Decision support for grape harvesting at a South African winery

Abstract

Recent technological advances have had a major impact on the management of traditional wineries, giving rise to the prospect of computerised decision support with respect to a range of complex harvesting and wine making decisions which have to be taken routinely. In this paper, two nested scheduling problems are considered. The first, referred to as the active cellar scheduling problem, is concerned with making good scheduling decisions within a winery (i.e. optimal assignments of grape intake batches to different processor sets inside the active part of the cellar). The harvest scheduling problem, on the other hand, refers to the larger, over-arching problem of selecting the best possible dates on which to harvest the respective vineyard blocks in order to preserve grape quality. A nested tabu search approach is presented to solve these two scheduling problems simultaneously. This solution approach has been implemented as a computerised decision support tool, called VinDSS, and the practical workability of this tool is demonstrated by means of a special case study at a winery in the South African Western Cape.