Edge-based video analytics faces the dual challenge of dynamic network conditions and strict real-time processing requirements. Existing offloading and scheduling methods often fail to adapt efficiently to varying link capacities, resulting in high latency, unstable detection accuracy, and frame loss. In this paper, we propose LDKite, a reinforcement learning-driven, linkadaptive framework for real-time video analytics in dynamic edge networks. LDKite jointly optimizes computation placement and frame offloading decisions by continuously learning from network state feedback, enabling adaptive scheduling that accounts for both network bandwidth variations and task-specific processing demands. The framework incorporates a lightweight policy network that efficiently guides offloading decisions while maintaining scalability to large edge networks. Extensive experiments on realistic edge scenarios demonstrate that LDKite outperforms state-of-the-art baselines, achieving up to 25% reduction in frame processing delay, only 4% frame loss, and 91% detection accuracy. The results validate LDKite's effectiveness in delivering robust, scalable, and high-performance video analytics under dynamic edge conditions, highlighting its potential for deployment in real-world edge computing environments.

The smart traffic light (STL) system, as one of the key components of smart cities, relies on the ubiquitous intelligence of edge computing. Various artificial intelligence (AI) services are enhanced by the resource-constrained edge servers (ESs). However, deploying ESs and resources to establish a largescale service coverage can be extremely costly and requires tremendous efforts. In this paper, we unveil the potential of crowd edge intelligence by designing EdgeLight, a novel STL system that does not require dedicated deployment of ESs. The key insight of EdgeLight is to empower STLs by exploiting the edge devices carried by the surrounding crowds. The video frames captured by the traffic cameras will be offloaded to the crowd devices for processing, and the results are then sent to the traffic lights for smart control. We establish the above paradigm by proposing novel techniques including service discovery and task splitting. We implement EdgeLight and conduct real world experiments, and the comparison to existing STL solutions shows a significant improvement, with a 92.41% reduction in total latency and a 53.26% reduction in payment.

Natural Orifice Transluminal Endoscopic Surgery (NOTES) holds great promise due to its ability to eliminate external incisions, reduce trauma, and accelerate recovery. However, the adoption of NOTES is hindered by the limited capabilities of existing instruments, particularly in achieving the required balance between compact size, dexterity, and load capacity. This paper introduces a novel robotic manipulator designed for NOTES, featuring a 5 mm diameter and 7 degrees of freedom (DoF). The manipulator incorporates an innovative 3-PRS flexible parallel mechanism combined with a continuum parallel structure, achieving enhanced dexterity and variable stiffness functionality within a miniaturized design. A kinematic and variable stiffness analysis is performed, and experimental validation demonstrates its bending performance and stiffness modulation. Additionally, the feasibility and practicality of the robotic system are confirmed through a peg-transfer experiment, proving its potential for real-world surgical applications. This research offers a viable solution for enhancing the performance of NOTES instruments.

Machine learning has been a driving force in the evolution of tremendous computing services and applications in the past decade. Traditional learning systems rely on centralized training and inference, which poses serious privacy and security concerns. To solve this problem, distributed learning over wireless edge networks (DLWENs) emerges as a trending solution and has attracted increasing research interests. In DLWENs, corresponding services need to be placed onto the edge servers to process the distributed tasks. Apparently, different placement of training services can significantly affect the performance of all distributed learning tasks. In this article, we propose TASP, a task-aware service placement scheme for distributed learning in wireless edge networks. By carefully considering the structures (directed acyclic graphs) of the distributed learning tasks, the fine-grained task requests and inter-task dependencies are incorporated into the placement strategies to realize the parallel computation of learning services. We also exploit queuing theory to characterize the dynamics caused by task uncertainties. Extensive experiments based on the Alibaba ML dataset show that, compared to the state-of-the-art schemes, the proposed work reduces the overall delay of distributed learning tasks by 38.6% on average.

With the emergence of the 5G/6G communications, edge computing has attracted increasing research interests in recent years. To provide pervasive 5G/6G edge computing services, numerous edge servers are required for service coverage, and the deployment cost can be$\gt$10000 times larger than the deployment cost of the 4G infrastructure. To address this fundamental limit, we propose ParallEdge, a deployment scheme that employs mobile edge servers for cost-effective service coverage. ParallEdge is designed based on the observation that the processing delay and server moving delay become comparable in many computing-intensive applications in the 5G/6G edge computing. Unlike the traditional “move-then-process” frameworks, ParallEdge follows a “move-while-processing” paradigm, which exploits the parallelism between task processing and server movement to enable resource sharing among more users. Moreover, with the joint optimization of path planning and task scheduling for multiple mobile servers, the deployment cost for service coverage can be further reduced. We analyze the approximation gap of the proposed algorithm, and conduct extensive simulation experiments based on the real-world application data, and the results show that ParallEdge can significantly reduce deployment cost and improve resource utilization compared to the state-of-the-art schemes.

Vision-based real-time object detection has become a key fundamental service for smart-city applications such as auto-drive and digital twins. Due to the limited resource available at camera devices, edge-assisted object detection has attracted increasing research attention. The existing edge-assisted schemes often assume stable or averaged wireless links during the frame offloading process. However, the assumption does not hold in real-world dynamic edge networks and will lead to significant performance degradation in terms of both detection latency and accuracy. In this paper, we propose$Kite$, a link-adaptive scheme for real-time object detection. Based on measurement studies and systematic analysis, we devise a lightweight yet representative performance indicator – “frame-anchor” distance, to incorporate the immeasurable impact of wireless dynamics into a measurable metric. Based on this performance indicator, we model the offloading process as an integer nonlinear programming problem, and propose an online link-adaptive algorithm for frame offloading decisions. We implement$Kite$in a neuro-enhanced live streaming application and conduct comparative experiments with four different datasets in WiFi/LTE based edge networks. The results show thatKitecan improve the detection accuracy by 40.53% in highly dynamic networks, compared to the state-of-the-art works.

The combination of 5G/6G and edge computing has been envisioned as a promising paradigm to empower pervasive and intensive computing for the Internet-of-Things (IoT). High deployment cost is one of the major obstacles for realizing 5G/6G edge computing. Most existing works tried to deploy the minimum number of edge servers to cover a target area by avoiding coverage overlaps. However, following this framework, the resource requirement per server will be drastically increased by the peak requirement during workload variations. Even worse, most resources will be left under-utilized for most of the time. To address this problem, we propose CoopEdge, a cost-effective server deployment scheme for cooperative multi-access edge computing. The key idea of CoopEdge is to allow deploying overlapped servers to handle variable requested workloads in a cooperative manner. In this way, the peak demands can be dispersed into multiple servers, and the resource requirement for each server can be greatly reduced. We propose a Two-step Incremental Deployment (TID) algorithm to jointly decide the server deployment and cooperation policies. For the scenarios involving multiple network operators that are unwilling to cooperate with each other, we further extend the TID algorithm to a distributed TID algorithm based on the game theory. Extensive evaluation experiments are conducted based on the measurement results of seven real-world edge applications. The results show that compared with the state-of-the-art work, CoopEdge significantly reduces the deployment cost by 38.7% and improves resource utilization by 36.2%, and the proposed distributed algorithm can achieve a comparable deployment cost with CoopEdge, especially for small-coverage servers.

Detection&tracking framework enables real-time object detection services on resource-limited mobile devices in edge networks, where mobile devices only offload few key frames to edge servers for detection and track the other frames locally. Following this framework, the offloading decisions become more important, as fewer frames can be offloaded and their results can directly affect tracking accuracy of the subsequent frames. To make wise frame offloading decisions, it is crucial to leverage the relationship between the detected frame and the tracked frame. However, the existing studies solely use the content-level information to reflect the above relationship, i.e., they tend to offload the frames with the significant pixel differences from the adjacent frames. Link impact on such relationship is completely ignored, thus leading to significant accuracy degradation. In this paper, we propose Kite, a link-adaptive and real-time object detection in dynamic edge networks, which integrates both the link-level and content-level impact into frame offloading. Kite exploits a novel performance metric, "frame-anchor" distance, to indicate the impact of dynamic wireless links. With this metric, we can incorporate both link and content information into the offloading process. The real-world experiment results show that Kite can improve the detection accuracy in dynamic edge networks.

The combination of 5G and edge computing has been envisioned as a promising paradigm to empower pervasive and intensive computing for the Internet-of-Things (IoT). High deployment cost is one of the major obstacles for realizing 5G edge computing. Most existing works tried to deploy the minimum number of edge servers to cover a target area by avoiding coverage overlaps. However, following this framework, the resource requirement per server will be drastically increased by the peak requirement during workload variations. Even worse, most resources will be left under-utilized for most of the time. To address this problem, we propose CoopEdge, a cost-effective server deployment scheme for cooperative multi-access edge computing. The key idea of CoopEdge is to allow deploying overlapped servers to handle variable requested workloads in a cooperative manner. In this way, the peak demands can be dispersed into multiple servers, and the resource requirement for each server could be greatly reduced. We further propose a two-step incremental algorithm, which jointly decides the server deployment and cooperation policies for fast convergence. We evaluate CoopEdge based on seven real-world edge applications. The results show that compared with the state-of-the-art works, CoopEdge significantly reduces the deployment cost by 38.7% and improves resource utilization by 36.2%.

With the remarkable development of the 5G technologies, more and more real-time and complex computational tasks from the Internet-of-Things (IoT) systems can be fulfilled by 5G edge servers. While the ultradense deployment is required for 5G edge services, in the upcoming era of 6G with an even more limited communication range, it is almost impossible to achieve 6G service coverage with dense deployments. To address this fundamental limit, we propose EdgeGO, a mobile resource-sharing framework that employs mobile edge servers to provide a cost-effective deployment of 6G edge computing, which enables edge resource sharing for massive IoT devices. Unlike traditional mobile cloudlets, EdgeGO exploits the asynchronization between requests receiving and results returning to decouple the stringent delay and resource requirements for edge computing. As a result, the server moving and task processing could be paralleled. Besides, EdgeGO incorporates a two-layer iterative updating algorithm, which jointly optimizes path planning and task scheduling to improve the overall task efficiency. Extensive simulation results show that by careful managing mobility and task execution of the edge servers, EdgeGO is able to drastically increase the resource utilization by 166.67% and decrease the deployment cost of 6G edge computing by 25.58%.