The advancement towards B5G/6G relies on the synthesis of connect-compute platforms and their use in highly heterogeneous clusters featuring hardware accelerators. While these accelerators offer improved computational efficiency, sill, they make development, deployment, and orchestration of services more complex, with limited flexibility, and necessitate domain-specific knowledge. In AI@EDGE we are targeting seamless integration of such diverse platforms for executing AI-related tasks. This paper focuses on acceleration aspects and presents a MEC system that facilitates AI servicing over a cluster of FPGA, GPU, and CPU nodes. To this end, we develop our custom tools for generating multi-variant AI models, informative function descriptors, flexible MEC orchestrators, and runtime resource managers. The results show successful interoperability, with generic Python models getting deployed/migrated across distinct platforms for performance gains in the area of 10x.

Abstract The School-Work Alternation (SWA) programme was developed (under a European Commission call) to bridge the gaps and establish a well-tuned partnership between education and the job market. This work details the development of the AI4Citizen pilot, an AI software suite designed to support the SWA programme. The AI4Citizen pilot, developed within the H2020 AI4EU project, offers AI tools to automate and enhance the current SWA process. At the same time, the AI4Citizen pilot offers novel tools to support the complex problem of allocating student teams to internship programs, promoting collaborative learning and teamwork skills acquisition. Notably, the AI4Citizen pilot corresponds to a pipeline of AI tools, integrating existing and novel technologies. Our exhaustive empirical analysis confirms that the AI4Citizen pilot can alleviate the difficulties of current processes in the SWA, and therefore it is ready for real-world deployment.

An effective, efficient, and ecological transport service needs a decision support system to inform the administrations, while intelligently assisting citizens' daily transportation choices. This work presents a full-fledged Gamification Platform to develop and run sustainable mobility campaigns promoting individual green mobility behaviors. We organize geolocalized and temporal information on users' tracked trips into a rich dataset that decision-makers can exploit to analyze citizens' daily transportation choices and balance the demand and the offer of the mobility ecosystem. Through the Gamification Platform, we define three different use case scenarios - i.e., mobility within the city, home-work mobility, and home-school mobility. We also evaluate the platform according to both gameful design guidelines and persuasive technology best practices. Our findings show how long-term retention and engagement can be achieved when the gameful system's design and maintenance are assisted by the Gamification Platform, merging both administrative requirements and users' needs towards an iteratively adaptive and personalized experience.

The idea to build systems based on services, by reusing and combining software made available independently via different technologies and channels and dynamically organizing them into coherent processes, has a very well recognized potential. Achieving this potential stands crucially on the ability to recognize and exploit the context in which such applications operate, in terms of the available services, of the actual setup at run-time, and of the interaction with human actors. Changing contexts require run-time reaction, by adapting the ongoing overall process enacted by the service-based system to unexpected deviations. Continuous context-aware adaptation is hencefore a strong requirement in this setting. In this paper, we propose a service delivery platform designed for the continuous context-aware adaptation of service-based systems, based on the idea of monitoring the underlying context via a hierarchical model, and using the context to drive the choice and execution of adaptive pervasive flows. We describe the approach through an example from the smart cities e-mobility domain.

Data-flow requirements is an important aspect of service composition. Although several approaches have been proposed to specify data-flow requirements, they cannot be efficiently exploited in dynamic setting, for example, where the composition participants (i.e., component services) need to be dynamically replaced. In this paper, we propose a new modeling methodology for data-flow requirements, in which we explicitly distinguish a data model of a composite service from data models of component services. We show that following our methodology, a composition can be adjusted to various dynamic changes with significantly less effort. We implement our solution using planning techniques and make its basic evaluation on a scenario from the travel domain.

Adaptation of service-based applications (SBA) is not trivial in their heterogeneous and dynamic execution context. While different approaches exist, most of them focus on a specific part of the SBA ignoring the overall impact of the adaptation on the whole application. In this paper we propose a cross-layer adaptation manager (CLAM) that tackles this problem.

Automated composition of services is a key functionality for the adoption of the service-oriented development paradigm. Solving this problem in practice requires the ability to consider asynchronous stateful services and to express complex composition requirements which may span different phases of the life-cycle of component services. In this paper we present a novel automated service composition approach which addresses these challenges by associating so-called 'objects' to services, and by introducing a simple yet powerful notation to express composition requirements on them. We recast this view of the problem as a specific form of planning; our experiments on a prototype implementation witness the ability of our approach to deal with realistic scenarios and requirements that cannot be tackled by other current approaches.

Telecommunication is a key area where the use of web services has an enormous potential to facilitate the development of powerful and complex functionalities on top of existing ones. At the same time, the specific features of TelCo applications (asynchronous, event-driven communications, handling concurrent, long-running transactions, dynamically evolving sets of partners) pose difficult challenges to the adoption of standard languages and tools for web services. In this work, based on our analysis of TelCo standards and applications, we discuss a set of orchestration patterns, and show how these can be modeled using the WS-BPEL language. We also address the issue of guaranteeing the correctness of such applications, providing an automated support for the formal analysis of their behavior.

In this paper we present an approach for modelling and analyzing time-related properties of Web service compositions defined as a set of BPEL4WS processes. We introduce a formalism, called Web service timed state transition systems (WSTTS), to capture the timed behavior of the composite Web services. We also exploit an interval temporal logic to express complex timed assumptions and requirements on the system's behavior. Building upon of this formalization, we provide techniques and tools for model checking BPEL4WS compositions against time-related requirements. We perform a preliminary experimental evaluation of our approach and tools with the help of the e-government case study.

The data exchanged among the Web services participating to a composition are clearly very relevant for a correct behavior of the composition. Nevertheless, most of the approaches existing in the literature for the static verification of Web service compositions ignore data, or require very small ranges to be associated to the data types. In this paper, we propose an approach for the verification of Web service compositions that takes into account the dataflows among the component process. The approach exploits abstraction techniques for modeling those aspects of data that are relevant for the correctness of the composition and hiding the aspects that are irrelevant. We show that building the right abstraction corresponds to defining those assumptions on the data manipulations performed by the component services which are crucial for the correctness of the composition

In this paper we address the problem of qualitative and quantitative analysis of timing aspects of Web service compositions defined as a set of BPEL4WS processes. We introduce a formalism, called Web service timed state transition systems (WSTTS), to capture the timed behavior of the composite Web services. We also exploit an interval temporal logic to express complex timed assumptions and requirements on the system's behavior. Building on top of this formalization, we provide techniques and tools for model-checking BPEL4WS compositions against time-related requirements. We also present a symbolic algorithm that can be used to compute duration bounds of behavioral intervals that satisfy such requirements. We perform a preliminary experimental evaluation of our approach and tools with the help of an e-Government case study

In this paper we describe an approach for the verification of Web service compositions defined by sets of BPEL processes. The key aspect of such a verification is the model adopted for representing the communications among the services participating in the composition. Indeed, these communications are asynchronous and buffered in the existing execution frameworks, while most verification approaches assume a synchronous communication model for efficiency reasons. In our approach, we develop a parametric model for describing Web service compositions, which allows us to capture a hierarchy of communication models, ranging from synchronous communications to asynchronous communications with complex buffer structures. Moreover, we develop a technique to associate with a Web service composition the most adequate communication model, i.e., the simplest model that is sufficient to capture all the behaviors of the composition. This way, we can provide an accurate model of a wider class of service composition scenarios, while preserving as much as possible an efficient performance in verification.