Monitoring and control of water distribution networks requires measurements of flow and other process parameters. The upcoming model of Internet of Things (IoT) based devices involves several thousands of sensors and controllers sensing data in the environment and transmitting to the cloud. With the decreasing cost of sensors and hardware, it is expected that IoT enabled flow sensors will be deployed in large numbers in water distribution networks. However, given the complexity, geographical scale and distribution of water networks, limited access to devices (buried pipelines) and typically Indian designs and operational practices, such a conventional model may not be ideal for water distribution networks in the Indian context. Our hypothesis is that it is possible to use low cost proxy sensors such as current, vibration, flow switches etc. and possibly other accurate measurements such as power and estimate flow using calibration data and models built using machine learning. The objective of this proposal is to generate high quality data at very high temporal and spatial resolution to validate this hypothesis.