Digital twins are computer models of the real business world. They help asset owners understand the details of what is happening, in real-time as well as retrospectively. They are increasingly being applied in the context of asset tracking, building and engineering maintenance, transport or cargo tracking, operations management, oil and gas flows, financial flows, compliance, and more.
Modern digital twins are built on top of knowledge graphs, platforms which can not only scale to the vast amounts of data accrued by assets and people, but also deal with the intricate structures and relationships between them. In turn, this deepens CIO visibility into key business processes.
The reason behind the success of this next generation of digital twins is the convergence of analytics, data science, machine learning, and AI (Artificial Intelligence). Knowledge graphs are being deployed because they make data smarter, and provide a superior underlay for those techniques.
A knowledge graph is an interconnected dataset enriched with business semantics. It allows you to reason about the underlying data, and use that data for complex decision-making at scale. And that’s not something traditional data management systems (like relational databases) can offer.
Connecting your digital twin with external data opens up use cases
That’s because when data gets ingested into a graph database, relationships are stored as first-class citizens, not as some afterthought to be expensively computed later. Business assets in the knowledge graph are natively connected to their neighbours, and their neighbours, and so on. That means that as the knowledge graph grows and gets richer, it becomes more useful.
Moreover, the rich network of data in your new graph-based knowledge graph becomes very useful to your data science team. The topology of the knowledge graph provides opportunities for powerful graph analytics and graph machine learning – tools which are only available to graph users.
Adding onto that graph visualisation means that users who adopt a graph-based digital twin get an immediate head-start in understanding and managing their physical business, as well as being able to respond quickly to events and look for future problems. And as knowledge graph users find, connecting a digital twin with external data from assets, sensors, markets, and even weather forecasts opens up many use cases.
The kind of living simulation mirroring the real world a digital twin embodies allows security experts to run vulnerability tests without disrupting everyday services. It’s a technology that can be used to simulate cyberattacks, providing a great aid with threat detection and smart decision-making should a breach occur. Digital twins can be used to carry out network analysis across connected IT systems to rapidly help the security team better identify vulnerabilities and quarantine them before they spread to other parts of the infrastructure.
In fact, creating and analysing a graph digital twin of your infrastructure is one of the most effective measures you can take for improving your cybersecurity posture. It’s also very helpful for managing the endless, dynamic complexity of cybersecurity vulnerabilities and threats.
Mapping complex what-if queries and event impacts
A great example of a digital twin knowledge graph comes from Lending Club, a US peer-to-peer lending company. Its knowledge graph perfectly complements its expansive, microservices-based architecture. The Lending Club knowledge graph listens to the systems around the network, including its hundreds of microservices and the underlying servers, switches, and racks the microservices need to operate.
This real-time view of its systems is piped into the knowledge graph, delivering one central view of all events and metrics, so that Lending Club can make sense of a connected domain. Engineers can see what-if real-time events and ask, ‘What happens if this router dies?’ and map the ripples through the graph of which applications, which customers, or which loans might be affected.
Finally, the UK’s Transport for London (TfL) is using graph technology as the basis of a digital twin to achieve quicker identification of traffic disruptions. It states that a graph-based digital twin is more capable than relational databases at handling this interconnected data, enabling faster and more effective interventions. Andy Emmonds, its Chief Transport Analyst, reports that when COVID hit, graph technology was the only way to accurately estimate how long it might take an ambulance to travel from a London hospital to one of the newly-established Nightingale Centres.
These use cases demonstrate that graphs are the perfect solution for data complexity.
If you’re an enterprise looking to build a digital twin to capture real-world complexity and volume, you should model it as a knowledge graph. Non-graph technologies struggle to cope with the complexity and might well fail to give you the meaningful, timely analysis your business needs.
Maya Natarajan is responsible for knowledge graphs at Neo4j. She is passionate about bringing different technologies together to solve complex problems. At Neo4j, Maya is championing the use of knowledge graphs to bring context to various systems. Maya has positioned technologies from Blockchain to Predictive & User-Based Analytics to Machine Learning to Deep Learning to Search to BPM and beyond in a myriad of industries at various small and large companies. Maya started her career in the biotechnology area where she was in R&D focusing on cardiovascular drugs, and she has five patents to her name.