The SmartH2O anonymized datasets of Terre di Pedemonte and Valencia

Anonymized datasets of SmartH2O project

This repository contains the anonymized datasets of water consumptions of Terre di Pedemonte and Valencia SmartH2O's users. Each dataset is stored in its named folder, and have the same file naming:

anonymizer.zip: the compressed archive of water consumptions and households features

Once decompressed, the archived files are smarth2o_anonymized_households.csv and smarth2o_anonymized_consumptions.csv

smarth2o_anonymized_households.csv: It contains the features of the households' users.   

The columns meaning is:

1. index The number of the row in the csv file
2. smart_meter_id The smart meter's ID
3. household_size The size of the Household (in squared meters)
4. household_garden_area The size of the garden (in squared meters)
5. household_pool_volume The volume of the pool (in cubic meters)
6. household_pool The presence of the pool (boolean)
7. household_garden The presence of the garden (boolean)
8. residency_type The type of residency (Flat, House, Single Family, ...)
9. number_bathrooms The number of bathrooms
10. environmental_attitude The environmental attitude sensitivity of the user (High, Medium, Low)
11. irrigation_system The presence of an irrigation system (boolean)
12. house_plants The presence of house plants (boolean)
13. balcony_plants The presence of balcony plants (boolean)
14. building_size The size of the building (in squared meters)
15. name The name of a complex device (washing mascine, dishwater, ...)
16. efficiency The nefficiency of the complex device ( A, A+. A++, ...)
17. ecomode The presence of the Eco-Mode feature in the complex device (boolean)
18. timer The presence of the timer in the complex device (boolean)
19. name.1 The name of a simple device (toilet, sink, bathtub, ...)
20. number The number of the simple device

For all columns, a NULL value means that the user doesn't provided the information.

smarth2o_anonymized_consumptions.csv: it contains the periodic readings of the smart meters.   

The columns meaning is:

1. index The number of the row in the csv file
2. smart_meter_id The smart meter's ID
3. tst The timestamp of the reading
4. meter_reading The value read

The difference of the reading values between two consecutive rows gives the water consumption.

In order to certificate the authenticity of the datasets, we provide these additional files:

• anonymizer.zip.asc: the anonymizer.zip signature made by the SmartH2O OpenPGP key
• sha256sum.txt: the sha256 hash generated for anonymizer.zip
• sha256sum.txt.asc: the sha256sum.txt signature made by the SmartH2O OpenPGP key

The SmartH2O key, available here, has this fingerprint: 7F14 4F03 BCB9 9A3C D99D 7483 9739 174C 8B57 ACA9

Contacts

For any type of further questions write to smarth2o@idsia.ch. The maintainer of this dataset is Corrado Valeri (corrado.valeri@supsi.ch).