当前位置: X-MOL 学术Water Resour. Res. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Policy Representation Learning for Multiobjective Reservoir Policy Design With Different Objective Dynamics
Water Resources Research ( IF 5.4 ) Pub Date : 2021-11-10 , DOI: 10.1029/2020wr029329
Marta Zaniolo 1 , Matteo Giuliani 1 , Andrea Castelletti 1
Affiliation  

Most water reservoir operators make use of forecasts to inform their decisions and enhance water systems flexibility and resilience by anticipating hydrological extremes. Yet, despite numerous candidate hydro-meteorological variables and forecast horizons may potentially be beneficial to operations, the best information set for a given problem is often not evident. Additionally, in multipurpose systems characterized by multiple demands with varying vulnerabilities and temporal scales, this information set might change according to the objective tradeoff. In this work, we contribute a novel method to learn the optimal policy representation (i.e., policy input set) by combining a feature selection routine with a multiobjective Direct Policy Search framework in order to retrieve the best policy input set online (i.e., while learning the policy) and dynamically with the objective trade-off. The selected policy search routine is the Neuro-Evolutionary Multi-Objective Direct Policy Search (NEMODPS) which generates flexible policy shapes adaptive to online changes in the input set. This approach is demonstrated on the case study of Lake Como (Italy), where the operating objectives are highly heterogeneous in their dynamics (fast and slow) and vulnerabilities (wet and dry extremes). We show how varying objectives, and tradeoffs therein, benefit from a different policy representation, ultimately yielding remarkable results in terms of conflict mitigation between different users. More informed policies, moreover, show higher robustness when re-evaluated across a suite of different hydrological conditions.

中文翻译:

具有不同目标动态的多目标水库政策设计的政策表示学习

大多数水库运营商利用预测来为他们的决策提供信息,并通过预测水文极端事件来提高水系统的灵活性和恢复力。然而,尽管有许多候选的水文气象变量和预测范围可能有利于运营,但针对给定问题的最佳信息集通常并不明显。此外,在以具有不同脆弱性和时间尺度的多种需求为特征的多用途系统中,该信息集可能会根据客观权衡而改变。在这项工作中,我们通过将特征选择例程与多目标直接策略搜索框架相结合,贡献了一种学习最佳策略表示(即策略输入集)的新方法,以便在线检索最佳策略输入集(即,在学习策略时)并动态地进行客观权衡。选定的策略搜索例程是神经进化多目标直接策略搜索 (NEMODPS),它生成灵活的策略形状,以适应输入集中的在线变化。这种方法在科莫湖(意大利)的案例研究中得到了证明,其中运营目标的动态(快和慢)和脆弱性(湿和干极端)高度异质。我们展示了不同的目标和其中的权衡如何从不同的策略表示中受益,最终在不同用户之间的冲突缓解方面产生显着的结果。此外,当在一系列不同的水文条件下重新评估时,更明智的政策显示出更高的稳健性。选定的策略搜索例程是神经进化多目标直接策略搜索 (NEMODPS),它生成灵活的策略形状,以适应输入集中的在线变化。这种方法在科莫湖(意大利)的案例研究中得到了证明,其中运营目标的动态(快和慢)和脆弱性(湿和干极端)高度异质。我们展示了不同的目标和其中的权衡如何从不同的策略表示中受益,最终在不同用户之间的冲突缓解方面产生显着的结果。此外,当在一系列不同的水文条件下重新评估时,更明智的政策显示出更高的稳健性。选定的策略搜索例程是神经进化多目标直接策略搜索 (NEMODPS),它生成灵活的策略形状,以适应输入集中的在线变化。这种方法在科莫湖(意大利)的案例研究中得到了证明,其中运营目标的动态(快和慢)和脆弱性(湿和干极端)高度异质。我们展示了不同的目标和其中的权衡如何从不同的策略表示中受益,最终在不同用户之间的冲突缓解方面产生显着的结果。此外,当在一系列不同的水文条件下重新评估时,更明智的政策显示出更高的稳健性。
更新日期:2021-11-27
down
wechat
bug