Organizational Performance-Design Process

Abstract

Inverse simulation involves finding the control inputs required to achieve a particular performance measure. The designer simulates the process numerically by varying the controllable input for generating desirable output. Clearly, this trial and error is not efficient and effective. This chapter proposes a “stochastic approximation” algorithm to estimate the necessary controllable input parameters within a desired accuracy given a target value for the performance function. The proposed algorithm is based on iterative Newton's method using a single-run simulation to minimize the expected loss function (i.e. risk function). The validity of the input parameter estimates are examined by applying it to some reliability and queuing systems with known analytical solutions. (Keywords: Performance management by simulation; prescriptive analysis for parameter setting; decision support for product and service design; data analysis and design; inverse business performance measure.)