Harnessing digital twins and simulation modelling for strategic advantages

Digital twin technology and simulation modelling 

The use of digital twin and simulation modelling has become an increasingly crucial tool in modern supply chain management to respond to ever-increasing complexity and disruptions. More manufacturers and retailers are embracing the pervasive mission to build digital twins. By creating virtual representations of physical assets, systems, and processes, they facilitate operational enhancements, cost reduction, and risk mitigation. Through the integration of real-time data from diverse sources like sensors and machines, digital twins provide comprehensive, unbiased models of how things behave in the real world. This capability empowers organizations to design, monitor, analyze, and optimize assets and operations in real-time, resulting in more accurate decisions and more efficient operations. 

Simulation modelling, on the other hand, is a potent tool that permits organizations to construct virtual representations of their operations and simulate various scenarios based on pre-determined parameters. It encompasses various sophisticated techniques such as Monte Carlo simulation, discrete event simulation, and agent-based modelling. These are integral tools in decision-making for companies like General Motors, Proctor and Gamble, Pfizer, Bristol-Myers Squibb, and Eli Lilly. By utilizing mathematical algorithms and computer simulations, organizations mimic real-world processes and analyze their performance. Highly realistic simulation models, fed with both structured and unstructured data and utilizing advanced analytics, can determine precise outcomes to different scenarios. 

Consequently, this relationship between digital twins and simulation modelling is interdependent and mutually beneficial, enhancing the effectiveness and efficiency of both methodologies. 

Benefits and applications of digital twins in supply chain implementation 

In a multi-site distribution model, digital twin technology enhances supply chain resilience by providing insights into bottleneck identification, inventory positioning and management, transportation routes and mapping, distribution strategies, planning and forecasting.  

Businesses are empowered to dynamically adjust these parameters within the virtual environment to optimize resilience and respond effectively to unexpected events or changes in market conditions. 

Integrating digital twins into supply chain management improves efficiency, agility, decision-making, and risk assessment. Digital twins visualize and optimize end-to-end supply chain operations, quickly finding and fixing inefficiencies, and bottlenecks. This real-time monitoring and analysis enable fast responses, thus boosting overall supply chain performance and profitability. As digital twins can run many simulations to monitor and study any number of processes, it is possible to experiment with endless design iterations in the virtual world without stopping the production line.  

This requires a significant reliance on automated modeling techniques that include hyperparameter tuning, self-supervised learning (SSL) techniques, and model searches for predefined recurrent patterns. In this way, an automated proof-of-concept (auto PoC) can be performed with minimal effort to ascertain whether the volume and quality of data are sufficient to generate a baseline model. Since all validation and reporting processes are automated, this baseline model may subsequently be deployed to the production platform without requiring human intervention. On the one hand, this degree of automation guarantees complete compliance with minimal effort. On the other hand, the “auto PoC” step also has the advantage that it is reiterated every time new or more data comes in, to help deciding on model re-training. Increasing twin automation clearly means envisioning a “twin core product” which is more real-world data-centric than based on time consuming mechanistic models that needs subject matter expert (SMEs) and simulated data not reflecting real world variance and noise. 

Digital twin technology provides real-time insights into individual store performance, inventory levels, and demand patterns. By simulating store-specific scenarios, retailers optimize inventory allocation, promotional strategies, loyalty programs, and store replenishment processes, even potentially creating digital twins of customers (DToCs), enhancing customer satisfaction, and maximizing sales performance across their retail network. 

Impact on trial-and-error in supply chain management 

Digital twin technology and simulation modelling significantly reduce trial-and-error in supply chain management. Instead of relying on physical changes and evaluations, organizations simulate scenarios virtually, making data-driven decisions that enhance efficiency and reduce costs. By simulating inventory scenarios, optimizing stock keeping unit (SKU) management, and predicting demand fluctuations, the digital twin enables proactive measures to mitigate stockouts even creating specific scenarios for sets of products that have specific and unique requirements or dependencies, improve supply chain resilience.  

Other benefits and requirements 

Digital twins and simulation modelling enhance communication, collaboration, and decision-making in supply chain management. They require extensive data collection, integration, validation, and continuous improvement to accurately reflect and optimize physical supply chain operations. 

Combining digital twin insights with pricing and promotion strategies lets retailers adjust pricing and promotions based on SKU performance and market conditions. 

Implementation strategies 

Implementing digital twin technology and simulation modelling varies in complexity and duration based on factors such as supply chain size, data availability, and modelling accuracy requirements. This process involves data collection, data integration, model development, validation, integration with other systems, and real-world testing, offering long-term benefits in operational optimization and risk mitigation. 

By simulating inventory scenarios, optimizing SKU management, and predicting demand fluctuations, the digital twin enables proactive measures to mitigate stockouts (e.g., for sets requiring specific components with an elevated risk of shortage) and improve supply chain resilience. Digital twin implementations rely heavily on data integration and analytics. The people side of the implementation must not be overlooked: Even clear mechanistic models, that do not technically suffer from the black box aspect of artificial intelligence (AI), can still feel like a black box to employees not properly prepared for a transformation of these characteristics. Actively mitigating people-related risks such as mistrust, misalignment and misinformation will be paramount to the success of the implementation. Therefore, these are key considerations for successful implementation: 

• Scalability: Develop scalable digital twin solutions that can accommodate diverse supply chain environments, from single-site operations to multi-site global networks. Implementing scalable architectures ensures flexibility and adaptability as supply chain operations evolve. 

• Data privacy and security: Address data privacy and security concerns by implementing robust cybersecurity measures. Ensure compliance with data protection regulations and standards to safeguard sensitive supply chain data used in digital twin simulations. 

• Integration with emerging technologies: Explore integration opportunities with emerging technologies like blockchain, AI, and Internet of Things (IoT) to enhance supply chain visibility, traceability, and automation. Leveraging these technologies enables real-time data exchange and interoperability across supply chain systems. 

• Organizational readiness and change management: Assess, identify, and mitigate people-related risks to ensure organizational readiness for the digital transformation. Design the case for change and foster buy-in across key stakeholders and senior leadership to give the transformation traction. Drive a change in organizational culture towards innovation and data-driven decision-making, enabling the upskilling of supply chain teams in data literacy, for a broader understanding of how to effectively work with data, and digital twin technologies, to ensure efficiency in working with the implemented technology. 
  

• Performance monitoring and continuous improvement: Establish metrics and key performance indicators (KPIs) to monitor the performance of digital twin implementations. Use quantitative analysis to measure improvements in operational efficiency, cost savings, and risk reduction. Continuously iterate and refine digital twin models based on performance insights to drive ongoing improvement. 

• Data architecture & governance: Creating a framework that allows for the efficient and effective management of data throughout its lifecycle. Maintain a single source of truth for data, which reduces the risk of errors, redundancies, and inconsistencies. This improves the efficiency and effectiveness of decision-making, which is one of the primary benefits of using digital twins. Governance is essential for implementing a digital twin as it ensures data is managed consistently, controlled, ethically, securely, and in compliance with regulatory requirements. 

Real-world case studies: Digital twins as a sustainability enabler 

Industry leaders have successfully leveraged digital twins to enhance sustainability within their supply chain. As Springler has reported, Nestle utilized digital twin technology to reconfigure distribution networks, resulting in significant cost and emission reductions. Microsoft achieved substantial cost and emission savings by optimizing its supply chain using digital twin solutions, enjoying a 10% savings in cost and carbon footprint. In addition, Amazon Web Services (AWS) found in a recent article that digital twins help to reduce the greenhouse gas emissions and carbon footprint of an existing building by up to 50%, alongside cost savings of up to 35%. By integrating carbon emission (scope 1,2, and 3) calculations directly into the digital twin’s environment, organizations gain actionable insights to make informed decisions that balance environmental sustainability with supply chain efficiency. Similarly, as reported in MIT Sloan Management review, the home furnishings company Ikea enables digital twins to simulate the performance of new materials in sustainable packaging. Likewise, companies such as Levi’s, BASF and Unilever are reinforcing digital twins with lifecycle assessment (LCA) to track and trace the journey of the materials from the production, to reusing and recycling. Digital twins, especially when coupled with sustainability footprint management software like SAP, is capable of converting noise into signals, insights, and finally actions, which significantly reduce carbon emissions along the end-to-end supply chain.  

Challenges and considerations 

Digital twin implementations rely heavily on data integration and analytics. Despite its transformative potential, implementing digital twins and simulation modelling in supply chain management poses challenges. These include data quality, privacy concerns, complexity in data integration, and organizational readiness for digital transformation.  

We are Cognizant 

The collaboration between Cognizant and Aston Martin in Formula One, resulting in the transformation to Aston Martin Aramco Formula One (AMF1), positions us as leaders in the field of digital twins. We ensure a scalable technology, based on qualitative and automatic data flows, leveraging TwinOps, a platform consisting of building blocks for data ingestion from multiple sources and testing model releases in an automated fashion using continuous integration and continuous delivery (CI/CD), validation to enable explainability through automated reporting, monitoring scripts for data and model drifts, and pipelines to score models against predefined business KPIs, transformation and storage. With the TwinOps platform in place, there is a sustainable and scalable link between data on one side and digital twins on the other. TwinOps is important not only for scalability, speed, and compliance, but also to get the most out of digital twins. The goal is to connect models to their production environments. Data feeds the models, which offers insights based on simulations. Initially, these are then fed back to a human operator, but eventually such a smart system can adjust parameters itself and optimize the entire end-to-end supply chain management. 

The impact of digital twins and simulation modelling on supply chain management 

In conclusion, digital twin technology and simulation modelling represent a paradigm shift in supply chain management. Their ability to create virtual replicas of physical assets and processes, coupled with advanced analytics and scenario simulations, empowers organizations to optimize operations, reduce costs, and mitigate risks. As technology continues to evolve, the adoption of digital twins and simulation modelling will become increasingly vital for organizations seeking to thrive in the dynamic and complex landscape of modern supply chains. 

By optimizing inventory management, production scheduling, and distribution strategies within the digital twin environment, businesses will ensure sufficient product availability, minimize stockouts, and capitalize on peak sales opportunities. 

Beyond immediate operational benefits, digital twin technology supports businesses’ continuous improvement efforts by enabling iterative testing of new strategies or innovations within the virtual environment. Businesses evaluate the impact of introducing sustainable materials on cost, logistics, and environmental outcomes before implementation in the physical supply chain. 

Additional Contributors:
Maria Nikolaidou, Senior Sustainability Advisor
Udit Arora, Associate Director Supply Chain Planning
Nishtha Sharma, Strategy Consultant
Ana Giacone, Change Management Consultant