Task Relatedness-Based Multitask Genetic Programming for Dynamic Flexible Job Shop Scheduling

<p><b>Dynamic flexible job shop scheduling (DFJSS) has received widespread attention from academia and industry due to its reflection in real-world scheduling applications such as order picking in the warehouse and the manufacturing industry. It requires complex routing and sequencing decisions under unpredicted dynamic events. Genetic programming, as ahyper-heuristic approach (GPHH), has been successfully applied to evolve scheduling heuristics for DFJSS automatically due to its flexible representation. Although GPHH has achieved certain success in solving the DFJSS problems, there are still some limitations for applying GPHH to DFJSS, particularly in terms of its training efficiency, large search space, search mechanism, and multitask solving ability. The overall goal of this thesis is to develop effective GPHH algorithmsto evolve scheduling heuristics for DFJSS efficiently. Different machine learning techniques, i.e., surrogate, feature selection, specialised genetic operator, and multitask learning, are incorporated in this thesis to tackle the limitations.</b></p> <p>First, this thesis develops a novel multi-fidelity based surrogate-assisted GPHH for DFJSS to improve the training efficiency of GPHH. Specifically, multi-fidelity based surrogate models are first designed by simplifying the problem to be solved. Then, an effective collaboration mechanism with knowledge transfer is proposed for utilising the advantages of the multifidelity based surrogate models to solve the problem. The results show that the proposed algorithm can dramatically reduce the computational cost of GPHH without sacrificing the performance in all the test scenarios. With the same training time, the proposed algorithm can achieve significantly better performance than its counterparts in most scenarios while no worse in others.</p> <p>Second, this thesis designs a novel two-stage GPHH framework with feature selection to evolve scheduling heuristics for DFJSS automatically. Based on this framework, this thesis further proposes to evolve scheduling heuristics with only the selected features by eliminating the unselected features properly. Specifically, individual adaptation strategies are proposed to generate individuals with only the selected features by utilising the information of both the selected features and the investigated individuals during the feature selection process. The results show that the proposed algorithm can successfully achieve scheduling heuristics with fewer unique features and smaller sizes, which tends to be more interpretable. In addition, the proposed algorithm can evolve comparable scheduling heuristic with that obtained by the traditional GPHH within a much shorter training time.</p> <p>Third, this thesis proposes a novel recombinative mechanism to provide guidance for GPHH based on the importance of subtrees to realise effective and adaptive recombination for parents to produce offspring. Two measures are proposed to measure the importance of all the subtrees of an individual. The first one is based on the frequency of features, and the second is based on the correlation between the behaviour of subtrees and the whole tree (i.e., an individual). The importance information is utilised to decide the crossover points for the parents. The proposed recombinative guidance mechanism attempts to improve the quality of offspring by preserving the promising building-blocks of one parent and incorporating good building-blocks from the other. The results show that the proposed algorithm based on the correlation importance measure performs better than the proposed algorithm based on the feature frequency importance measure. In addition, the proposed algorithm based on the correlation importance measure between the behaviour of subtrees significantly also outperforms the state-of-the-art algorithms on most tested scenarios.</p> <p>Last, this thesis proposes a multitask GPHH approach and a surrogate-assisted multitask GPHH approach to solving multiple DFJSS tasks simultaneously. First, an effective hyper-heuristic multitask algorithm is proposed by adapting the traditional evolutionary multitask algorithms based on the characteristics of GPHH. Second, this thesis develops a novel surrogate-assisted multitask GPHH approach to solving multiple DFJSS tasks by sharing useful knowledge between different DFJSS scheduling tasks. Specifically, the surrogate-assisted multitask GPHH algorithm employs the phenotypic characterisation technique to measure the behaviours of scheduling rules to build a surrogate for each task accordingly. The built surrogates are not only used to improve the efficiency of solving each single DFJSS task but also utilised for knowledge sharing between multiple DFJSS tasks in multitask learning. The results show that the proposed algorithm can significantly improve the quality of scheduling heuristics for all the test scenarios. The results also observe that the proposed algorithms manage to solve multiple tasks collaboratively in terms of the evolved scheduling heuristics for different tasks in a multitask scenario.</p>

This paper presents an optimization via simulation approach to solve dynamic flexible job shop scheduling problems. In most real-life problems, certain operation of a part can be processed on more than one machine, which makes the considered system (i.e., job shops) flexible. On one hand, flexibility provides alternative part routings which most of the time relaxes shop floor operations. On the other hand, increased flexibility makes operation machine pairing decisions (i.e., the most suitable part routing) much more complex. This study deals with both determining the best process plan for each part and then finding the best machine for each operation in a dynamic flexible job shop scheduling environment. In this respect, a genetic algorithm approach is adapted to determine best part processing plan for each part and then select appropriate machines for each operation of each part according to the determined part processing plan. Genetic algorithm solves the optimization phase of solution methodology. Then, these machine-operation pairings are utilized by discrete-event system simulation model to estimate their performances. These two phases of the study follow each other iteratively. The goal of methodology is to find the solution that minimizes total of average flowtimes for all parts. The results reveal that optimization via simulation approach is a good way to cope with dynamic flexible job shop scheduling problems, which usually takes NP-Hard form.

This paper focuses on multi-objective dynamic flexible job shop scheduling problem (MODFJSP) with machine breakdown. First, a multi-objective dynamic scheduling model is established, with objectives to minimize makespan and total machine workload. Second, according to the processing status of faulty machine, a hybrid rescheduling strategy including transfer rescheduling strategy and complete rescheduling strategy is proposed to react to stochastic machine breakdown. The performance of two rescheduling strategies is analyzed in terms of the scheduling efficiency and its stability, from the delay extent and initial scheduling deviation, respectively. Besides, the optimal adaptation conditions of both scheduling strategies are obtained. Furthermore, the non-dominated sorting genetic algorithm (NSGA-II) is employed to solve the constructed model. Experimental results demonstrate the effectiveness of the proposed strategies on reducing the impact of machine breakdown in real scheduling.

In real scheduling problems, unexpected changes may occur frequently such as changes in task features. These changes cause deviation from primary scheduling. In this article, a heuristic model, inspired from Artificial Bee Colony algorithm, is proposed for a dynamic flexible job-shop scheduling (DFJSP) problem. This problem consists of n jobs that should be processed by m machines and the processing time of jobs deviates from estimated times. The objective is near-optimal scheduling after any change in tasks in order to minimise the maximal completion time (Makespan). In the proposed model, first, scheduling is done according to the estimated processing times and then re-scheduling is performed after determining the exact ones considering machine set-up. In order to evaluate the performance of the proposed model, some numerical experiments are designed in small, medium and large sizes in different levels of changes in processing times and statistical results illustrate the efficiency of the proposed algorithm.

Research on Design Method of Dynamic Shop Floor Scheduling System Based on Human-computer Interaction

In this paper, an intelligent approach based on gene expression programming (GEP) is proposed to discover scheduling strategies for dynamic flexible job shop scheduling problem (DFJSP). In the approach, an indirect encoding and decoding scheme is designed in which the concept of automatically defined functions (ADF) is introduced. In the evaluation of the proposed GEP-based approach, simulation experiments are conducted with respect to the objective of minimizing mean tardiness. The results show that GEP-based approach can automatically find more efficient scheduling strategies for DFJSP under a big range of processing conditions.

© 2020, Springer Nature Switzerland AG. Dynamic flexible job shop scheduling (DFJSS) is a very valuable practical application problem that can be applied in many fields such as cloud computing and manufacturing. In DFJSS, machine assignment and operation sequencing decisions need to be made simultaneously in dynamic environments with unpredicted events such as new job arrivals. Scheduling heuristic is an ideal candidate for solving the DFJSS problem due to its efficiency and simplicity. Genetic programming (GP) has been successfully applied to evolve scheduling heuristics for job shop scheduling automatically. However, GP has a huge search space, and the traditional search algorithms do not utilise effectively the information obtained from the evolutionary process. This paper proposes a new method to make better use of the information during the evolutionary process of GP to further enhance the ability of GP. To be specific, this paper proposes two adaptive search strategies based on the frequency of features in promising individuals to guide GP to evolve effective rules. This paper examines the proposed algorithm on six different DFJSS scenarios. The results show that the proposed GP with adaptive search can converge faster and achieve significantly better performance than the GP without adaptive search in most scenarios while no worse in all other scenarios without increasing the computational cost.

Flexible Job Shop Scheduling (FJSS) problem has many real-world applications such as manufacturing and cloud computing, and thus is an important area of study. In real world, the environment is often dynamic, and unpredicted job orders can arrive in real time. Dynamic FJSS consists of challenges of both dynamic optimisation and the FJSS problem. In Dynamic FJSS, two kinds of decisions (so-called routing and sequencing decisions) are to be made in real time. Dispatching rules have been demonstrated to be effective for dynamic scheduling due to their low computational complexity and ability to make real-time decisions. However, it is time consuming and strenuous to design effective dispatching rules manually due to the complex interactions between job shop attributes. Genetic Programming Hyper-heuristic (GPHH) has shown success in automatically designing dispatching rules which are much better than the manually designed ones. Previous works only focused on standard job shop scheduling with only the sequencing decisions. For FJSS, the routing rule is set arbitrarily by intuition. In this paper, we explore the possibility of evolving both routing and sequencing rules together and propose a new GPHH algorithm with Cooperative Co-evolution. Our results show that co-evolving the two rules together can lead to much more promising results than evolving the sequencing rule only.

Genetic programming has been explored in recent works to evolve hyper-heuristics for dynamic flexible job shop scheduling. To generate optimum rules, the algorithm searches a space of trees composed from a set of terminals and operators. Since the search space is exponentially proportional to the size of the terminal set, it is preferred to opt out any insignificant terminals. Feature selection techniques has been employed to reduce the terminal set size without discarding any important information and they have proven to be effective for enhancing search performance and efficiency for dynamic flexible job shop scheduling. In this paper, we extends our previous work by adding a modified version of the two-stage genetic programming algorithm and by comparing the different methods in a larger experimental setup. The results show that feature selection can generate better rules in most of the cases while also being more efficient to in a production environment.KeywordsFeature selectionFlexible job shop schedulingDynamic schedulingGenetic programmingHyper heuristics

In this paper, 4S auto maintenance shop scheduling with multi-constraint machines is of concern. In 4S auto maintenance shop, it may appear temporary bottlenecks except for the long-term bottlenecks, and they form multi-constraint machines jointly with the task size reaching the peak. Through scheduling the constraint machines effectively, it can improve overall performance of the system to satisfy the customers’ requirements. First, we describe and construct a model for the scheduling problem which can be designed as the dynamic flexible job shop scheduling problem (FJSP) with multi-constraint machines for the goal of minimizing customers’ waiting time. Then, putting an emphasis on the constraint machines, we apply the theory of constraint to decompose and simplify the complex system and also construct the coordination mechanism between constraint machines and non-constraint machines. After that, an improved constraint-guided heuristic algorithm is proposed to solve the constraint machine scheduling problem, while different dispatching rules are selected for solving the non-constraint machine scheduling according to the location of the non-bottleneck in the system. What is more, we design the rescheduling rules combing characteristics of the problem to realize dynamic scheduling with multi-constraint machines. Finally, 4S auto maintenance shop scheduling with high workload during the rush hour (on the eve of the holiday) served as the actual cases, and the proposed algorithm is compared with three different dispatching rules under various size of problems. The result obtained from the computational study has shown that the proposed algorithm is much better.

Dynamic flexible job-shop scheduling (DFJSS) is a challenging combinational optimization problem that takes the dynamic environment into account. Genetic programming hyperheuristics (GPHH) have been widely used to evolve scheduling heuristics for job-shop scheduling. A proper selection of the terminal set is a critical factor for the success of GPHH. However, there is a wide range of features that can capture different characteristics of the job-shop state. Moreover, the importance of a feature is unclear from one scenario to another. The irrelevant and redundant features may lead to performance limitations. Feature selection is an important task to select relevant and complementary features. However, little work has considered feature selection in GPHH for DFJSS. In this article, a novel two-stage GPHH framework with feature selection is designed to evolve scheduling heuristics only with the selected features for DFJSS automatically. Meanwhile, individual adaptation strategies are proposed to utilize the information of both the selected features and the investigated individuals during the feature selection process. The results show that the proposed algorithm can successfully achieve more interpretable scheduling heuristics with fewer unique features and smaller sizes. In addition, the proposed algorithm can reach comparable scheduling heuristic quality with much shorter training time.

Genetic programming (GP) has achieved great success in evolving effective scheduling rules to make real-time decisions in dynamic flexible job shop scheduling (DFJSS). To improve generalization, a commonly used strategy is to change the training simulation(s) at each generation of the GP process. However, with such a simulation rotation, GP may lose potentially promising individuals that happen to perform poorly in one particular generation. To address this issue, this paper proposed a new multi-tree GP with archive (MTAGP) to evolve the routing and sequencing rules for DFJSS. The archive is used to store the potentially promising individuals of each generation during evolution of genetic programming. The individuals in the archive can then be fully utilized when the simulation is changed in subsequent generations. Through extensive experimental tests, the MTAGP algorithm proposed in this paper is more effective than the multi-tree GP without archive algorithm in a few scenarios. Further experiments were carried out to analyze the use of the archive and some possible guesses were ruled out. We argue that the use of archives does increase the diversity of the population. However, the number of individuals in the archive that ranked in the top five of the new population is small. Therefore, the archive may not be able to greatly improve the performance. In the future, we will investigate better ways to use the archive and better ways to update individuals in the archive.

Dynamic flexible job shop scheduling (JSS) is a challenging combinatorial optimization problem due to its complex environment. In this problem, machine assignment and operation sequencing decisions need to be made simultaneously under the dynamic environments. Genetic programming (GP), as a hyperheuristic approach, has been successfully used to evolve scheduling heuristics for dynamic flexible JSS. However, in traditional GP, recombination between parents may disrupt the beneficial building blocks by choosing the crossover points randomly. This article proposes a recombinative mechanism to provide guidance for GP to realize effective and adaptive recombination for parents to produce offspring. Specifically, we define a novel measure for the importance of each subtree of an individual, and the importance information is utilized to decide the crossover points. The proposed recombinative guidance mechanism attempts to improve the quality of offspring by preserving the promising building blocks of one parent and incorporating good building blocks from the other. The proposed algorithm is examined on six scenarios with different configurations. The results show that the proposed algorithm significantly outperforms the state-of-the-art algorithms on most tested scenarios, in terms of both final test performance and convergence speed. In addition, the rules obtained by the proposed algorithm have good interpretability.

Dynamic flexible job shop scheduling (DFJSS) is a critical and challenging problem in production scheduling such as order picking in the warehouse. Given a set of machines and a number of jobs with a sequence of operations, DFJSS aims to generate schedules for completing jobs to minimise total costs while reacting effectively to dynamic changes. Genetic programming, as a hyper-heuristic approach, has been widely used to learn scheduling heuristics for DFJSS automatically. A scheduling heuristic in DFJSS includes a routing rule for machine assignment and a sequencing rule for operation sequencing. However, existing studies assume that the routing and sequencing are equally important, which may not be true in real-world applications. This paper aims to propose an importance-aware GP algorithm for automated scheduling heuristics learning in DFJSS. Specifically, we first design a rule importance measure based on the fitness improvement achieved by the routing rule and the sequencing rule across generations. Then, we develop an adaptive resource allocation strategy to give more resources for learning the more important rules. The results show that the proposed importance-aware GP algorithm can learn significantly better scheduling heuristics than the compared algorithms. The effectiveness of the proposed algorithm is realised by the proposed strategies for detecting rule importance and allocating resources. Particularly, the routing rules play a more important role than the sequencing rules in the examined DFJSS scenarios.KeywordsImportance-aware scheduling heuristics learningGenetic programmingHyper-heuristicDynamic flexible job shop scheduling

Dynamic flexible job shop scheduling (DFJSS) problem is an important scenario in intelligent manufacturing domain with the requirement of real-time decision-making under complex constraints. Existing approaches struggle to handle dynamic environments and heterogeneous job-resource relationships effectively while keeping optimum scheduling performance simultaneously. To address this challenge, a heterogeneous graph reinforcement learning framework combining question-aware neighborhood aggregation and interoption prompt attention (QIHGRL) is presented to address the DFJSS problem with new job insertions and variable processing times to minimize total tardiness. The optimization objectives are transformed into attention-guided signals by the question-aware neighborhood aggregation module to improve feature representation in the heterogeneous graph encoding stage of the QIHGRL. The competition and collaboration among scheduling actions are explicitly modeled by the interoption prompt attention layer in the policy optimization phase of the QIHGRL via adjusting action selection weights through a multihead attention mechanism to balance exploration and exploitation of the candidates in the population of the QIHGRL. The experimental results testified that the performance and efficiency of the QIHGRL outperforms that of the state of the arts algorithms.