The arrival of 100K+ GPU clusters marks a new frontier in AI infrastructure. Standard communication stack meets new challenges as physical topologies span multiple datacenter buildings, introducing high bandwidth-delay product links where latency increases by up to 30× compared to intra-rack traffic. Furthermore, the transition toward Mixture-of-Experts architectures generating bursty all-to-all patterns that create transient congestion hotspots. These constraints, combined with an operational environment where hardware failures shift from anomalies to frequent occurrences, renders traditionally lightweight operations like initialization and resource management challenging.

User-generated content (UGC) videos often exhibit complex distortions and diverse content, posing significant challenges for traditional video quality assessment (VQA) methods. Approaches that directly merge distortion and semantic information risk feature conflicts and the loss of details. In addition, simple concatenation of spatiotemporal features fails to capture vital interactions, limiting predictive accuracy. Motivated by these challenges, this paper proposes a Multi-level Distortion Adaptation and Spatiotemporal Cross-Attention Fusion framework for VQA, named MACA-VQA. Specifically, a novel multi-level adaptive strategy progressively incorporates distortion information into each Transformer layer of the CLIP model, enabling layer-wise fusion of semantic and distortion features. Furthermore, a newly introduced cross-attention fusion mechanism dynamically integrates spatiotemporal features, capturing complex, multidimensional interactions. Extensive experiments demonstrate that MACA-VQA achieves state-of-the-art performance on multiple public datasets, validating its effectiveness and robustness in both intra-dataset and inter-dataset scenarios. The source code is available at https://github.com/BoHu90/MACA-VQA

RDMA datacenters are proliferating to meet the demand of emerging workloads such as AI training and inference as well as distributed storage. This trend has opened up a critical knowledge gap: the traffic characteristics of congestion in these networks remain unknown. We do not know, for example, which layers of the network are the most congested, if the network is load balanced effectively, how long congestion events last, and how accurate existing telemetry systems are in capturing congestion. This paper bridges this gap by investigating congestion in a large-scale RDMA datacenter dedicated to distributed AI training. We provide insights into three specific congestion patterns: (a) location and distribution in the network, (b) burstiness, e.g., the duration and synchrony of bursts, and (c) observability using existing telemetry methods. We show, for instance, that the deployment of Priority Flow Control (PFC) in RDMA networks has shifted the location of congestion one level up: from the edge-host in legacy TCP/IP datacenters to the network core in RDMA datacenters. At the same time, we show that the same protocol enables us to observe and understand congestion better, even bursty events. The findings of this research reveal open challenges for measuring, characterizing, and managing congestion in RDMA networks, paving the way for future research.

With the development of Internet of Things (IoT) technology, user identity recognition technology has become an important line of defense to ensure application access and privacy security. Ultra-Wideband (UWB) bio-radar, with its high range resolution and non-contact penetration detection advantages, can accurately capture the individual-specific and dynamic continuous surface micro-motion characteristics caused by cardiac structural movement through transmitted microwaves, namely Microwave HeartPrint, provides a new technological path for non-contact identity recognition. However, current radar-based non-contact cardiac motion recognition mostly treats the micro-movement of the chest wall as a single scattering point target and primarily relies on single-domain data, thereby limiting the effectiveness of the recognition mechanism. To address the aforementioned issue, this paper first employs UWB bio-radar to continuously monitor the multi-point micro-motions in the range dimension of the cardiac body surface area along the radial direction, and then achieves the selection of effective range unit echoes from the perspective of multiple range tomographic planes. Secondly, based on the echo heartbeat segmentation and combined with short-time fourier transform (STFT) time-frequency transform, the Microwave Heartprint dual-domain data corresponding to the effective range units are obtained. Finally, a multi-view dual-domain feature fusion recognition network is proposed, where the multi-view single-domain feature fusion module (MV-SFFM) is designed to effectively fuse the differential and complementary micro-motion features of effective range units on the cardiac surface. In addition, the cross-attention dual-domain feature fusion module (CA-DFFM) effectively fuses the time-domain and time-frequency domain features to further improve the feature representation capability. Actual experiments show that the recognition accuracy of this method can reach more than 95%. Ablation experiments and visualization analysis strongly demonstrates the rationality and effectiveness of comprehensively utilizing the micro-motion information of multiple effective range units of the heart and dual-domain features.

Managing data center networks with low loss requires understanding traffic dynamics at short (millisecond) time-scales, especially the burstiness of traffic, and to what extent bursts contend for switch buffer resources. Yet, monitoring traffic over such intervals is a challenge at scale.

Mobile ad hoc networks can be widely used in many scenes, for example, military communication, emergency communication, and 5G wide area coverage as well as ultradense network scenes. A cluster‐based network can decrease network overhead effectively and then constitute a large‐scale network through extending network scale by clustering and cascading. In view of multiservice simultaneous transmission demand for small‐scale dense networking scene and large‐scale extended networking scene, a MAC protocol based on scheduling of cluster head is proposed, which can avoid collision and retransmission between nodes effectively, and then the network synchronizing in intercluster and intracluster as well as the time‐slot scheduling is solved fast and efficiently. A network synchronization algorithm based on clock spread of the sponsorship node is proposed to achieve network self‐synchronizing, and a modified schedule‐tree algorithm based on cluster head and exactly sponsorship node is proposed to decrease network overhead and to increase network fairness, then MAC protocol based on scheduling of cluster head is verified by simulated analysis. Finally, a dynamic gateway selection algorithm based on link stability is proposed in this paper to decrease intercluster communication control overhead and improve intercluster communication reliability.

Modern end-host network stacks have to handle traffic from tens of thousands of flows and hundreds of virtual machines per single host, to keep up with the scale of modern clouds. This can cause congestion for traffic egressing from the end host. The effects of this congestion have received little attention. Currently, an overflowing queue, like a kernel queuing discipline, will drop incoming packets. Packet drops lead to worse network and CPU performance by inflating the time to transmit the packet as well as spending extra effort on retansmissions. In this paper, we show that current end-host mechanisms can lead to high CPU utilization, high tail latency, and low throughput in cases of congestion of egress traffic within the end host. We present zD, a framework for applying backpressure from a congested queue to traffic sources at end hosts that can scale to thousands of flows. We implement zD to apply backpressure in two settings: i) between TCP sources and kernel queuing discipline, and ii) between VMs as traffic sources and kernel queuing discipline in the hypervisor. zD improves throughput by up to 60%, and improves tail RTT by at least 10x at high loads, compared to standard kernel implementation.

BGP was initially created assuming by default that all ASes are equal. Its policies and protocols, namely BGP, evolved to accommodate a hierarchical Internet, allowing an autonomous system more control over outgoing traffic than incoming traffic. However, the modern Internet is flat, making BGP asymmetrical. In particular, routing decisions are mostly in the hands of traffic sources (i.e., content providers). This leads to suboptimal routing decisions as traffic sources can only estimate route capacity at the destination (i.e., ISP). In this paper, we present the design of Unison, a system that allows an ISP to jointly optimize its intra-domain routes and inter-domain routes, in collaboration with content providers. Unison provides the ISP operator and the neighbors of the ISP with an abstraction ISP network in the form of a virtual switch. This abstraction allows the content providers to program the virtual switch with their requirements. It also allows the ISP to use that information to optimize the overall performance of its network. We show through extensive simulations that Unison can improve ISP throughput by up to 30% through cooperation with content providers. We also show that cooperation of content providers only improves performance, even for non-cooperating content providers (e.g., a single cooperating neighbour can improve ISP throughput by up to 6%).

It has become increasingly important for content providers (CPs) to reach consumers with low latency. Peering links that connect CPs directly to access Internet service providers (access ISPs) have been used for this purpose thus providing one-hop AS paths from CPs to users. While providing improved latency, these peering links still do not give CPs control over the entire end-to-end path to their users. This has made it difficult for CPs to completely manage user experience. Motivated by this, we propose the deployment of Zero-Hop Networks (ZeN), where a CP's entire end-to-end path to users is under its control. We believe it is important to respond to the compelling demand for ZeN and enable its provision over the shared Internet infrastructure so that all may continue to reap its benefits. In this paper we lay out the vision for ZeN, describing its goals and challenges. We propose to deploy ZeN by allowing CPs to extend their network's control over the access ISP substrate in a way that allows the CP to control the entire end-to-end path. We develop two strawman architectures based on Software-Defined Networking ideas: one based on resource reservation and the other based on network virtualization. We also discuss some elements of a research agenda that is needed to bring ZeN deployments to realization.

Abstract As a new networking paradigm, opportunistic networking communications have great vision in animal migration tracking, mobile social networking, network communications in remote areas and intelligent transportation, and so on. Opportunistic networks are one of the evolutionary mobile ad hoc networks, whose communication links often suffer from frequent disruption and long communication delays. Therefore, many opportunistic forwarding protocols present major security issues, and the design of opportunistic networks faces serious challenges such as how to effectively protect data confidentiality and integrity and how to ensure routing security, privacy, cooperation, and trust management. In this paper, we first systematically describe the security threats and requirements in opportunistic networks; then propose a general security architecture of opportunistic networks; and then make an in‐depth analysis on authentication and access control, secure routing, privacy protection, trust management, and incentive cooperation mechanisms; and at the same time, we present a comparison of various security and trust solutions for opportunistic networks. Finally, we conclude and give future research directions. Copyright © 2014 John Wiley & Sons, Ltd.

The maturity of Software Defined Network (SDN) and network virtualization has inspired the development of software switch. This paper studies the behavior of soft switch in network virtualization environment. We investigate main performance factors and evaluate their impacts. Based on these measurements, we extend resource allocation among multiple soft switch instances with consideration of topology design. Simulation results show that proper coordination between resource allocation and topology greatly improves performance.

Scheduling schemes of wireless networks determine packet transmission opportunities for each network node by considering network parameters such as link quality, transmission rate, and delay. However, security has not been taken into account in these schemes, although it plays a critical role in network performance. In this paper a new scheduling scheme is proposed to determine packet transmissions under the constraint of achieving perfect physical layer security. Incorporating this new scheduling scheme into the distributed coordination function (DCF) of IEEE 802.11 medium access control (MAC) leads to a secure MAC protocol called SecDCF. Simulations are conducted to evaluate the performance of SecDCF, and results illustrate that SecDCF significantly outperform IEEE 802.11 DCF when physical layer security is enforced.