Abstract

Abstract

Abstract
[No abstract available]

Abstract
The structural changes in the energy sector caused by renewable sources and digitization have resulted in an increased use of Artificial Intelligence (AI), including Machine Learning (ML) models. However, these models' black-box nature and complexity can create issues with transparency and trust, thereby hindering their interpretability. The use of Explainable AI (XAI) can offer a solution to these challenges. This paper explores the application of an XAI-based framework to analyze and evaluate a photovoltaic energy generation forecasting problem and contribute to the trustworthiness of ML solutions.

Abstract
Automatic energy management systems allow users' active participation in flexibility management while assuring their energy demands. We propose a transparent framework for automated energy management to increase trust and improve the learning process, combining machine learning, experts' knowledge, and semantic reasoning. A practical example of thermal comfort shows the advantages of the framework.

Abstract
The significant changes the electricity sector has been suffering in the latest decades increased the complexity and unpredictability of power and energy systems (PES). To deal with such a volatile environment, different software tools are available to simulate, study, test, and support the decisions of the various entities involved in the sector. However, being developed for specific subdomains of PES, these tools lack interoperability with each other, hindering the possibility to achieve more complex and complete simulations, management, operation and decision support scenarios. This paper presents the Intelligent Energy Systems Ontology (IESO), which provides semantic interoperability within a society of multi-agent systems (MAS) in the frame of PES. It leverages the knowledge from existing and publicly available semantic models developed for specific domains to accomplish a shared vocabulary among the agents of the MAS society, overcoming the existing heterogeneity among the reused ontologies. Moreover, IESO provides agents with semantic reasoning, constraints validation, and data uniformization. The use of IESO is demonstrated through a case study that simulates the management of a distribution grid, considering the validation of the network's technical constraints. The results demonstrate the applicability of IESO for semantic interoperability, reasoning through constraints validation, and automatic units' conversion. IESO is publicly available and accomplishes the pre-established requirements for ontology sharing.