Digital-twin platforms are increasingly adopted in energy infrastructure management for smart grids. Novel opportunities arise from emerging artificial intelligence technologies to increase user trust by enhancing predictive and prescriptive analytics capabilities and by improving user interaction paradigms. This paper presents a novel data-driven and knowledge-based energy digital-twin framework and architecture. Data integration and mining based on machine learning are integrated into a knowledge graph annotating asset status data, prediction outcomes, and background domain knowledge in order to support a retrieval-augmented generation approach, which enhances a conversational virtual assistant based on a large language model to provide user decision support in asset management and maintenance. Components of the proposed architecture have been mapped to commercial-off-the-shelf tools to implement a prototype framework, exploited in a case study on the management of a section of the high-voltage energy infrastructure in central Italy.

Home and building automation (HBA) trends toward the Ambient Intelligence paradigm, which aims to autonomously coordinate and control appliances and subsystems in a given environment. Nevertheless, HBA is based on an explicit user-home interaction and basically enables static and predetermined scenarios. This paper proposes a more flexible multi-agent approach, leveraging semantic-based resource discovery and orchestration for HBA applications. Backward-compatible enhancements to EIB/KNX domotic standard allow to support the semantic characterization of user profiles and device functionalities, thus enabling: 1) negotiation of the most suitable home services/functionalities according to implicit and explicit user needs and 2) device-driven interaction for adapting the environment to context evolution. A power-management problem in HBA is presented as a case study to better clarify the proposal and assess its effectiveness.

Novel Internet of Things (IoT) applications and services rely on an intelligent understanding of the environment leveraging data gathered via heterogeneous sensors and micro-devices. Though increasingly effective, Machine Learning (ML) techniques gen

The Semantic Web and Internet of Things visions are converging toward the so-called Semantic Web of Things (SWoT). It aims to enable smart semantic-enabled applications and services in ubiquitous contexts. Due to architectural and performance issues, it is currently impractical to use existing Semantic Web reasoners. They are resource consuming and are basically optimized for standard inference tasks on large ontologies. On the contrary, SWoT use cases generally require quick decision support through semantic matchmaking in resource-constrained environments. This paper presents Mini-ME, a novel mobile inference engine designed from the ground up for the SWoT. It supports Semantic Web technologies and implements both standard (subsumption, satisfiability, classification) and non-standard (abduction, contraction, covering) inference services for moderately expressive knowledge bases. In addition to an architectural and functional description, usage scenarios are presented and an experimental performance evaluation is provided both on a PC testbed (against other popular Semantic Web reasoners) and on a smartphone.

Due to the rapid expansion of e-commerce and urbanization, Last-Mile Delivery (LMD) faces increasing challenges related to cost, timeliness, and sustainability. Artificial intelligence (AI) techniques are widely used to optimize fleet management, while augmented and mixed reality (AR/MR) technologies are being adopted to enhance warehouse operations. However, existing approaches often treat these aspects in isolation, missing opportunities for optimization and operational efficiency gains through improved information visibility across different roles in the logistics workforce. This work proposes the adoption of novel technological solutions integrated in an LMD framework that combines AI-based optimization of shipment allocation and vehicle route planning with a knowledge graph (KG)-driven decision support system. Additionally, the paper discusses the exploitation of relevant recent tools, including large language model (LLM)-powered conversational assistants for managers and operators and MR-based headset interfaces supporting warehouse operators by providing real-time data and enabling direct interaction with the system through virtual contextual UI elements. The framework prioritizes the customizability of AI algorithms and real-time information sharing between stakeholders. An experiment with a system prototype in the Apulia region is presented to evaluate the feasibility of the system in a realistic logistics scenario, highlighting its potential to enhance coordination and efficiency in LMD operations. The results suggest the usefulness of the approach while also identifying benefits and challenges in real-world applications.