Journal
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
Volume 9, Issue 2, Pages 479-493Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCCN.2023.3235773
Keywords
Task analysis; Delays; Artificial intelligence; Computational modeling; Energy consumption; Servers; Inference algorithms; Mobile augmented reality; edge intelligence; mobile edge computing; resource allocation
Categories
Ask authors/readers for more resources
This paper presents a method for completing video-based AI inference tasks in a mobile edge computing system. By using an alternating optimization algorithm, the problem is decomposed into two sub-problems: resource allocation for devices that complete tasks locally and resource allocation for devices that offload tasks. To further reduce complexity, a distributed algorithm based on alternating direction method of multipliers (ADMM) is proposed. Numerical experiments demonstrate the effectiveness of the proposed algorithms.
The high computational complexity and energy consumption of artificial intelligence (AI) algorithms hinder their application in augmented reality (AR) systems. However, mobile edge computing (MEC) makes it possible to solve this problem. This paper considers the scene of completing video-based AI inference tasks in the MEC system. We formulate a mixed-integer nonlinear programming problem (MINLP) to reduce inference delays, energy consumption and to improve recognition accuracy. We give a simplified expression of the inference complexity model and accuracy model through derivation and experimentation. The problem is then solved iteratively by using alternating optimization. Specifically, by assuming that the offloading decision is given, the problem is decoupled into two sub-problems, i.e., the resource allocation problem for the devices set that completes the inference tasks locally, and that for the devices set that offloads tasks. For the problem of offloading decision optimization, we propose a Channel-Aware heuristic algorithm. To further reduce the complexity, we propose an alternating direction method of multipliers (ADMM) based distributed algorithm. The ADMM-based algorithm has a low computational complexity that grows linearly with the number of devices. Numerical experiments show the effectiveness of proposed algorithms. The trade-off relationship between delay, energy consumption, and accuracy is also analyzed.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available