Fifth Generation (5G) networks and beyond are envisioned to provide user-focused communications, supporting diverse services with enhanced Quality of Service (QoS). Pivotal to this evolution is user equipment, which is increasingly performing advanced computational tasks beyond the edge of the network, known as the Extreme-Edge. Seamless integration of Extreme-Edge devices (EEDs) into the 5 G framework is however hindered, due to challenges in terms of device management, resource restrictions and interoperability issues. To address these barriers, we realize the Extreme-Edge Orchestrator (EEO), a management and orchestration framework enabling the extension of the 5 G cloud-to-edge continuum towards the Extreme-Edge. The EEO enables real-time resource monitoring and lifecycle management of network applications, including Artificial Intelligence/Machine Learning (AI/ML) tasks, deployed on EEDs. Unlike existing theoretical studies, our solution is deployed on an operational research-center-wide 5 G testbed and evaluated using an AI/ML-based network QoS prediction application, in the automotive domain. Our results show that the EEO supports efficient resource utilization, dynamic EED selection under device mobility scenarios and maintains robust service performance under computational stress-demonstrating its capability to support next-generation network services.

The advent of 5G and beyond systems is expected to shape the automotive vertical, as safety-critical vehicular applications rely on the network to meet their stringent Quality of Service (QoS) requirements. Predictive QoS (pQoS) has been proposed as a mechanism that allows automotive applications to proactively adapt in view of forthcoming QoS changes. Although pQoS is typically facilitated via classical (centralized) Machine Learning (ML) methods, the demand for data privacy has led to the emergence of distributed ML schemes. Efficient training of ML models however requires large volumes of (kinematic-state and connectivity) QoS data, so as to capture the involved spatio-temporal effects.To that end we hereby present and publicly share NordicDat, a QoS dataset collected during a two-week measurement campaign, driving across three European countries. NordicDat contains over 90K samples of physical layer, network and mobility-related features. Contrary to prior works, it includes multiple instances of cross-boarder roaming, diverse vehicle speed profiles and radio access technologies (generations). Further, we provide a thorough NordicDat data analysis, highlighting the dependencies between the NordicDat’s features and the resulting QoS values (throughput, delay). To showcase its broad usability, we train pQoS ML models over NordicDat in classical and distributed fashion. Our results demonstrate for the first time the viability of distributed pQoS with real-word data, which achieves similar (within a margin of 10%) accuracy to that of classical ML, cropping privacy-preserving benefits.

Edge computing is a recent paradigm where the processing takes place close to the data sources. It therefore reduces latency and saves bandwidth compared to traditional cloud computing. The latter can continue to play a supportive role. Edge-cloud computing provides benefits in many use cases including distributed computation algorithms, where the processing is divided into a number of tasks that are executed in parallel on different equipment. An important relevant challenge is to allocate the appropriate resources to process the data that are continuously generated from user devices. The issue becomes more complicated when we take into account the variations in the volume of the generated data as a function of time. In this paper we present a resource allocation algorithm for distributed computation with emphasis on machine learning algorithms. We consider that the resource requirements vary with time in a semi-static way that exhibits some daily pattern. We distinguish between periodic (expected) variations that occur during the day, and sporadic variations due to unexpected events. We propose an Integer Linear Programming algorithm to allocate the periodic resource requirements. To handle the non-periodic requirements, we consider a suitable prediction algorithm coupled with a reconfiguration algorithm that allocates the predicted required resources. Our results indicate that our proposal outperforms traditional allocation algorithms in terms of resource utilization, monetary cost and achieved accuracy.

Edge computing has emerged as a computing paradigm where the application and data processing takes place close to the end devices. It decreases the distances over which data transfers are made, offering reduced delay and fast speed of action for general data processing and store/retrieve jobs. The benefits of edge computing can also be reaped for distributed computation algorithms, where the cloud also plays an assistive role. In this context, an important challenge is to allocate the required resources at both edge and cloud to carry out the processing of data that are generated over a continuous (“infinite”) time horizon. This is a complex problem due to the variety of requirements (resource needs, accuracy, delay, etc.) that may be posed by each computation algorithm, as well as the heterogeneous resources’ features (e.g., processing, bandwidth). In this work, we develop a solution for serving weakly coupled general distributed algorithms, with emphasis on machine learning algorithms, at the edge and/or the cloud. We present a dual-objective Integer Linear Programming formulation that optimizes monetary cost and computation accuracy. We also introduce efficient heuristics to perform the resource allocation. We examine various distributed ML allocation scenarios using realistic parameters from actual vendors. We quantify trade-offs related to accuracy, performance and cost of edge/cloud bandwidth and processing resources. Our results indicate that among the many parameters of interest, the processing costs seem to play the most important role for the allocation decisions. Finally, we explore interesting interactions between target accuracy, monetary cost and delay.

Edge computing has emerged as a paradigm for local computing/processing tasks, reducing the distances over which data transfers are made. Thus, an opportunity is presented for data transfer-intensive, distributed machine learning. In this paper we develop a solution for serving distributed Machine Learning (ML) training jobs at the edge– cloud continuum. We model the specific requirements of each ML job, and the features of the edge and cloud resources. Next, we develop an Integer Linear Programming algorithm to perform the resource allocation. We examine different scenarios (different processing and bandwidth costs) and quantify tradeoffs related to performance and cost of edge/cloud bandwidth and processing resources. Our simulations indicate that even though there are many parameters that determine the allocation, the processing costs seem to play on average the most important role. The cloud b/w costs can be significant in certain scenarios. Finally, in certain examined cases, significant monetary benefits can be achieved through the collaboration of both edge and cloud resources when compared to using exclusively edge or cloud resources.

The convergence of Machine Learning (ML) with the edge computing paradigm has paved the way for distributing processing-heavy ML tasks to the network's extremes. As the edge deployment details still remain an open issue, distributed ML schemes tend to be network-agnostic; thus, their effect on the underlying network's resource consumption is largely ignored.In our work, assuming a network tree structure of varying size and edge computing characteristics, we introduce an analytical system model based on credible real-world measurements to capture the end-to-end consumption of ML schemes. In this context, we employ an edge-based (EL) and a federated (FL) ML scheme and in-depth compare their bandwidth needs and energy footprint against a cloud-based (CL) baseline approach. Our numerical evaluation suggests that EL exhibits a minimum of 25% bandwidth-efficiency compared to CL and FL, if employed by a few nodes higher in the edge network, while halving the network's energy costs.

The proliferation of machine learning (ML) applications has lately witnessed a considerable shift to more distributed settings, even reaching hand-held mobile devices; there, contrary to typical Centralized learning (CL) whereby the involved (large amounts of) training data are centrally gathered to train models, the load of training tasks is distributed across a set of capable mobile learners at the expense of their own energy. The idea of Federated learning (FL) has emerged as a privacy-preserving mechanism suggesting that the ML model parameters rather than data, are sent over the network to a central point of aggregation. However, when relaxing the privacy concerns, the debate strongly relates to the available network resources. Interestingly, the sofar theoretical or even experimental comparison of the two approaches overlooks network conditions and remains of low realism. In this work we rely on past measurement studies to introduce a realistic system model that accounts for all involved mobile network conditions such as bandwidth and data availability (af-fecting training accuracy and model aggregation) as well as user mobility patterns (affecting data loss). A dedicated simulation framework we have developed replays rich mobile-traces allowing for a comprehensive comparison of the two ML approaches over a large set of training data shedding light on network-resources utilization, energy efficiency and training convergence. Intuitively, our results suggest that the ratio between the employed raw data and the corresponding ML model shapes the conditions under which FL acts as a network-efficient alternative to CL. Interestingly enough, asymmetry in data availability across users as well as their varying number are shown to hardly affect the FL approach in traffic and energy needs, pointing both to its promising potential and the need for further research.

A Connected Vehicle System (CVS) is a cyberphysical system of highly-equipped infrastructure-connected vehicles interconnected with road-side units and cloud-based services to offer safer driving. Despite the ever increasing relevant research, the testing of CVS functionalities and communication features remains problematic; computer-based simulation requires detailed system models while field-testing is expensive, focusing on few components and may raise safety concerns. In this paper, we present a full CVS prototype testbed enabled to realize a broad set of timely Vehicle-to-Infrastructure (V2I) use-cases and serve as the basis for automotive cybersecurity testing. The testbed designed and built in the context of the H2020 SAFERtec project, is described in terms of its hardware requirements, software design and implementation. The conducted testing activities on its capability to realize the considered V2I use-cases and support cybersecurity testing is explained. More importantly, the paper details take-home lessons derived from the CVS implementation experiences aiming to assist future development of automotive prototype testbeds.

Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.

Security assurance is defined as the degree of confidence that the security requirements of an IT system are satisfied. In view of the emerging paradigm of connected vehicles i.e., dynamic Cyber-Physical systems of highly-equipped infrastructure-connected vehicles, specifying the involved assurance becomes highly-critical yet challenging; vehicles increasingly exploit various communication means to exchange rich data of relevance with the infrastructure resulting in a large attack surface. Both the complexity and uncertainty are increased rendering the so-far generic methods for security assurance costly-to-apply. In this position paper we introduce a security assurance framework tailored for connected vehicles, as explored by the EU-funded H2020 SAFERtec project. We put under the microscope two instances of vehicle-to-infrastructure communications and relying on an innovative modeling methodology we identify the involved security and privacy requirements. We then present the way to enhance the processes of the credible yet generic Common Criteria approach to gain evidence that the above requirements are met. The experimental evaluation of the framework is carried-out over a reference implementation of a prototype vehicle connected to road-side units and cloud-based services. The expectations are that our work assists to effectively construct assurance arguments increasing trust in connected vehicles.

The optimal placement of service facilities largely determines the capability of a data network to efficiently support its users' service demands. As centralized solutions over large-scale distributed environments are extremely expensive, inefficient or even infeasible, distributed approaches that rely on partial topology and demand information are the only credible approaches to the service placement problem, even at the expense of non-guaranteed optimality. In this paper, we propose a distributed service migration heuristic that iteratively solves instances of the 1-median problem pushing progressively the service to more cost-effective locations. Key to our algorithm is a traffic-aware centrality metric, called weighted conditional betweenness centrality (wCBC), that captures the ability of a node to act as service demand concentrator and is employed in both selecting the nodes and setting their weights for the 1-median problem instance. The assessment of our heuristic proceeds in two steps. First, assuming (ideal) knowledge of the invoked wCBC metric, we carry out a proof-of-concept study that demonstrates the effectiveness of the heuristic over synthetic and real-world topologies as well as its advantages against comparable local-search-like migration schemes. Next, we devise practical protocol implementations that approximate the heuristic using local measurements of transit traffic and preserve the excellent accuracy and fast convergence properties of the algorithm for different routing policies. Our solution applies to a broad range of networking scenarios, and is very relevant to the emerging trends for in-network storage and involvement of the end-user in the creation and distribution of lightweight (autonomic) service facilities.