Deep reinforcement learning (DRL) has the potential to tackle complexities that used to be very challenging as it relies on deep neural networks for function approximation and representation. This technology has conquered many fields due to its impressive results and can effectively revolutionise the water industry. In this presentation, we will focus on the findings of a three year doctoral research involving various applications of DRL in the water industry. We will also highlight how using DRL algorithms minimised leakage in pressure management case studies. . This ability for unsupervised learning makes DRL a great tool for the instantaneous optimisation of any foreign network hence possible globalising it for use on water networks across the country.
• Introduction
• The race towards Artificial Intelligence
• Water industry applications
• Key challenges of DRL
• Leakage case study
• Benchmarking
• Conclusions