The escalating complexity and length of online privacy policies pose a substantial obstacle to user comprehension, thereby undermining informed consent. While manual annotation efforts have improved transparency, they are inherently limited in scalability. To address this challenge, we introduce COAT (Comprehensive Online Agreement Transparency), a novel framework for the automated analysis and risk scoring of privacy policies using Large Language Models (LLMs). Within the COAT system, this paper presents a comparative study evaluating several LLMs, including OpenAI’s GPT series and open-source models. Our methodology benchmarks LLM performance against humanannotated privacy risk scores using a set of specific policy clauses. This study validates the feasibility of using LLMs for scalable, automated privacy policy evaluation and highlights the performance disparities among current models. To foster further research and evaluation, the resulting dataset of LLM-generated scores is made publicly available.

The Edge-Cloud Continuum (ECC) represents an emerging distributed, multi-tier computing infrastructure that integrates the capabilities of cloud and edge computing to offer a versatile environment capable of hosting applications with specific requirements, such as low latency and high computing capacity, which neither cloud nor edge computing can individually guarantee. However, ensuring Quality of Service (QoS) across the ECC remains a complex task, particularly with regard to networking parameters, due to the limited controllability and predictability of public network segments. This work introduces a QoS-aware mechanism for constructing logical overlay networks that aim to ensure required network performance with high probability, despite the inherent variability of public network environments. The proposed approach builds the overlay by organizing nodes into layers, each defined by a target level of network Qos (e.g., latency). The construction process consists of two key stages: first, collecting network metrics among the available nodes, and second, assigning nodes to layers based on the observed metrics. To validate the proposed approach, this work presents a Monte Carlo simulation campaign that assesses its effectiveness in constructing overlay networks capable of meeting, with high probability, the required QoS levels.

The term Edge Cloud Continuum (ECC) identifies an emerging distributed, multi-tier computing infrastructure that combines the cloud and edge computing capabilities to offer a versatile environment where it is possible to deploy and manage a new type of applications - typically related to mobile and IoT fields - having specific requirements such as low-latency, high computing capabilities - that neither cloud nor edge can offer singularly. This capability comes from the combination and integration of multiple heterogeneous technologies, typically owned and offered by independent and autonomous resource and service providers. In such a scenario, the processes of deployment and management of an application are challenging issues that require the ability to coordinate multiple controllers to address fluctuations in service and resource availability, network latency, and workload demands. In this paper, the authors propose an SLA-driven, AI-based QoS Manager that, abstracting the heterogeneity of the resources and their providers, influences the performance of a distributed application by inferring the proper hardware configuration for each one of its components.

DevOps methodologies reduce the gap between Developers and Operations teams, enabling automation, integration, monitoring, and team collaboration by exploiting continuous integration and deployment and providing high-scale performance for the cloud software delivery life-cycle. AIOps seems to represent the future of IT automation by leveraging DevOps methodologies, Big Data, and AI-enabled strategies for the smart orchestration of Cloud-native applications. Based on the Ananke monitoring model, this paper investigates design issues and strategies required to enable integration between clusters and applications managed by Ananke, and their metrics stored in the Prometheus Monitoring system. Some classic algorithms for anomaly detection and forecasting of time series have been introduced in the proposed AIOps Prometheus Framework for the system analysis and orchestration of applications. Finally, we propose, as a case study, an auto-scaling strategy based on the prediction of traffic peeks for a web application using the Facebook Prophet model.

Micro-service architecture enables smarter management of applications life-cycle. However, the increasing of the number of components also increases complexity, especially on operations like migration and horizontal scaling. While operations, in monolithic systems, involve only one component, operations in micro-services based applications can get complex and should involve parameters and properties like connection throughput, resources usage, robustness or consistency and reliability. To perform this kind of operations and optimization strategies in micro-services applications, we propose Ananke, a framework consisting of a time-varying multi-layer graph-based model and architecture to profile micro-services and their interactions in a platform-as-a-service environment. The aim of Ananke is to provide support and facilities for optimization strategies that a Cloud Provider can exploit to guarantee quality of service and service-level agreements better.

Mobility on Demand (MoD) services are revolutionizing the way people move in cities around the world and are often considered a convenient alternative to public transit. MoD is usually intended as a door-to-door service. However, there has been recent interest toward consolidating, e.g., aggregating, the travel demand by limiting the number of admitted stop locations. This implies users have to walk from/to their intended origin/destination.The contribution of this paper is a systematic study the impact of consolidation on the operator cost and on user QoS. We introduce a MoD system where pick-ups and drop-offs can only occur in a limited subset of admitted stop locations. The density of such locations is a system parameter: the less the density, the more the user demand is consolidated. We show that, by decreasing stop density, we can increase system capacity (number of passengers we are able to serve). On the contrary, increasing it, we can improve QoS. The system is tested in AMoDSim, an open-source simulator.This work is a first step toward flexible mobility services that are able to autonomously re-conFigure themselves, favoring capacity or QoS, depending on the amount of travel demand coming from users. In other words, the services we envisage in this work shift their operational mode to any intermediate point in the range from a taxi-like door-to-door service to a bus-like service, with few served stops and more passengers on-board.

This track has made signicant contribution to advance the current state of the art in enterprise distributed application management across datacenters, and clouds public or private. A new computing model proposing extensions to the current von Neumann implementation of the Turing machine was contributed by the efforts of several participants in this conference since 2009. Keeping with this tradition, this year a new paper demonstrates theory and practice that pushes the Church-Turing thesis boundaries and demonstrates a novel low-latency and high-performance edge computing solution. In addition, there are nine full papers describing advances in current distributed and cloud computing practices dealing with quality of service, business intelligence, cloud security, Internet of Things, cloud performance and economics.

Advances in our understanding of the nature of cognition in its myriad forms (Embodied, Embedded, Extended, and Enactive) displayed in all living beings (cellular organisms, animals, plants, and humans) and new theories of information, info-computation and knowledge are throwing light on how we should build software systems in the digital universe which mimic and interact with intelligent, sentient and resilient beings in the physical universe. Recent attempts to infuse cognition into computing systems to push the boundaries of Church-Turing thesis have led to new computing models that mimic biological systems in encoding knowledge structures using both algorithms executed in stored program control machines and neural networks. This paper presents a new model and implements an application as hierarchical named network composed of microservices to create a managed process workflow by enabling dynamic configuration and reconfiguration of the microservice network. We demonstrate the resiliency, efficiency and scaling of the named microservice network using a novel edge cloud platform by Platina Systems. The platform eliminates the need for Virtual Machine overlay and provides high performance and low-latency with L3 based 100 GbE network and SSD support with RDMA and NVMeoE. The hierarchical named microservice network using Kubernetes provisioning stack provides all the cloud features such as elasticity, autoscaling, self-repair and live-migration without reboot. The model is derived from a recent theoretical framework for unification of different models of computation using “Structural Machines.” They are shown to simulate Turing machines, inductive Turing machines and also are proved to be more efficient than Turing machines. The structural machine framework with a hierarchy of controllers managing the named service connections provides dynamic reconfiguration of the service network from browsers to database to address rapid fluctuations in the demand for or the availability of resources without having to reconfigure IP address base networks.

Cloud Computing is evolving towards big infrastructures with next generation hardware and services embedding business service intelligence to create complex distributed workflow execution services. Servide providers want to assure service delivery on a massive scale with global interoperability. The scale of distributed applications and their management have taken a new dimension demanding tolerance to wild fluctuations both in workloads and available computing resource pools. In this context, the problem of vendor lock-in is still a very discussed issue and companies are experimenting multi-cloud and various cloud agnostic solutions. In this 2018 edition of CDCGM there are 6 papers describing solutions to improve the current cloud computing practices dealing with quality of service, adaptive algorithms and software defined network architectures.

In recent years, the widespread use of container technologies has significantly altered the interactions between cloud service providers and their customers when developing and offering services. The shift away from Virtual Private Server scenarios in Infrastructure-as-a-Service environments requires drastically changing the deployment strategies adopted by service providers. This also opens many questions on what information must be supplied by customers and how to improve the performance of user applications, especially in the case of communication-intensive applications. In this work, the authors propose the adoption of a new framework for Mesos Clusters that aims to improve the deployment strategies of communication intensive applications. Coope4M is based on the partitioning of the user application graph via the Isolation Index parameter obtained through user-knowledge on the degree of the communication between its components.

This track started in 2009 with opening remarks from the Chair observing that the computing cloud evolution depends on research efforts from the infrastructure providers creating next generation hardware that is service friendly, service developers that embed business service intelligence in the computing infrastructure to create distributed business workflow execution services and service providers who assure service delivery on a massive scale with global interoperability. The state of the art architecture and evolution of the cloud at that time was already increasing datacenter complexity by piling up new layers of management over the many layers that already exist. Since then, the scale of distributed applications and their management have taken a new dimension demanding tolerance to wild fluctuations both in workloads and available computing resource pools. There are many calls to go cloud native and architect applications using the many services provided by the cloud providers such as Amazon Web Services. On the other hand, there are also calls for avoiding vendor lock-in by going multi-cloud and becoming cloud agnostic. In this conference there is a new paper that proposes cloud agnostic approach with globally interoperable cloud network using private or public network while reducing the complexity of Virtual machine image motion across clouds. In addition, there are 7 papers describing advances in current distributed and cloud computing practices dealing with quality of service, adaptive algorithms and software defined network architectures.

This paper describes the extension of the work started in the first Cloud Computing session in WETICE 2009. A new computing paradigm using distributed intelligent managed elements (DIME) and DIME network architecture introduced in WETICE2010 is used to demonstrate globally interoperable public and private cloud network deploying cloud agnostic workloads. The workloads are cognitive and capable of self-provisioning, self-healing, self-monitoring and self-controlling to adjust their structure and maintain desired quality of service. The agent architecture brings work-load resiliency and tolerance to fluctuations both in demand and available resource pools at scale. A three tier marketing application consisting of an author module, publisher module and a dispatcher module is used to demonstrate workload deployment in an interoperable cloud network using the public Internet. Cloud agnostic inter-cloud and intra-cloud auto-scaling, auto-failover and live migration are demonstrated. This approach goes against the current trend to make workloads cloud-native and provides workload management on any infrastructure be it a bare-metal server, a virtual machine or a container.

In the last years, several projects are emerged with the aim to addressing the challenge of providing solutions for deployment, monitoring, adaptation, and management of clouds belonging to different enterprises/organisations. In such scenarios the network connectivity is one of the key factors. SDN technologies represent a good solution to face this challenge. Separating the control plane from the data plan, they can supply the cloud provider with the opportunity to specify on-the fly both the network topologies and routing schemes, guaranteeing, at same time, specific level of isolation. ASSDN, the framework presented in this paper, represents the first attempt to face this kind of issue. Driving the SDN controllers of all the Network Providers involved, it allows to create, handle and monitor virtual networks that are able to span across several heterogeneous cloud environments so to guarantee specific level of QoS.

This track has made significant contribution to advance the current state of the art in enterprise distributed application management across data centers, and clouds public or private. The scale of distributed applications and their management have taken a new dimension demanding tolerance to wild fluctuations both in workloads and available computing resource pools. A new computing model proposing extensions to the current von Neumann implementation of the Turing machine was contributed by the efforts of participating in this conference since 2009. The result is a practical demonstration of these concepts, showing infrastructure agnostic auto-fail over, auto-scaling and live-migration of even state-sensitive distributed applications. By eliminating virtual image motion which is the current state of the art, this approach improves efficiency and reduces complexity and tool fatigue prevalent in todays enterprises. In addition, a review of the super recursive algorithms and inductive Turing machines in this track provides the theoretical foundation for new computing. In addition, there are five full papers describing advances in current distributed and cloud computing practices dealing with quality of service, adaptive algorithms and software defined network architectures. One short paper discusses a new approach for resource allocation in distributed systems. On the eve of the 25th anniversary of WETICE, this track attests to its success where the work started here has contributed to both theoretical and practical application going from ideation to application within a span of 6 years.

This paper describes the result of the work started in the first Cloud Computing session in WETICE 2009. During the last seven years, collaboration from participants in WETICE has resulted in a new computation model and a commercial product that advances the state of the art in infrastructure agnostic distributed application life-cycle quality of service management. In WETICE 2016, celebrating its 25th anniversary, we demonstrate the resulting new technology with extensions to the Turing machine models to include manageability of distributed applications in the face of wild fluctuations in available computing resources or fluctuations introduced by the interactions between the computation and its environment or both.

This track started with the first Cloud Computing session in WETICE2009 with the observation that the cloud computing evolution depends on research efforts from the infrastructure providers creating next generation hardware that is service friendly, service developers that embed business service intelligence in the network to create distributed business workflow execution, assure service delivery on a massive scale with global interoperability while dealing with non-functional requirements such as security, availability, performance, compliance, cost and fluctuations both in resources and workloads. It was pointed out that the architecture and evolution of the cloud is increasing data enter complexity by piling up new layers of management over the many layers that already exist. Current session proves the epigram by Jean-Baptiste (1849) "plus ça change, plus c'est la mêeme chose." Literally "The more it changes, the more it's the same thing". In this conference, one paper presents the result of the discussions started in these sessions in 2009 that led to a policy based dynamic workflow orchestration independent of the infrastructure orchestration which eliminates the need for moving Virtual Machine images and interfaces to myriad infrastructure management systems at runtime. The architecture is derived from the well-understood and time-tested distributed systems such as cellular organisms, human organizational structures and telecommunication networks. In addition, eight full papers and three short papers continue to make progress on current state of the art. Based on the papers presented in these sessions over the last six years, we boldly predict that we are on the verge of a synthesis of the thesis of current state of the art and the anti-thesis of increasing complexity to address scaling and fluctuations in distributed systems.

Distributed systems are dynamic systems where software and hardware together deliver information processing services to allow modelling, interaction, reasoning, analysis and control of the external environment. The intent of the distributed computation is to execute computational workflows using computing resources. The software contains the algorithms that specify the tasks while the hardware provides the required resources to execute the algorithms. The initial structure is defined by the association of software with hardware and the dynamic structure is defined by their temporal evolution. The meta-knowledge of the intent of the algorithm, the association of specific algorithm to a specific device, their temporal evolution and exception handling when the computation deviates from the intent is outside the software and hardware design and is expressed in non-functional requirements. In this paper, we describe an architecture to capture the meta-knowledge in meta-containers and enforce the intent of the computation while the computation is in progress.

Today, the Infrastructure as a Service (IaaS) cloud environments represent a market share on which many big economical players (Amazon, Microsoft, Rack space) are converging. The hetereogenity and the degree of customization of Cloud features and funcionalities supplied, the different pricing model adopted, the different QoS strategies proposed to the customer make this market very fragmented. Within this context, the workflows represent a common models to describe both business and scientific enterprise application. This paper proposes a novel modular workflow management system called IWoM (Iaas Workflow Manager) that can work with different (public or private) IaaS platforms. Through IWoM a Cloud provider can offer to its customers a simple way to compose a workflow, associate to it with a set of QoS parameters, automatically deploy it on a IaaS middleware and handle all the operations related with the QoS provisioning. To probe the benefits of IWoM, authors analyse the deployment of workflows on the PRISMA platform, a cloud infrastructure oriented to the the provision, control and monitoring of business process belonging to EU public administrations.

Current state-of-the-art infrastructure-centric deployment and management of distributed web-scale applications cannot scale and meet the demands of changing workloads and increasing demands on application availability, mobility and security. The DIME network architecture has matured during the last four years to offer an alternative to provide a post-Hyper visor, Hyper-Cloud network of applications spanning across physical or virtual servers with self-management properties. The first paper presented in this conference, addresses a new computing architecture. A second paper describes an implementation showing its usefulness in addressing fault, configuration, accounting, performance, as well security of service transactions spanning across data enters and multiple clouds with or without virtualization. In addition, infrastructure optimization strategies for Cloud computing continue to provide a fertile ground for research and five papers address these topics. Two papers address scheduling and optimization issues in Grid computing while three more papers address various aspects of content management, distributed and parallel computing. The remaining papers embrace interesting topics related to applications of Cloud Computing in different areas of scientific Cloud computing, collaborative platforms, and big data analysis.

The advent of virtualization technologies and cloud computing has improved application provisioning speed, resource utilization, fault-management, availability using auto-failover and performance optimization using auto-scaling in distributed computing environments. However, heterogeneous virtualization technologies offered by different service providers with disparate infrastructure and their orchestration and management systems have also increased the complexity of managing distributed applications and vendor lock-in. In this paper we utilize new computing, management and programming models introduced using the DIME network architecture to provide end to end service visibility and control across distributed physical or virtual infrastructure. Resulting decoupling of application and service transaction management from myriad distributed infrastructure management systems at run-time enables policy based, secure, service mobility across physical servers or virtual machines deployed in data enters or public clouds. Using the new architecture we have implemented service self-repair, auto-scaling, live-migration and end-to-end service transaction security independent of server and network security mechanisms.

The use of virtualization technologies and the introduction of multi-core processors have strongly influenced the way of designing and developing software systems. Thus controlling and effectively managing them is became a fundamental issue, especially in distributed scenarios, as Clouds or Grids, providing QoS-assured services on demand. In this work, the authors propose the adoption of a management layer composed by several, parallel and cooperating sub managers (acting as independent controllers) handling, each one, different aspects (i.e., concerns or topics) of the underlying control system. The separation of concerns, together with the parallelism of managers and with their fractal organization, are fundamental for improving the performance of the whole management system.

By introducing signaling and self-management in a Turing node and a signaling network as an overlay over the computing network, the current von-Neumann computing model is evolved to bring the architectural resiliency of cellular organisms to computing infrastructure. The DIME computing model introduces the genetic transactions of replication, repair, recombination and reconfiguration to program self-resiliency in distributed computing systems executing a managed workflow. The injection of parallelism and network based composition of "Self" identity are the first steps in introducing the elements of homeostasis and self-management in the computing infrastructure. DIMEs inject the architectural resiliency of cellular organisms to create a new class of distributed autonomic computing systems using managed Turing machine networks.

The optimal allocation of Communication-Intensive Applications is a well-know complex issue in Clouds. This kind of applications, due to the strong impact of communications on their performance, requires not only that their tasks are allocated on resources able to satisfy their computational requirements but also that the distance among these resources, in terms of communication delay or latency, is the smallest. The allocation strategies currently used, based on a static vision of resources' status, are not suitable for managing effectively the peculiarities of these applications. In this work we propose an innovative allocation strategy that, using information about the sequence of their internal interactions, improves the deployment of Communication-Intensive Applications on available resources. In particular, this strategy allows reducing the number of resources needed for executing each application and, very important, it allows reducing the influence of each application over the performance of the other ones running on the same cloud.