Abstract: An improved scheduling system is effective to schedule resources in a resource constrained environment. The first step in the process is initialization wherein the set of requests to be scheduled and the processing controls are input to the system. A primary sort is done to determine the order of request processing according to an "importance" ranking. Next, the feasible segments are determined. This determination defines the times where the request could conceivably be scheduled with respect to constraints and resource availabilities. A dynamic laxity determination implements a set of heuristics which models a request's allocation possibilities by taking into account the remaining unscheduled requests with which it conflicts. Account is taken of those requests which require multiple concurrent resources by combining multiple resources. A worthiness determination is made which defines a function indicating advantageous start times admitting high worth values.

Abstract: A system and method for forecasting that combines a neural network with a statistical forecast is presented. A neural network having an input layer, a hidden layer, and an output layer with each layer having one or more nodes is presented. Each node in the input layer is connected to each node in the hidden layer and each node in the hidden layer is connected to each node in the output layer. Each connection between nodes has an associated weight. One node in the input layer is connected to a statistical forecast that is produced by a statistical model. All other nodes in the input layer are connected to a different historical datum from the set of historical data. The neural network being operative by outputting a forecast, the output of the output layer nodes, when presented with input data. The weights associated with the connections of the neural network are first adjusted by a training device.