Advanced Strategies for Monitoring Water Consumption Patterns in Households Based on IoT and Machine Learning

Abstract

Water resource management represents a fundamental aspect of a modern society. Urban areas present multiple challenges requiring complex solutions, which include multidomain approaches related to the integration of advanced technologies. Water consumption monitoring applications play a significant role in increasing awareness, while machine learning has been proven for the design of intelligent solutions in this field. This paper presents an approach for monitoring and predicting water consumption from the most important water outlets in a household based on a proposed IoT solution. Data processing pipelines were defined, including K-means clustering and evaluation metrics, extracting consumption events, and training classification methods for predicting consumption sources. Continuous water consumption monitoring offers multiple benefits toward improving decision support by combining modern processing techniques, algorithms, and methods.

Effects of Seawater Intrusion on the Groundwater Quality of Multi-Layered Aquifers in Eastern Saudi Arabia

“…K-mean clustering has been utilized by researchers in GW quality studies [ 40 , 54 ]. It is a useful tool for defining hydrochemical processes that control water quality for water quality assessment [ 55 ].…”

“…The silhouette score or silhouette coefficient has been reported by many researchers as a key index for validating clustering analysis and determining the optimal number of clusters [ 38 , 39 , 40 ]. The silhouette coefficient ranges in value from −1 to 1, with high values indicating high performance in clustering analysis.…”

Integrated clustering analysis for delineating seawater intrusion and heavy metals in Arabian Gulf Coastal groundwater of Saudi Arabia

“…Numerous studies within the literature have indisputably confirmed the significance of the silhouette coefficient as a crucial metric to verify the effectiveness of the clustering techniques and determining the optimum clusters [ [49] , [50] , [51] ]. The coefficient range is between −1 and 1, where a high positive value indicates a well-performing clustering analysis.…”

IoT Innovations in Sustainable Water and Wastewater Management and Water Quality Monitoring: A Comprehensive Review of Advancements, Implications, and Future Directions

“…For instance, in one study by Purkovic et al [64], the EnOcean long-range, low-power communication protocol was utilized to transmit data over longer distances, allowing information collection from sensors placed in remote locations. Another commonly used protocol for data transmission is the MQTT messaging broker, where Arsene et al [65] have employed this protocol to transmit data from the NodeMCU development board to a central database or cloud-based platform. Similarly, Afifi et al [66] leveraged the MQTT IoT protocol to transmit data from sensing nodes to a central web server, providing a reliable and efficient method for data transmission.…”