Hybrid cloud for manufacturing equals resiliency, agility and flexibility

The manufacturing industry, spurred by COVID-19, is increasing its automation efforts with cloud technologies that offer resiliency, agility and flexibility. However, on the shop floor, slow progress to modernize infrastructure and applications prevents companies from achieving gains in productivity and operational efficiency. One of the key reasons for this lagging adoption is the reluctance of plant managers to implement digital technologies. This exists due to concerns around security, latency and resiliency, as well as a lack of understanding about new generation cloud technologies and how they can coexist with legacy applications.  

How manufacturing is evolving

Manufacturing 4.0, often interchanged with Industry 4.0 or Smart Manufacturing, is a term referring to the paradigm shift comprised of major technological innovations in manufacturing. These include cloud and artificial intelligence (AI) technologies that address manufacturers’ challenges and build confidence through application and infrastructure modernization efforts. This tech maturity unlocks benefits through intelligent automation using, but not limited to, the following: Sensors and digital transfer of data, advanced robotics, Internet of Things (IoT), mobile services, 3-D printing and data analytics.  

Cloud computing is paramount for manufacturing companies undertaking this shift — especially in the areas of data processing, data storage and enterprise resource planning systems. Hybrid cloud brings cloud directly to the manufacturing facility and provides benefits such as on-demand computing failover and auto-scaling, while ensuring that the operations keep running even if there is a connectivity failure. It also allows control decisions to be made in real time.  

Scalability is the key for success

The manufacturing industry is on the forefront of technology. Consider an average steel plant, oil refinery or an aluminum smelter, all of which had considerable industrial automation built at the equipment level long before we started talking about IoT. For these types of manufacturing, there is a great deal of legacy technology investment in the plant.  

Much of the data generated at the equipment level is used for running the plant and improving operations. Coupled with the fact that many large facilities are in remote areas — often in proximity to mines or oil well. In remote facilities, telecommunication infrastructure and skill availability are more often than not an issue. This inhibits the manufacturer from taking full advantage of Manufacturing 4.0.  

Open integration and supporting microservices enables an architecture that is flexible and scalable. This scalability and flexibility need to be accompanied with resiliency from a failover and model-drift perspective. Performance and security aspects cannot be over-emphasized considering the real-time and mission-critical nature of manufacturing operations.  

Hybrid cloud benefits

There are four primary benefits to hybrid cloud in manufacturing: faster cycle time, improved visibility, reduced cost and better management of plant applications.  

Faster cycle time and improved visibility: In typical analytics projects in plants, if data scientists spend three weeks doing the initial analysis, they spend three months trying to discover data, collect data and provision servers. Machine learning and AI workloads running in isolation may not be able to extract the intelligence of out of the huge data volume. When visibility improves, data scientists can access data on-demand and spend more time on the value-add activities of actual analysis and model building.  

To achieve faster cycle time, we need to use AI and ML services offered by public cloud, while addressing the challenges of security across locations, data latency, operational visibility, compliance and regulations. 

IBM Cloud Satellite can incorporate any public cloud service to plant-level data without moving it to cloud. By deploying IBM Cloud Satellite in plant locations or within an existing data center, access to public cloud service is possible. This reduces the cycle time of projects, improves productivity and allows manufacturers to run more projects.  

Cost reduction and improved plant management

In an audit of where data is generated, stored and used, frequent data movement is visible. This movement is wasteful and expensive. Currently, many plants aggregate data before storing in consideration of cost and network congestion. An on-premise database managed by IBM Cloud Satellite solution saves on data egress charges and reduces the management effort of plant IT teams. Better IoT integration and smarter data placement reduces costs, enables faster projects and cuts the hot-data access time significantly.  

An industrial edge (powered by data fabric and IBM Edge Application Manager) helps us to generate relevant and timely insights at scale. Creating Continuous Integration/Continuous Development (CI/CD) pipelines for plant applications provides more confidence to push changes in the operational technology (OT) landscape that reduces the need for a longer shutdown. The iterative learning related to training, deploying, learning and redeploying is especially important in data science and AI application. Enabling agile iterations allows users to improve AI applications and get more value.  

Hybrid cloud for the manufacturing industry is unique given the mission-critical, real-time applications that require low latency and high security. These factors lead to multiple smaller on-premise clouds instead of one large cloud. Hybrid cloud in manufacturing follows a hub-and-spoke model, where each satellite node has a relative lower footprint. A central on-premise cloud will manage these multiple mini clouds which may lead to some variance in standardization across various clouds requiring multi-cloud management technologies.  

Many plant applications are tied to hardware and are critical for plant control. Migrating these applications to new architecture requires special care. There are multiple legacy applications and the importance of these applications may warrant an incremental modernization instead of modernization of all applications at once. Hybrid cloud needs to support bare metals and virtual machines during the journey to containerization and cloud-native computing.  

IBM and Red Hat architecture ensures a journey to cloud that balances the imperative to modernize with the need to minimize disruptions in operation.

Source: ibm.com