Water is a principal resource in almost all kind of our lives like in homes; it is used for clearing, drinking and other many activities. Governments have already implemented strategic plans for this nature resource to be supplied where people live like in cities and villages. Although, there are millions of people continue living without proper access to this resources due to inadequate management and lack of its monitoring.
However, inadequate management of water resource services after it is produced and supplied can cause poor social economic development as well as poor human welfare. Consequently, this can lead to water planning or inability to the implementation of the strategic plans that the governments have already set. The decision making about water planning should also focus on the population growth of the targeted region. In the current research, we have not only designed an IoT based intelligent system that can monitor and manage household water consumption but also a predictive machine learning model that can predict the household water based on the population growth of the targeted region.
For monitoring the household water consumption, we have designed an IoT smart meter that can monitor the household consumption and connected to server in xamp platform. For machine learning modeling, we have built a predictive model in python using data merged from different institutions. Mainly 7 years water data from WASAC (2014-2021) and population data from Kigali city extracted based on two last consecutive censuses (2002-2012).
The predictive model was built using Random Forest algorithm and gave 96.1% and 91.3% of training and testing accuracies respectively. And finally the IoT based intelligent household consumption has been prototyped to monitor water consumption via dashboards by installing IoT smart water meter at household.