To promote intelligent water services and accelerate the water industry's modernization process, accurately predicting regional residents' water demand and reducing energy consumption for secondary water supply is a major challenge for scientific scheduling and efficient management of urban water supply. This paper proposes a deep learning-based approach for demand forecasting in residential communities. The approach first identifies and corrects outliers in raw water supply data, and incorporates additional features such as epidemics and meteorological information.

Dataset Files

You must be an IEEE Dataport Subscriber to access these files. Subscribe now or login.

[1] Dali li, "Water supply forecast dataset", IEEE Dataport, 2023. [Online]. Available: http://dx.doi.org/10.21227/6m4z-s813. Accessed: Feb. 21, 2024.
@data{6m4z-s813-23,
doi = {10.21227/6m4z-s813},
url = {http://dx.doi.org/10.21227/6m4z-s813},
author = {Dali li },
publisher = {IEEE Dataport},
title = {Water supply forecast dataset},
year = {2023} }
TY - DATA
T1 - Water supply forecast dataset
AU - Dali li
PY - 2023
PB - IEEE Dataport
UR - 10.21227/6m4z-s813
ER -
Dali li. (2023). Water supply forecast dataset. IEEE Dataport. http://dx.doi.org/10.21227/6m4z-s813
Dali li, 2023. Water supply forecast dataset. Available at: http://dx.doi.org/10.21227/6m4z-s813.
Dali li. (2023). "Water supply forecast dataset." Web.
1. Dali li. Water supply forecast dataset [Internet]. IEEE Dataport; 2023. Available from : http://dx.doi.org/10.21227/6m4z-s813
Dali li. "Water supply forecast dataset." doi: 10.21227/6m4z-s813