Hybrid Attention Networks for Flow and Pressure Forecasting in Water Distribution Systems
This work addresses operational decision-making and anomaly detection for urban water management, but it is incremental as it builds on existing attention mechanisms.
The authors tackled the challenge of forecasting flow and pressure in water distribution systems by proposing a hybrid dual-stage spatial-temporal attention-based RNN, which outperformed 9 baseline models on a real-world dataset.
Multivariate geo-sensory time series prediction is challenging because of the complex spatial and temporal correlation. In urban water distribution systems (WDS), numerous spatial-correlated sensors have been deployed to continuously collect hydraulic data. Forecasts of monitored flow and pressure time series are of vital importance for operational decision making, alerts and anomaly detection. To address this issue, we proposed a hybrid dual-stage spatial-temporal attention-based recurrent neural networks (hDS-RNN). Our model consists of two stages: a spatial attention-based encoder and a temporal attention-based decoder. Specifically, a hybrid spatial attention mechanism that employs inputs along temporal and spatial axes is proposed. Experiments on a real-world dataset are conducted and demonstrate that our model outperformed 9 baseline models in flow and pressure series prediction in WDS.