TY - JOUR
T1 - On considering robustness in the search phase of Robust Decision Making
T2 - A comparison of Many-Objective Robust Decision Making, multi-scenario Many-Objective Robust Decision Making, and Many Objective Robust Optimization
AU - Bartholomew, Erin
AU - Kwakkel, Jan H.
PY - 2020
Y1 - 2020
N2 - In recent years, a family of approaches has emerged for supporting decision-making on complex environmental problems characterized by deep uncertainties and competing priorities. Many-Objective Robust Decision Making (MORDM), Multi-scenario MORDM and. Many-Objective Robust Optimization (MORO) differ with respect to the degree to which robustness is considered during the search for promising candidate solutions. To assess the efficacy of these three methods, we compare them using three different policy formulations of the lake problem: inter-temporal, planned adaptive, and direct policy search. The more robustness is considered in the search phase, the more robust solutions are also after re-evaluation but also the lower the performance in individual reference scenarios. Adaptive policy formulations positively affect robustness, but do not reduce the price for robustness. Multi-scenario MORDM strikes a pragmatic balance between robustness considerations and optimality in individual scenarios, at reasonable computational costs.
AB - In recent years, a family of approaches has emerged for supporting decision-making on complex environmental problems characterized by deep uncertainties and competing priorities. Many-Objective Robust Decision Making (MORDM), Multi-scenario MORDM and. Many-Objective Robust Optimization (MORO) differ with respect to the degree to which robustness is considered during the search for promising candidate solutions. To assess the efficacy of these three methods, we compare them using three different policy formulations of the lake problem: inter-temporal, planned adaptive, and direct policy search. The more robustness is considered in the search phase, the more robust solutions are also after re-evaluation but also the lower the performance in individual reference scenarios. Adaptive policy formulations positively affect robustness, but do not reduce the price for robustness. Multi-scenario MORDM strikes a pragmatic balance between robustness considerations and optimality in individual scenarios, at reasonable computational costs.
KW - Deep uncertainty
KW - Many Objective Robust Decision Making
KW - Many Objective Robust Optimization
UR - http://www.scopus.com/inward/record.url?scp=85081671003&partnerID=8YFLogxK
U2 - 10.1016/j.envsoft.2020.104699
DO - 10.1016/j.envsoft.2020.104699
M3 - Article
AN - SCOPUS:85081671003
SN - 1364-8152
VL - 127
JO - Environmental Modelling and Software
JF - Environmental Modelling and Software
M1 - 104699
ER -