I'm in the terminal side of this business. While this seems very interesting, and I'm sure some line will poke at it, it seems very academic. I'm curious if they actually partnered with a shipping line to come up with this.<p>On the terminal side, all I can say is that I am knee-deep in container optimizations right now and it's a damn nightmare. Every terminal does things extremely differently, even if the terminal is owned by the same company. Even the terminology is often different within a company. You optimize for one terminal, and you have to build 80% of it from scratch for the next terminal. Any solution is incredibly difficult to scale.
I just happen to be reading "The Box", about the early history of containerization... and boy am I enjoying it. I really really recommend it to anyone seeking a good enjoyable read that mixes engineering, design, business and history.<p>It also ridiculizes my little coding problems x)
Apparently, container optimization was unsolved for very large fleets. I did not know this.<p>Google OR improves existing solutions by 10%-20% utilization which is incredible.
I am very curious if anyone will actually use this API endpoint they're releasing <a href="https://developers.google.com/optimization/service/shipping/network_design" rel="nofollow">https://developers.google.com/optimization/service/shipping/...</a><p>It's very cool nonetheless
It is really worth a try when demurrage is not even accounted for?<p><a href="https://developers.google.com/optimization/service/reference/rest/v1/shipping/designShippingNetwork#vesselcost" rel="nofollow">https://developers.google.com/optimization/service/reference...</a>
Omega Tau Podcast did a really great episode [0] on container shipping, including the optimization of container placement and route planning, highly recommended.<p>[0]: <a href="https://omegataupodcast.net/146-container-shipping/" rel="nofollow">https://omegataupodcast.net/146-container-shipping/</a>
> Unlike airplanes ... cargo ships are in nearly constant operation<p>Cargo ships do do much of their maintenance underway, but other than that, I'd say the difference is a lot less. (Not that this is a big deal, more pedantic). Cargo ships turn around in ports over a few days, unloading, loading. They may also wait for hours or days for a berth.<p><a href="https://www.flightradar24.com/data/aircraft/n513dz" rel="nofollow">https://www.flightradar24.com/data/aircraft/n513dz</a> - Delta A350. Basically running 24/7 other than 3 hour turnarounds at airports.
Make me think of every shopowner or manager of local restaurants or something said they had headache planning schedule for part-time employees. Some even say that is the reason they are paid well. I thought, but why don't you just use some algorithms to solve it?
I still wonder about stowage plans for these. I guess t's the next level down to solve approximately after the route plan for each container. They come later and have constraints that are more contingent than the global system level view.<p>Ballpark, optimistically, shore cranes can do 30-50 moves per hour, 2 or 4, maybe 6 cranes per vessel, and you have to unpack shell layer by layer.<p>* Ultra Large Container Vessel (ULCV): 14,501 TEU and higher<p>* New Panamax: 10,000-14,500 TEU<p>* Post-Panamax: 5,101-10,000 TEU<p>* Panamax: 3,001-5,100 TEU<p>24,000 TEU (Twenty-foot Equivalent Units), say 12k 40-foot containers<p><pre><code> 4 cranes * 50 containers/crane-hour * 24 hours/day = 1.2k containers / day
</code></pre>
<a href="https://en.wikipedia.org/wiki/Stowage_plan_for_container_ships#Logistical_factors" rel="nofollow">https://en.wikipedia.org/wiki/Stowage_plan_for_container_shi...</a><p>Stowage plans for ships also have weight, balance, power, and value acceptability criteria beyond availability at a port.<p>These overheads made me curious enough to write up some napkin math, since they mention cut-and-run early departures from ports.
Sounds like they are beginning to offer OR-tools as a service. I’d be willing to pay for GCP compute to run it, if they can get me a better API than the Python bindings to ortools!
Count me excited for advances in AI that don't involve ML! If for no other reason than it is refreshing =). One thing that strikes me about the write up is that the team deeply understands what their model is actually _doing_.
Just last week I was looking into OptaPlanner [1] and MiniZinc [2]. OptaPlanner even has a real-time/continuous optimization mode. There are a whole bunch of other solutions, but these were the most interesting to me.<p>I wonder why Google didn't just go with an off the shelf solution and integrate it instead of building their own solution?<p>[1] <a href="https://www.optaplanner.org/" rel="nofollow">https://www.optaplanner.org/</a>
[2] <a href="https://www.minizinc.org/" rel="nofollow">https://www.minizinc.org/</a>
This optimization exercise still assumes that a bunch of variables are constant, e.g. berthing slots at ports, port operational schedules, ship speed vs fuel consumption, etc. It makes me wonder how much more efficient the system as a whole could be, for companies, consumers and the planet. (Disclaimer: I'm not in the shipping business.)
I am surprised that three hours in and no one has mentioned constraint satisfaction yet: <a href="https://en.wikipedia.org/wiki/Constraint_satisfaction" rel="nofollow">https://en.wikipedia.org/wiki/Constraint_satisfaction</a>
I would be curious to understand the constraints for adding new lines. When viewed as purely a network or graph problem it might seem "easy", but not all waters are created equal. Do they have to avoid high seas? Storms? Pirates?
This seems pretty incredible but Im mostly surprised Google is dipping their toes into this domain at all. Feels fairly outside the Google wheelhouse. I could understand Alphabet having another company provide this kind of functionality but it just seems out of place.<p>Who are they competing with?
Good<p>But the question here is why any of the shipping companies should adopt this given the fact that Google likes to deprecate things at a whim?<p>Shipping companies mostly do this internally already
Nothing new, nothing to learn here. Pure pr.<p>Aka give me one OR guy and a gurobi license and we will beat their result.<p>Bonus at the end of the excercise you will have an or guy that can help you solve other use cases as well.