Acceleration of pipeline analysis for irrigation networks through parallelisation in Graphic Processing Units

Abstract

This paper reports on the development of a Farming irrigation network Analysis and Simulation Tool (FAST) on Graphic Processing Units (GPU). The tool is oriented to accelerate the optimisation of pressurised hydraulic networks equipped with hydrants and/or sprinklers, which may require millions of hydraulic simulations to converge to the optimal solution. GPU devices contain a large number of processors working in parallel and are capable of applying the same computational algorithms over different simulation parameters. Collective and on-farm pressurised irrigation networks typically have a branched structure, without flow recirculation. This permits to implement massive parallelisation of hydraulic calculations. The efficiency of the proposed code was compared to the EPANET hydraulic software, which is widely used worldwide for this type of problems. Results show efficiency gains larger than 6,000x with respect to simulations performed using the EPANET developer's toolkit. An evaluation of the efficiency scalability in terms of the network size was also assessed. Results showed a dramatic performance improvement as the network size increased. FAST-GPU leverages the massive parallelisation capabilities of GPUs to achieve a staggering speedup compared to traditional CPU-bound simulations. This paradigm shift opens the doors for complex irrigation network analysis previously considered computationally prohibitive. This is particularly necessary for the optimisation of network design and management processes.