Since severe environmental problem in manufacturing industries is becoming increasingly prominent, energy-efficient production scheduling has gained more and more attentions. This paper studies an energy-efficient distributed fuzzy hybrid blocking flow-shop scheduling problem (EEDFHBFSP), where processing time and setup time are uncertain. The objective is to minimize fuzzy makespan and total fuzzy energy consumption simultaneously. To solve such problem, a mixed-integer linear programming model is firstly presented to format it. Then, a meta-Q-learning-based multi-objective metaheuristic (MQL-MM) is proposed. In MQL-MM, a machine-position-based dispatch rule is designed as the decoding scheme. A decomposition-based constructive heuristic is employed to generate the initial population with high quality and diversity. Several problem-specific search operators are developed to explore and exploit the solution space. A meta-Q-learning-based multi-objective search framework is presented to guide the using of search operators, which includes a meta-training phase and an adaptive search phase. The meta-training phase is employed to train the search operators to construct the Q-learning model. The adaptation search phase utilizes such model to conduct the automatic selection of the search operators. Moreover, an energy saving strategy is designed to improve the candidate solutions. Finally, we conduct extensive experiments. The experimental results show that the designs of MQL-MM are effective, and MQL-MM performs better than several well-performing methods on solving EEDFHBFSP.

Hyperedges, as extensions of pairwise edges, can characterize higher-order relations among multiple individuals. Due to the necessity of hypergraph detection in practical systems, hyperedge prediction has become a frontier problem in complex networks. However, previous hyperedge prediction models encounter three challenges: (i) failing to predict dynamic and arbitrary-order hyperedges simultaneously, (ii) confusing higher-order and lower-order features together to propagate neighborhood information, and (iii) lacking the capability to learn physical evolution laws, which lead to poor performance of the models. To tackle these challenges, we propose D$^{3}$HP, aDual-viewDesynchronization hypergraph learning for arbitrary-orderDynamicHyperedgePrediction. Specifically, D$^{3}$HP extracts the dynamic higher-order and lower-order features of hyperedges separately through an elastic hypergraph neural network (EHGNN) and an alternate desynchronization graph convolutional network (ADGCN) at each time snapshot. EHGNN is designed to incrementally mine the implicit higher-order relations and propagate neighborhood information. Moreover, ADGCN aims to combine GCN with desynchronization learining to learn the physical evolution of lower-order relations and alleviate the over-smoothing problem. Further, we improve the prediction performance of the model by rationally fusing the features learned from the dual views. Extensive experiments on 8 dynamic higher-order networks demonstrate that D$^{3}$HP outperforms 14 state-of-the-art baselines.

With increasing complex workflow application and computational resources requirement, distributed computing has attracted growing attention. Meanwhile, cloud computing has emerged as a prominent solution due to its elasticity, heterogeneity, and on-demand capabilities. However, data security and execution reliability in cloud are still urgent issues that need to be addressed. Based on the data encryption and task redundancy mechanism, this paper presented a many-objective workflow scheduling problem (RSWSP) with the objectives of minimizing the execution time, cost, risk, and non-reliability. Then, a two-stage learning-driven many-objective memetic algorithm (TMMA) with tailored designs is introduced to address the RSWSP. First, several problem-specific heuristics are employed for cooperative initialization, generating a diverse set of initial solutions. Second, a two-stage global diversification approach is implemented to explore the problem space, which clusters the population into sub-populations and adoptive selects leader solutions based on the state of the population. In addition, a learning-driven local intensification strategy is incorporated for exploitation, encompassing six neighbor search operators and a Q-learning-based selection mechanism. Extensive experiments have been conducted to validate the performance of TMMA. The statistical comparison reveals that the TMMA is superior to state-of-the-art algorithms in solving the RSWSP in terms of solution quality and robustness.

This article studies an energy-efficient scheduling problem in a two-stage manufacturing system with distributed heterogeneous hybrid flow shops and mixed-model assembly lines (EDHHFSP-MMAL). A mixed-integer linear programming model is proposed that simultaneously optimizes total tardiness and energy consumption (including operational, idle, and common energy components). To solve this multiobjective problem, a learning competitive swarm optimizer (LCSO) is proposed that integrates two novel mechanisms: 1) environmental-competitive learning through probability models capturing product-task relationships and 2) comprehensive learning utilizing reinforcement learning to guide local search based on nondominated solution states. The hybrid approach balances convergence speed and solution diversity by combining solution-space and policy-space learning perspectives. Experimental results demonstrate LCSO’s superior performance over compared methods, achieving 25% improvement in energy-time tradeoff compared to other state-of-the-art multiobjective optimizers in solving related problems. The proposed method particularly excels in optimizing complex energy-time tradeoffs while maintaining better solution diversity and convergence across different problem scales.

Lot planning and production scheduling are two strong coupled sub-problems in the manufacturing process. The lot-streaming technique divides the products into several lots. The production scheduling determines the processing order of products. This paper focuses on the integration of lot sizing and scheduling problem in the distributed heterogeneous hybrid flow shop (DHHFSLSP) which considers determining the quantity and size of lots, factory assignment, machine selection, and order sequence. A learning-driven iterated local search algorithm (LDILS) is proposed for solving the DHHFSLP. Firstly, a framework of learning-driven trajectory-based meta-heuristics is proposed, where a learning engine is integrated to guide the state of searching. Then, an NEH-based constructive heuristic is proposed to generate a promising initial solution. Next, several lot sizing and scheduling searching operators are proposed. Based on these operators,Q-learning is regarded as a learning engine to capture the searching state and choose a searching action. Finally, a restart mechanism is used to calibrate searching direction by copying the best solution found so far. A comprehensive experiment based on amounts of testing instances is conducted to investigate the effectiveness of initialization,Q-learning framework, and searching operators. Compared to relevant algorithms, LDILS can solve the DHHFSLSP effectively and efficiently.Note to Practitioners—This paper studies a lot sizing and scheduling problem in the distributed heterogeneous hybrid flow shop, which are always faced by planners and production managers. The reasonable lot sizing plans and schedules can increase the efficiency of production. The model of this paper can be used in many real productions when meeting the following conditions, i.e. heterogeneous factories, flow shops, and parallel machines, and the jobs can be split into several sub-lots. This paper proposes a learning-driven iterated local search algorithm, which can obtain high-quality solutions for decision-makers. The experiment results demonstrate its high effectiveness and efficiency.

The cloud workflow scheduling problem has important applications in modern commercial and industrial areas. In the public cloud environment, the workflow suffers from security threats because of the multiple tenants and the distribution of computational resources. This paper models cloud workflow scheduling as a novel multi-objective optimization problem that aims to minimize execution time, cost, and risk. Due to the complexity of the considered problem, a multi-objective cluster-based cooperative co-evolutionary (CBCC) algorithm with several novel designs is proposed. First, a new initialization strategy is presented to generate potential non-dominated solutions. Based on the cluster-based multi-objective optimization framework, a novel collaboration model is proposed, and it adopts four populations to address the subproblems, respectively. Moreover, a diversification strategy is designed to maintain the diversity of the global archive. Furthermore, a problem-specific intensification strategy is designed to intensify the potential solutions. A comprehensive computational and statistical campaign was carried out to verify the performance of CBCC. The results show that the proposed CBCC outperforms several meta-heuristics adapted from closely related scheduling models in the literature by a significantly considerable margin.Note to Practitioners—This paper describes a novel approach called CBCC for minimizing the cost, time, and risk when scheduling a workflow in the cloud environment. CBCC seamlessly combines the cluster-based multi-objective optimization framework and several problem-specific components such as initialization, diversification, and intensification strategies. As the considered problem has not been previously addressed in the literature, five state-of-the-art algorithms for closely related problems, which include I_MaOPSO (improved many objective particle swarm optimization), EMS-C (evolutionary multi-objective scheduling for cloud), ch-PICEA-g (enhanced multi-objective co-evolutionary algorithm), VaEA (vector angle-based evolutionary algorithm), and DQN-based MARL (Deep-Q-network-based Multi-agent Reinforcement Learning) are adopted as baselines. The results demonstrate that CBCC significantly outperforms the baselines with a 95% confidence level.

Workflow scheduling in cloud environments has become a significant topic in both commercial and industrial applications. However, it is still an extraordinarily challenge to generate effective and economical scheduling schemes under the deadline constraint especially for the large scale workflow applications. To address the issue, this article investigates the cloud workflow scheduling problem with the aim of minimizing the whole cost of workflow execution whereas maintaining its execution time under a predetermined deadline. A novel knowledge-based adaptive discrete water wave optimization (KADWWO) algorithm is developed based on the problem-specific knowledge of cloud workflow scheduling. In the proposed KADWWO, a discrete propagation operator is designed based on the idle time knowledge of hourly-based cost model to adaptively explore the huge search space. The adaptive refraction operator is employed to avoid stagnation and expand the available resource pool. Meanwhile, the dynamic grouping based breaking operator is designed to exploit the excellent block structure knowledge of task allocation scheme and corresponding resource to intensify the local region and accelerate convergence. Extensive simulation experiments on the well-known scientific workflow demonstrate that the KADWWO approach outperforms several recent state-of-the-art algorithms.

In consideration of the uncertainty of the scientific workflows, an interval-based multi-objective cloud workflow scheduling problem is investigated, which widely exists in the cloud environment. This problem aims at allocating the workflow to the public cloud environment. The uncertain workload and communication data of workflow as well as the processing ability and bandwidth of the resources are represented by an interval number, which models the uncertainty of these variables. The objectives are to minimize the total execution time and cost. To address this problem, a discrete interval-based multi-objective memetic algorithm (DIMOMA) is proposed. A hybrid initial strategy is employed to generate the potential population. With the contribution-based selection mechanism, the self-adaptive genetic operators are designed to perform a global search in the problem space. Then, a novel local search procedure is incorporated to perform intensification and accelerate the convergence. A comprehensive computational experiment and comparisons with several meta-heuristics adapted from the related problems are conducted based on an extended benchmark set. The simulated results reveal that the proposed method can achieve better trade-off fronts between the execution time and cost of workflow. On the performance metric hypervolume which measures both execution time and cost, the proposed DIMOMA can improve by 3.90%, 9.30%, 6.25%, and 7.74% compared with EMS-C, MOACS, ch-PICEA-g, and I_MaOPSO, respectively. Besides, DIMOMA can achieve better robustness, which means the difference between the lower and upper bounds of the execution time and cost of the solutions obtained by DIMOMA are over smaller than the state-of-the-art algorithms.

With the development of cloud computing, multi-cloud systems have become common platforms for hosting and executing workflow applications in recent years. However, the complexity of workflow scheduling increases exponentially because of the diversified billing mechanisms, heterogeneous virtual machines, and reliability of multi-cloud systems. This article focuses on a multi-objective workflow scheduling problem in multi-cloud systems (MOWSP-MCS). The makespan, cost, and reliability are considered the optimization objectives from the perspective of users. Compared with the classical multi-objective workflow scheduling in the cloud environment, MOWSP-MCS allows users to apply the backup technique to improve reliability. To solve the MOWSP-MCS, this article proposes a reliability-aware multi-objective memetic algorithm (RA-MOMA) containing a diversification strategy and intensification strategy. In the diversification strategy, several problem-specific genetic operators are introduced to construct the diversified offspring individuals. In the intensification strategy, four problem-specific neighborhood operators are designed based on the critical path and resource utilization rate to improve the quality of the individuals in the archive set. A comprehensive numerical experiment is conducted to evaluate the effectiveness of RA-MOMA. The comparisons with several related algorithms demonstrate the superiority of RA-MOMA for solving the MOWSP-MCS.

This article studies a distributed heterogeneous hybrid flow shop scheduling problem under nonidentical time-of-use electricity tariffs (DHHFSP-NTOU). The makespan and the total electricity charge are considered as the optimization objectives from the view of production and management. The DHHFSP-NTOU considers different processing capabilitie and time-of-use electricity tariffs for each factory. The mixed-integer linear programming (MILP) model of DHHFSP-NTOU is established. To solve the DHHFSP-NTOU, this article proposes an ant colony optimization behavior-based multiobjective evolutionary algorithm based on decomposition (ACO_MOEA/D). A problem-specific ant colony behavior is presented to construct offspring individuals. Eight neighborhoods within the factory and between factories are adopted to improve the quality of the individuals in the archive set. A right-shift movement is used to reduce the electricity charge. A large number of numerical experiments and comprehensive investigations are carried out to test the efficiency and effectiveness of ACO_MOEA/D. The experimental results show that each component (e.g., ant colony behavior, neighborhoods move operators, right-shift movement) contributes to the performance of ACO_MOEA/D. The comparisons with several related algorithms show the superiority of ACO_MOEA/D for solving the DHHFSP-NTOU. Note to Practitioners—From the managers’ insights, the electricity charge is a large cost in the production. The scheduling is an economical approach to reduce the electricity charge. For the time-of-use (TOU) tariffs, the managers can adjust the schedule to reduce the idle time or move some operations to the interval period with a lower electric price. This article studies a distributed heterogeneous hybrid flow shop scheduling problem under nonidentical TOU (UTOU) electricity. This model can be used in many manufacturing enterprises that have several heterogeneous factories. This article proposes an ant colony optimization behavior-based multiobjective evolutionary algorithm based on decomposition (ACO_MOEA/D) to minimize the makespan and the total electricity charge. The ACO_MOEA/D can provide the economy and high-efficiency schedules for practitioners. The computational results confirm its effectiveness and efficiency.

Influenced by the economic globalization, the distributed manufacturing has been a common production mode. This paper considers a multiobjective distributed no-wait flow-shop scheduling problem with sequence-dependent setup time (MDNWFSP-SDST). This scheduling problem exists in many real productions such as baker production, parallel computer system, and surgery scheduling. The performance criteria are the makespan and the total weight tardiness. In the MDNWFSP-SDST, several identical factories are considered with the related flow-shop scheduling problem with no-wait constraints. For solving the MDNWFSP-SDST, a Pareto-based estimation of distribution algorithm (PEDA) is presented. Three probabilistic models including the probability of jobs in empty factory, two jobs in the same factory, and the adjacent jobs are constructed. The PWQ heuristic is extended to the distributed environment to generate initial individuals. A sampling method with the referenced template is presented to generate offspring individuals. Several multiobjective neighborhood search methods are developed to optimize the quality of solutions. The comparison results show that the PEDA obviously outperforms other considered multiobjective optimization algorithms for addressing MDNWFSP-SDST.

This paper proposes a hybrid iterated greedy (HIG) algorithm to solve the distributed no-wait flow shop scheduling problem (DNWFSP) with the makespan criterion. The HIG mainly consists of four components, i.e. initialization phase, construction and destruction, local search, acceptance criterion. In the initialization phase, a modified NEH (Nawaz-Enscore-Ham) is proposed to generate a promising initial solution. In the local search phase, four local searching methods based on problem properties (i.e. insert move within factory, insert move between factories, swap move between factories) are proposed to enhance searching ability. The effectiveness of the initialization phase and local search method is shown by numerical comparison, and the comparisons with the recently published iterated greedy algorithms demonstrate the high effectiveness and searching ability of the proposed HIG for solving the DNWFSP.