Smart Water Management in Agriculture: a Proposal for an Optimal Scheduling Formulation of a Gravity Water Distribution System

Agriculture represents one of the most water demanding sectors and its role is central on defining water saving policies. In this work, we propose an improved approach to the irrigation scheduling problem, reducing water wastage while satisfying farmers’ demands and crops’ water needs.For water distribution system managed with on-demand distribution approach, the efficiency of irrigation relies on the ability of the network manager (i.e., gatekeeper) to guarantee a proper service, consisting in: the irrigation scheduling, the definition of the volume of water passing through the channels at a given time, and the operations on gates and sluices to make the water reach the farms. Consequently, the irrigation scheduling inefficiencies might be limited by: i) reducing the water wastage, ii) minimizing the gatekeeper work and iii) maximizing the satisfaction of the farmers’ requirements.We propose an improved mixed-integer linear optimization formulation that adds the possibility to store water in the channels and takes seepage into account. This new formulation is able to better represent the physical behavior of the water flow in the channels network, also avoiding the presence of flooding. The proposed optimization solution is embedded within a wider monitoring framework with the intent to fully exploit the availability of a complex network of models, repositories and sensors installed in the field.The resulting problem is solved by one of the most used optimization solvers (IBM ILOG Cplex) and tested on a synthetic benchmark. Furthermore, we validate the results on a digital copy of the network that performs a hydraulic simulation of the irrigation system. The scheduling is accepted if the water introduced in the system can satisfy farmers’ requests with the considered timing and does not produce flooding.