Mobile Vision Analytics (MVA) is essential for advancing applications, which analyze visual data using deep neural network (DNN) models to extract contextual insights. While cloud based approach is common, the high latency incurred in transmission leading to a shift toward edge computing. However, the limited resource on edge leads to the challenge of concurrent DNN execution on shared GPU. This paper proposes a novel mathematical framework that models MVA workflows over an edge infrastructure, including the partitioning of GPU resources for concurrent DNNs. Our model integrates local and remote processing steps, accounting for wireless transmission and GPU sharing, and provides a structured approach to estimating per-step time consumption. A detailed numerical evaluation demonstrates the latency and resource utilization of each part of the system under varied scenarios, offering insights for the design of latency-sensitive MVA solutions with concurrent models on shared edge GPU infrastructure.

Mobile augmented reality (MAR) has gained increased attention thanks to its potential to transform applications in different domains. One of the challenges to realizing MAR systems is the processing of video frames efficiently. MAR user devices are often resource-constrained and unsuitable for real-time object detection and recognition from video streams. Edge computing has tremendous potential to enable MAR systems, where processing instances (e.g., serverless functions, containers, or virtual machines) can implement and manage the execution of convolutional neural networks (CNNs) for processing MAR offloaded video frames. One of the challenges is how to balance the video frames across the edge servers and processing instances. In this article, we proposed the LAOS orchestrator for resource management and load balancing of distributed edge servers for MAR systems. The LAOS orchestrator balances incoming video frames among processing instances at the edge servers that process video frames. It also determines when to spawn new instances of the CNN functions aimed at ensuring a predefined latency threshold for the processing of video frames. Besides, we devised a novel queuing-based framework for modeling the resource management problem of distributed edge servers for MAR systems. The obtained numerical results show that the proposed LAOS orchestrator reduces the latency and efficiently manages the edge computing resources when dynamic workload peaks are considered.

Augmented reality (AR) is gaining increasing attention thanks to its potential for enhancing applications in different domains. However, AR systems will reply to different computation-intensive tasks (e.g., object detection, object classification, and content rendering), which are demanding in terms of energy and latency. The use of multi-access edge computing (MEC) technology can significantly reduce the latency and energy cost of AR systems by providing computational resources closer to mobile AR users. In this paper, we proposed a reinforcement learning-based orchestrator for the management and allocation of networked edge servers’ computing resources for AR mobile users. The proposed Migration Enabled Task Allocation (META) orchestrator takes into consideration the AR tasks and edge servers characteristics when deciding if an incoming AR task will be admitted or not, and in which edge server it will be executed in case it is admitted. Moreover, the proposed orchestrator migrates tasks among edge servers if needed to free resources during the incoming of a new AR task. We also design the deep META-DQN and META-PPO algorithms to be used by the META orchestrator for predicting AR tasks’ arrival and learning the optimal policy in terms of allocating edge computing resources. Obtained results show that our proposed META-PPO model decreased the task blocking rate by up to 180% when compared to related work.