登入選單

返回Google圖書搜尋

An Approximated Dynamic Programming Model for the Supply Vessel Fleet Sizing Problem

Leonardo Souza Ribeiro

出版	SSRN, 2023
URL	http://books.google.com.hk/books?id=5sH5zwEACAAJ&hl=&source=gbs_api

註釋

The offshore oil and gas exploration and production activities must be supported by a fleet of supply vessels. The offshore installations are supplied by these vessels on a periodic basis from an onshore supply depot. Petrobras must decide on the number of supply vessels hired to perform the operations for two years ahead. This decision has a strong economic effect as the daily rates for one supply vessel can amount to tens of thousands of USDs. The aim of this work is to present an Approximated Dynamic Programming model that solves this heterogeneous fleet sizing problem taking into consideration uncertainty in sea conditions and future demand. Two types of approximate value functions were tested, a piecewise linear concave value function and a neural network value function. The computational results showed that the proposed method produces good results and can be applied to real-life instances for assessing the the ideal fleet composition.