Managing water in urban areas is an ever increasingly complex challenge. Technology enables sustainable urban water management and with integrated smart metering solutions, massive amounts of water consumption data from the end users can be collected. However, the possibility of generating data from the end user holds no value in itself. It is with the use of data analysis the vast amount of the collected data can provide more insightful information creating potential benefits. It is recognized that a deeper understanding of the end user could potentially provide benefits for operational managers as well as for the end users. A single case study of a data set containing high frequency end user water consumption data from rental apartments has been conducted, where the data set was analyzed in order to see what possible information that could be extracted and interpreted based on an exploratory data analysis (EDA). Furthermore, an interview with the operational manager of the buildings under study as well as a literature review have been carried out in order to understand how the gathered data is used today and to which contexts it could be extrapolated to provide potential benefits at a building level. The results suggests that the EDA is a powerful method approach when starting out without strong preconception of the data under study and have successfully revealed patterns and a fundamental understanding of the data and its structure. Through analysis, variations over time, water consumption patterns and excessive water users have been identified as well as a leak identification process. Even more challenging than to make meaning of the data is to trigger actions, decisions and measures based on the data analysis. The unveiled information could be applied for an improved operational building management, to empower the customers, for business and campaign opportunities as well as for an integrated decision support system. To summarize, it is concluded that the usage of smart water metering data holds an untapped opportunity to save water, energy as well as money. In the drive towards a more sustainable and smarter city, smart water meter data from end users have the potential to enable smarter building management as well as smarter water services.

The diploma thesis describes the actual situation of smart water metering, an overview of water meters suitable for remote data reading and individual components for application of remote data transmission including transmission itself. The thesis also contains the characteristics of available wireless data communication technologies and detailed solutions according to two companies specializing in remote transmission of water meter data. Subsequently, the pilot projects of large water company are presented, including practical findings. The practical part deals with the implementation of smart water metering in three specific municipalities, including a description of the area of interest, water supply system specification and possible limitations, the recommended technology, the requirements for putting in into operation and the pricing of technology and services according to two specialized companies. Finally, the possibilities of other using of smart water meter technology are discussed.

Sustainable management of finite resources is vital for ensuring livable conditions for both current and future generations. Measuring the total water consumption of residential households at high temporal resolutions and automatically disaggregating the sole signal into classified end usages (e.g. shower, sink) allows for identification of behavioural patterns that could be improved to minimise wasteful water consumption. Such disaggregation is not trivial, as water consuming patterns vary greatly depending on consumer behaviour, and further since at any given time, an unknown amount of fixtures may be used simultaneously. In this work, we approach the disaggregation problem by evaluating the performance of a set of recurrent and convolutional neural network structures provided approximately one year of high resolution water consumption data from a single apartment in Sweden. Unlike previous approaches to the problem, we let the models process the full, uninterrupted flow traces (as opposed to extracted segments of water consuming activity) in order to allow for temporal dependencies within and between water consuming activities to be learned. Out of four networks applied to the task, we find that a deeper temporal convolutional network structure yields the best overall results on the test data, with prediction accuracy of 85% and F1-score above 0.8 averaged over all end-use categories - a performance exceeding that of commercial analysis tools, and comparable to components of current state-of-the-art approaches. However, significant decreases in performance are observed for all of the networks, particularly for toilet and washing machine activity, when evaluating the models on unseen and augmented data from the apartment, indicating the results can not be fully generalised for usage in other households. / Hållbar användning av ändliga resurser är avgörande för att försäkra god livskvalitet för både nutida och framtida generationer. I Sverige är vatten för många en självklarhet, vilket öppnar upp för slösaktigt användande. En metod för att utbilda användare och identifiera icke hållbara beteenden är att kvantifiera vattenförbrukningen i hushåll baserat på syfte (t.ex. tvätta händerna, diska) eller källa (t.ex. dusch, handfat) av slutanvändningen. För att göra en sådan sammanställning mäts den totala åtkomsten av vatten i hög upplösning från hushåll, och signalen delas sedan upp i respektive kategori av slutanvändning. En sådan disaggregering är inte trivial, och försvåras av skillnader i beteendemönster hos användare samt faktumet att vi inte vid någon tidpunkt vet hur många vattenarmaturer som används samtidigt. I syftet att förbättra nuvarande tekniker för disaggregeringsproblemet implementerar och utvärderar vi alternativa lösningar baserade på rekurrenta och konvolutionerande neurala nätverk, på flödesdata insamlad med hög upplösning från en lägenhet i Sverige under en period av cirka ett år. Till skillnad från tidigare förhållningssätt till problemet låter vi våra modeller bearbeta den fullständiga, oavbrutna, flödesdatan (i motsats till extraherade segment av vattenförbrukande aktiviteter) för att möjliggöra lärandet av tidsmässiga beroenden inom och mellan vattenförbrukande aktiviteter. Utav fyra testade nätverk finner vi att ett djupt konvolutionerande nätverk ger den bästa klassificeringen överlag, givet testdata, med genomsnittlig igenkänningsnogrannhet på 85%. Signifikant försämrade resultat observerades för samtliga modeller i kategorierna toalett och tvättmaskin när nätverken testades på augmenterad data från hushållet, vilket indikerar att resultaten inte kan generaliseras för användning i andra lägenheter.