INTEGRATED MANAGEMENT OF THE RED THAI BINH RIVER DAM SYSTEMS

Andrea, Castelletti¹, Matteo, Giuliani¹, Truong Van Anh²,

¹Dept. of Electronics, Information, and Bioengineering, Politecnico di Milano, P.za Leonardo da Vinci, 32, 20133 Milano, Italy;

²Faculty of Meteorology and Hydrology, Hanoi University of Natural Resources and Environment, 41A, Phu Dien, North Tu Liem, Hanoi, Vietnam.

Abstract:

In the past, optimal management policies for water reservoir operation are generally designed via stochastic dynamic programming (SDP). However, the challenge of this algorithm when applying in the real world is the three curses of dimensionality, modeling, and multiple objectives. This paper focuses on the use of evolutionary multi-objective direct policy search algorithm (EA) to design Pareto-approximate closed-loop operating policies for multipurpose water reservoirs. This analysis explores the technical and practical implications of using EA through a careful diagnostic assessment of the effectiveness and reliability of the overall EA solution design as well as of the resulting Pareto-approximate operating policies. The case study for testing this algorithm is the multi-purposes reservoirs system in Red river basin in Vietnam, where water operators are seeking to balance the conflicting objectives of maximizing hydropower production, minimizing flood risks and water supply deficit. A key choice in the EA approach is the selection of alternative formulations for flexibly representing reservoir operating policies. The result shows an effective computational times to find out a set of Pareto solutions which are very better than the current operational policy that is applying in this case study.

Keywords: water resources management, optimization, evolution algorithm, multi- reservoirs system, Red river basin.

Các nội dung khác »

---

• Alfio Bernardo_ SWS Consulting Engineering srl, Roma, Italy (05/10/2019)
• Aiko Sakurai _Toyo Eiwa University, Japan (05/10/2019)