Efficient multinomial selection in simulation

Consider a simulation experiment consisting of v independent vector replications across k systems, where in any given replication one system is selected as the best performer (i.e., it wins). Each system has an unknown constant probability of winning in any replication and the numbers of wins for the individual systems follow a multinomial distribution. The classical multinomial selection procedure of Bechhofer, Elmaghraby, and Morse (Procedure BEM) prescribes a minimum number of replications, denoted as v*, so that the probability of correctly selecting the true best system (PCS) meets or exceeds a prespecified probability. Assuming that larger is better, Procedure BEM selects as best the system having the largest value of the performance measure in more replications than any other system. We use these same v* replications across k systems to form (v*)^k pseudoreplications that contain one observation from each system, and develop Procedure AVC (All Vector Comparisons) to achieve a higher PCS than with Procedure BEM. For specific small-sample cases and via a large-sample approximation we show that the PCS with Procedure AVC exceeds the PCS with Procedure BEM. We also show that with Procedure AVC we achieve a given PCS with a smaller v than the v* required with Procedure BEM. © 1998 John Wiley & Sons, Inc. Naval Research Logistics 45: 459–482, 1998     

A guarantee rate optimization model for wastewater treatment system design under uncertainty

We consider a design problem for wastewater treatment systems that considers uncertainty in pollutant concentration levels at water sources. The goal is to optimize the selection of treatment technologies and pipeline connections, so that treated wastewater can achieve specified effluents discharge limits as well as possible. We propose a new two-stage model to optimize a set of guarantee levels, that is, the maximum concentration level of source pollutants for which treated wastewater can be compliant with discharge limits. In the first stage, treatment technologies and pipeline connections are selected. In the second stage, when pollutant concentration levels are revealed, wastewater distribution and mixing are determined. A key attractiveness of the proposed guarantee rate optimization model is that it can be simplified into a single-stage mixed-integer linear program. In our numerical experiments based on real-world pollutants data, the guarantee rate model demonstrates its advantages in terms of computational efficiency, scalability and solution quality, compared with the standard probability maximization model. Finally, the methodology proposed in this paper can also be applied to other two-stage problems under uncertainty with similar uncertainty characteristics.     

Estimating the probability that a simulated system will be the best

Consider a stochastic simulation experiment consisting of v independent vector replications consisting of an observation from each of k independent systems. Typical system comparisons are based on mean (long‐run) performance. However, the probability that a system will actually be the best is sometimes more relevant, and can provide a very different perspective than the systems' means. Empirically, we select one system as the best performer (i.e., it wins) on each replication. Each system has an unknown constant probability of winning on any replication and the numbers of wins for the individual systems follow a multinomial distribution. Procedures exist for selecting the system with the largest probability of being the best. This paper addresses the companion problem of estimating the probability that each system will be the best. The maximum likelihood estimators (MLEs) of the multinomial cell probabilities for a set of v vector replications across k systems are well known. We use these same v vector replications to form v^k unique vectors (termed pseudo‐replications) that contain one observation from each system and develop estimators based on AVC (All Vector Comparisons). In other words, we compare every observation from each system with every combination of observations from the remaining systems and note the best performer in each pseudo‐replication. AVC provides lower variance estimators of the probability that each system will be the best than the MLEs. We also derive confidence intervals for the AVC point estimators, present a portion of an extensive empirical evaluation and provide a realistic example. © 2002 Wiley Periodicals, Inc. Naval Research Logistics 49: 341–358, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/nav.10019     

Estimating critical path and arc probabilities in stochastic activity networks

This article describes a new procedure for estimating parameters of a stochastic activity network of N arcs. The parameters include the probability that path m is the longest path, the probability that path m is the shortest path, the probability that arc i is on the longest path, and the probability that arc i is on the shortest path. The proposed procedure uses quasirandom points together with information on a cutset ? of the network to produce an upper bound of O[(log K)^N?|?|+1/K] on the absolute error of approximation, where K denotes the number of replications. This is a deterministic bound and is more favorable than the convergence rate of 1/K^1/2 that one obtains from the standard error for K independent replications using random sampling. It is also shown how series reduction can improve the convergence rate by reducing the exponent on log K. The technique is illustrated using a Monte Carlo sampling experiment for a network of 16 relevant arcs with a cutset of ? = 7 arcs. The illustration shows the superior performance of using quasirandom points with a cutset (plan A) and the even better performance of using quasirandom points with the cutset together with series reduction (plan B) with regard to mean square error. However, it also shows that computation time considerations favor plan A when K is small and plan B when K is large.     

A multifaceted heuristic for the orienteering problem

The orienteering problem involves the selection of a path between an origin and a destination which maximizes total score subject to a time restriction. In previous work we presented an effective heuristic for this NP-hard problem that outperformed other heuristics from the literature. In this article we describe and test a significantly improved procedure. The new procedure is based on four concepts—center of gravity, randomness, subgravity, and learning. These concepts combine to yield a procedure which is much faster and which results in more nearly optimal solutions than previous procedures.     

Institutions,information, and commitment: the role of democracy in conflict

This paper explores the hypothesis that both the preexisting quality of democracy in a polity at the onset of conflict and the quality of democracy expected to emerge in the aftermath influence the likelihood of civil war. An empirical investigation of the hypothesis presents a challenge due to concerns of endogeneity and selection: the post-conflict level of democracy is endogenous to the pre-conflict level. Further, for a given time period, either a number of countries have not experienced civil war; or if they did, did not resolve the conflict. We overcome this selection bias by implementing a three-step extension to the Heckman procedure using an unbalanced cross-country panel of 77 countries over the period 1971–2005. Consistent with our hypothesis, we find that a standard deviation improvement in the existing level of democracy reduces the probability of civil war by approximately 9 percentage points and a corresponding improvement in expected post-conflict democratization increases the probability of conflict by approximately 48 percentage points.     

Combined variance reduction techniques in fully sequential selection procedures

In the past several decades, many ranking‐and‐selection (R&S) procedures have been developed to select the best simulated system with the largest (or smallest) mean performance measure from a finite number of alternatives. A major issue to address in these R&S problems is to balance the trade‐off between the effectiveness (ie, making a correct selection with a high probability) and the efficiency (ie, using a small total number of observations). In this paper, we take a frequentist's point of view by setting a predetermined probability of correct selection while trying to reduce the total sample size, that is, to improve the efficiency but also maintain the effectiveness. In particular, in order to achieve this goal, we investigate combining various variance reduction techniques into the fully sequential framework, resulting in different R&S procedures with either finite‐time or asymptotic statistical validity. Extensive numerical experiments show great improvement in the efficiency of our proposed procedures as compared with several existing procedures.     

Optimal selection of the t best of a sequence with sampling cost

This article deals with the problem of selecting the t best of n independent and identically distributed random variables which are observed sequentially with sampling cost c per unit. Assume that a decision for acceptance or rejection must be made after each sampling and that the reward for each observation with value x is given by px - c, where p is 1 if the observation is accepted, or 0 otherwise. The optimal decision procedure (strategy) for maximizing the total expected reward is obtained. The critical numbers which are necessary to carry out the optimal decision procedure is presented by two recursive equations. The limit values of the critical numbers and the expected sample size are also studied.     

Optimum sequential search with discrete locations and random acceptance errors

Much work has been done in search theory; however, very little effort has occurred where an object's presence at a location can be accepted when no object is present there. The case analyzed is of this type. The number of locations is finite, a single object is stationary at one location, and only one location is observed each step of the search. The object's location has a known prior probability distribution. Also known are the conditional probability of acceptance given the object's absence (small) and the conditional probability of rejection given the object's presence (not too large); these Probabilities remain fixed for all searching and locations. The class of sequential search policies which terminate the search at the first acceptance is assumed. A single two-part optimization criterion is considered. The search sequence is found which (i) minimizes the probability of obtaining n rejections in the first n steps for all n, and (ii) maximizes the probability that the first acceptance occurs within the first n steps and occurs at the object's location for all n. The optimum sequential search policy specifies that the next location observed is one with the largest posterior probability of the object's presence (evaluated after each step from Bayes Rule) and that the object is at the first location where acceptance occurs. Placement at the first acceptance seems appropriate when the conditional probability of acceptance given the object's absence is sufficiently small. Search always terminates (with probability one). Optimum truncated sequential policies are also considered. Methods are given for evaluating some pertinent properties and for investigating the possibility that no object occurs at any location.     

A worst‐case formulation for constrained ranking and selection with input uncertainty

In this research, we consider robust simulation optimization with stochastic constraints. In particular, we focus on the ranking and selection problem in which the computing time is sufficient to evaluate all the designs (solutions) under consideration. Given a fixed simulation budget, we aim at maximizing the probability of correct selection (PCS) for the best feasible design, where the objective and constraint measures are assessed by their worst‐case performances. To simplify the complexity of PCS, we develop an approximated probability measure and derive the asymptotic optimality condition (optimality condition as the simulation budget goes to infinity) of the resulting problem. A sequential selection procedure is then designed within the optimal computing budget allocation framework. The high efficiency of the proposed procedure is tested via a number of numerical examples. In addition, we provide some useful insights into the efficiency of a budget allocation procedure.     

Fully sequential procedures for comparing constrained systems via simulation

We consider the problem of finding the system with the best primary performance measure among a finite number of simulated systems in the presence of a stochastic constraint on a single real‐valued secondary performance measure. Solving this problem requires the identification and removal from consideration of infeasible systems (Phase I) and of systems whose primary performance measure is dominated by that of other feasible systems (Phase II). We use indifference zones in both phases and consider two approaches, namely, carrying out Phases I and II sequentially and carrying out Phases I and II simultaneously, and we provide specific example procedures of each type. We present theoretical results guaranteeing that our approaches (general and specific, sequential and simultaneous) yield the best system with at least a prespecified probability, and we provide a portion of an extensive numerical study aimed at evaluating and comparing the performance of our approaches. The experimental results show that both new procedures are useful for constrained ranking and selection, with neither procedure showing uniform superiority over the other.© 2010 Wiley Periodicals, Inc. Naval Research Logistics, 2010     

System comparison procedures for automatic target recognition systems

Estimating the performance of an automatic target recognition (ATR) system in terms of its probability of successfully identifying a target involves extensive image collection and processing, which can be very time‐consuming and expensive. Therefore, we investigate the Wald sequential test for the difference in two proportions as a sample size‐reducing alternative to ranking and selection procedures and confidence intervals. An analysis of the test parameters leads to a practical methodology for implementing the Wald test for fairly comparing two systems, based on specific experimental goals. The test is also extended with the modified, sequentially rejective Bonferroni procedure for the multiple pairwise comparison of more than two systems. Two sampling schemes for different experimental goals are also discussed. The test methodology is applied to actual data to compare different configurations of a specific ATR system, with the results demonstrating that the modified Wald sequential procedure is a useful alternative to comparing proportions with confidence intervals, particularly when data are expensive. © 1999 John Wiley & Sons, Inc. Naval Research Logistics 46: 357–371, 1999     

Nonstationary stochastic gold-mining: A time-sequential tactical-allocation problem

This paper presents an extension of gold-mining problems formulated in earlier work by R. Bellman and J. Kadane. Bellman assumes there are two gold mines labeled A and B, respectively, each with a known initial amount of gold. There is one delicate gold-mining machine which can be used to excavate one mine per day. Associated with mine A is a known constant return rate and a known constant probability of breakdown. There is also a return rate and probability of breakdown for mine B. Bellman solves the problem of finding a sequential decision procedure to maximize the expected amount of gold obtained before breakdown of the machine. Kadane extends the problem by assuming that there are several mines and that there are sequences of constants such that the jth constant for each mine represents the return rate for the jth excavation of that mine. He also assumes that the probability of breakdown during the jth excavation of a mine depends on j. We extend these results by assuming that the return rates are random variables with known joint distribution and by allowing the probability of breakdown to be a function of previous observations on the return rates. We show that under certain regularity conditions on the joint distributions of the random variables, the optimal policy is: at each stage always select a mine which has maximal conditional expected return per unit risk. This gold-mining problem is also a formulation of the problem of time-sequential tactical allocation of bombers to targets. Several examples illustrating these results are presented.     

Multicriteria efficiency with arbitrary finite sets and cyclic preferences

It is shown that when X is an arbitrary finite subset of an n-factor product set and preference relations on each factor or criterion are assumed only to be asymmetric, efficient (undominated) points always exist in the set P of probability distributions on X when the preference relations are extended to probability distributions on the factors according to SSB utility theory. Thus, arbitrary finite structures and potentially cyclic preferences do not present a problem for the theory of efficiency under the convexification-extension procedure.     

Some limiting distributions associated with sequences of multinomial trials

A series of independent trials is considered in which one of k ≥ 2 mutually exclusive and exhaustive outcomes occurs at each trial. The series terminates when m outcomes of any one type have occurred. The limiting distribution (as m → ∞) of the number of trials performed until termination is found with particular attention to the situation where a Dirichlet distribution is assigned to the k vector of probabilities for each outcome. Applications to series of races involving k runners and to spares problems in reliability modeling are discussed. The problem of selecting a stopping rule so that the probability of the series terminating on outcome i is k^?1 (i.e., a “fair” competition) is also studied. Two generalizations of the original asymptotic problem are addressed.     

基于结构加权的海面编队预定目标选择方法

海面目标运动和编队阵型的约束特性,使得通过对装订阵型和末制导探测阵型进行点集匹配来选择预定目标成为一种有效途径。但当编队目标释放干扰时,会引起阵型结构发生局部变化,导致目标选择性能恶化。本文基于反舰导弹目标选择需求,分析了传感器导航和探测误差、装订信息误差、编队目标运动和释放干扰等因素所引起的位置点集变形,通过利用阵型中未污染的结构信息,提出了基于几何散列法和结构加权平均Hausdorff距离的编队预定目标选择方法。理论分析和实验结果表明,该方法不受传感器导航误差和编队目标整体运动的影响,在编队存在冲淡干扰时能有效提高目标选择能力。     

A multiserver queue with markovian arrivals and group services with thresholds

We consider a multiserver queueing system in which arrivals are governed by a Markovian arrival process. The system is attended by K identical exponential servers. Under a dynamic probabilistic service rule which depends on two threshold parameters, this model is studied as a Markov process. The steady-state probability vector is shown to be of (modified) matrix-geometric type. Efficient algorithmic procedures for the computation of the steady-state probability vector and some key performance measures of the system are developed. Some numerical examples are discussed. © 1993 John Wiley & Sons, Inc.     

The probability of the existence of a feasible flow in a stochastic transportation network

Stochastic transportation networks arise in various real world applications, for which the probability of the existence of a feasible flow is regarded as an important performance measure. Although the necessary and sufficient condition for the existence of a feasible flow represented by an exponential number of inequalities is a well‐known result in the literature, the computation of the probability of all such inequalities being satisfied jointly is a daunting challenge. The state‐of‐the‐art approach of Prékopa and Boros, Operat Res 39 (1991) 119–129 approximates this probability by giving its lower and upper bounds using a two‐part procedure. The first part eliminates all redundant inequalities and the second gives the lower and upper bounds of the probability by solving two well‐defined linear programs with the inputs obtained from the first part. Unfortunately, the first part may still leave many non‐redundant inequalities. In this case, it would be very time consuming to compute the inputs for the second part even for small‐sized networks. In this paper, we first present a model that can be used to eliminate all redundant inequalities and give the corresponding computational results for the same numerical examples used in Prékopa and Boros, Operat Res 39 (1991) 119–129. We also show how to improve the lower and upper bounds of the probability using the multitree and hypermultitree, respectively. Furthermore, we propose an exact solution approach based on the state space decomposition to compute the probability. We derive a feasible state from a state space and then decompose the space into several disjoint subspaces iteratively. The probability is equal to the sum of the probabilities in these subspaces. We use the 8‐node and 15‐node network examples in Prékopa and Boros, Operat Res 39 (1991) 119–129 and the Sioux‐Falls network with 24 nodes to show that the space decomposition algorithm can obtain the exact probability of these classical examples efficiently. © 2016 Wiley Periodicals, Inc. Naval Research Logistics 63: 479–491, 2016     

基于神经网络的柴油机特征参数评价与选择

在设备故障诊断中,正确地提取与选择特征参数对于诊断结果的有效性和准确性具有关键性的意义,在提出评价判据时样本的概率分布往往难以确定,针对模式识别中特征量的选择方法,结合人工神经网络原理,提出了利用人工神经网络进行故障特征量评价与选择的方法,实现了对柴油机特征参数的提取及选择,有效地解决了柴油机状态监测与故障诊断中测试参数多而难以优化的问题。     

Operations analysis during the underwater search for Scorpions

This paper discusses the operations analysis in the underwater search for the remains of the submarine Scorpion The a priori target location probability distribution for the search was obtained by monte-carlo procedures based upon nine different scenarios concerning the Scorpion loss and associated credibility weights. These scenarios and weights were postulated by others. Scorpion was found within 260 yards of the search grid cell having the largest a priori probability Frequent computations of local effectiveness probabilities (LEPs) were carried out on scene during the search and were used to determine an updated (a posteriori) target location distribution. This distribution formed the basis for recommendation of the current high probability areas for search The sum of LEPs weighted by the a priori target location probabilities is called search effectiveness probability (SEP) and was used as the overall measure of effectiveness for the operation. SEP and LEPs were used previously in the Mediterranean H-bomb search On-scene and stateside operations analysis are discussed and the progress of the search is indicated by values of SEP for various periods during the operation.