Dispatching Rule Selection Research Articles

Clustering and Dispatching Rule Selection Framework for Batch Scheduling

In this study, a batch scheduling with job grouping and batch sequencing is considered. A clustering algorithm and dispatching rule selection model is developed to minimize total tardiness. The model and algorithm are based on the constrained k-means algorithm and neural network. We also develop a method to generate a training dataset from historical data to train the neural network. We use numerical examples to demonstrate that the proposed algorithm and model efficiently and effectively solve batch scheduling problems.

Dynamic dispatching system using a deep denoising autoencoder for semiconductor manufacturing

Deep denoising autoencoders (DDAE), which are variants of the autoencoder, have shown outstanding performance in various machine learning tasks. In this study, we propose using a DDAE to address a dispatching rule selection problem that represents a major problem in semiconductor manufacturing. Recently, the significance of dispatching systems for storage allocation has become more apparent because operational issues lead to transfer inefficiency, resulting in production losses. Further, recent approaches have overlooked the possibility of a class imbalance problem in predicting the best dispatching rule. The main purpose of this study is to examine DDAE-based predictive control of the storage dispatching systems to reduce idle machines and production losses. We conducted an experimental evaluation to compare the predictive performance of DDAE with those of five other novelty detection algorithms. Finally, we compared our adaptive approach with the optimization and existing heuristic approaches to demonstrate the effectiveness and efficiency of the proposed method. The experimental results demonstrated that the proposed method outperformed the existing methods in terms of machine utilizations and throughputs.

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 semantics-based dispatching rule selection approach for job shop scheduling

Dispatching rules are commonly used for job shop scheduling in industries because they are easy to implement, and they yield reasonable solutions within a very short computational time. Many dispatching rules have been developed but they can only perform well in specific scenarios. This is because a dispatching rule or a combination of dispatching rules always pursues a single or multiple fixed production objectives. A lot of approaches (e.g. simulation based or machine learning based approaches) have been published in the literatures attempted to solve the problem of selecting the proper dispatching rules for a given production objective. To select a combination of dispatching rules per randomly selected combination of objectives, this paper investigates a novel semantics-based dispatching rule selection system. Each of the dispatching rules and production objectives relates to a set of scheduling parameters like processing time, remaining work, total work, due date, release date, tardiness, etc. These parameters are semantically interrelated so that a dispatching rule and a production objective can also be semantically related through their semantic expressions. A semantic similarity value can be calculated by comparing their semantic expressions. Based on this idea, a semantics-based dispatching rule selection system for job shop scheduling is developed to generate a combination of dispatching rules given randomly selected combination of production objectives. A proof-of-concept verification process is provided at the end of the paper.

A combined OWA–DEA method for dispatching rule selection

Dispatching rule selection is an important issue in dynamic scheduling of production systems. When there are multiple performance criteria, identification of the most efficient dispatching rule is not an easy task. This paper considers an ordered weighted averaging (OWA) methodology combined with a data envelopment analysis (DEA) model for identifying the best dispatching rule in a flowshop environment. Standard DEA cannot be used directly, due to ambiguity in the inputs and outputs that may be specified in the flowshop scheduling problem. To overcome this drawback, an OWA method is used to first assess the dispatching rules, measured in terms of multiple factors, for different decision making optimism levels. This is followed by using a DEA model to aggregate the OWA assessments, in order to identify the dispatching rule(s) with the best overall performance. A computational analysis is performed by using randomly generated test problems, and different scenarios involving different factor priorities. The results demonstrate that the proposed OWA–DEA approach successfully identifies which dispatching rules are efficient, and which are not.

A hybrid computer simulation-adaptive neuro-fuzzy inference system algorithm for optimization of dispatching rule selection in job shop scheduling problems under uncertainty

Unstable environment of industrial systems is a source of various uncertainties in production features such as processing times. Moreover, selecting appropriate dispatching rules is a complex and significant issue in practical problems under uncertainty. Most previous studies have pointed out that using a single dispatching rule does not necessarily result in an optimal schedule. This study proposes a novel hybrid algorithm based on computer simulation and adaptive neuro-fuzzy inference system (ANFIS) to select optimal dispatching rule for each machine in job shop scheduling problems (JSSPs) under uncertain conditions so that makespan is minimized. It captures uncertainty using fuzzy set theory and assumes that processing times are in the form of fuzzy numbers. This algorithm contributes to the previous works in two important ways. First, the inherent uncertainty of JSSPs is reflected in fuzzy processing times. Second, this is the first study that develops an approach based on computer simulation and ANFIS for selecting the optimal dispatching rules and minimizing the makespan in JSSPs under uncertainty. The computational results demonstrate the superiority of this algorithm over the previous studies in the literature.

Production Rate Based Dynamic Dispatching Rule Selection in a Wafer FAB

Abstract — This paper proposes a state-dependent dispatching rule to achieve on-time delivery as well as minimum of mean cycle time in a wafer FAB. Dispatching rule should be selected dynamically according to current system state and operation objective, since condition in a wafer fab is dynamically changed. In this paper, we use ‘pegging’ to identify a current state of a wafer FAB. Pegging is defined as the process of assigning wafer lots to orders, and it is very essential to meet customers’ demands in terms of quality, quantity, and due dates in a wafer FAB. As a result, pegging decides target move for each step, it is necessary to select WIP lot to be processed next. The proposed state-dependent dispatching rule consists of two stages. At the first stage, WIP lots are classified into two groups which has priority, and classical dispatching rule is applied to select a WIP lot at the second stage. The target move and actual move are computed by the combination of pegging and simulation. We developed a simulation model by using MIMAC6, and conducted simulation with SEEPLAN

Dispatching rule selection with Gaussian processes

Decentralized scheduling with dispatching rules is applied in many fields of logistics and production, especially in highly complex and dynamic scenarios, such as semiconductor manufacturing. Many dispatching rules are proposed in the literature, which perform well on specific scenarios. No rule is known, however, consistently outperforming all other rules. One approach to meet this challenge and improve scheduling performance is to select and switch dispatching rules depending on current system conditions. For this task machine learning techniques (e.g., Artificial Neural Networks) are frequently used. In this paper we investigate the use of a machine learning technique not applied to this task before: Gaussian process regression. Our analysis shows that Gaussian processes predict dispatching rule performance better than Neural Networks in most settings. Additionally, already a single Gaussian Process model can easily provide a measure of prediction quality. This is in contrast to many other machine learning techniques. We show how to use this measure to dynamically add additional training data and incrementally improve the model where necessary. Results therefore suggest, Gaussian processes are a very promising technique, which can lead to better scheduling performance (e.g., reduced mean tardiness) compared to other techniques.

An AIS-based hybrid algorithm with PDRs for multi-objective dynamic online job shop scheduling problem

The dynamic online job shop scheduling problem (JSSP) is formulated based on the classical combinatorial optimization problem – JSSP with the assumption that new jobs continuously arrive at the job shop in a stochastic manner with the existence of unpredictable disturbances during the scheduling process. This problem is hard to solve due to its inherent uncertainty and complexity. This paper models this class of problem as a multi-objective problem and solves it by hybridizing the artificial intelligence method of artificial immune systems (AIS) and priority dispatching rules (PDRs). The immune network theory of AIS is applied to establish the idiotypic network model for priority dispatching rules to dynamically control the dispatching rule selection process for each operation under the dynamic environment. Based on the defined job shop situations, the dispatching rules that perform best under specific environment conditions are selected as antibodies, which are the key elements to construct the idiotypic network. Experiments are designed to demonstrate the efficiency and competitiveness of this model.

A hybrid computer simulation-artificial neural network algorithm for optimisation of dispatching rule selection in stochastic job shop scheduling problems

Industrial systems are constantly subject to random events with inevitable uncertainties in production factors, especially in processing times. Due to this stochastic nature, selecting appropriate dispatching rules has become a major issue in practical problems. However, previous research implies that using one dispatching rule does not necessarily yield an optimal schedule. Therefore, a new algorithm is proposed based on computer simulation and artificial neural networks (ANNs) to select the optimal dispatching rule for each machine from a set of rules in order to minimise the makespan in stochastic job shop scheduling problems (SJSSPs). The algorithm contributes to the previous work on job shop scheduling in three significant ways: (1) to the best of our knowledge it is the first time that an approach based on computer simulation and ANNs is proposed to select dispatching rules; (2) non-identical dispatching rules are considered for machines under stochastic environment; and (3) the algorithm is capable of finding the optimal solution of SJSSPs since it evaluates all possible solutions. The performance of the proposed algorithm is compared with computer simulation methods by replicating comprehensive simulation experiments. Extensive computational results for job shops with five and six machines indicate the superiority of the new algorithm compared to previous studies in the literature.

Composite dispatching rule design for dynamic scheduling with customer‐oriented production priority control

AbstractIn practice, the criteria considered for production scheduling objectives are generally derived from some desired production performance factors of a manufacturing system. On the other hand, customer‐oriented production priority management focuses on the analysis of operational production management policies that cannot be readily measured in a quantitative manner. This paper presents an approach for multiobjective composite dispatching rule design, which simultaneously considers scheduling criteria and the customer‐oriented production priority management policies. The correctness of elementary dispatching rule selection is a critical aspect of composite dispatching rule design. Data envelopment analysis is adopted to select a set of corresponding elementary rules that appropriately convey the scheduling criteria. The selected elementary rules are composed with weighted aggregation to optimize the scheduling criteria of interest. Analytic hierarchy process is used for overall job prioritization by combining the different schedules derived from the composite dispatching rule and the customer‐oriented production priority rules. The implementation of the presented approach on single‐machine, multiobjective, dynamic scheduling is demonstrated by a case study. The production performance of composite dispatching rules that would be subsequently achieved by the presented approach is compared with some conventional dispatching rules, and the results are found to be satisfactory. © 2011 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Analyzing the effect of dispatching rules on the scheduling performance through grammar based flexible scheduling system

In this paper, the effects of dispatching rules on the scheduling performance of job-shops with different flexibility levels are analyzed. Four different flexibility levels are defined for operations. Five dispatching rules are evaluated according to mean tardiness as the performance criteria for the scheduling system. Performance variations of dispatching rules among different machine flexibility levels are determined and statistically analyzed. It is found out after detailed analysis that the effect of dispatching rule selection on job shop performance weakens as the job shop flexibility increases. This important finding should be taken into account while designing scheduling systems for job shops that are flexible.

Genetic Programming Based Data Mining Approach to Dispatching Rule Selection in a Simulated Job Shop

In this paper, a genetic programming based data mining approach is proposed to select dispatching rules which will result in competitive shop performance under a given set of shop parameters (e.g. interarrival times, pre-shop pool length). The main purpose is to select the most appropriate conventional dispatching rule set according to the current shop parameters. In order to achieve this, full factorial experiments are carried out to determine the effect of input parameters on predetermined performance measures. Afterwards, a genetic programming based data mining tool that is known as MEPAR-miner (multi-expression programming for classification rule mining) is employed to extract knowledge on the selection of best possible conventional dispatching rule set according to the current shop status. The obtained results have shown that the selected dispatching rules are appropriate ones according to the current shop parameters. All of the results are illustrated via numerical examples and experiments on simulated data.

Data-mining-based dynamic dispatching rule selection mechanism for shop floor control systems using a support vector machine approach

The purpose of this paper is to develop a data-mining-based dynamic dispatching rule selection mechanism for a shop floor control system to make real-time scheduling decisions. In data mining processes, data transformations (including data normalisation and feature selection) and data mining algorithms greatly influence the predictive accuracy of data mining tasks. Here, the z-scores data normalisation mechanism and genetic-algorithm-based feature selection mechanism are used for data transformation tasks, then support vector machines (SVMs) is applied for the dynamic dispatching rule selection classifier. The simulation experiments demonstrate that the proposed data-mining-based approach is more generalisable than approaches that do not employ a data-mining-based approach, in terms of accurately assigning the best dispatching strategy for the next scheduling period. Moreover, the proposed SVM classifier using the data-mining-based approach yields a better system performance than obtained with a classical SVM-based dynamic dispatching rule selection mechanism and heuristic individual dispatching rules under various performance criteria over a long period.

Development of two-level decision tree-based real-time scheduling system under product mix variety environment

Most of the research on machine learning-based real-time scheduling (RTS) systems has been aimed toward product constant mix environments. However, in a product mix variety manufacturing environment, the scheduling knowledge base (KB) is dynamic; therefore, it would be interesting to develop a procedure that would automatically modify the scheduling knowledge when important changes occur in the manufacturing system. All of the machine learning-based RTS systems (including a KB refinement mechanism) proposed in earlier studies periodically require the addition of new training samples and regeneration of new KBs. Hence, previous approaches investigating machine learning-based RTS systems have been confronted with the training data overflow problem and an increase in the scheduling KB building time, which are unsuitable for RTS control. The objective of this paper is to develop a KB class selection mechanism that can be supported in various product mix ratio environments. Hence, the RTS KB is developed by a two-level decision tree (DT) learning approach. First, a suitable scheduling KB class is selected. Then, for each KB class, the best (proper) dispatching rule is selected for the next scheduling period. Here, the proposed two-level DT RTS system comprises five key components: (1) training samples generation mechanism, (2) GA/DT-based feature selection mechanism, (3) building a KB class label by a two-level self-organizing map, (4) DT-based KB class selection module, and (5) DT-based dynamic dispatching rule selection module. The proposed two-level DT-based KB RTS system yields better system performance than that by a one-level DT-based RTS system and heuristic individual dispatching rules in a flexible manufacturing system under various performance criteria over a long period.

A neural network for dispatching rule selection in a job shop

This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines.

Application of reinforcement learning for agent-based production scheduling

Reinforcement learning (RL) has received some attention in recent years from agent-based researchers because it deals with the problem of how an autonomous agent can learn to select proper actions for achieving its goals through interacting with its environment. Although there have been several successful examples demonstrating the usefulness of RL, its application to manufacturing systems has not been fully explored yet. In this paper, Q-learning, a popular RL algorithm, is applied to a single machine dispatching rule selection problem. This paper investigates the application potential of Q-learning, a widely used RL algorithm to a dispatching rule selection problem on a single machine to determine if it can be used to enable a single machine agent to learn commonly accepted dispatching rules for three example cases in which the best dispatching rules have been previously defined. This study provided encouraging results that show the potential of RL for application to agent-based production scheduling.

Learning policies for single machine job dispatching

Reinforcement learning (RL) has received some attention in recent years from agent-based researchers because it deals with the problem of how an autonomous agent can learn to select proper actions for achieving its goals through interacting with its environment. Each time after an agent performs an action, the environment's response, as indicated by its new state, is used by the agent to reward or penalize its action. The agent's goal is to maximize the total amount of reward it receives over the long run. Although there have been several successful examples demonstrating the usefulness of RL, its application to manufacturing systems has not been fully explored. In this study, a single machine agent employs the Q-learning algorithm to develop a decision-making policy on selecting the appropriate dispatching rule from among three given dispatching rules. The system objective is to minimize mean tardiness. This paper presents a factorial experiment design for studying the settings used to apply Q-learning to the single machine dispatching rule selection problem. The factors considered in this study include two related to the agent's policy table design and three for developing its reward function. This study not only investigates the main effects of this Q-learning application but also provides recommendations for factor settings and useful guidelines for future applications of Q-learning to agent-based production scheduling.

Linguistic-based meta-heuristic optimization model for flexible job shop scheduling

In this paper, a linguistic based meta-heuristic modelling and solution approach for solving the Flexible Job Shop Scheduling Problem (FJSSP) is presented. FJSSP is an extension of the classical job-shop scheduling problem. The present problem definition is to assign each operation to a machine out of a set of capable machines ( the routing problem ) and to order the operations on the machines ( the sequencing problem ), such that a predefined performance measure is optimized. The scope of the problem is widened by taking into account the alternative process plans for each part ( process plan selection problem ) in the present study. Moreover, instead of using operations to represent product processing requirements and machine processing capabilities, machine independent capability units, which are known as Resource Elements (RE), are used. Representation of unique and shared capability boundaries of machine tools and part processing requirements is possible via RE. Using REs in scheduling can also reduce the problem size. The FJSSP is presented as a grammar and the productions in the grammar are defined as controls. Using these controls and the Giffler and Thompson (1960) priority rule-based heuristic, a simulated annealing algorithm is developed to solve FJSSP. This novel approach simplifies the modelling process of the FJSSP and enables usage of existing job shop scheduling algorithms for its solution. The results obtained from the computational study have shown that the proposed algorithm can solve this complex problem effectively within reasonable time. The results have also given some insights on the effect of the selection of dispatching rules and the flexibility level on the job shop performance. It is observed that the effect of dispatching rule selection on the job shop performance diminishes by increasing the job shop flexibility.

Experimental investigation of iterative simulation-based scheduling in a dynamic and stochastic job shop

Abstract A vital component of modern manufacturing systems is the scheduling and control system, which determines companies' overall performance in their respective supply chains. This paper studies iterative simulation-based scheduling mechanisms for manufacturing systems that operate in dynamic and stochastic environments. Also assessed are the issues involved when these mechanisms are used to make higher-level scheduling decisions, such as dispatching rule selection, instead of generation of a full schedule. A typical simulation-based system is outlined and tested under various experimental conditions. Examined are the effects of stochastic events such as machine breakdowns and processing time variations on the system performance, and the effectiveness of the simulation-based approach from the control point of view is evaluated. Finally, different levels of two important factors (look-ahead window and scheduling period) are compared for the iterative approach. Computational results show that, although simulation-based scheduling proves effective when these parameters are properly set, the overall performance diminishes due to the dynamic and stochastic nature of the system, which degrades the multi-pass improvement capability of the simulation runs. Experimental results also support the initial expectation in that frequent updates to the higher-level schedule may not be necessary when these decisions are naturally “adaptive” to the unexpected system changes.