A clustering solution for analyzing residential water consumption patterns
نویسندگان
چکیده
Water utility companies in urban areas face two major challenges: ensuring there is enough water for everyone during prolonged drought and maintaining adequate pressure the hours of peak demand. These issues can be overcome by applying data analytics machine learning to gathered from digital meters. For conservation demand management strategies effective, need gain a better understanding consumer behaviours, habits routines. To accomplish this goal, we adapted clustering approach reveal residential consumption patterns within metered data. In experiment, used sets (engineered features set as well times use weighted probabilities set) based on collected over 10 months 306 households Melbourne, Australia. engineered set, first, identified number optimal clusters. We then performed extensive experiments find best terms performance evaluation quality. chose hierarchical agglomerative technique nature objective study. observed that k-means performing after considering metrics. other found clusters varies type water-consumption event, day (i.e., weekday or weekend), profiling interval probability use. addition, insight into tap-water usage could determine population’s adaptation hygiene practices an unprecedented time, such COVID-19 pandemic. Finally, recommend future studies also employ aligned socio-demographic key features. • Discussed detailed methodology analyse clustering. Performed comprehensive experimental study methods. Identified most suitable similarity among items each cluster. Observed how hand-hygiene like scenarios.
منابع مشابه
Analyzing Residential Electricity Consumption Patterns Based on Consumer’s Segmentation
The identification of energy consumption patterns contributes for the tailoring of energy efficiency solutions. This paper contributes to this issue by addressing the characterization of electricity consumption data with 15 min sampling of twenty two households, in Lisbon. The consumers have been segmented according to: social class, contracted power, number of rooms, family size and type of ta...
متن کاملAustralian Residential Telecommunications Consumption and Substitution Patterns
Better telecommunications pricing decisions are able to be made when more complete information concerning relationships among services is available. This study analyses residential fixed-line and mobile telephony, and Internet access and usage demands in an encompassing framework. The discrete-continuous framework allows for service interaction within and between service portfolios. Model estim...
متن کاملForecasting Hot Water Consumption in Residential Houses
An increased number of intermittent renewables poses a threat to the system balance. As a result, new tools and concepts, like advanced demand-side management and smart grid technologies, are required for the demand to meet supply. There is a need for higher consumer awareness and automatic response to a shortage or surplus of electricity. The distributed water heater can be considered as one o...
متن کاملAnalyzing Problem Frames together with Solution Patterns
The Problem Frames approach defines identifiable problem classes based on, among other things, their context and the characteristics of their domains, interfaces and requirements, without going deeply into the solution. Other software engineering approaches deal with the concept of patterns that present wellknown solutions, such as archetype, analysis and design patterns. We can say, for instan...
متن کاملIterative Clustering Algorithm for Analyzing Temporal Patterns of Gene Expression
Microarray experiments are information rich; however, extensive data mining is required to identify the patterns that characterize the underlying mechanisms of action. For biologists, a key aim when analyzing microarray data is to group genes based on the temporal patterns of their expression levels. In this paper, we used an iterative clustering method to find temporal patterns of gene express...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Knowledge Based Systems
سال: 2021
ISSN: ['1872-7409', '0950-7051']
DOI: https://doi.org/10.1016/j.knosys.2021.107522