Digital Twins (DTs) are emerging as key enablers for Connected and Autonomous Vehicles (CAVs), offering virtual representations that support various applications ranging from offline, large-scale traffic analysis to real-time driver assistance. These use cases pose significantly diverse Quality of Service (QoS) requirements on DTs, including ultra-low latency for real-time synchronization with the physical counterparts. Deploying DTs at the network edge offers a promising solution, considering the increasingly advanced compute and network resources potentially available in a city-wide infrastructure. However, edge deployments introduce additional complexity: DT developers must deal with heterogeneous resources, optimize their usage for different QoS levels, and handle vehicle mobility. That process requires a high level of specialization and makes development time-consuming and error-prone. In this paper, we first introduce a DT communication model based on three key interfaces: to physical devices, to peer DTs, and to centralized applications. We then analyze the distinct QoS requirements of these interfaces and propose the adoption of a data distribution platform that maps them directly to edge network capabilities, hiding complexity and easing the DT development process. Early evaluations on a real testbed demonstrate the platform's potential to meet CAV DTs' QoS demands efficiently.

The emerging paradigm of resource disaggregation enables the deployment of cloud-like services across a pool of physical and virtualized resources, interconnected using a network fabric. This design embodies several benefits in terms of resource efficiency and cost-effectiveness, service elasticity and adaptability, etc. Application domains benefiting from such a trend include cyber-physical systems (CPS), tactile internet, 5G networks and beyond, or mixed reality applications, all generally embodying heterogeneous Quality of Service (QoS) requirements. In this context, a key enabling factor to fully support those mixed-criticality scenarios will be the network and the system-level support for time-sensitive communication. Although a lot of work has been conducted on devising efficient orchestration and CPU scheduling strategies, the networking aspects of performance-critical components remain largely unstudied. Bridging this gap, we propose KuberneTSN, an original solution built on the Kubernetes platform, providing support for time-sensitive traffic to unmodified application binaries. We define an architecture for an accelerated and deterministic overlay network, which includes kernel-bypassing networking features as well as a novel userspace packet scheduler compliant with the Time-Sensitive Networking (TSN) standard. The solution is implemented as tsn-cni, a Kubernetes network plugin that can coexist alongside popular alternatives. To assess the validity of the approach, we conduct an experimental analysis on a real distributed testbed, demonstrating that KuberneTSN enables applications to easily meet deterministic deadlines, provides the same guarantees of bare-metal deployments, and outperforms overlay networks built using the Flannel plugin.

Edge cloud computing is a promising programming and deployment paradigm to empower delay-sensitive applications. By executing close to the network edge, distributed applications can have quicker reactions to event occurrence and consequently prompter dynamic adaptations. In addition, recent improvements in connectivity support allow developers to benefit from heterogeneous and alternative communication technologies (e.g., RDMA, DPDK, XDP, etc.) to meet the requirements of network-intensive edge applications. However, exploiting these technologies makes applications statically tailored to a specific network interface; this significantly limits the potential of edge cloud computing, where application components should be able to migrate seamlessly at runtime. INSANE aims at solving that issue by exposing a technology-agnostic middleware API that lets developers simply specify their QoS communication requirements; the dynamic selection of the most appropriate technology on the currently hosting edge node is delegated to INSANE. The paper also presents how it is possible to develop two different INSANE-based applications (a decentralized messaging system and an image streaming framework) with a few lines of code. Finally, an extensive performance evaluation shows that our middleware adds very limited ns-scale overhead to the raw acceleration technologies.

The recent trend of moving cloud computing capabilities to the edge of the network is reshaping the way applications and their middleware supports are designed, deployed, and operated. This new model envisions a continuum of virtual resources between the traditional cloud and the network edge, which is potentially more suitable to meet the heterogeneous Quality of Service (QoS) requirements of the supported application domains. Yet, mission-critical applications such as those in manufacturing, automation, or automotive, still rely on communication standards like the Time-Sensitive Networking (TSN) protocol and 5G to ensure a deterministic network behavior: in this context, virtualization might introduce unacceptable network perturbations. In this paper, we demonstrate that latency-sensitive applications can execute in virtual machines without disruptions to their network operations. We propose a novel approach to support the TSN protocol in virtual machines through a precise clock synchronization method and we implement it in integration with state-of-the-art and highly-efficient network virtualization techniques. Our experimental results show that it is possible to achieve deterministic and ultra-low latency end-to-end communication in the cloud continuum, for example providing a guaranteed sub-millisecond latency between remote virtual machines.

Modern networking technologies such as Remote Direct Memory Access (RDMA) promise huge speedups in I/O bound platforms, but software layering overheads must first be overcome. Our paper studies this issue in a system that replicates small data objects using atomic multicast: a case in which internal synchronization is unavoidable, and any delay will be particularly impactful. Spindle, the methodology we propose, entails a series of optimizations including memory polling integrated with novel sender and receiver batching techniques, null-message send logic, and improved multi-thread synchronization. We applied Spindle to Derecho, an open-source library for atomic multicast, and obtained significant performance improvements both for the library itself and for an OMG-compliant avionics DDS layered on it. Derecho’s multicast bandwidth utilization for 10KB messages rose from 1GB/s to 9.7GB/s on a 12.5GB/s network, and it became more robust to delays even as latency dropped by nearly two orders of magnitude. While our focus is on the Derecho library and the OMG DDS, the same techniques should be relevant to databases, file systems, and IoT infrastructures.

Next-generation AI applications benefit from executing close to the network edge to better exploit co-locality to datasources and controlled actuators, and to meet stringent latency requirements. In the edge-enabled cloud continuum, time and safety-critical traffic coexists with best-effort flows, resulting in heterogeneous requirements that current networking middleware and frameworks struggle to support. This paper proposes INSANE, INtegrated Selective Acceleration at the Network Edge, the first edge-oriented middleware that integrates different network acceleration techniques (XDP, DPDK, RDMA, and TSN) within the same data distribution service. INSANE offers a uniform and simple interface, useful to support common data distribution patterns, that allow developers to exploit at runtime the most suitable network technology available in the dynamically determined deployment environment.

Serverless platforms are increasingly gaining importance in the cloud computing landscape due to their benefit of shortening the time to market of solutions and capability of automatic, fast, fine-grained scaling of resources. In this context, function chaining represents an appealing feature, allowing the composition of two or more functions to create a complex computation from simpler units while incentivizing modularity and reusability of functions. In this paper, we propose a portable and transparent, container-based serverless architecture that introduces an innovative infrastructural support, enabling an efficient composition of functions co-located on the same host. The proposal relies on a shared-memory approach and a message-oriented middleware serving as a communication medium among components. The experimental assessment shows the approach comes with the benefit of optimized resource usage and performance benefits measured in terms of request completion rate and a decrease in response latency.

We propose a cooperative control scheme for a heterogeneous multi-robot system, consisting of an Unmanned Aerial Vehicle (UAV) equipped with a camera and multiple identical Unmanned Ground Vehicles (UGVs). Our control scheme takes advantage of the different capabilities of the robots. Since the system is highly redundant, the execution of multiple different tasks is possible. The primary task is aimed at keeping the UGVs well inside the camera field of view, so as to allow our localization system to reconstruct the identity and relative pose of each UGV with respect to the UAV. Additional tasks include formation control, navigation and obstacle avoidance. We thoroughly discuss the feasibility of each task, proving convergence when possible. Simulation results are presented to validate the proposed method.

We develop a localization method for a single-UAV/multi-UGV heterogeneous system of robots. Considering the natural supervisory role of the UAV and the challenging (but realistic) assumption that the UAV-to-UGV measurements do not include the identities of the UGVs, we have adopted the PHD filter as a multi-target tracking technique. However, the standard version of this filter does not take into account odometric information coming from the targets, nor does it solve the problem of estimating their identities. Hence, we design ID-PHD, a modification of the PHD filter that is able to reconstruct the identities of the targets by incorporating odometric data. The proposed localization method has been successfully validated through experiments. Some preliminary results of a localization-based control scheme for the multi-robot system are also presented.