Universal Digital Twin - A Dynamic Knowledge Graph

Abstract

This paper introduces a dynamic knowledge-graph approach for digital twins and illustrates how this approach is by design naturally suited to realizing the vision of a Universal Digital Twin. The dynamic knowledge graph is implemented using technologies from the Semantic Web. It is composed of concepts and instances that are defined using ontologies, and of computational agents that operate on both the concepts and instances to update the dynamic knowledge graph. By construction, it is distributed, supports cross-domain interoperability, and ensures that data are connected, portable, discoverable, and queryable via a uniform interface. The knowledge graph includes the notions of a “base world” that describes the real world and that is maintained by agents that incorporate real-time data, and of “parallel worlds” that support the intelligent exploration of alternative designs without affecting the base world. Use cases are presented that demonstrate the ability of the dynamic knowledge graph to host geospatial and chemical data, control chemistry experiments, perform cross-domain simulations, and perform scenario analysis. The questions of how to make intelligent suggestions for alternative scenarios and how to ensure alignment between the scenarios considered by the knowledge graph and the goals of society are considered. Work to extend the dynamic knowledge graph to develop a digital twin of the UK to support the decarbonization of the energy system is discussed. Important directions for future research are highlighted.

Universal Digital Twin: Land use

“…The design of the World Avatar has been demonstrated as one way to implement a comprehensive Universal Digital Twin, for example a digital twin of the UK (Akroyd et al, 2021). The design confers a number of advantages which include the adoption of a distributed architecture that supports a uniform interface to query multiple data sources, the ability to use logical reasoning to verify the consistency of semantic models (Devanand et al, 2021), and a mechanism that allows computational agents to interact to answer questions (Zhou et al, 2019(Zhou et al, , 2020.…”

“…This is a complex challenge and the ability to explore and assess different options can be aided through digitalization (Inderwildi et al, 2020). Dynamic knowledge graph technology developed as part of the World Avatar project (Eibeck et al, 2019; The World Avatar, 2021a) has been shown to provide an architecture that is suitable for implementing a Universal Digital Twin that can support the analysis of choices involving complex systems that is inherent to this type of challenge (Akroyd et al, 2021; CMCL Innovations, 2021). In this approach, autonomous computational agents interact to perform tasks including updating the knowledge graph to ensure that it remains current in time, simulating the behavior of systems and sending responses back to the physical world.…”

“…In this approach, autonomous computational agents interact to perform tasks including updating the knowledge graph to ensure that it remains current in time, simulating the behavior of systems and sending responses back to the physical world. It has been shown how this architecture can be used to implement digital twins that provide information about the state of the world, provide intelligent control using computational agents to model the behavior of complex systems and provide support for intelligent design via what-if scenario analysis (Eibeck et al, 2020; Akroyd et al, 2021). The World Avatar approach employs Semantic Web technologies (Berners-Lee et al, 2001; W3C, 2015) to provide a uniform method to query and host distributed data.…”

“…The design concept is illustrated in Figure 1.

Figure 1. The design of the World Avatar dynamic knowledge graph. Image reproduced from Akroyd et al (2021) under a CC BY 4.0 license.

…”

“…Work to develop a dynamic-knowledge-graph-based Universal Digital Twin of the UK (Akroyd et al, 2021; CMCL Innovations, 2021) is ongoing. The digital twin currently includes a description of all the power plants in the UK (Atherton et al, 2021).…”