Datasets
Standard Dataset
Water Consumption Dataset of Smart City Users
- Citation Author(s):
-
JamunaC J
BMS College of EngineeringRanganath AshokKumarBMS College of Engineering - Submitted by:
- Jamuna C J
- Last updated:
- Tue, 01/04/2022 - 08:57
- DOI:
- 10.21227/ejpw-mb86
- Data Format:
- License:
5225 Views- Categories:
- Keywords:
Abstract
The dataset originally was taken from DAIAD, which has the mechanism to monitor the water consumption in real time using a validated platform for different cities. These datasets had the record of different water consumption values taken from the smart water meters that indicates, total water consumption by different users in Litres with the time interval of one hour for a year.
Out of which we have selected 50 random user's records here by the process of data cleaning, where this data would hold total water consumption by users on daily basis for a year acting as our training dataset. While choosing the dataset we have kept in mind regarding the water usage that has different criterions like water usage for the day-to-day activities, weekend’s and in different seasons, especially during the summer and winter from an individual perspective on a smart city.
With all these factors taken into consideration one could carry out any experiment on these datasets by following suitable pre-processing and analysis methods to get accurate results.
The dataset records, total water consumption in terms of Litres from the smart water meters present in each house/flat that different users consumes in a smart city for every day in a year.
Each training datasets has 365(not considering a leap-year) records of water consumption values of a user.
The clustering dataset is formed by grouping training datasets having similar water usage (this was carried out using the clustering algorithm).
The testing dataset again has the water consumption values of different users taken at random (other than training dataset having 365 values) for a year (could be used to process against clustering or the training dataset using machine learning or neural network algorithms as per the requirement to perform the analysis).
Dataset Files
- Training Dataset of Anomaly Detection in Water Consumption among Smart City Users using LSTM Autoencoder Model train_dataset.zip (79.54 kB)
- Clustering Dataset of Anomaly Detection in Water Consumption among Smart City Users using LSTM Autoencoder Model cluster_dataset.zip (60.42 kB)
- Testing Dataset of Anomaly Detection in Water Consumption among Smart City Users using LSTM Autoencoder Model test_dataset.zip (6.44 kB)
Comments
Water Consumption value taken from a Smart Water Meter
Water
water consumption
w
water
Water
water
Water
water
water