Premium
Linear decision rule in reservoir management and design: 4. A rule that minimizes output variance
Author(s) -
ReVelle Charles,
Gundelach Jose
Publication year - 1975
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/wr011i002p00197
Subject(s) - decision rule , admissible decision rule , minification , rule based system , variance (accounting) , mathematical optimization , mathematics , computer science , statistics , data mining , optimal decision , artificial intelligence , decision tree , weighted sum model , economics , accounting
A linear decision rule (LDR) in reservoir management and design is reviewed and transformed. A generalized formulation of a new LDR is presented, and the necessary steps to implement it are carried out for a particular form of the new rule. The proposed rule permits further minimization of expected losses arising from deviations of releases from prespecified target levels. The use of the rule also makes possible a larger minimum commitment of water. The problem is solved for historical data from the Gunpowder River in Maryland under both the previous and the new form of the LDR. Results obtained are compared for the two cases.