Optimal scheduling of water pipe replacement using genetic algorithms

Like most other utilities, water authorities must manage many ageing capital assets that are in varying degrees of deterioration; some of which are nearing the end of their useful lives. The annual funds available to the water authorities for the rehabilitation of these assets are only a small fraction of the total replacement cost of the infrastructure. It is important, therefore, that the available funds are used in the most effective manner. This paper demonstrates the use of the genetic algorithm technique to find a near optimal schedule for the replacement of the water supply pipes. The goal is to minimize the present value of capital, repair, and damage costs. A case study in Adelaide, Australia shows that the genetic algorithm can be a powerful tool to assist in planning the rehabilitation of water pipes.