Quantum Lessons Learned at the Port of Los Angeles - Quantum Computing Report

Quantum Lessons Learned at the Port of Los Angeles – Quantum Computing Report

Photo of Pier 300 at the Port of Los Angeles showing unloading of ships and containers in the storage yard. Credit: Google Earth

Earlier this year, we reported on a logistics optimization program at Pier 300 at the Port of Los Angeles carried out by a team from SavantX and Fenix ​​Marine Services to optimize logistics for the Pier 300 container terminal project at the Port of Los Angeles. Port of Los Angeles, one of the largest shipping terminals in the United States. At the dock, shipping containers would be unloaded from ships and temporarily placed in a storage yard for later pickup. Later, trucks came to pick up their individual loads and a huge mobile crane called an RTG (Rubber Tire Gantry) moved to the location of the container, picked it up and placed it on the truck. The problem is that bottlenecks could occur in this process and they could have excessive RTG movement and trucks could have a long wait time before receiving their container.

The team used a program from SavantX called HONE (Hyper Optimization Nodal Efficiency) which used optimization algorithms on D-Wave quantum annealing and they are now reporting improvements ranging from 30% to 60% as shown in the table below below according to the metric. These upgrades are worth millions of dollars.

Improvements to Quai 300 using HONE. Credit: D-Wave

We’ve seen a lot of announcements about quantum companies working with end-users, but when we take a closer look, we see that almost all of them are in the research or proof-of-concept stage, but not in production. regular. Sometimes companies do an experiment to show that there is some potential in using quantum computing, but they never end up putting it into production. We wrote an article about this last year titled The Last Mile Might be the Toughest which explains some of the challenges of bringing a quantum application into production.

So we decided to interview the SavantX team to understand the status and if this particular app was in full production. We learned a lot of things. First, we discovered that the team had been working on this project for three years. The first 18 months were dedicated to setting up an initial implementation and the following 18 months to optimizing the implementation. We also learned that this application is indeed in full production. The app continuously optimizes logistics and is call D-Wave annealing approximately every 10 seconds for two shifts per day. They also reported that the reliability of the D-Wave systems was very good and that they had hardly encountered any downtime issues.

But we also learned that these improvements were not just about moving from a classical optimization program to a quantum one. The team put a lot of effort into creating a digital twin of dockside operations, fully understanding the logistics, determining the most important parameters, and experimenting with different algorithms to determine which one worked the best. As an example, they found that when trucks are queuing up to pick up their load, using a FIFO ordering them to pick up their container is not the best way to do it. In many cases, it may be better to let the third or fourth truck in the line pass, as this will minimize the movements of these RTG cranes. The RTG’s total movement per day was one of the key metrics they discovered. In another case, they found that when unloading an arriving ship, it is not best to place all of that ship’s containers in the same area of ​​the storage yard. This is because a group of trucks picking up the containers will create a bottleneck as they will all want to enter the same area at the same time to pick up their loads. The team then modified the algorithm to distribute container placement from a specific ship to many areas of the tank yard. This allows multiple trucks to be handled in parallel when picking up their loads.

Diagram of some of the data flows and requirements that go into the HONE Engine. 1 credit

Thus, the question arises, the use of a quantum computer was the main factor in achieving the improvements. Probably not. We believe that the key factor in these improvements has been the work of creating the digital twin, optimizing the algorithms and integrating the process into the procedures used by port operations personnel. Could the team have used a classic optimization program to achieve the same result? Maybe. The team has not done an exhaustive analysis of all the latest classic optimization solutions that exist. But they chose the D-Wave annealing solution because they knew it best and it worked well for their needs.

For quantum vendors, the lesson may be that having an absolute quantum advantage over the best classical algorithms is not always an absolute requirement for obtaining production revenue. But making it easier for an end user to use a quantum solution can help them gain ground over the classical solution, provided it is good enough. And the lesson for end users that simply moving a solution from classical to quantum without making further changes may not be enough. As people look at various problems where quantum could be used, it is imperative to work with the subject matter experts and understand how quantum fits into the whole system to achieve the desired results using quantum technology .

There is good documentation and white papers that provide additional information on this project that we can recommend to interested readers. D-Wave has published a case study which you can find on their website here. SavantX just released a 14-page white paper that they posted on LinkedIn here. A webpage for the HONE software is available on the SavantX webpage here. Additionally, D-Wave and SavantX held a webinar in May 2022 on this project and you can find the recording at Youtube here.

November 26, 2022

#Quantum #Lessons #Learned #Port #Los #Angeles #Quantum #Computing #Report

Leave a Comment

Your email address will not be published. Required fields are marked *