We deliver solutions for the AI era—combining symbolic computation, data-driven insights and deep technical expertise
From the creators of Mathematica and Wolfram|Alpha
Optimizing Workforce Transportation for Remote Operations
Client Results (17)
Every day, remote mining operations depend on a quiet piece of logistics most people never see: moving the right people to the right place at the right time. Employees rotate in and out on fixed schedules, while limited flight availability means mine sites cannot simply pause when transportation planning falls behind.
What looks like scheduling on the surface is really a constant optimization problem. Each decision changes the next one: how many workers need transport, where they leave from, which aircraft can reach them and how to maintain staffing levels without driving flight costs higher. A small inefficiency repeated across hundreds of employees and multiple locations quickly becomes a major operational expense.
For a global mining and energy company, transportation planning across remote mining sites required more than spreadsheets and static scheduling. Working with Wolfram Consulting, the company developed an optimization system that computed cost-efficient flight assignments while preserving workforce continuity, giving planners a practical way to respond to operational constraints without turning every schedule change into a manual bottleneck.
The Cost of Manual Scheduling
Across the company’s network, roughly 1,500 employees were spread across multiple home locations and pickup airports, working rotational schedules that required constant movement in and out of remote sites. Most followed a two-weeks-in, two-weeks-out roster, with employees arriving early in the week and returning later in the same cycle. About 90 percent of the workforce operated within this rotation, which meant transportation planning had to keep staffing levels stable every day, not just at the start of a schedule.
Each planning cycle required specific decisions:
- How many employees needed transport on a given day
- Which locations they should be picked up from
- Which aircraft could move them at the lowest practical cost
- How to maintain required staffing levels without unnecessary flight expense
The system had to compute those decisions across employee base locations, aircraft availability, airport constraints, and staffing requirements for more than one hundred positions across the mining network.
Solving the entire problem as one optimization model was not practical. A full calculation across all variables could take months or even years of continuous computation using conventional methods, making it useless for day-to-day operations.The organization needed Wolfram to replace slow manual scheduling with a system that could compute decisions fast enough to be both actionable and timely.
Building a Computable Scheduling System
Wolfram Consulting developed a scheduling system that computed transportation plans across a two-week operating cycle, matching the workforce rotation instead of treating each day as a separate scheduling problem. Rather than relying on manual scheduling adjustments, planners could run the full rotation at once and return flight assignments that balanced cost with operational continuity.
To make the problem solvable in practice, the Wolfram team divided the model into two stages:
- Level 1 optimization: Grouped airports into clusters and identified the most economical flight patterns between those clusters, including which aircraft should be used and how many flights were required. For example, moving 34 employees from Saskatoon to the mines could produce several aircraft options, ranked by cost, allowing the system to select the most economical combination instead of relying on fixed assumptions.
- Level 2 optimization: Refined those results by assigning specific employees to specific flights. The system minimized unnecessary stops by filling aircraft from the most efficient locations first and reducing extra visits between clusters and mine sites. This made the model practical for daily operations, not just long-range planning. When staffing changed or flights were disrupted, planners could rerun the model and generate updated schedules without rebuilding the entire process by hand.
Planners interact with the system through a single interface that allows them to select a scheduling scenario, import workforce data, check inputs for errors, and run optimization directly. Instead of rebuilding schedules manually across disconnected tools, they could adjust constraints, rerun the model, and export updated results from the same environment.
Why Wolfram
The consulting team computed schedules, ran analyses, and generated reports using Wolfram Language without having to custom-code those functions from scratch. This reduced development time and made iteration faster during implementation.
That speed showed up in practical development decisions. In one case, the client needed a specific function that would have required three to four days of development time. Using native Wolfram functionality, the same result was built in about thirty minutes. That difference mattered because the client planned to keep extending the system after deployment, and faster iteration meant new features could be tested and added without long development cycles.
From model design to optimization, analysis, and deployment, Wolfram Consulting built everything within Mathematica, eliminating integration overhead.
Rather than relying on conventional sequential execution, Wolfram’s built-in parallel computing framework made use of multiple processor cores to execute optimization tasks concurrently. Large optimization problems that would have required months of computation using traditional approaches was decomposed into smaller optimization problems and solved in parallel.
Wolfram Consulting built the backend using Wolfram Web Engine, while the frontend used React and integrated with the client’s Azure-based cloud infrastructure. Authentication connected through existing enterprise systems, including PingFederate and Azure AD groups, which meant users could access the system through existing enterprise credentials instead of managing separate logins.
Mathematica’s dynamic GUI allows analysts to explore optimization landscapes and assess solutions in real time. The client continued using the system after launch and expanded development internally with ongoing support by Wolfram Consulting. This moved the system beyond a one-time implementation and into a daily operating process the client continued to build on.
Optimization Built for Real-World Operations
The challenges faced by this organization are common across many industries. Organizations with complex logistics quickly run into the same problem: too many variables, too many constraints, and decisions that must be made fast enough to matter.
That is where Wolfram Language changes the equation. By combining optimization and reporting inside the same computational environment, Wolfram Consulting makes it possible to solve problems that would otherwise remain trapped in spreadsheets, disconnected tools or months of manual analysis. The result is a system planners can rerun when parameters change, inspect when decisions need justification, and extend as operations grow more complex.
Turn complex workforce transportation planning into fast, cost-efficient schedules with Wolfram Consulting.
Quantifying Risk at Enterprise Scale with Wolfram Consulting
Client Results (17)
Many organizations still evaluate operational risk using spreadsheets and qualitative estimates. Analysts assign ranges to possible outcomes, run calculations and distribute static reports. The result is a process that is difficult to repeat and difficult to share across teams.
A large global retailer faced this challenge. The company already had a risk-modeling algorithm, but the surrounding software environment made the system difficult to use and difficult to integrate with other enterprise tools.
To address this problem, the organization partnered with Wolfram Consulting to build a platform using Wolfram Language for quantitative risk modeling based on Factor Analysis of Information Risk (FAIR). The system allows analysts to model risk scenarios and evaluate potential losses through Monte Carlo simulation within a collaborative enterprise environment.
From Isolated Models to Enterprise Risk Analysis
The retailer already had a quantitative risk-modeling approach in place. The underlying algorithm could estimate potential losses across different risk scenarios. However, the surrounding software environment limited how effectively the model could be used across the organization.
The existing platform was distributed across multiple systems and relied on a third-party drag-and-drop application that was difficult to extend. Calculations were performed in one environment using a high-level interpreted language, then the results had to be moved manually into another application for additional analysis. This fragmented workflow created additional overhead for analysts. At the same time, analysts typically created scenarios individually and shared results by exporting PDF reports, which limited collaboration across teams.
The new platform needed to:
- unify modeling and analysis within a shared environment
- support collaboration across teams and departments
- integrate with enterprise authentication systems
- connect simulation outputs with internal applications
The goal was not to redesign the underlying risk methodology but to create a computational platform that could support scenario modeling and simulation at enterprise scale.
Building the FAIR Platform with Wolfram
Wolfram Consulting developed a web-based risk-analysis platform designed for scenario modeling and probabilistic simulation. The system was built to support the retailer’s existing risk methodology while providing a more flexible and integrated software environment.
The platform architecture combined several technologies:
- Wolfram Language powering the analytical backend
- Wolfram Web Engine providing computational services
- React-based web interfaces for analysts
- Azure infrastructure for deployment within the client’s environment
The backend implemented the core analytical logic using Wolfram Language. The front end interface allowed analysts to define scenarios and run calculations through a web application. Prior to development, Wolfram also provided an updated UI and UX design that gave the client a clear view of the intended workflow and helped align implementation with project requirements.
Authentication was integrated with the client’s identity systems through PingFederate and Azure Active Directory. Analysts could access the platform using existing enterprise credentials, which helped support a smooth transition from the legacy system without disrupting user access or existing workflows.
The system was deployed within the client’s Azure cloud environment and integrated with internal services through APIs. This architecture allowed the platform to operate within the organization’s security requirements while supporting integration with other internal applications.
Modeling Risk with Scenarios and Simulation
The platform models risk through a structured scenario workflow. Analysts begin by defining potential loss events and estimating probability ranges for each outcome. A flooding incident at a retail store, for example, might include inputs representing minimum loss, most likely loss and maximum loss. Possible consequences could include damaged inventory, liability claims from customers or lost revenue during a store closure.
These estimates are converted into probability distributions and evaluated through Monte Carlo simulation. Using Wolfram Language, typical analyses run millions of iterations and finish in roughly one minute. Multiple scenarios can be aggregated to evaluate broader operational risks. Analysts can model the impact of large-scale events such as natural disasters or cybersecurity incidents across groups of facilities. The system also replaces the earlier model of isolated analysis with a collaborative environment.
Key capabilities include:
- shared scenario libraries that allow analysts to reuse existing models
- portfolio structures that organize analyses across departments
- APIs that allow simulation results to connect with other internal applications
The platform generates analytical reports using Wolfram Notebooks. These reports include interactive visualizations that allow users to explore simulation outputs directly.
Because the analytical engine is built in Wolfram Language, new computational features can be added as requirements evolve. Additional statistical methods, new data inputs or new reporting formats can be incorporated without redesigning the underlying system.
Impact and Future Applications
The platform has now been in use for roughly three years. Analysts report that risk scenarios can be prepared and evaluated far more quickly than before, because existing models can be reused and adapted rather than rebuilt from scratch. The result is a repeatable framework for quantitative risk assessment that supports collaboration across teams and connects directly with enterprise decision systems.
Projects like this illustrate how custom computational platforms can transform complex analytical workflows. Wolfram Consulting works with organizations to design systems that combine advanced computation with real operational processes. When businesses need tools for risk analysis, simulation or large-scale data modeling, Wolfram develops analytical platforms tailored to the structure of the problem and the environment in which they will be used.
Bring your analytical methodology to life in a secure, integrated platform built by Wolfram Consulting.
Beyond the Hype: Providing Computational Superpowers for Enterprise AI
AI (10)Client Results (17)
Sure, it was laughable when X’s AI chatbot Grok accused NBA star Klay Thompson of a vandalism spree after users described him as “shooting bricks” during a recent game, but it was no joke when iTutorGroup paid $365,000 to job applicants rejected by its AI in a first-of-its-kind bias case. On a larger scale, multiple healthcare companies—including UnitedHealth Group, Cigna Healthcare and Humana—face class-action lawsuits based on their AI algorithms that are alleged to have improperly denied hundreds of thousand of patient claims.
So, while AI—driven by large language models (LLMs)—has emerged as a groundbreaking innovation for streamlining workflows, its current limitations are becoming more apparent, including inaccurate responses and weaknesses in logical and mathematical reasoning.
To address these challenges, Wolfram Research has developed a suite of tools and technologies to enhance the capabilities of LLMs. Wolfram’s technology stack, including the Wolfram Enterprise Private Cloud (EPC) and Wolfram|Alpha, increases the productivity of AI applications in multiple enterprise environments. By leveraging Wolfram’s extensive experience in computational intelligence and data curation, organizations can overcome LLM limitations to achieve greater accuracy and efficiency in AI-driven workflows.
At the same time, Wolfram Consulting Group is not confined to one specific LLM. Instead, we can enhance the capabilities of any sophisticated LLM that utilizes tools and writes computer code, including OpenAI’s GPT-4 (where Wolfram GPT is now available), Anthropic’s Claude 3 and Google’s Gemini Pro. We can also incorporate these tools in a privately hosted LLM within your infrastructure or via public LLM services.
Wolfram’s Integrated Technology Stack
Wolfram has a well-developed tech stack available to modern LLMs: data science tools, machine learning algorithms and visualizations. It also allows the LLM to write code to access your various data sources and store intermediate results in cloud memory, without consuming LLM context-window bandwidth. The Wolfram Language evaluation engine provides correct and deterministic results in complex computational areas where an unassisted LLM would tend to hallucinate.
When your organization is equipped with the Wolfram technology stack for tool-assisted AIs, the productivity of your existing experts is enhanced with methods that support exploratory data analysis, machine learning, data science, instant reporting and more:
- The LLM can interpret expert user instructions to generate Wolfram code and tool requests performing a wide variety of computational tasks, with instant feedback and expert verification of the intermediate results.
- Custom tools for accessing corporate/proprietary structured and unstructured data, models and digital twins, and business logic feed problems to the Wolfram Language algorithms implementing your analytic workflows.
- Working sessions create a documented workflow of thought processes, prompts, tool use and code that can be reused on future problems or reviewed for audit purposes.
Designed for system integration flexibility, use the platform as a fully integrated system or as a component in an existing one. In the full-system integration, the Wolfram tech stack seamlessly manages all communications between the LLM and other system components. Alternatively, use it as a set of callable tools integrated into your existing LLM stack as our modular and extensible design readily adapts to your changing needs. Also access the integrated Wolfram tech stack through a variety of user interfaces, including a traditional chat experience, a custom Wolfram Chat Notebook, REST APIs and other web-deployed custom user interfaces.
Wolfram Enterprise Private Cloud (EPC)
Wolfram’s EPC serves as a private, centralized hub for accessing Wolfram’s collection of LLM tools and works in commercial cloud environments such as Microsoft Azure, Amazon Web Services (AWS) and Google Cloud. For organizations preferring in-house solutions, EPC can also operate on dedicated hardware within your data center.
Once deployed, EPC can connect to various structured and unstructured data sources. These include SQL databases, graph databases, vector databases and even expansive data lakes. Applications deployed on EPC are accessible via instant web service APIs or through web-deployed user interfaces, including Chat Notebooks. As Wolfram continues to innovate, the capabilities of EPC also grow.
Wolfram|Alpha Infrastructure
Wolfram|Alpha can also be a valuable asset for your suite of tools. With a vast database of curated data across diverse realms of human knowledge, Wolfram|Alpha can augment your existing resources.
Top-tier intelligent assistants, websites, knowledge-based apps and various partners have trusted Wolfram|Alpha APIs for over a decade. These APIs have answered billions of queries across hundreds of knowledge domains. Designed for use by LLMs, Wolfram|Alpha’s public LLM-specific API endpoint is tailored to enable smooth communication and data consumption.
If your LLM platform requires a customized version of Wolfram|Alpha, our sales and engineering teams will work with you to optimize your access to its extensive capabilities. This ensures that you have the right setup to harness the full potential of Wolfram|Alpha in your specific context.
Preparing Knowledge for Computation
While many platforms give an LLM access to data retrieval tools, what sets Wolfram apart is extensive experience in preparing knowledge for computation. For over a decade, Wolfram has provided knowledge curation services and custom versions of Wolfram|Alpha to diverse industries and government institutions with sophisticated data curation workflows and exposed ontologies and schemas to AI systems. Direct access to vast amounts of data alone is not enough; an LLM requires context for data and an understanding of the user’s intent.
Wolfram consultants can establish workflows and services to equip your team with tools for programmatic data curation through an LLM. This process involves creating a list of questions and identifying the subjects or entities to which these questions apply. The LLM, with the aid of the appropriate retrieval tools, then finds the answers and cites its sources. These workflows alleviate the workload of extensive curation tasks, and the enhanced curation capabilities then operate within the EPC infrastructure.
At the same time, you’ll retain ownership of any intellectual property created for your funded project, including custom plugins or tools Wolfram develops, ensuring you have full control over the solutions created for your organization.
Enterprise AI the Wolfram Way
When you decide you need a custom LLM solution, let Wolfram Consulting Group build one tailored to your specific needs. From developing runtime environments that help your teams integrate Wolfram technology into existing platforms to creating application architecture, preparing data for computation and performing modeling and digital twin implementation, Wolfram has the unique experience across all areas of computation for the right balance of approaches to achieve optimal results.
By working with Wolfram, you get the best people and the best tools to keep up with developments in the rapidly changing AI landscape. The result? You will capture the full potential of the new generation of LLMs.
Contact Wolfram Consulting Group to learn more about using Wolfram’s tech stack and LLM tools to generate actionable business intelligence.
Advancing Electric Truck Simulation with Wolfram Tools: Wolfram Consulting Group
AI (10)Client Results (17)
Heavy-duty electric trucks don’t have the luxury of wasted heat. Every watt must either be stored or redirected, which makes thermal control one of the hardest parts of vehicle design. For a global manufacturer of commercial freight vehicles developing its next electric platform, simulation speed became the barrier. Each test cycle ran for hours, slowing every decision about how to warm the cabin and protect the batteries.
Wolfram Consulting replaced that process with a unified computational model and a neural network able to predict and correct thermal behavior in real time. What once ran overnight now runs in seconds.
The Challenge
Designing the thermal system of a heavy-duty electric truck means balancing efficiency with durability and driver comfort. The job demands precise control of temperature across batteries, motors and cabin spaces, while keeping energy use as low as possible.
At the start of development, separate engineering groups produced their own heat data for a four-hour reference route between company facilities. The battery team modeled pack heating, the driveline group estimated motor losses, and the cabin group focused on air-handling loads. The thermal group then merged these datasets by hand in spreadsheets to approximate whole-system behavior.
Detailed GT-Suite runs that took hours were reproduced in tens of seconds in System Modeler. For closed-loop control experiments that adjust valves/pumps on the fly, the team identified a real-time simulation constraint that required running at 1×, which is why those validation runs were executed overnight.
The Solution
Wolfram Consulting delivered a two-step solution: first, a high-fidelity System Modeler framework that replaced manual thermal analysis, and second, a neural network trained on those simulations to predict and optimize real-time performance.
The team replaced static spreadsheets with a computable model of the truck’s thermal circuit, similar to the one shown here. Engineers built a two-tier System Modeler library for early exploration and for detailed dynamics. The first tier used simplified components with basic mass-flow inputs, so engineers could visualize and test circuit concepts before detailed data existed. The second tier added hydraulic flow and pressure behavior, including pipe diameters, pump curves and coolant properties that vary with temperature and pressure.
These models produced results consistent with GT-Suite in a fraction of the time. A full run of the same route that once took three to four hours could be completed in about 35 seconds. The library enabled rapid iteration and reuse across projects, giving the thermal group a practical foundation that matched operating conditions.
Once validated, the team generated steady-state simulations spanning valve positions and pump speeds under varied operating conditions. The resulting data trained a neural network that learned how each configuration affected the battery systems and the cabin. It could predict future temperatures and, more importantly, compute the control settings needed to hit a target.
This invertible approach made the network an adaptive control layer. During a full cycle, the system adjusted parameters in real time to avoid under- or over-temperature events. When battery temperature fell below range, the controller identified the precise valve and pump changes needed to recover. It could also ease compressor load when limits were stable.
Together, the simulation framework and control layer created a self-correcting thermal system that improved speed and accuracy.
The Results
The framework delivered immediate gains. Engineers moved from multi-hour runs to seconds-scale iteration, testing new circuit layouts and control strategies that had been impossible to study before.
The adaptive control layer turned static calibration into a data-driven process. Instead of tuning modes by hand, the system maintained target ranges automatically during validation, adjusting pump speeds and valve positions to keep all components within their limits.
The libraries are now used beyond the initial program. The battery group is modeling internal heat generation, and the controls team has integrated the thermal model through FMI for co-simulation. Working from the same computable foundation, teams report faster decisions and more consistent results.
Building a Scalable Modeling Standard
By replacing a slow, siloed workflow with a unified computational framework, Wolfram Consulting turned thermal modeling from a bottleneck into a continuous design process. What began as a single EV program has become a shared modeling standard across engineering groups and now extends to electrical and control work.
When you need to speed up simulations or optimize system performance, Wolfram Consulting can help you build models that deliver faster, more reliable results.
Solving the Data Bottleneck: LabV’s Six-Week Path to Real-Time Insight and Quality Control
AI (10)Client Results (17)
Labs generate more data than they can easily use. The result? Manual workflows and fragmented tools slow down decisions. LabV, a lab data management company, decided to design a system that makes it faster to identify issues and communicate them clearly—both internally and externally.
LabV worked with Wolfram Consulting to build a digital assistant for real-time lab data analysis. A single prompt now surfaces trends that once took hours to uncover. In one case, it revealed a correlation between density and heat resistance—guiding product decisions without manual analysis or coding. This made LabV one of the first AI-powered solutions for material testing labs, combining AI’s fluency with a computational foundation so every output is both fast and verifiable.
The Prerequisites for Smarter Analysis
Meeting regulatory standards requires collecting and analyzing hundreds of data points across batches and suppliers. But LabV’s instruments weren’t fully connected to its laboratory information management system (LIMS), and much of the data still lived in spreadsheets. Even routine retrieval was slow. Deeper comparisons—like tracking material behavior by supplier—were often skipped entirely.
While generative AI tools were readily available, they couldn’t access LabV’s proprietary datasets or guarantee accurate answers. Without a way to ground responses in the lab’s own data, AI risked producing results that looked plausible but couldn’t be trusted. Research shows that disorganized, siloed data delays batch approvals, extends development cycles and drives up costs by consuming engineering hours in redundant work.
More fundamentally, the fragmented system made automation impossible. Traditional LIMS platforms weren’t designed for complex data integration or analysis at scale. To move forward, LabV had to build a centralized, structured dataset—one capable of supporting real-time decisions and enabling smarter tools. Without that foundation, AI was just out of reach.
Making Data Usable at Scale
LabV couldn’t move forward until it fixed its data layer. Traditional LIMS systems aren’t built to connect every instrument or consolidate outputs. Wolfram helped create a unified framework where test results could be collected, structured and searched—laying the groundwork for automation and eventual AI-powered analysis.
Once the data was structured, LabV and Wolfram Consulting built a digital assistant to work on top of it. The interface relies on a large language model to process natural language queries, while Wolfram’s back end handles the actual analysis—ensuring accuracy and preventing AI hallucinations. The assistant’s chat interface connects through Wolfram Enterprise Private Cloud, which coordinates LabV’s structured datasets, Wolfram’s computation results and the language model output. This architecture ensures every response comes from verified data and is computed with the same algorithms used in scientific and engineering applications.
The assistant isn’t built for show—it’s built to be used. LabV’s approach reflects best-practice machine learning workflows: data generation, preparation, model training, deployment and maintenance—keeping predictive insights accurate, explainable and current. Powered by Wolfram’s tech stack, a single prompt can return correlation tables, batch-level comparisons or supplier performance charts in seconds, using both historical and current data.
Real Results, Not Just Output
LabV replaced fragmented workflows with prompt-driven analysis powered by Wolfram’s back end. Batch issues that once went unnoticed were flagged in seconds. One manufacturer reported a 10% reduction in engineering hours by running fewer tests without sacrificing quality—time they could redirect toward faster development.
In coatings R&D, the assistant has identified optimal formulations for extreme environmental conditions by combining historical data with defined requirements, cutting development cycles and improving resource efficiency. Visual outputs improved supplier communication, and customized data handling reduced errors—helping the lab meet standards without extra head count or production delays.
Plus, the project’s six-week delivery window showed the team could move quickly without cutting corners. That speed, paired with Wolfram’s technical foundation, helped validate LabV’s approach and reinforced its credibility as a scalable platform for lab data oversight.
From Complexity to a Competitive Edge
LabV’s results were made possible by a system built to handle complexity from the start. Wolfram’s tech stack supports legacy data, real-time queries and evolving compliance needs. For leaders, that kind of scalability isn’t theoretical—it’s what makes automation sustainable under real-world demands.
Wolfram’s hybrid approach—combining a language model front end with a computational back end—delivers usable results without guesswork. Prompts return verifiable outputs, not vague summaries. Teams can surface patterns, outliers or points of interest in moments, interpret their significance and rapidly iterate through potential solutions—giving LabV clients an agility advantage in R&D and quality control.
By embedding a computational layer between the language model and the underlying data, Wolfram Consulting ensures AI output isn’t just plausible—it’s correct, explainable and backed by traceable sources. Since machine learning models return probabilities rather than certainties, having verifiable computation in the loop means every result can be trusted and acted upon. That’s why it’s not just about adding AI—it’s about making your data work for you.
When you’re ready to move beyond fragmented data, Wolfram Consulting can help you build the system that makes better decisions possible.
The CORE Project: Bringing Open 5G to Cambridgeshire, UK, and Beyond
AI (10)Client Results (17)
Radio Access Networks (RANs) form the essential bridge between mobile devices and a network’s core infrastructure. For 3G and 4G networks, mobile operators have traditionally relied on proprietary RAN systems—typically sourced from a single vendor—which can limit interoperability, raise long-term costs and slow adaptation to new technical demands.
In the shift to 5G, Wolfram has shown how AI-driven network optimisation and a deployable full-stack environment extend what Open RAN can deliver, giving developers direct access to built-in machine learning and advanced visualisation inside the network.
That vision of a more open and adaptable network underpins Wolfram’s work in the Cambridgeshire Open RAN Ecosystem (CORE) project. The initiative—one of 19 regional trials funded through the UK government’s Open Networks Ecosystem program—served as a live, multi-vendor testbed.
Wolfram’s role centred on building and deploying a predictive optimisation rApp inside this multi-vendor network, demonstrating how machine learning can guide real-time decisions and proving that the full Wolfram stack can operate natively in an Open RAN environment.
An Open Way Forward
As 5G networks evolve to support increasingly complex demands—from real-time media streaming to dense device connectivity—open, interoperable infrastructure offers a path toward more adaptive and cost-effective deployments. Countries like the United States and Japan have already begun scaling Open RAN technologies in live environments, while adoption in Europe is still in the early stages.
Wolfram collaborated with eight partners ranging from infrastructure providers to academic researchers to deploy a testbed Open RAN 5G network in Cambridgeshire. Unlike prior lab demonstrations, the CORE network operated across public venues and supported hardware and software from multiple vendors, demonstrating the viability of a modular, interoperable network at scale. In field testing, Wolfram’s predictive optimisation rApp helped the network sustain download speeds of 700 Mbps with latency under 10 milliseconds—performance levels proven during a live augmented-reality concert demo.
Wolfram’s role in this project centred on building an rApp within the RAN Intelligent Controller, showing how AI-driven insight can support real-time policy decisions without sacrificing explainability or control. Just as significant, the project proved that the full Wolfram technology stack can run natively inside an Open RAN environment, giving developers immediate access to advanced computation previously available only outside the network. As UK operators explore new architectures and supply-chain diversification, the CORE project stands as a concrete example of what’s possible—and what’s ready to scale.
Wolfram’s Network Optimisation rApp
In the Open RAN architecture, rApps are standardised software applications that run in the non-real-time RAN Intelligent Controller (Non-RT RIC). Their role is to analyse historical and near-real-time network data to support intelligent traffic management, anomaly detection and policy optimisation—helping operators adapt to changing network conditions without manual intervention.
rApps are a core component of the O-RAN specification, and Wolfram developed a native Wolfram Language implementation for the CORE project. The result was a customised rApp that provided predictive analytics and explainable decision support within a multi-vendor environment. It also established a foundational Open RAN SDK to drive future data and AI-powered app development.
Wolfram’s Network Optimisation rApp is a full-stack implementation designed to support intelligent decision-making in Open RAN environments. Built using Wolfram Language, the system combines a back-end machine learning engine that analyses network data and predicts performance patterns with a front-end dashboard that visualises key metrics and delivers actionable recommendations to engineers.
Developed as part of the CORE project, the rApp was successfully deployed alongside partner hardware in a multi-vendor testbed. This deployment also confirmed that the entire Wolfram technology stack could operate natively within the RAN environment, giving developers direct access to advanced computation and machine learning without external integration.
The back end of Wolfram’s rApp processes live network performance data to support intelligent optimisation. It ingests key performance indicators (KPIs) such as throughput, latency, signal strength and packet loss—core metrics used to assess the health and efficiency of a 5G network. Using these inputs, the machine learning model identifies patterns in traffic behavior, detects anomalies and generates recommendations aimed at improving network performance. These outputs are designed to help operators proactively manage traffic flow and resource allocation across the network. While retraining frequency depends on deployment parameters, the model is intended to operate continuously in tandem with incoming telemetry data.
The front-end dashboard of Wolfram’s rApp provides a visual interface for monitoring network performance in real time. Engineers can view KPIs such as throughput and signal strength using standard visualisations, with options to compare multiple data streams or focus on specific time windows. Users have control over which metrics are displayed and can adjust the timeframe to analyse short-term fluctuations or longer-term trends.
One view, for example, displays throughput across two adjacent cells, offering a side-by-side comparison that helps operators quickly identify load imbalances or performance deviations. This interface supports decision-making by making underlying patterns immediately visible and aligning visualisations with actionable insights generated by the back end.
The rApp’s recommendation system translates back-end analysis into actionable suggestions for network engineers. When the model identifies a configuration that could improve performance—such as activating additional cells to handle rising traffic—it surfaces a recommendation through the dashboard interface. These suggestions are presented alongside relevant context and supporting metrics but are not applied automatically; engineers remain responsible for reviewing and approving any changes. Here is an example recommendation detailing a traffic-steering policy for a specific cell based on predicted demand.
“Cellular network engineers would traditionally spend hours manually analysing and optimising a network’s performance. The O-RAN framework, enhanced by Wolfram’s rApp, transforms this paradigm completely. It not only reduces intervention time from hours to mere seconds, but also enables proactive, real-time network optimisation based on actual usage patterns. This represents a fundamental shift from manual troubleshooting to intelligent, automated network management.”
—Tony Aristeidou, Lead Developer of Wolfram’s rApp
The Promise of Open 5G: Higher Speeds, Exciting Applications
Tests conducted during the CORE project trial in Cambridgeshire demonstrated that the open 5G network consistently achieved download speeds exceeding 700 Mbps with sub-10-millisecond latency and 100% uptime during live operation. These results were obtained using commercially available devices under typical deployment conditions, not lab-simulated scenarios.
Performance was well above the ITU’s recommended 5G benchmark of 100 Mbps for user-experienced throughput and outperformed trial speeds reported in similar UK Open RAN pilots, such as Three UK’s 520 Mbps deployment in Glasgow—confirming that Open RAN configurations can deliver production-grade connectivity in high-demand settings.
To evaluate network performance under immersive, high-bandwidth conditions, the CORE consortium organised a public augmented-reality concert trial. A live performance at the Cambridge Corn Exchange was streamed in real time to a second location, where participants wearing Meta Quest and Apple Vision Pro headsets viewed the show as spatial 3D video with synchronised audio.
The feed—captured using custom 8K 3D cameras and streamed over the open 5G network—was delivered with less than 1.5 seconds of latency and maintained flawless audio-visual sync across multiple headsets. This setup provided a realistic stress test of the network’s capacity to handle sustained, low-latency, multi-device loads in a public setting.
The successful execution of the augmented-reality concert trial underscores the potential of Open RAN to support next-generation applications that demand both high throughput and ultra-low latency. It also validated the ability of a multi-vendor, standards-compliant architecture to deliver consistent performance under real-world load conditions.
While this trial was limited in geographic scope, the results provide a working proof of concept for scalable, interoperable network design. By adding software-defined intelligence through Wolfram’s rApp, the project showed that intelligent optimisation and real-time responsiveness can coexist—a model for broader adoption of adaptive 5G deployments across the UK.
“By investigating an O-RAN neutral host solution, the network will be able to support multiple mobile operators over a single site. This will encourage mobile network supply chain diversification—reducing costs for deploying and operating a network, and opening up business opportunities in the O-RAN ecosystem.”
— Michael Stevens, Connecting Cambridgeshire’s Strategy & Partnership Manager
Ready to Build Smarter Networks?
The CORE Project proved two things: that Wolfram’s full technology stack can run natively inside an Open RAN environment—powering rApps, dashboards and machine learning–driven optimisation—and that Wolfram can deliver those results while working closely with industry partners and government-led initiatives. Together, these capabilities position Wolfram Consulting as a partner ready to help operators and vendors turn network data into real-time intelligence and adaptive 5G solutions.
Contact Wolfram Consulting to put the full Wolfram tech stack to work inside Open RAN—delivering predictive optimisation and actionable insights out of the box.
Wolfram Supports Organizations Large and Small
