What is a digital twin and why is it important to IoT?

The use of digital twins – digital representations that mimic the structure and behavior of physical objects or systems – is on the rise. Digital twin technology has moved beyond manufacturing, where it got its start, and into many other industries, driven by advances in sensor technologies, artificial intelligence and data analytics.

In the world of IT, enterprises can use digital twins to replicate their IT environments, including infrastructure, network equipment, and Internet of Things (IoT) devices, and then run simulations or what-if scenarios to test the impact of changes and to optimize performance. They can be used to validate the current state of a network, for example, and test configuration changes, firmware updates, or adjustments to security policies.

What is a digital twin?

A digital twin is a digital representation of a physical object or system. In essence, a digital twin is a computer program that takes real-world data about a physical object or system as inputs and produces as outputs predictions or simulations of how that physical object or system will be affected by those inputs.

The digital twin concept first arose at NASA: full-scale mockups of early space capsules, used on the ground to mirror and diagnose problems in orbit, eventually gave way to fully digital simulations.

The technology behind digital twins has expanded to include buildings, factories and even cities, and some have argued that even people and processes can have digital twins, expanding the concept even further.

The term really took off after Gartner named digital twins as one of its top 10 strategic technology trends for 2017, saying that within three to five years, “billions of things will be represented by digital twins, a dynamic software model of a physical thing or system.” 

Today, digital twin technologies continue to gain traction because of their potential to bridge the gap between physical and virtual worlds, according to Grand View Research, which says the global digital-twin market is forecast to expand at a compound annual growth rate (CAGR) of 38% from 2023 to 2030. Incorporating technologies such as artificial intelligence (AI), cloud computing and IoT into digital twin systems is expected to boost market growth in the forecast period, Grand View says.

How does a digital twin work?

A digital twin begins its life being built by specialists, often experts in data science or applied mathematics. These developers research the physics that underlies the physical object or system being mimicked and use that data to develop a mathematical model that simulates the real-world original in digital space.

The twin is constructed so that it can receive input from sensors gathering data from a real-world counterpart. This allows the twin to simulate the physical object in real time, in the process offering insights into performance and potential problems. The twin could also be designed based on a prototype of its physical counterpart, in which case the twin can provide feedback as the product is refined; a twin could even serve as a prototype itself before any physical version is built.

Digital twin vs. simulation

The terms simulation and digital twin are often used interchangeably, but they are different things. A simulation is designed with a CAD system or similar platform, and can be put through its simulated paces, but may not have a one-to-one analog with a real physical object. A digital twin, by contrast, is built out of input from IoT sensors on real equipment, which means it replicates a real-world system and changes with that system over time. Simulations tend to be used during the design phase of a product’s lifecycle, trying to forecast how a future product will work, whereas a digital twin provides all parts of the business insight into how some product or system they’re already using is working now.

Digital twin use cases

Potential use cases for digital twins are expansive. Objects such as aircraft engines, trains, offshore oil platforms, and turbines can be designed and tested digitally before being physically produced. These digital twins could also be used to help with maintenance operations. For example, technicians could use a digital twin to test that a proposed fix for a piece of equipment works before applying the fix.

Manufacturing is the area where rollouts of digital twins are probably the furthest along, with factories already using digital twins to simulate their processes. Automotive digital twins are made possible because cars are already fitted with telemetry sensors, but refining the technology will become more important as more autonomous vehicles hit the road. Healthcare is the sector that could produce digital twins of people; tiny sensors could send health information back to a digital twin used to monitor and predict a patient’s well-being.

What kind of value can digital twins bring to an organization?

Just as digital twins serve different purposes in different industries, the value of digital twins differs depending on the application.

In the world of manufacturing, for example, a digital twin can enable product designers to try out prototypes before settling on a final design. It’s a way to use digital resources to develop and refine products instead of tapping physical engineering resources. With a digital replica of a product that simulates the real thing in a virtual space, designers can rapidly generate new iterations, optimize their product designs, and improve product quality along the way.

In the semiconductor industry, digital twins can exist in the cloud and replace physical research models. In May 2024, the Biden Administration announced plans to fund up to $285 million to create a CHIPS Manufacturing USA institute focused on digital twins for the semiconductor industry: Digital twin-based research can leverage AI “to help accelerate the design of new U.S. chip development and manufacturing concepts and significantly reduce costs by improving capacity planning, production optimization, facility upgrades, and real-time process adjustments,” the US Department of Commerce said in the announcement.

Digital twins have had appeal in certain industries – manufacturing, oil and gas, utilities, mining – “basically physical, high-capital, asset-intensive verticals,” said Jonathan Lang, research director, worldwide IT/OT convergence strategies, at research firm IDC, in an interview with Network World.

In these settings, the rationale for digital twins has been clear, thanks to potential benefits that include better visibility into the health of assets, improved reliability, cost savings, and the ability to ensure stable operations, Lang says. “IT environments such as infrastructure, network equipment, connected devices, etc., have the same value drivers,” he says.

What kinds of digital twins are there?

IBM offers a categorization scheme based not on specific industries but on the complexity of what’s being twinned. This provides a useful way to think about the needs in specific use cases and gives a look at the broad spectrum of what digital twins can do:

• Component or part twins simulate the smallest example of a functioning component.
• Asset twins simulate two or more components working together and let you study the interactions between them.
• System or unit twins let you see how multiple systems assets work together, simulating an entire production line, for instance.
• Process twins take the absolute top-level view of systems working together, letting you figure out how an entire factory might operate.

It’s worth noting that adding more components to the mix adds complexity. In particular, mixing and matching components from different manufacturers can be difficult because you’d need everyone’s intellectual property to play nice together within the world of your digital twin.

Advantages and benefits of digital twins

In the world of IT, digital twins that simulate IT infrastructure can:

• Strengthen security: “Network digital twins offer noteworthy security benefits, including critical vulnerability identification and prioritized remediation plans specific to individual device configurations and features in use,” said Chiara Regale, senior vice president, product and user experience at Forward Networks, in an interview with Network World about reasons to consider a network digital twin.
• Improve documentation: “Every enterprise is terrible at documentation, due to priorities around delivery, lack of standards on how to record infrastructure changes, and sprawl,” Michael Wynston, director of network architecture and automation at financial services firm Fiserv, told Network World. Digital twin technology can provide insights into the infrastructure beyond just configurations, including what the environment is doing at any given time. This is essential for successful documentation.
• Boost efficiency: Digital twins enable simulation of data across multiple business systems. IDC research has shown that IT organizations are losing lots of time searching for necessary information to perform a job function. “By unifying the data in a single interface, as well as performing analysis across multiple data sets, digital twins improve worker efficiency and the quality and accuracy of analytical outputs,” said IDC analyst Jonathan Lang.
• Create a better digital experience: A company can create a digital twin to help enhance digital experience, which is the sum of a user’s digital-based interactions with a product, service, device, etc. “Digital experience twins are a new concept that virtualizes an end user, application, or IoT device to validate the network experience and predict problems before they impact user experience,” says Bob Friday, chief AI officer at Juniper Networks.

How can a digital twin affect an organization’s environmental sustainability?

The proportion of companies implementing a data center infrastructure sustainability program will rise from about 5% in 2022 all the way to 75% by 2027, as sustainability becomes an increasingly central consideration for cost optimization and risk management, according to data from Gartner Research. Industry watchers have made the case that a digital twin can aid in companies’ sustainability efforts. Some potential tie-ins between digital twins and sustainability in the IT arena include:

• Improved systems management, which can lead to lower downtime and more advanced power-management capabilities.
• Better inventory and asset-management practices, which allow IT to maximize enterprise server and storage deployments and identify idle capacity.
• Easier identification of older, energy-hogging gear, which can be replaced with newer generation hardware with better energy performance.

Dr. Mano Rao, IT director for global manufacturing at General Motors, wrote this in a blog about GM’s work with GE Digital to pursue model-based system engineering: “At GM, we developed a Virtual Factory Testbed to provide the tools and environment needed to test all manufacturing process variations that are necessary to support build-to-order manufacturing, as well as all permutations of outcomes that can result from each operation. We employ a process digital twin to mimic plant-floor behavior and test the integration of OT and IT systems—without requiring the physical lines to be deployed, and without requiring physical products flowing down the line. Not only does this help GM’s competitive advantage, but it brings us closer to our sustainability commitments.”

Applications of digital twin in various industries

Digital twins can be deployed in many industries. Here are some examples:

• Enterprise IT:  A digital twin can replicate an IT environment, including infrastructure, network equipment, and IoT devices. IT teams can use the digital twin to test configuration changes or adjust security policies, for example.
• Semiconductor industry: Digital twins can enable more collaborative design among engineers and researchers, speeding the exchange of ideas and reducing the cost of research and development.
• Manufacturing operations: In the manufacturing industry, a digital twin can streamline design processes, improve collaboration among designers, and help to reduce the material used in a product’s design.
• Healthcare services: In the world of healthcare, a digital twin can improve health monitoring and diagnostic capabilities.
• Automotive industry: Automotive designers and manufacturers use digital twins to shorten time to market, improve safety procedures, monitor product performance, and identify potential maintenance issues.
• Power-generation and utilities: Energy and utility companies can creating a digital twin, or a virtual model, of a power plant or distribution network and use it to streamline operations and identify opportunities to improve performance.
• Urban planning: For urban planning and infrastructure projects, a digital twin can allow city planners to run simulations of new designs – trying out scenarios that could impact traffic congestion or air pollution, for example.

Digital twins and IoT

The explosion of IoT sensors is part of what makes digital twins possible. And as IoT devices are refined, digital-twin scenarios can include smaller and less complex objects, giving additional benefits to companies.

Digital twins can be used to predict different outcomes based on variable data. With additional software and data analytics, digital twins can often optimize an IoT deployment for maximum efficiency, as well as help designers figure out where things should go or how they operate before they are physically deployed.

Digital twin vendors

Building a digital twin is complex, and there is as yet no standardized platform for doing so. The Digital Twin Consortium is a global ecosystem of users who are driving best practices for digital twin usage and defining requirements for new digital twin standards.

One group that’s working to increase awareness, adoption, interoperability, and development of digital twin technology is the Digital Twin Consortium. It’s a global ecosystem of users – including industry, academia, and government members – who are driving best practices for digital twin usage and defining requirements for new digital twin standards.

In contrast with many emerging technologies that are driven by startups, commercial digital-twin offerings are coming from some of the largest companies in the field. For instance, GE, which developed digital-twin technology internally as part of its jet-engine manufacturing process, is now offering its expertise to customers, as is Siemens, another industrial giant heavily involved in manufacturing. Not to be outdone by these factory-floor suppliers, IBM is marketing digital twins as part of its IoT push, and Microsoft is offering its own digital-twin platform under the Azure umbrella.

Digital twin news in the enterprise IT world

Although digital twins have been around for some time, it’s still an early adopter technology. But the number of vendors that offer digital twin solution is growing, and recent upgrades to digital twin offerings in the enterprise IT industry include:

• Forward Networks launched AI Assist, a generative AI feature built into its Forward Enterprise digital twin platform. The addition is designed to give network and security operations professionals comprehensive insights into network performance via natural language prompts. With AI assist, network engineers of varying skill levels can conduct sophisticated network queries, so they can quickly assess network behavior and identify potential issues.
• Juniper Networks introduced Marvis Minis, an AI-native networking digital experience twin that uses the company’s Mist AI technology to proactively simulate user connections. That way it can instantly validate network configurations and detect problems without users being present. The Minis product simulates end-user, client, device and application traffic to learn the network configuration through unsupervised ML, and to proactively highlight network issues. Data from Minis is continuously fed back into Mist AI, providing an additional source of insight for the best responses.
• Nokia extended the capabilities of its existing Nokia Network Digital Twin to include all Android devices, the company announced late last year. Coverage and performance data for Wi-Fi, private and public cellular networks can be automatically collected in real time and processed on Nokia’s edge platform to give enterprises a view of how changes in their operations impact network performance.

Challenges of digital twins

Digital twins offer a real-time look at what’s happening with physical assets, which can radically alleviate maintenance burdens. But keep in mind that that Gartner warns that digital twins aren’t always called for, and can unnecessarily increase complexity. “[Digital twins] could be technology overkill for a particular business problem. There are also concerns about cost, security, privacy, and integration.”

Potential challenges in developing and deploying a digital twin can include:

• Data management: Data ownership can become a problematic point if not addressed, particularly if an organization is partnering with other entities to run its digital twins, said Kayne McGladrey, a senior member of the Institute of Electrical and Electronics Engineers (IEEE), a nonprofit professional association, and field CISO at Hyperproof, in an interview with CSO.
• Security: If proper cybersecurity controls aren’t put in place, digital twins can expand a company’s attack surface, give threat actors access to previously inaccessible control systems, and expose preexisting vulnerabilities, CSO notes in a recent feature.
• Supplier collaboration: A digital twin might have multiple engineers and designers collaborating on a model, so it’s important to create and adhere to well-documented practices for constructing and modifying the models.
• Complexity: A digital twin may only model a single physical asset, but in more complex environments with multiple stakeholders and complicated processes, companies may need to invest in more advanced digital twins, which in turn require advanced skillsets.
• Privacy: Legal and regulatory issues come into play with digital twins, too, McGladrey told CSO. The primary concerns are around whether the operators of digital twins can ensure that the data being used in their digital twins is handled in ways that meet regulatory requirements around privacy, confidentiality, and even the geography where data can be housed.

Digital twin skills

Interested in becoming a digital twin pro? The skill sets are demanding, and require specialized expertise in machine learning, artificial intelligence, predictive analytics, and other data-science capabilities. That’s part of the reason why big companies are hanging out their shingle: The little guy might find it more reasonable to hire a consultant team than to upskill their in-house workers. 

Other digital twin resources

• U.S. Government Accountability Office: Digital Twins—Virtual Models of People and Objects
• Microsoft: Digital Twins in Discrete Manufacturing
• GE: Predix Digital Twin site
• GE: Digital Twin at Work: The Technology that’s Changing Industry
• IBM: Industry Transformation with IBM Digital Twin (PDF)
• Siemens: Digitization in machine building
• Oracle: Digital Twins for IoT Applications (PDF).