Systems Navigator - Dropboard - Advanced predictive planning
P.E.F. Klop (TU Delft - Electrical Engineering, Mathematics and Computer Science)
S.M. Shah (TU Delft - Electrical Engineering, Mathematics and Computer Science)
A.R. Sitaram (TU Delft - Electrical Engineering, Mathematics and Computer Science)
M. T.J. Spaan – Coach (TU Delft - Algorithmics)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
During this project, we have explored the possibilities for an algorithm that can schedule multiple visits taking into consideration constraints and KPIs. The solution we came up with has been integrated into Dropboard and is ready to be used in production by Dropboard’s clients. Our algorithm takes as input the visits to be scheduled. It then sorts these visits based on heuristics and schedules each visit in this order on its best location, using the single visit/ single resource allocation algorithm that was already present in Dropboard. Multiple plans are generated and post schedule optimised to possibly improve their rating. These plans are shown to the user with their rating in each KPI, and the user can select them to view them on the chart. Finally, a user is able to select a plan and persist it into the operational plan.