Back to top

Optimising supply chain planning with edge computing

Optimising supply chain planning with edge computing

Self-improving sensors working at the edge can help to make supply chains more efficient

Elly Yates-Roberts |

Edge computing is an open architecture that decentralises computing and empowers processing of data locally by a device or sensor rather than being sent to a central system. Sensors are becoming more intelligent and have adequate computing power to detect and process data as they receive it and respond accordingly. In a way this is not that different from shock absorbers that detect bumps on the road and prevent the shock from reaching the passengers. Obviously, these are not as intelligent as a sensor with an embedded processor, but it is nevertheless a local response.

When it comes to self-improving systems, the experiences at the local levels may have to be shared with other parts of the system when relevant. For example, what happens if a local computer is too slow to react or does not have enough capability to respond to an event? More powerful computers or other parts of the system need to be notified to respond immediately or to understand the trend so that preventive measures can be taken. Using our shock absorber analogy, if the car is constantly on a rough terrain, then more powerful shock absorbers are needed.

Supply chain planning systems are constantly exposed to all kinds of data. Many require a real-time response, and some can wait. A late delivery notice from supplier or a hurricane at a site may have an immediate impact that requires re-planning. On the other hand, a message from a supplier regarding material delivery that is three days late but still not needed for a week does not require much attention. In all these cases an ‘agent’ or sensor can receive the message, analyse it and then process it accordingly.

However, there is more an agent can do. It can communicate the messages to relevant people or processes. For example, tell the ‘planning agent’ there is a late delivery, so that the latter can decide to replan or not. Secondly, the agent can learn from its experiences and respond better, and make the whole system more effective by communicating what it learned to other agents. If the supplier is late many times, a trend is detected and the entire system is informed that this supplier is not reliable and the lead times for delivery need to be increased. We can constantly make better and more accurate plans as the system adapts itself to its environment.

At Adexa, we refer to these agents as Adexa Genies, independent processes that function as a digital expert working in a distributed environment with other Genies. There are many different agents for all kinds of business processes. They sense, respond and learn. They communicate findings with each other and their users to constantly get better and self-improve. They are capable of recommending actions to be taken, such as the optimal safety stock, the use of the right policies for forecasting, or focusing on customers which have been subjected to late deliveries lately.

Bill Green is vice president of solutions and strategy at Adexa

Subscribe to the Technology Record newsletter

  • ©2023 Tudor Rose, Inc. All Rights Reserved. Technology Record is published by Tudor Rose with the support and guidance of Microsoft.