Optimization Techniques for Chlorine Dosage Scheduling in Water Distribution Networks: A Comparative Analysis
Optimization Techniques for Chlorine Dosage Scheduling in Water Distribution Networks: A Comparative Analysis
复制标题
配水管网氯剂量调度优化技术：比较分析
DOI：
10.1061/9780784484852.091
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Abokifa, Ahmed A.
中科院分区：
文献类型：
--
作者：
Moeini, Mohammadreza;Sela, Lina;Taha, Ahmad F.;Abokifa, Ahmed A.
需要使用足够剂量的消毒剂，以保持整个饮用水分配系统（WDS）的最低残留量。然而，过量的氯基消毒剂会导致危险的消毒副产物的形成。在以前的文献中已经提出了几个框架，通过最小化总剂量，同时保持均匀分布的残留物在整个白龙会，以优化氯剂量计划。许多这些研究依赖于进化算法（EA），如遗传算法（GA）和粒子群优化（PSO）。众所周知，EA需要对计算昂贵的水质（WQ）模型进行大量评估，并且通常具有许多需要仔细调整的参数。最近，贝叶斯优化（BO）已被提出作为替代的进化算法的水质优化在供水系统。为了加速收敛，BO构建概率代理模型（例如， 高斯过程）代替原始的黑盒模型，然后利用预测来显式控制探索/开发权衡。然而，目前还不清楚BO的性能如何与EA的WDS优化相比。本研究的目的是填补这一知识空白进行系统的比较BO，GA和PSO的性能优化加氯剂量的时间表。为此，对每种优化方法进行全面的敏感性分析，以了解不同的优化参数如何影响其性能。结果表明，BO需要显着更少的评估比GA和PSO收敛到高质量的解决方案。另一方面，GA表现出较低的敏感性，在优化参数的变化相比BO和PSO。
A sufficient dose of disinfectant needs to be applied to maintain a minimum residual throughout drinking water distribution systems (WDSs). Yet, excessive dosing of chlorine-based disinfectants leads to the formation of hazardous disinfection byproducts. Several frameworks have been proposed in previous literature to optimize chlorine dosing schedules by minimizing the total dose while maintaining evenly distributed residuals throughout the WDS. Many of these studies relied on evolutionary algorithms (EAs), such as the genetic algorithm (GA) and particle swarm optimization (PSO). EAs are known to require numerous evaluations of computationally expensive water quality (WQ) models and typically feature many parameters that require careful tuning. Recently, Bayesian optimization (BO) has been proposed as an alternative to EAs for the optimization of water quality in WDSs. To speed up convergence, BO builds a probabilistic surrogate model (e.g., Gaussian process) in place of the original black-box model and then leverages the predictions to explicitly control the exploration/exploitation trade-off. Yet, it is still unclear how BO’s performance compares against EA’s for the optimization of WDSs. This study aims to fill this knowledge gap by conducting a systematic comparison between the performance of BO, GA, and PSO for the optimization of chlorine dosage schedules. To that end, a comprehensive sensitivity analysis is conducted on each optimization approach to understand how different optimization parameters influence their performance. The results revealed that BO requires significantly fewer evaluations than GA and PSO to converge to high-quality solutions. On the other hand, GA displayed lower sensitivity to the change in the optimization parameters compared to BO and PSO.
配水系统中泵送和增压氯注射的联合优化调度
DOI：
--
发表时间：
2006
期刊：
影响因子：
--
作者：
A. Ostfeld;Elad Salomons
通讯作者：
Elad Salomons
DOI：
10.1061/(asce)wr.1943-5452.0000473
发表时间：
2015
影响因子：
3.1
作者：
M. T. Ayvaz;E. Kentel
通讯作者：
E. Kentel