Using Hopfield to Solve Resource-Leveling Problem

TL;DR

This paper introduces an augmented permute matrix and a hybrid Hopfield-SA model to effectively solve complex resource leveling problems, which are NP-hard, by enhancing neural network descriptions and optimization capabilities.

Contribution

It proposes a novel augmented permute matrix and a hybrid neural network model combining Hopfield and simulated annealing for resource leveling.

Findings

Augmented permute matrix effectively describes resource leveling constraints.

Hybrid model improves optimization efficiency.

Results demonstrate successful problem solving with high efficiency.

Abstract

Although the traditional permute matrix coming along with Hopfield is able to describe many common problems, it seems to have limitation in solving more complicated problem with more constrains, like resource leveling which is actually a NP problem. This paper tries to find a better solution for it by using neural network. In order to give the neural network description of resource leveling problem, a new description method called Augmented permute matrix is proposed by expending the ability of the traditional one. An Embedded Hybrid Model combining Hopfield model and SA are put forward to improve the optimization in essence in which Hopfield servers as State Generator for the SA. The experiment results show that Augmented permute matrix is able to completely and appropriately describe the application. The energy function and hybrid model given in this study are also highly efficient in solving resource leveling problem.