order to jointly finish the DNN partitioning and general computing resource allocation decisions within each time slot, this paper develops a Joint Collaborative Inference and Resource Allocation Algorithm (JCIRA). There are three steps in the algorithm (Algorithm 1). To determine the ideal DNN model partitioning point for the task, the first step balances the estimated latency against energy penalties based on the comprehensive cost function. Task urgency, remaining computational load, data volume, and global energy deficit state are all mapped into high-dimensional feature vectors in the second stage, which presents a joint attention mechanism based on the key-query-value paradigm. To accomplish cooperative distribution of general computing resources, the matching degree is computed using a scaled dot product attention mechanism. In order to improve the system's utilization rate of general computing resources and lower the average end-to-end latency of multi-user inference tasks while closely adhering to long-term energy consumption constraints, the third stage creates a closed-loop decision-making process by monitoring execution progress and updating queue status. Results and Discussions In this simulation experiment, the task arrival process is random and has a Poisson distribution. In this experiment, three distinct deep neural network models were employed: ResNet18, MobileNetV2, and EfficientNet-B0. When compared to other algorithms, JCIRA's actual energy consumption under various load scenarios consistently falls below the budget threshold, demonstrating the proposed algorithm's ability to manage long-term energy consumption constraints (Fig. 2). Furthermore, JCIRA's virtual queue length is always brief (Fig. 3). Among all schemes that meet the energy consumption constraints, JCIRA's latency is consistently below the 300 ms QoS threshold (Fig. 4). It performs better and successfully resolves the problem of other algorithms' insufficient processing power under heavy loads. Finally, the algorithm maintains the highest task completion rate even with 1300 concurrent tasks in a high load scenario (Fig. 5). Conclusions To address the challenges of limited computing resources and long-term energy consumption constraints in DNN collaborative inference within a MEC environment, this paper proposes an energy-aware and attention-driven edge-end collaborative inference and resource allocation method. The long-term energy consumption hard constraint is separated into a low-complexity single-slot deterministic optimization subproblem using Lyapunov optimization theory. In order to accomplish systematic scheduling of DNN model partitioning and computing resources, a joint optimization algorithm called JCIRA is created. Simulation results show that the suggested approach significantly lowers the average end-to-end latency of multi-user inference tasks under different load conditions and efficiently optimizes the use of computing resources while guaranteeing strict satisfaction of long-term energy consumption constraints.
- Mobile Edge Computing (MEC) /
- long-term energy constraint /
- collaborative inference /
- resource allocation

HTML全文

图 1 系统模型图

下载: 全尺寸图片幻灯片

图 2 不同负载下ES能耗对比

下载: 全尺寸图片幻灯片

图 3 能量赤字队列变化

下载: 全尺寸图片幻灯片

图 4 不同负载下端到端时延对比

下载: 全尺寸图片幻灯片

图 5 不同算法下的任务完成率

下载: 全尺寸图片幻灯片

1 JCIRA

输入：任务到达集合$ \{{J}_{k}(t)\} $，系统带宽$ {B}_{\text{total}} $，用户设备与服务器算力参数，能耗预算$ {E}_{\text{budget}} $，控制参数$ V $
输出：最优决策变量集$ {\Pi }^{}=\{{p}_{k}{}^{}(t),B_{k}^{\text{alloc}}{}^{}(t),F_{\text{ES,}k}^{\text{alloc}}{}^{}(t)\} $
1: 系统初始化能量赤字队列$ {Q}_{\text{e}}(0)\leftarrow 0 $, ES负载$ {L}_{\text{ES}}(0)\leftarrow 0 $;
2: for 时隙$ t=0,1,2,\cdots $do
3: 　获取当前时隙的待处理任务集合$ {J}_{\text{pending}}(t) $;
4: 　if $ {J}_{\text{pending}}(t) $非空 do
5: 　　阶段一：能量感知的DNN划分决策。对集合中每个未确定划分点的任务$ {J}_{k}(t) $,确定其最优划分点$ p_{k}^{*}(t) $;
6: 　　阶段二：联合注意力驱动的通算资源分配。针对$ {J}_{\text{pending}}(t) $联合分配上行带宽$ B_{k}^{\mathrm{alloc}}(t) $和ES计算资源$ F_{\text{ES},k}^{\text{alloc}}(t) $；
7: 　　阶段三：任务执行与状态更新。根据所分配的资源并行执行任务，并更新任务的剩余工作量；
8: 统计当前时隙ES的总能耗$ E_{\text{ES}}^{\text{actual}}(t) $;
9: 根据式(5)更新能量赤字队列$ {Q}_{\text{e}}(t+1) $;
10: 更新下一时隙的ES初始负载$ {L}_{\text{ES}}(t+1) $;

下载: 导出CSV

参考文献(24)

[1]	陈佳美, 孙慧雯, 李玉峰, 等. 基于双深度Q网络算法的无人机辅助密集网络资源优化策略[J]. 电子与信息学报, 2025, 47(8): 2621–2629. doi: 10.11999/JEIT250021. CHEN Jiamei, SUN Huiwen, LI Yufeng, et al. Double deep q network algorithm-based unmanned aerial vehicle-assisted dense network resource optimization strategy[J]. Journal of Electronics & Information Technology, 2025, 47(8): 2621–2629. doi: 10.11999/JEIT250021.
[2]	MAO Yuyi, YU Xianghao, HUANG Kaibin, et al. Green edge AI: A contemporary survey[J]. Proceedings of the IEEE, 2024, 112(7): 880–911. doi: 10.1109/JPROC.2024.3437365.
[3]	DAI Penglin, HAN Biao, LI Ke, et al. Joint optimization of device placement and model partitioning for cooperative DNN inference in heterogeneous edge computing[J]. IEEE Transactions on Mobile Computing, 2025, 24(1): 210–226. doi: 10.1109/TMC.2024.3457793.
[4]	YE Dongmei, SUN Zhengqing, ZHONG Weifeng, et al. Optimal flight speed scheduling and battery swapping in UAV-enabled mobile edge computing[J]. IEEE Transactions on Mobile Computing, 2026, 25(1): 948–960. doi: 10.1109/TMC.2025.3601743.
[5]	QIU Qijie, LI Lingjie, XIAO Zhijiao, et al. Joint service caching and task allocation in digital twin-enabled mobile edge computing systems: A bilevel optimization approach[J]. IEEE Transactions on Consumer Electronics, 2025, 71(4): 9208–9220. doi: 10.1109/TCE.2025.3622657.
[6]	RZIG I, JAAFAR W, JEBALIA M, et al. Energy-efficient vehicular task offloading using multi-mode MEC and RIS-equipped aerial platforms[J]. IEEE Open Journal of the Communications Society, 2025, 6: 7604–7619. doi: 10.1109/OJCOMS.2025.3606340.
[7]	XU Xiaodong, YAN Kaiwen, HAN Shujun, et al. Learning-based edge-device collaborative DNN inference in IoVT networks[J]. IEEE Internet of Things Journal, 2024, 11(5): 7989–8004. doi: 10.1109/JIOT.2023.3317785.
[8]	FANG Yujie, LI Meng, SI Pengbo, et al. Computational offloading and resource allocation for Internet of vehicles based on UAV-assisted mobile edge computing system[J]. China Communications, 2025, 22(9): 333–351. doi: 10.23919/JCC.ja.2022-0656.
[9]	卢先领, 李德康. 面向大规模多接入边缘计算场景的任务卸载算法[J]. 电子与信息学报, 2025, 47(1): 116–127. doi: 10.11999/JEIT240624. LU Xianling and LI Dekang. Task offloading algorithm for large-scale multi-access edge computing scenarios[J]. Journal of Electronics & Information Technology, 2025, 47(1): 116–127. doi: 10.11999/JEIT240624.
[10]	SUN Yanzan, QIU Jiacheng, PAN Guangjin, et al. Energy optimization of multitask DNN inference in MEC-assisted XR devices: A Lyapunov-guided reinforcement learning approach[J]. IEEE Internet of Things Journal, 2025, 12(11): 17499–17513. doi: 10.1109/JIOT.2025.3536879.
[11]	LI Jing, LIANG Weifa, LI Yuchen, et al. Throughput maximization of delay-aware DNN inference in edge computing by exploring DNN model partitioning and inference parallelism[J]. IEEE Transactions on Mobile Computing, 2023, 22(5): 3017–3030. doi: 10.1109/TMC.2021.3125949.
[12]	LIU Xiangzhi, ZHAI Huazhen, ZHOU Xiaotian, et al. Joint resource allocation and computation offloading for DNN inference with model partition and early exit in MEC networks[J]. Chinese Journal of Electronics, 2026, 35(1): 215–232. doi: 10.23919/cje.2024.00.344.
[13]	HOU Yanzhao, WANG Chengrui, ZHU Min, et al. Joint allocation of wireless resource and computing capability in MEC-enabled vehicular network[J]. China Communications, 2021, 18(6): 64–76. doi: 10.23919/JCC.2021.06.006.
[14]	ZHANG Rongrong, ZHOU Chen, GUAN Yong, et al. Human mobility-driven offloading and resource allocation in MEC-enabled WBANs[J]. Chinese Journal of Electronics, 2025, 34(4): 1331–1343. doi: 10.23919/cje.2024.00.302.
[15]	LI Kuixian, FAN Haodong, YANG Yandie, et al. Multi-agent reinforcement learning-based UAV path and resource allocation for ground-to-air communication network[J]. IEEE Internet of Things Journal, 2025, 12(21): 44243–44254. doi: 10.1109/JIOT.2025.3602122.
[16]	ZHENG Tong, BI Yuanguo, HAN Guangjie, et al. Optimizing multi-DNN parallel inference performance in MEC networks: A resource-aware and dynamic DNN deployment scheme[J]. IEEE Transactions on Computers, 2025, 74(11): 3938–3952. doi: 10.1109/TC.2025.3605749.
[17]	LIU Zhang, DU Hongyang, LIN Junzhe, et al. DNN partitioning, task offloading, and resource allocation in dynamic vehicular networks: A Lyapunov-guided diffusion-based reinforcement learning approach[J]. IEEE Transactions on Mobile Computing, 2025, 24(3): 1945–1962. doi: 10.1109/TMC.2024.3486728.
[18]	. LI Yuepeng, ZENG Deze, GUT L, et al. DNN partitioning and assignment for distributed inference in SGX empowered edge cloud[C]. 2024 IEEE 44th International Conference on Distributed Computing Systems, Jersey City, USA, 2024: 635–644. doi: 10.1109/ICDCS60910.2024.00065.
[19]	. KANG Yiping, HAUSWALD J, GAO Cao, et al. Neurosurgeon: Collaborative intelligence between the cloud and mobile edge[C]. Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, Xi'an, China, 2017: 615–629. doi: 10.1145/3037697.3037698.
[20]	LI Hui, LI Xiuhua, FAN Qilin, et al. Adaptive model partitioning and pruning for collaborative DNN inference in mobile edge-cloud computing networks[J]. IEEE Transactions on Mobile Computing, 2026, 25(3): 3744–3759. doi: 10.1109/TMC.2025.3620344.
[21]	ZHANG Wenzhao, HAN Shujun, XU Xiaodong, et al. Joint service placement and model partitioning for accelerating DNN inference in edge intelligence empowered vehicle networks[J]. IEEE Transactions on Vehicular Technology, 2025, 74(9): 14645–14660. doi: 10.1109/TVT.2025.3564471.
[22]	ZHANG Mengyuan, FANG Juan, TENG Ziyi, et al. Joint DNN partitioning and task offloading based on attention mechanism-aided reinforcement learning[J]. IEEE Transactions on Network and Service Management, 2025, 22(3): 2914–2927. doi: 10.1109/TNSM.2025.3561739.
[23]	SU Yi, FAN Wenhao, GAO Li, et al. Joint DNN partition and resource allocation optimization for energy-constrained hierarchical edge-cloud systems[J]. IEEE Transactions on Vehicular Technology, 2023, 72(3): 3930–3944. doi: 10.1109/TVT.2022.3219058.
[24]	施建锋, 陈忻阳, 李宝龙. 面向物联网的云边端协同计算中任务卸载与资源分配算法研究[J]. 电子与信息学报, 2025, 47(2): 458–469. doi: 10.11999/JEIT240659. SHI Jianfeng, CHEN Xinyang, and LI Baolong. Research on task offloading and resource allocation algorithms in cloud-edge-end collaborative computing for the internet of things[J]. Journal of Electronics & Information Technology, 2025, 47(2): 458–469. doi: 10.11999/JEIT240659.