Explainable cyber-physical energy systems based on knowledge graph

Explainability can help cyber-physical systems alleviating risk in automating decisions that are affecting our life. Building an explainable cyber-physical system requires deriving explanations from system events and causality between the system elements. Cyber-physical energy systems such as smart grids involve cyber and physical aspects of energy systems and other elements, namely social and economic. Moreover, a smart-grid scale can range from a small village to a large region across countries. Therefore, integrating these varieties of data and knowledge is a fundamental challenge to build an explainable cyber-physical energy system. This paper aims to use knowledge graph based framework to solve this challenge. The framework consists of an ontology to model and link data from various sources and graph-based algorithm to derive explanations from the events. A simulated demand response scenario covering the above aspects further demonstrates the applicability of this framework.