Re:Traffic Prediction with Advanced Graph Neural Networks
by wardrop on Saturday September 05, 2020 @06:10PM
(#24387254)
Indeed, the central hypothesis of most of the traffic simulation tools is what’s known as a Wardrop Equilibrium, in which users choose selfishly optimal routes until the traffic is evenly spread and no user has an incentive to deviate to an alternative route. Of course this is an instance of the more general and well known notion of Nash equilibrium.
https://en.m.wikipedia.org/wiki/Route_assignment#Equilibrium...
In theory, if Google Maps starts directing some portion of traffic through an alternate route, it's because it's less congested. As it does so, the main route also becomes less congested. In theory, it should reach a point where roughly, cars are being assigned to both routes, as both routes have roughly equalized in performance. In theory.