A novel scheduling algorithm for delay-oriented services based on hopfield neural networks methodology

This paper proposes a novel dynamic resource allocation algorithm that makes use of the Hopfield neural network (HNN) methodology, which provides a fast way of finding the optimum resource allocation that minimises a given energy function reflecting specific service and system constraints. The proposed algorithm is applied to schedule the downlink transmissions in a CDMA scenario with delay-oriented services, although by a proper modification of the constraints imposed in the energy function, it could be easily extended to other services or access technologies. The algorithm is evaluated by means of simulations and compared with a reference scheme, revealing its ability to adapt to the specific service and traffic conditions