Joint Optimization of Video-Based AI Inference Tasks in MEC-Assisted Augmented Reality Systems

Abstract

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 ADMMbased 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.

Dynamic task offloading edge-aware optimization framework for enhanced UAV operations on edge computing platform

“…This algorithm's implementation framework is shown in Fig. 5 24 . The suggested method dynamically adjusts emission energy levels to increase energy efficiency and ED operational time.…”

The Role of Artificial Intelligence in the Metaverse

“…As AI algorithms evolve and become extra sophisticated, they may in addition beautify the immersive reviews provided by using the metaverse. The integration of AI in the metaverse additionally allows customized virtual environments, wherein individuals can interact with the usage of personalized digital avatars that mimic real-lifestyle situations (Pan et al,2023). By leveraging AI, metaverse platforms can examine consumer conduct and alternatives to offer custom-designed content and studies.…”

Innovations in the Metaverse: Merging Augmented Reality and Artificial Intelligence for Immersive User Experiences

“…One of the most significant issues is guaranteeing data privacy and security in the metaverse, which entails the collecting and processing of sensitive medical information. (Mystakidis 2022) Another problem is the necessity for smooth interoperability among various healthcare systems and devices, as well as data format standardization. Furthermore, ethical concerns about the use of AI in healthcare must be addressed, such as assuring AI algorithm acceptance and explainability.…”

“…It enables seamless communication and collaboration among users, as well as more precise manipulation of virtual objects. Overall, incorporating augmented reality and artificial intelligence into the Metaverse broadens the possibilities for human-computer interaction, creating a more immersive, interactive, and engaging virtual environment (Pan et al, 2023). The introduction of artificial intelligence into the Metaverse allows for the www.iiste.org ISSN 2224-6061 (Paper) ISSN 2225-059X (Online) Vol.110, 2024 generation of digital content and the extraction of usable information from enormous amounts of data (Truong et al, 2023).…”