A heuristic and a benchmark for the stowage planning problem
- PDF / 1,873,867 Bytes
- 29 Pages / 439.37 x 666.142 pts Page_size
- 52 Downloads / 210 Views
A heuristic and a benchmark for the stowage planning problem Rune Larsen1 · Dario Pacino1 Accepted: 8 October 2020 © Springer Nature Limited 2020
Abstract The stowage planning problem has recently gained the attention of a number of academic researchers. Unfortunately, many of the published works are either based on oversimplified assumptions or on confidential data. This practice hinders the research field from growing. In this paper, we present a novel set of realistic vessel data along with a set of benchmark instances. Moreover, a formal definition of a single-port stowage planning problem, based on the current state of the art, is presented. The proposed optimisation problem is solved using a variant of the adaptive large neighbourhood search framework, where novel repair and destroy methods are presented. Computational results show that the solution approach is able to find high-quality seaworthy stowage plans within 60 s. Keywords Stowage planning · Liner shipping · Benchmark · ALNS · Optimisation
1 Introduction Container shipping operates on cyclical routes with published schedules. The cargo is transported on standard-sized metallic containers, which can carry both dry goods, liquids (in tank containers) and cargo with temperature requirements (in refrigerated containers). Each container is 8 foot wide and 8′6 foot high, although there are containers that are 9′6 foot high, called high-cube. Most containers are 20′, 40′ or 45′ long, and refrigerated containers (reefers) require power connections. To take advantage of the standardisation of containers, specialised vessels are used. Figure 1 shows the layout of a container vessel. As depicted, a vessel is divided into sections called bays. Each bay is divided into an above- and below-deck part, divided by a hatch cover (a watertight structure). Each bay is composed of a number of stacks. Container positions within a stack are called cells. A cell can hold either two 20- or * Dario Pacino [email protected] 1
DTU Management, Technical University of Denmark, Building 358, 2800 AkademivejKgs. Lyngby, Denmark Vol.:(0123456789)
R. Larsen, D. Pacino
Fig. 1 Vessel longitudinal layout and bay details
one 40-foot container and are vertically indexed by tiers. Longer (e.g. 45-foot) containers are commonly stowed above-deck. Depending on the size of the vessel, each bay can have between one and four hatch covers. The set of stacks above, and below, each hatch cover are often grouped into logical partitions used during planning, and they are referred to as locations or blocks (see e.g. Ambrosino et al. 2018; Christensen and Pacino 2017). The industry uses a special numbering system to identify bays, tiers and stacks. Since this is not relevant here, we refer the interested reader to Ambrosino et al. (2004) for details. Given a set of containers to load on a vessel (a loadlist), stowage planning is the problem of finding a profitable assignment of containers to cells ensuring the seaworthiness of the vessel (a stowage plan). Moreover, a stowage plan should minim
Data Loading...
