With the rapid proliferation of Industrial Internet of Things (IIoT) devices, massive Delay Sensitive and Computation Intensive (DSCI) tasks are generated. Traditional Mobile Edge Computing (MEC) systems face limitations like inter-cell interference at cell edges, degrading Quality of Service (QoS). To address this, Cooperative Access Edge Networks (CAEN) enable dynamic Access Point (AP) clusters for enhanced transmission reliability in IIoT. However, challenges arise from multi-user interference, bandwidth contention, dynamic environments, and heterogeneous resources, complicating joint resource orchestration. This paper proposes EdgeDiffuse, a diffusion-enhanced distributed resource orchestration algorithm, which optimizes task offloading selection, transmission power control, and computational resource allocation to minimize long term task completion time while promoting system load balancing. EdgeDiffuse enables adaptive and hierarchical coordination between user agents and edge servers. It integrates diffusion models under a Multi-Agent Deep Reinforcement Learning (MADRL) framework for improved policy exploration in high dimensional offloading decision spaces, and further uses convex optimization for server side resource allocation. Experimental results demonstrate that EdgeDiffuse achieves 28.17% reduction in task completion time, 7.40% improvement in task transmission rates, and 15.71% enhancement in load balancing compared to advanced baselines, showcasing superior performance in multi-user and resource constrained scenarios.

With rapid evolution of mobile core network (MCN) architectures, large-scale control-plane traffic (CPT) traces are critical to studying MCN design and performance optimization by the R&D community. The prior-art control-plane traffic generator SMM heavily relies on domain knowledge which requires re-design as the domain evolves. In this work, we study the feasibility of developing a high-fidelity MCN control plane traffic generator by leveraging generative ML models. We identify key challenges in synthesizing high-fidelity CPT including generic (to data-plane) requirements such as multimodality feature relationships and unique requirements such as stateful semantics and long-term (time-of-day) data variations. We show state-of-the-art, generative adversarial network (GAN)-based approaches shown to work well for data-plane traffic cannot meet these fidelity requirements of CPT, and develop a transformer-based model, CPT-GPT, that accurately captures complex dependencies among the samples in each traffic stream (control events by the same UE) without the need for GAN. Our evaluation of CPT-GPT on a large-scale control-plane traffic trace shows that (1) it does not rely on domain knowledge yet synthesizes control-plane traffic with comparable fidelity as SMM; (2) compared to the prior-art GAN-based approach, it reduces the fraction of streams that violate stateful semantics by two orders of magnitude, the max y-distance of sojourn time distributions of streams by 16.0%, and the transfer learning time in deriving new hourly models by 3.36×.

On-device sensors in mobile systems, e.g., autonomous vehicles and AR/VR, use odometry for real-time positioning, but they risk capturing sensitive data of non-consenting bystanders. Prior works have investigated various privacy-preserving techniques to protect those sensitive data. However, it is still unclear about the impact of such approaches on the accuracy of odometry. In this work, we investigate the impact of various privacy-preserving obfuscation techniques on the accuracy of monocular visual odometry. We focus on three widely used obfuscation methods: Gaussian Blur, Gaussian Noise, and Laplacian Noise, applied to protect bystander privacy. Our investigation reveals that some obfuscation techniques can increase the odometry errors by up to 56.9%, while others surprisingly reduce the errors by up to 66.8%, compared to raw data. Our key findings indicate that data obfuscation primarily affects the duration of tracking loss in ORB-SLAM3, which is the main source of the errors, and successful relocalization immediately following tracking loss plays a crucial role in reducing the overall errors.

After 4 years of rapid deployment in the US, 5G is expected to have significantly improved the performance and overall user experience of mobile networks. However, recent measurement studies have focused either on static performance or a single aspect (e.g., handovers) under driving conditions of 5G, and do not provide a complete picture of cellular network performance today under driving conditions - a major use case of mobile networks. Through a cross-continental US driving trip (from LA to Boston, 5700km+), we conduct an in-depth measurement study of user-perceived experience (network coverage/performance and QoE of a set of major latency-critical 5G "killer'' apps) To understand the root cause of the observed network performance, while collecting low-level 5G statistics and signaling messages. Our study shows disappointingly low coverage of 5G networks today under driving and highly fragmented coverage by cellular technologies. More importantly, network and application performance are often poor under driving even in areas with full 5G coverage. We also examine the correlation of technology-wise coverage and performance with geo-location and the vehicle's speed and analyze the impact of a number of lower layer KPIs on network performance.

With 5G deployment gaining momentum, the control-plane traffic volume of cellular networks is escalating. Such rapid traffic growth motivates the need to study the mobile core network (MCN) control-plane design and performance optimization. Doing so requires realistic, large control-plane traffic traces in order to profile and debug the mobile network performance under real workload. However, large-scale control-plane traffic traces are not made available to the public by mobile operators due to business and privacy concerns. As such, it is critically important to develop accurate, scalable, versatile, and open-to-innovation control traffic generators, which in turn critically rely on an accurate traffic model for the control plane. Developing an accurate model of control-plane traffic faces several challenges: (1) how to capture the dependence among the control events generated by each User Equipment (UE), (2) how to model the inter-arrival time and sojourn time of control events of individual UEs, and (3) how to capture the diversity of control-plane traffic across UEs. We present a novel two-level hierarchical state-machine-based control-plane traffic model. We further show how our model can be easily adjusted from LTE to NextG networks (e.g., 5G) to support modeling future control-plane traffic. We experimentally validate that the proposed model can generate large realistic control-plane traffic traces. We have open-sourced our traffic generator to the public to foster MCN research.

For its stringent QoE requirement, augmented reality (AR) has been widely hailed as a representative of ultra-high bandwidth and ultra-low latency apps that will be enabled by 5G networks/edge clouds. Such a portrait of AR by the telco and cloud industry raises an important research question - can 5G enable latency-critical applications such as (edge-assisted) AR? In this paper, we conduct to our knowledge the first in-depth measurement study of whether 5G mmWave in combination with in-network edge cloud can support the baseline edge-assisted object detection. After we discover 5G mmWave is unlikely to achieve the level of uplink network performance needed to support a baseline edge-assisted object detection implementation in the near future, we quantify the performance benefits in retrofitting app-level optimizations developed in the pre-5G era on top of baseline edge-assisted object detection, as well as the performance benefits from hardware upgrade on the edge. We find that these optimizations can significantly boost object detection performance over both LTE and 5G mmWave; however, the improvement with 5G mmWave over LTE is marginal, and 5G mmWave still fails to provide satisfactory performance in all scenarios under consideration. Overall, we conclude that today's 5G mmWave deployment is not a deciding factor in enabling edge-assisted object detection.

Immersive applications such as Augmented Reality (AR) and Mixed Reality (MR) often need to perform multiple latency-critical tasks on every frame captured by the camera, which all require results to be available within the current frame interval. While such tasks are increasingly supported by Deep Neural Networks (DNNs) offloaded to edge servers due to their high accuracy but heavy computation, prior work has largely focused on offloading one task at a time. Compared to offloading a single task, where more frequent offloading directly translates into higher task accuracy, offloading of multiple tasks competes for shared edge server resources, and hence faces the additional challenge of balancing the offloading frequencies of different tasks to maximize the overall accuracy and hence app QoE.

In this paper, we study how to support high-quality immersive multiplayer VR on commodity mobile devices. First, we perform a scaling experiment that shows simply replicating the prior-art 2-layer distributed VR rendering architecture to multiple players cannot support more than one player due to the linear increase in network bandwidth requirement. Second, we propose to exploit the similarity of background environment (BE) frames to reduce the bandwidth needed for prefetching BE frames from the server, by caching and reusing similar frames. We find that there is often little similarly between the BE frames of even adjacent locations in the virtual world due to a "near-object" effect. We propose a novel technique that splits the rendering of BE frames between the mobile device and the server that drastically enhances the similarity of the BE frames and reduces the network load from frame caching. Evaluation of our implementation on top of Unity and Google Daydream shows our new VR framework, Coterie, reduces per-player network requirement by 10.6X-25.7X and easily supports 4 players for high-resolution VR apps on Pixel 2 over 802.11ac, with 60 FPS and under 16ms responsiveness.

This paper explores network-side cellular user localization using fingerprints created from the angle measurements enabled by 5G. Our key idea is a binning-based fingerprinting technique that leverages multipath propagation to create fingerprint vectors based on angles of arrival of signals along multiple paths at each user. In network simulations that recreate urban environments with 3D building geometry and base station locations for a major city, our binning-based fingerprinting for 5G achieves significantly lower localization errors with a single base station than signal strength-based fingerprinting for LTE.

With the advent of bandwidth-hungry applications and the new advancements in wireless LAN standards (802.11ad, 802.11ay) and cellular technologies (5G), modern smartphones need to be able support multi-Gbps data rates. In this work, we explore if today's smartphones are capable of handling such high-speed network traffic. Using two high-end smartphones, we show that, contrary to previous beliefs, they can indeed support Gbps data rates without significant strain on their hardware resources. Using projections, we further show that up to 12.8 Gbps could be supported with just 50% CPU utilization. Finally, we explore the factors that make this possible and the contribution of each of them.