Abstract / Description
The University of Cambridge in collaboration with the Cambridge Centre for Advanced Research and Education in Singapore (CARES) started research related to “The World Avatar” (TWA) in 2013. TWA is a dynamic world model based on knowledge graph technology, so far mainly used in the areas of energy, chemical industry and urban digitalisation and planning. This research has received considerable funding from the Singapore Government and international recognition over the last decade. The TWA concept intends to capture the idea of representing every aspect of the real world in a digital world. This is essentially an extension of the Digital Twin notion. A natural continuation is the application of this approach beyond the industrial context – the virtualisation of any abstract concept or process, similar to the extension of the Internet of Things to the Internet of Services.
TWA started with a focus on virtualising the industrial operations on the Jurong Island Eco-Industrial Park in Singapore, but has since expanded well beyond this original scope. Fundamental to TWA is a dynamic knowledge graph that is envisaged as general-purpose and all-encompassing. Beyond mere data representation, TWA contains an ecosystem of autonomous software agents that act on the knowledge graph, constantly updating it so that it evolves in time. Crucially, the agents themselves are part of the knowledge graph, governed by an agent ontology. Agents have been developed for automatic agent discovery and composition, i.e. to create new composite agents for more complex tasks. An agent marketplace based on blockchain technology and smart contracts has been developed to facilitate the use of agents and simplify the identification of an agent suitable for a specific task.
This application of dynamic knowledge graphs presents a candidate to solve problems caused by lack of interoperability between different types of data and models. We believe that it has the potential to unify many different research streams, promoting synergistic effects that would be difficult to achieve in other ways. The attached paper explains 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.
More information and open access preprints for all our work can be found on our group website: https://como.ceb.cam.ac.uk/research/cps/.
A preview of some of the areas that we have investigated with our collaborators at CMCL can be found here: https://kg.cmclinnovations.com/.