Use of genetic algorithm in optimization of irrigation pumping stations

Energy costs constitute the largest expenditure for nearly all water utilities worldwide and can consume up to 65% of a water utility's annual operating budget. One of the greatest potential areas for energy cost savings is in the scheduling of pump operations. This paper presents a new management model, WAPIRRA Scheduler, for the optimal design and operation of water distribution systems. The model makes use of the latest advances in genetic algorithm (GA) optimization to automatically determine annually the least cost of pumping stations while satisfying target hydraulic performance requirements. Optimal design and operation refers to selecting pump type, capacity, and number of units as well as scheduling the operation of irrigation pumps that results in minimum design and operating cost for a given set of demand curves. The optimization process consists of three main steps: (1) generating randomly an initial set of pump combinations to start the optimization process for a given demand-duration curve; (2) minimizing the total annual cost, which consists of operation and maintenance costs and depreciation cost of the initial investment, by changing the set and discharge of pump sets based on the provided model; and (3) achieving the final criterion to stop the optimization process and reporting the optimized results of the model. Computational analysis is based upon one major objective function and solving it by means of a computer program that is developed following the GA approach to find the optimized solution of generated equations. Application of the model to a real-world project shows considerable savings in cost and energy.