With the rapid upsurge of deep learning tasks at the network edge,effective edge artificial intelligence(AI)inference becomes critical to provide lowlatency intelligent services for mobile users via leveraging the edg...With the rapid upsurge of deep learning tasks at the network edge,effective edge artificial intelligence(AI)inference becomes critical to provide lowlatency intelligent services for mobile users via leveraging the edge computing capability.In such scenarios,energy efficiency becomes a primary concern.In this paper,we present a joint inference task selection and downlink beamforming strategy to achieve energy-efficient edge AI inference through minimizing the overall power consumption consisting of both computation and transmission power consumption,yielding a mixed combinatorial optimization problem.By exploiting the inherent connections between the set of task selection and group sparsity structural transmit beamforming vector,we reformulate the optimization as a group sparse beamforming problem.To solve this challenging problem,we propose a logsum function based three-stage approach.By adopting the log-sum function to enhance the group sparsity,a proximal iteratively reweighted algorithm is developed.Furthermore,we establish the global convergence analysis and provide the ergodic worst-case convergence rate for this algorithm.Simulation results will demonstrate the effectiveness of the proposed approach for improving energy efficiency in edge AI inference systems.展开更多
基金Part of this work was presented at the IEEE 90th Vehicu-lar Technology Conference(VTC2019-Fall)Honolulu,Hawaii,USA,Sept.2019[1]+1 种基金This work was supported in part by National Nature Science Foun-dation of China under Grant 61601290(Yuanming Shi)and a start-up fund of Hong Kong Polytechnic University(Project ID P0013883)(Jun Zhang)The associate editor coordinating the review of this paper and approving it for publication was R.Wang。
文摘With the rapid upsurge of deep learning tasks at the network edge,effective edge artificial intelligence(AI)inference becomes critical to provide lowlatency intelligent services for mobile users via leveraging the edge computing capability.In such scenarios,energy efficiency becomes a primary concern.In this paper,we present a joint inference task selection and downlink beamforming strategy to achieve energy-efficient edge AI inference through minimizing the overall power consumption consisting of both computation and transmission power consumption,yielding a mixed combinatorial optimization problem.By exploiting the inherent connections between the set of task selection and group sparsity structural transmit beamforming vector,we reformulate the optimization as a group sparse beamforming problem.To solve this challenging problem,we propose a logsum function based three-stage approach.By adopting the log-sum function to enhance the group sparsity,a proximal iteratively reweighted algorithm is developed.Furthermore,we establish the global convergence analysis and provide the ergodic worst-case convergence rate for this algorithm.Simulation results will demonstrate the effectiveness of the proposed approach for improving energy efficiency in edge AI inference systems.
