SAM - A STOCHASTIC ASSIGNMENT MODEL

摘要: Many previous empirical studies have demonstrated multi-routeing: the phenomenon whereby drivers travelling between same origin and destination select a variety of routes. Assignment methods fall into two classes depending on how they model multi-routeing. Equilibrium use functional relationships link cost flow, whilst stochastic take costs to be random variables. The best known methods, Burrell Dial, each some deficiencies or disadvantages. A new method, SAM (Stochastic Model) is described which overcomes these problems, an analytical counterpart Monte Carlo method. In applications test networks, behaves well, has acceptable properties. However, there are still remaining difficulties. These difficulties suggestions made for overcoming them. (A) For covering abstract conference see IRRD 851540.