A state‐space representation of water quality (WQ) dynamics describing disinfectant (e.g., chlorine) transport dynamics in drinking water distribution networks has been recently proposed. Such representation is a byproduct of space‐ and time‐discretization of the partial differential equations modeling transport dynamics. This results in a large state‐space dimension even for small networks with tens of nodes. Although such a state‐space model provides a model‐driven approach to predict WQ dynamics, incorporating it into model‐based control algorithms or state estimators for large networks is challenging and at times intractable. To that end, this paper investigates model order reduction (MOR) methods for WQ dynamics with the objective of performing post‐reduction feedback control. The presented investigation focuses on reducing state‐dimension by orders of magnitude, the stability of the MOR methods, and the application of these methods to model predictive control.
Real‐time water quality control (WQC) in water distribution networks (WDN), the problem of regulating disinfectant levels, is challenging due to lack of (i) a proper control‐oriented modeling considering complicated components (junctions, reservoirs, tanks, pipes, pumps, and valves) for water quality modeling in WDN and (ii) a corresponding scalable control algorithm that performs real‐time water quality regulation. In this paper, we solve the WQC problem by (a) proposing a novel state‐space representation of the WQC problem that provides an explicit relationship between inputs (chlorine dosage at booster stations) and states/outputs (chlorine concentrations in the entire network) and (b) designing a highly scalable model predictive control (MPC) algorithm that showcases fast response time and resilience against some sources of uncertainty.
more » « less- NSF-PAR ID:
- 10442579
- Publisher / Repository:
- DOI PREFIX: 10.1029
- Date Published:
- Journal Name:
- Water Resources Research
- Volume:
- 57
- Issue:
- 5
- ISSN:
- 0043-1397
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract -
more » « less
Abstract Variable water quality within buildings is of increasing concern due to public health impacts (e.g., lead,
Legionella pneumophila ,Naegleria fowleri , disinfection byproducts). Advances in data acquisition and analytics provide the opportunity to monitor real‐time building‐wide water quality variability. Accordingly, the goal of this research was to create a water quality sensor platform including data acquisition, storage, and mining methods able to monitor, and ultimately improve, water quality within buildings. The platform was used to monitor water temperature, pH, conductivity, oxidation–reduction potential, dissolved oxygen, and chlorine using sensors only. Other building data infrastructure, specifically Wi‐Fi logins by occupants, were used to approximate activity rates and associated water use. An advanced machine‐learning technique, gradient boosting machines, predicted the chlorine residuals throughout the building plumbing network better than multivariate linear regression models. Finally, the implications of water quality monitoring on costs, scalability, reliability, human dimensions, regulatory compliance, and future green building designs are considered. -
more » « less
Anytime algorithms enable intelligent systems to trade computation time with solution quality. To exploit this crucial ability in real-time decision-making, the system must decide when to interrupt the anytime algorithm and act on the current solution. Existing meta-level control techniques, however, address this problem by relying on significant offline work that diminishes their practical utility and accuracy. We formally introduce an online performance prediction framework that enables meta-level control to adapt to each instance of a problem without any preprocessing. Using this framework, we then present a meta-level control technique and two stopping conditions. Finally, we show that our approach outperforms existing techniques that require substantial offline work. The result is efficient nonmyopic meta-level control that reduces the overhead and increases the benefits of using anytime algorithms in intelligent systems.
-
more » « less
Abstract Risk management for drinking water often requires continuous monitoring of various toxins in flowing water. While they can be readily integrated with existing water infrastructure, two-dimensional (2D) electronic sensors often suffer from device-to-device variations due to the lack of an effective strategy for identifying faulty devices from preselected uniform devices based on electronic properties alone, resulting in sensor inaccuracy and thus slowing down their real-world applications. Here, we report the combination of wet transfer, impedance and noise measurements, and machine learning to facilitate the scalable nanofabrication of graphene-based field-effect transistor (GFET) sensor arrays and the efficient identification of faulty devices. Our sensors were able to perform real-time detection of heavy-metal ions (lead and mercury) and
E. coli bacteria simultaneously in flowing tap water. This study offers a reliable quality control protocol to increase the potential of electronic sensors for monitoring pollutants in flowing water. -
null (Ed.)Flooding in many areas is becoming more prevalent due to factors such as urbanization and climate change, requiring modernization of stormwater infrastructure. Retrofitting standard passive systems with controllable valves/pumps is promising, but requires real-time control (RTC). One method of automating RTC is reinforcement learning (RL), a general technique for sequential optimization and control in uncertain environments. The notion is that an RL algorithm can use inputs of real-time flood data and rainfall forecasts to learn a policy for controlling the stormwater infrastructure to minimize measures of flooding. In real-world conditions, rainfall forecasts and other state information are subject to noise and uncertainty. To account for these characteristics of the problem data, we implemented Deep Deterministic Policy Gradient (DDPG), an RL algorithm that is distinguished by its capability to handle noise in the input data. DDPG implementations were trained and tested against a passive flood control policy. Three primary cases were studied: (i) perfect data, (ii) imperfect rainfall forecasts, and (iii) imperfect water level and forecast data. Rainfall episodes (100) that caused flooding in the passive system were selected from 10 years of observations in Norfolk, Virginia, USA; 85 randomly selected episodes were used for training and the remaining 15 unseen episodes served as test cases. Compared to the passive system, all RL implementations reduced flooding volume by 70.5% on average, and performed within a range of 5%. This suggests that DDPG is robust to noisy input data, which is essential knowledge to advance the real-world applicability of RL for stormwater RTC.more » « less
