The Multi Crane Scheduling Problem: A Comparison Between Genetic Algorithm and Neural Network Approaches based on Simulation Modeling

The internal logistics for warehouses of many industrial applications, based on the movement of heavy goods, is commonly solved by the installment of a multi-crane system. The job scheduling of a multi-crane system is an interesting problem of optimization, solved in many ways in the past. This paper describes a comparison between the optimization by the use of Genetic Algorithms (GA) and introduce a framework for the solution of the problem using machine learning driven by Neural Networks (NN). Even though this last approach is not implemented in this paper, performances very close to GA ones are expected with NN. A case-study for steel coil production is proposed as a test frame for two different simulation software tools, one based on a heuristic solution and one on machine learning; performances and data achieved from reviews and simulations are compared.