Scheduling with neural networks—the case of the hubble space telescope

Abstract

Creating an optimum long-term schedule for the Hubble Space Telescope is difficult by almost any standard due to the large number of activities, many relative and absolute time constraints, prevailing uncertainties and an unusually wide range of timescales. This problem has motivated research in neural networks for scheduling. The novel concept of continuous suitaility functions defined over a continuous time domain has been developed to represent soft temporal relationships between activities. All constraints and preferences are automatically translated into the weights of an appropriately designed artificial neural network. The constraints are subject to propagation and consistency enhancement in order to increase the number of explicitly represented constraints. Equipped with a novel stochastic neuron update rule, the resulting GDS-network effectively implements a Las Vegas-type algorithm to generate good schedules with an unparalleled efficiency. When provided with feedback from execution the network allows dynamic schedule revision and repair.