Grid Infrastructures are inherently dynamic and unpredictable environments where resource management and scheduling play an important part in ensuring that Grid applications execute while satisfying defined cost and performance constraints. Traditional Grid Scheduling approaches have focused on the scheduling and optimisation of single applications, typically without regard to the state of the other applications and the Grid in general. Advance Reservation-based approaches, in particular, have been quite popular and play a pivotal part in most Grid scheduling architectures. In this paper, we aim to demonstrate that advance reservation-based approaches show uncertainty and their performance is heavily defined by the workload characteristics and resource costs and that these approaches do not scale well as the size of the Grid increases. We demonstrate that an alternative scheduling approach, which borrows from Capacity Planning and Operations Research techniques, can improve upon the performance of the existing Grid schedulers.