Concurrent Pump Scheduling and Storage Level Optimization Using Meta-Models and Evolutionary Algorithms

TL;DR

This paper presents a combined ANN meta-model and genetic algorithm approach to optimize pump scheduling and storage levels in water distribution systems, achieving cost savings and stable operation.

Contribution

It introduces a novel GA+ANN method for simultaneous pump and tank level optimization in real water systems, improving efficiency and stability.

Findings

Cost reduced by 10-15% compared to existing operations.

Pump switches kept below 4 per day.

Tank levels optimized for periodic, stable behavior.

Abstract

In spite of the growing computational power offered by the commodity hardware, fast pump scheduling of complex water distribution systems is still a challenge. In this paper, the Artificial Neural Network (ANN) meta-modeling technique has been employed with a Genetic Algorithm (GA) for simultaneously optimizing the pump operation and the tank levels at the ends of the cycle. The generalized GA+ANN algorithm has been tested on a real system in the UK. Comparing to the existing operation, the daily cost is reduced by about 10-15%, while the number of pump switches are kept below 4 switches-per-day. In addition, tank levels are optimized ensure a periodic behavior, which results in a predictable and stable performance over repeated cycles.