Henrik Grimm

A parallel surrogate-assisted multi-objective evolutionary algorithm for computationally expensive optimization problems

This paper presents a new efficient multi-objective evolutionary algorithm for solving computationally-intensive optimization problems. To support a high degree of parallelism, the algorithm is based on a steady-state design. For improved efficiency the algorithm utilizes a surrogate to identify promising candidate solutions and filter out poor ones. To handle the uncertainties associated with the approximative surrogate evaluations, a new method for multi-objective optimization is described which is generally applicable to all surrogate techniques. In this method, basically, surrogate objective values assigned to offspring are adjusted to consider the error of the surrogate. The algorithm is evaluated on the ZDT benchmark functions and on a real-world problem of manufacturing optimization. In assessing the performance of the algorithm, a new performance metric is suggested that combines convergence and diversity into one single measure. Results from both the benchmark experiments and the real-world test case indicate the potential of the proposed algorithm.

On-line instrumentation for simulation-based optimization

Traditionally, a simulation-based optimization (SO) system is designed as a black-box in which the internal details of the optimization process is hidden from the user and only the final optimization solutions are presented. As the complexity of the SO systems and the optimization problems to be solved increases, instrumentation - a technique for monitoring and controlling the SO processes - is becoming more important. This paper proposes a white-box approach by advocating the use of instrumentation components in SO systems, based on a component-based architecture. This paper argues that a number of advantages, including efficiency enhancement, gaining insight from the optimization trajectories and higher controllability of the SO processes, can be brought out by an on-line instrumentation approach. This argument is supported by the illustration of an instrumentation component developed for a SO system designed for solving real-world multi-objective operation scheduling problems

Simulation optimization for industrial scheduling using hybrid genetic representation

Simulation modeling has the capability to represent complex real-world systems in details and therefore it is suitable to develop simulation models for generating detailed operation plans to control the shop floor. In the literature, there are two major approaches for tackling the simulation-based scheduling problems, namely dispatching rules and using meta-heuristic search algorithms. The purpose of this paper is to illustrate that there are advantages when these two approaches are combined. More precisely, this paper introduces a novel hybrid genetic representation as a combination of both a partially completed schedule (direct) and the optimal dispatching rules (indirect), for setting the schedules for some critical stages (e.g. bottlenecks) and other non-critical stages respectively. When applied to an industrial case study, this hybrid method has been found to outperform the two common approaches, in terms of finding reasonably good solutions within a shorter time period for most of the complex scheduling scenarios.

Simulation-based optimization of a complex mail transportation network

The Swedish Postal Services receives and distributes over 22 million pieces of mail every day. Mail transportation takes place overnight by airplanes, trains, trucks, and cars in a transportation network comprising a huge number of possible routes. For testing and analysis of different transport solutions, a discrete-event simulation model of the transportation network has been developed. This paper describes the optimization of transport solutions using evolutionary algorithms coupled with the simulation model. The vast transportation network in combination with a large number of possible transportation configurations and conflicting optimization criteria make the optimization problem very challenging. A large number of simulation evaluations are needed before an acceptable solution is found, making the computational cost of the problem severe. To address this problem, a computationally cheap surrogate model is used to offload the optimization process.

A Metamodel-Assisted Steady-State Evolution Strategy for Simulation-Based Optimization

Evolutionary algorithms (EAs) have proven to be highly useful for optimization of real-world problems due to their powerful ability to find near-optimal solutions of complex problems [8]. A variety of successful applications of EAs has been reported for problems such as engineering design, operational planning, and scheduling. However, in spite of the great success achieved in many applications, EAs have also encountered some challenges. The main weakness of using EAs in real-world optimization is that a large number of simulation evaluations are needed before an acceptable solution can be found. Typically, an EA requires thousands of simulation evaluations and one single evaluation may take a couple of minutes to hours of computing time. This poses a serious hindrance to the practical application of EAs in real-world scenarios, and to address this problem the incorporation of computationally efficient metamodels has been suggested, so-called metamodel-assisted EAs [11]. The purpose of metamodels is to approximate the relationship between the input and output variables of a simulation by computationally efficient mathematical models. If the original simulation is represented as

OPTIMISE: An Internet-Based Platform for Metamodel-Assisted Simulation Optimization

Computer simulation has been described as the most effective tool for de-signing and analyzing systems in general and discrete-event systems (e.g., production or logistic systems) in particular (De ...