Abstract

Water is a crucial natural resource, and it is widely mishandled, with an estimated one third of world water utilities having loss of water of around 40% due to leakage. This paper presents a proposal for a system based on a wireless sensor network designed to monitor water distribution systems, such as irrigation systems, which, with the help of an autonomous learning algorithm, allows for precise location of water leaks. The complete system architecture is detailed, including hardware, communication, and data analysis. A study to discover the best machine learning algorithm between random forest, decision trees, neural networks, and Support Vector Machine (SVM) to fit leak detection is presented, including the methodology, training, and validation as well as the obtained results. Finally, the developed system is validated in a real-case implementation that shows that it is able to detect leaks with a 75% accuracy.

Highlights

  • Nowadays, technology takes a major role in our lives and we are always searching for better solutions to solve everyday problems, mainly to improve and ease repetitive tasks in an autonomous way with less effort

  • To optimize the daily management and control of possible leaks, this paper aims to create a system that can control and monitor water leaks through a system that collects data using a low-cost sensor network in order to evaluate possible leak points in the water system

  • The Random Forest (RF) trained model included in the Python script that receives the messages and stores the values in the database is able to evaluate in real time whether a leak is present as well as the location based on sensor data

Read more

Summary

Introduction

Technology takes a major role in our lives and we are always searching for better solutions to solve everyday problems, mainly to improve and ease repetitive tasks in an autonomous way with less effort This evolution in technology reached new potentials with the increase of devices being used every day, allowing for the concept of Internet of Things (IoT) to arise and be part of the proliferation of smart technologies and cities [1]. IoT is the evolution of the current Internet [2] and consists of a network of devices that are capable of collecting and controlling data from the physical world, with these devices being capable of perceiving, computing, executing, and communicating between users and things [3] These networks of devices are usually associated with the concept of Wireless Sensor Networks (WSN) and multiple small nodes that communicate among them using wireless links, covering large areas and collecting data in real time.

Objectives
Methods
Results
Discussion
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.