The rapid growth of AI models is placing unprecedented pressure on switch ASIC memory allocated for telemetry and flow monitoring. In this poster, we argue that the predictability of AI/ML traffic patterns can be exploited by perfect hashing techniques for accurate flow- and packet-tracking with minimal memory overhead.

An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are served directly by the end device (e.g., smartphones, IoT equipment, smart vehicles), or offloaded to a remote cloud. Both options may be unsatisfactory for many applications: local models may have inadequate accuracy, while the cloud may fail to meet delay constraints. In this paper, we present the novel idea of inference delivery networks (IDNs), networks of computing nodes that coordinate to satisfy ML inference requests achieving the best trade-off between latency and accuracy. IDNs bridge the dichotomy between device and cloud execution by integrating inference delivery at the various tiers of the infrastructure continuum (access, edge, regional data center, cloud). We propose a distributed dynamic policy for ML model allocation in an IDN by which each node dynamically updates its local set of inference models based on requests observed during the recent past plus limited information exchange with its neighboring nodes. Our policy offers strong performance guarantees in an adversarial setting and shows improvements over greedy heuristics with similar complexity in realistic scenarios.

Modern information and communication systems have become increasingly challenging to manage. The ubiquitous system logs contain plentiful information and are thus widely exploited as an alternative source for system management. As log files usually encompass large amounts of raw data, manually analyzing them is laborious and error-prone. Consequently, many research endeavors have been devoted to automatic log analysis. However, these works typically expect structured input and struggle with the heterogeneous nature of raw system logs. Log parsing closes this gap by converting the unstructured system logs to structured records. Many parsers were proposed during the last decades to accommodate various log analysis applications. However, due to the ample solution space and lack of systematic evaluation, it is not easy for practitioners to find ready-made solutions that fit their needs. This paper aims to provide a comprehensive survey on log parsing. We begin with an exhaustive taxonomy of existing log parsers. Then we empirically analyze the critical performance and operational features for 17 open-source solutions both quantitatively and qualitatively, and whenever applicable discuss the merits of alternative approaches. We also elaborate on future challenges and discuss the relevant research directions. We envision this survey as a helpful resource for system administrators and domain experts to choose the most desirable open-source solution or implement new ones based on application-specific requirements.

Edge Computing brings flexibility and scalability of virtualization technologies at the edge of the network, enabling service providers to deploy new applications over a richer network infrastructure. However, the coexistence of such variety of applications on the same infrastructure exacerbates the already challenging problem of coordinating resource allocation while preserving the resource assignment optimality. In fact, (i) each application can potentially require different optimization criteria due to their heterogeneous requirements, and (ii) we may not count on a centralized orchestrator due to the highly dynamic nature of edge networks. To solve this problem, we present DRAGON, a Distributed Resource AssiGnment and OrchestratioN algorithm that seeks optimal partitioning of shared resources between different applications running over a common edge infrastructure. We designed DRAGON to guarantee both a bound on convergence time and an optimal (1-1/e)-approximation with respect to the Pareto optimal resource assignment. We evaluate convergence and performance of DRAGON on a prototype implementation, assessing the benefits compared to traditional orchestration approaches.

Network and Service Providers are exploring different exploitation strategies for the Multi-access Edge Computing (MEC), mainly motivated by the opportunities for saving costs and generating new revenues (e.g., through new business models). On the other hand, the overall standardization picture is still very fragmented, delaying or even jeopardizing the real exploitation of MEC; furthermore, current standardization efforts are mainly envisioning a traditional monolithic architecture, with many technological partners but a single administrative domain. This paper argues that a clear separation of IaaS, PaaS and SaaS levels for MEC, together with standardized interfaces, will help accelerating the development of new business roles (e.g., IaaS, PaaS and SaaS providers) and models, possibly replacing the current competition-oriented practices in the telco domain with new forms of cooperation, which are already starting to appear in the IT sector. In this direction, this paper proposes a disaggregated MEC architecture and presents two use cases that show how different categories of resources and services could be provided by infrastructure, platform and software providers in an evolutionary scenario towards 5G.

Edge Computing is moving resources toward the network borders, thus enabling the deployment of a pool of new applications that benefit from the new distributed infrastructure. However, due to the heterogeneity of such applications, specific orchestration strategies need to be adopted for each deployment request. Each application can potentially require different optimization criteria and may prefer particular reactions upon the occurrence of the same event. This paper presents a Service-Defined approach for orchestrating cloud/edge services in a distributed fashion, where each application can define its own orchestration strategy by means of declarative statements, which are parsed into a Service-Defined Orchestrator (SDO). Moreover, to coordinate the coexistence of a variety of SDOs on the same infrastructure while preserving the resource assignment optimality, we present DRAGON, a Distributed Resource AssiGnment and OrchestratioN algorithm that seeks optimal partitioning of shared resources between different actors. We evaluate the advantages of our novel Service-Defined orchestration approach over some representative edge use cases, as well as measure convergence and performance of DRAGON on a prototype implementation, assessing the benefits compared to conventional orchestration approaches.

This paper presents an open-source orchestration framework that deploys end-to-end services across OpenStack-managed data centers and SDN networks controlled either by ONOS or OpenDaylight. The proposed framework improves existing software in two directions. First, it exploits SDN domains not only to implement traffic steering, but also to execute selected network functions (e.g., NAT). Second, it can deploy a service by partitioning the original service graph into multiple subgraphs, each one instantiated in a different domain, dynamically connected by means of traffic steering rules and parameters (e.g. VLAN IDs) negotiated at run-time.

With the NFV paradigm, network services are usually instantiated in datacenters (e.g., as VMs), while software-defined networks provide just plain connectivity. However, common SDN controllers can do much more than just traffic steering; particularly they can execute network applications such as NAT, DHCP, and more. This paper presents a software architecture that can advertise an SDN domain as having compute capabilities, hence enabling an overarching multi-domain orchestrator to instantiate a network function either in a cloud or in an SDN domain. This allows an overarching orchestrator to fully exploit the processing capability of an SDN infrastructure and potentially enabling more aggressive optimization strategies across domains.