No abstract

The second of the two case studies in the POWADIMA research project, the Valencia waterdistribution network, serves a population of approximately 1.2 million and is supplied by surface water via two treatment plants which have significantly different production costs. The only storage available is located at the treatment plants, each of which has its own pumping station.The management of the network is a complex operation involving 4 pressure zones and 49 operating valves, 10 of which are routinely adjusted. The electricity tariff structure varies with the hour of the day and month of the year. The EPANET hydraulic simulation model of the network has 725 nodes, 10 operating valves, 2 storage tanks and 17 pumps grouped at the two pumping stations. The control system that has been implemented comprises an artificial neural network predictor in place of the EPANET model and a dynamic genetic algorithm to optimize the control settings of pumps and valves up to a 24 h rolling operating horizon, in response to a highly variable demand. The results indicate a potential operational-cost saving of 17.6% over a complete (simulated) year relative to current practice, which easily justifies the cost of implementing the control system developed.

This paper is intended to serve as an introduction to the POWADIMA research project, whose objective was to determine the feasibility and efficacy of introducing real-time, near-optimal control for water-distribution networks. With that in mind, its contents include the current stateof-the-art and some of the difficulties that would need to be addressed if the goal of near-optimal control was to be achieved. Subsequently, the approach adopted is outlined, together with the reasons for the choice. Since it would be somewhat impractical to use a conventional hydraulic simulation model for real-time, near-optimal control, the methodology includes replicating the model by an artificial neural network which, computationally, is far more efficient. Thereafter, the latter is embedded in a dynamic genetic algorithm, designed specifically for real-time use. In this way, the near-optimal control settings to meet the current demands and minimize the overall pumping costs up to the operating horizon can be derived. The programme of work undertaken in achieving this end is then described. By way of conclusion, the potential benefits arising from implementing the control system developed are briefly reviewed, as are the possibilities of using the same approach for other application areas.

No abstract