Document Type


Publication Date



An increasing attention of intelligent water informatics has been registered in the recent years, specifically for monitoring water distribution systems. With a combination of smart sensor network technologies and water resource management systems, the intelligent water management system will be provided more easily to acquire the context information of water distribution systems, which aids to supply on a real-time monitoring/response/distribution framework through exchanging resource information in real time. In addition, endowing smart water grids with self-organizing capabilities is instrumental in helping operators cope with smart operations and maintenance. In this paper, we investigate the water resource allocation for heterogeneous smart water grids with context information. A water resource sharing algorithm is developed for efficient managing water resource in intelligent water informatics. Given the context information of water distribution grid, the reinforcement learning scheme, namely SWG-RL, is performed by virtue of two approaches: spectral clustering method and multi-agent reinforcement learning (RL). In the proposed SWG-RL scheme, the novel spectral clustering algorithm is proposed to cluster end-users into different communities with respect to the context information, and thereafter the community is modeled as an agent, which makes the online optimal decision for water resource allocation based on its interaction with the environment context dynamically. The proposed approach is tested and the numerical results show that the significant performance gain compared to conventional static schemes.


Session R69, Water Distribution Networks: Treatment and Resource Allocations



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.