Ahmed El-Bouri

A COMPARATIVE STUDY OF A NEW HEURISTIC BASED ON ADAPTIVE MEMORY PROGRAMMING AND SIMULATED ANNEALING: THE CASE OF JOB SHOP SCHEDULING

In this study, a general framework is proposed that combines the distinctive features of three well-known approaches: the adaptive memory programming, the simulated annealing, and the tabu search methods. Four variants of a heuristic based on this framework are developed and presented. The performance of the proposed methods is evaluated and compared with a conventional simulated annealing approach using benchmark problems for job shop scheduling. The unique feature of the proposed framework is the use of two short-term memories. The first memory temporarily prevents further changes in the configuration of a provisional solution by maintaining the presence of good elements of such solutions. The purpose of the second memory is to keep track of good solutions found during an iteration, so that the best of these can be used as the starting point in a subsequent iteration. Our computational results for the job shop scheduling problem clearly indicate that the proposed methods significantly outperform the conventional simulated annealing.

Application of a Genetic Algorithm to staff scheduling in retail sector

A Genetic Algorithm (GA) is developed for the retail staff scheduling problem. The proposed algorithm is implemented and compared with a conventional integer programming branch-and-bound approach. The performance of the algorithm is tested on six real-world problems. A sensitivity analysis is carried out on three problems for two genetic parameters: population size and mutation rate. Using statistical analysis, the effects of these parameters on the solution quality and computational times are studied. The comparative study shows that GA can produce near-optimal solutions for all of the test problems, and for half of them, it is more successful than the branch-and-bound method.

Heuristics for Large Scale Labour Scheduling Problems in Retail Sector

Abstract Labour scheduling in an organization is described as the process of producing optimized timetables for employees. During this process, the work regulations associated with the relevant workplace agreements must be observed and individual work preferences should be accommodated. The problem is further complicated by having many non-standard shift patterns with varying start and end times, and shifts of differing lengths. Generating all possible shift combinations results in a very large problem size and, consequently, the computational time needed to find an optimal schedule may become too excessive to be of any practical value. This paper proposes eight heuristics for generating candidate shifts. Our extensive analysis identified several patterns in intraday labour demand, ranging from a simple flat demand to a mixed fluctuating demand. Accordingly, a number of heuristics were developed for these different demand patterns, and an integer programming model was constructed to test their performance. Our computational analysis on small-scale test problems showed promising results by some of the heuristics in improving computational efficiency, without compromising the solution quality. The results indicated that a combination of some of these heuristics would be useful for the general case in which demand does not necessarily follow any specific pattern.

An investigation of initial solutions on the performance of an iterated local search algorithm for the permutation flowshop

This paper examines the effect of initial solutions on the performance of an iterated local search (ILS) algorithm for the permutation flowshop problem with the objective of minimizing total flowtime. An ILS algorithm is applied to a set of test problems, and in each separate trial the algorithm is started from an initial solution generated by one of six different methods. Experimental results indicate that initial solutions generated by a neural network are more effective in promoting the performance of the ILS algorithm towards better solutions. A modified version of the ILS algorithm, in which an initially restricted neighborhood search is gradually expanded with each iteration, is also proposed and tested. The results from this modified ILS compare very favorably with published results from a traditional ILS approach.

A minimax linear programming model for dispatching rule selection

Abstract Dispatching rule selection is an important problem in production scheduling. This paper introduces a minimax linear programming (LP) model for dispatching rule selection in the presence of multiple criteria. The multi-criteria dispatching rule selection problem is first converted into a preference voting system, and a minimax LP model is then introduced for solving the corresponding problem. The advantage of this conversion is that it provides a way to identify dispatching rules that are moderately good in all criteria, rather than selecting dispatching rules that are good respect to only a few variables. An experimental study considering two different production priority settings is used to show the applicability of the proposed method.

A score-based dispatching rule for job shop scheduling

The performance of dispatching rules tends to be state-dependent, and a rule that performs very well under a given set of shop floor conditions may not necessarily perform as well under different conditions. A new composite dispatching rule that scores jobs based on their priorities under five different dispatching rules is proposed. The score-based dispatching rule is evaluated by means of a comparative analysis in three categories of job shop problem and three levels of congestion. The results exhibit a statistically significant improvement in performance over other dispatching rules under elevated levels of shop floor congestion and machine utilization.

Search-enhanced job dispatching in a dynamic permutation flowshop

A dynamic flowshop that continuously receives jobs at random points in time is considered, with the objective of scheduling the jobs in an order that minimizes the mean flowtime. A tabu search is proposed for deciding which job to dispatch next to the flowshop, and the approach is then compared by means of a computational analysis with a number of other competing dispatching rules. The results demonstrate that the search-enhanced dispatching method achieves reductions of between 13% and 17% in the mean flowtimes in comparison to the other dispatching rules. However, the proposed method is not as competitive in comparison to a more complex cooperative dispatching approach when shop congestion levels are medium to low.

Scheduling a dynamic flowshop to minimize the mean absolute deviation from distinct due dates

A dynamic fowshop, where new job orders continuously arrive over the scheduling horizon, is considered in this study. The objective is to minimize the mean deviation from the due dates for the completed jobs. A cooperative dispatching approach is investigated for this objective, and its performance evaluated by comparison with other dispatching rules. The results from the comparative study indicate that the cooperative dispatching performs generally better than other dispatching rules for problems that are characterized by moderate to low due date tightness levels. In those instances where the jobs have moderately tight due dates, the cooperative dispatching approach produces mean absolute deviations that range between about 7 to 10% lower than the next best performing dispatching rule, across varying shop floor congestion levels.

An investigation of cooperative dispatching for minimising mean flowtime in a finite-buffer-capacity dynamic flowshop

Scheduling in a dynamic flowshop that receives jobs at random and unforeseen points in time has traditionally been done by using dispatching rules. This study compares the performances of leading dispatching rules with a cooperative dispatching approach, for the objective of minimising mean flowtime in a flowshop, in which the buffers that hold in-process jobs between machines have finite capacities. Cooperative dispatching employs a consultative and consensus-seeking methodology for deciding which job to dispatch next on a machine. Computational experiments using randomly generated test problems for three different utilisation (congestion) levels are carried out for 5- and 10-machine flowshops, under a wide range of buffer capacities. The results highlight the sensitivity of some of the popular dispatching rules to buffer size. In contrast, cooperative dispatching emerges as a robust method that performs consistently well across the range of buffer sizes and machine utilisations tested. The reductions in mean flowtime obtained by cooperative dispatching, in comparison to the other dispatching rules, are particularly large in flowshops that operate with very tight buffer capacities and elevated levels of congestion