Universal Alignment Probabilities and Subset Selection for Ordinal Optimization 1
نویسندگان
چکیده
We examine in this paper the subset selection procedure in the context of ordinal optimization introduced in [1]. Major concepts including goal softening, selection subset, alignment probability and ordered performance curve are formally introduced. A two-parameter model is devised to calculate alignment probabilities for a wide range of cases using two di erent selection rules: Blind Pick and Horse Race. Our major result includes the suggestion of quanti able subset selection sizes which are universally applicable to many simulation and modeling problems, as demonstrated by the examples in this paper.
منابع مشابه
Vector Ordinal Optimization
Ordinal Optimization is a tool to reduce the computational burden in simulation-based optimization problems. The major effort in this field so far focuses on single-objective optimization. In this paper we extend this to multi-objective optimization, and develop Vector Ordinal Optimization, which is different from the one introduced in Ref. 1. Alignment probability and ordered performance curve...
متن کاملConstrained Ordinal Optimization - A Feasibility Model Based Approach
Ordinal Optimization (OO) is a useful simulation-based approach for stochastic optimization problems such as the problems in Discrete Event Dynamic Systems (DEDS). However, OO cannot be applied directly for the problem since many infeasible decisions cannot be excluded from ordinal comparison without extensive computation involving the expectation operation. In this paper, a new approach for so...
متن کاملThe Expected Opportunity Cost and Selecting the Optimal Subset
In this paper, we discuss the concept of the expected opportunity cost of a potentially incorrect selection as a measure of selection quality on a new selection procedure that is used to selecting the top m systems for large scale problems. This procedure is used the ordinal optimization method to reduce the size of the search space, and then it is used the idea of computing budget allocation O...
متن کاملAn Adequate Choice of Initial Sample Size for Selection Approach
In this paper, we consider the effect of the initial sample size on the performance of a sequential approach that used in selecting a good enough simulated system, when the number of alternatives is very large. We implement a sequential approach on M/M/1 queuing system under some parameter settings, with a different choice of the initial sample sizes to explore the impacts on the performance of...
متن کاملComparison of selection rules for ordinal optimization
The evaluation of performance of a design for complex discrete event systems through simulation is usually very time consuming. Optimizing the system performance becomes even more computationally infeasible. Ordinal optimization (OO) is a technique introduced to attack this difficulty in system design by looking at “order” in performances among designs instead of “value” and providing a probabi...
متن کامل