Combining single objective dispatching rules into multi-objective ensembles for the dynamic unrelated machines environment

The concept of green scheduling, which deals with the environmental impact of the scheduling process, is becoming increasingly important due to growing environmental concerns. Most green scheduling problem variants focus on modelling the energy consumption during the execution of the schedule. However, the dynamic unrelated machines environment is rarely considered, mainly because it is difficult to manually design simple heuristics, called dispatching rules (DRs), which are suitable for solving dynamic, non-standard scheduling problems. Using hyperheuristics, especially genetic programming (GP), alleviates the problem since it enables the automatic design of new DRs. In this study, we apply GP to automatically design DRs for solving the green scheduling problem in the unrelated machines environment under dynamic conditions. The total energy consumed during the system execution is optimised along with two standard scheduling criteria. The three most commonly investigated green scheduling problem variants from the literature are selected, and GP is adapted to generate appropriate DRs for each. The experiments show that GP-generated DRs efficiently solve the problem under dynamic conditions, providing a trade-off between optimising standard and energy-related criteria.

A survey of dispatching rules for the dynamic unrelated machines environment

Dispatching rules are most commonly used to solve scheduling problems under dynamic conditions. Since designing new dispatching rules is a time-consuming process, it can be automated by using various machine learning and evolutionary computation methods. In previous research, genetic programming has been the most commonly used method for automatically designing new dispatching rules. However, there are many other evolutionary methods that use representations other than genetic programming that can be used to create dispatching rules. Some, such as gene expression programming, have already been used successfully, while others, such as Cartesian genetic programming or grammatical evolution, have not yet been used to generate dispatching rules. In this paper, six different methods (genetic programming, gene expression programming, Cartesian genetic programming, grammatical evolution, stack representation, and analytic programming) for generating dispatching rules for the unrelated machines environment are tested and the results for various scheduling criteria are analysed. It is also analysed how different individual sizes in the tested methods affect the performance and average size of the generated dispatching rules. The results show that, with the exception of grammatical evolution and analytic programming, all tested methods perform quite similarly, with results depending on the selected scheduling criterion. The results also show that Cartesian genetic programming is the most resistant to the occurrence of bloat and evolves dispatching rules with the smallest average size.

Collaboration methods for ensembles of dispatching rules for the dynamic unrelated machines environment

An incremental learning approach to dynamic parallel machine scheduling with sequence-dependent setups and machine eligibility restrictions

<p>Job shop scheduling (JSS) problems are difficult combinatorial optimisation problems that have been studied over the past 60 years. The goal of a JSS problem is to schedule the arriving jobs as effectively as possible on the limited machine resources on the shop floor. Each job has a sequence of operations that need to be processed on specific machines, but the machines can only process one job at a time. JSS and other types of scheduling are important problems in manufacturing systems, such as semiconductor manufacturing. In particular, this thesis focuses on dynamic JSS (DJSS) problems, where unforeseen events occur during processing that needs to be handled by the manufacturer. Examples of dynamic events that occur in DJSS problems are dynamic or unforeseen job arrivals, machine breakdowns, uncertain job processing times, and so on. A prominent method of handling DJSS problems is to design effective dispatching rules for the DJSS problem handled by the manufacturer. Dispatching rules are local decision makers that determine what job is processed by a machine when the machine finishes processing the previous job and becomes available. Dispatching rules have been investigated extensively by both academics and industry experts due to their simplicity, interpretability, low computational cost and their ability to cope effectively in dynamic environments. However, dispatching rules are designed for a specific DJSS problem and have no guarantee that they retain their effectiveness on other DJSS problems. In a real-world scenario, the properties of a manufacturing system can change over time, meaning that previously effective dispatching rule may longer be effective. Therefore, a manufacturer may need to redesign a dispatching rule to maintain a competitive edge on the market. However, designing an effective dispatching rule for a specific DJSS problem is expensive, and typically requires a human expert and extensive trial-and-error process to verify their effectiveness. To circumvent the manual design of dispatching rules, researchers have proposed hyper-heuristic approaches to automate the design of dispatching rules. In particular, various genetic programming based hyper-heuristic (GP-HH) approaches have been proposed in the literature to evolve effective dispatching rules for scheduling problems, including DJSS problems. However, there are many potential directions that have not been fully investigated. The overall goal of this thesis is to develop new and effective GP-HH approaches to designing high-quality dispatching rules for DJSS problems that aims to improve beyond the standard GP approach while maintaining computational efficiency. The focus will be on developing approaches which can decompose complex JSS problems down to simpler subcomponents, evolving multiple heuristics to handle the subcomponents, and developing GP-HH approaches that can handle complex DJSS problems by exploiting the problem properties. This thesis is the first to develop ensemble GP approaches that evolve ensembles of dispatching rules using cooperative coevolution. In addition, the thesis also investigates different combination schemes for one of the ensemble GP approaches to combine the ensemble member outputs effectively. The results show that ensemble GP approach evolves rules that perform significantly better than the rules evolved by the benchmark GP approach. This thesis provides the first investigation into applying GP-HH to a DJSS problem with dynamic job arrivals and machine breakdowns. In addition, the thesis also develops machine breakdown GP approach to the DJSS problem by incorporating machine breakdown GP terminals. The results show that the standard GP do not generalise well over the DJSS problem. The best rules from the machine breakdown GP approach do perform better than the best rule from the standard GP approach, and the analysis shows that the rules behaviour is similar to the shortest processing time rule in certain decision situations. This thesis is the first to develop a multitask GP approach to evolve a portfolio of dispatching rules for a DJSS problem with dynamic job arrivals and machine breakdowns. The multitask GP approach improve on the standard GP approach either in terms of the effectiveness of the output rules or the computation time required to evolve the rules. The analysis shows that the difference between DJSS problem having no machine breakdowns and having machine breakdowns is a more significant factor than the difference between two DJSS problems with different frequencies of machine breakdown investigated.</p>

Dynamic virtual machine consolidation using a multi-agent system to optimise energy efficiency in cloud computing

<p>Job shop scheduling (JSS) problems are difficult combinatorial optimisation problems that have been studied over the past 60 years. The goal of a JSS problem is to schedule the arriving jobs as effectively as possible on the limited machine resources on the shop floor. Each job has a sequence of operations that need to be processed on specific machines, but the machines can only process one job at a time. JSS and other types of scheduling are important problems in manufacturing systems, such as semiconductor manufacturing. In particular, this thesis focuses on dynamic JSS (DJSS) problems, where unforeseen events occur during processing that needs to be handled by the manufacturer. Examples of dynamic events that occur in DJSS problems are dynamic or unforeseen job arrivals, machine breakdowns, uncertain job processing times, and so on. A prominent method of handling DJSS problems is to design effective dispatching rules for the DJSS problem handled by the manufacturer. Dispatching rules are local decision makers that determine what job is processed by a machine when the machine finishes processing the previous job and becomes available. Dispatching rules have been investigated extensively by both academics and industry experts due to their simplicity, interpretability, low computational cost and their ability to cope effectively in dynamic environments. However, dispatching rules are designed for a specific DJSS problem and have no guarantee that they retain their effectiveness on other DJSS problems. In a real-world scenario, the properties of a manufacturing system can change over time, meaning that previously effective dispatching rule may longer be effective. Therefore, a manufacturer may need to redesign a dispatching rule to maintain a competitive edge on the market. However, designing an effective dispatching rule for a specific DJSS problem is expensive, and typically requires a human expert and extensive trial-and-error process to verify their effectiveness. To circumvent the manual design of dispatching rules, researchers have proposed hyper-heuristic approaches to automate the design of dispatching rules. In particular, various genetic programming based hyper-heuristic (GP-HH) approaches have been proposed in the literature to evolve effective dispatching rules for scheduling problems, including DJSS problems. However, there are many potential directions that have not been fully investigated. The overall goal of this thesis is to develop new and effective GP-HH approaches to designing high-quality dispatching rules for DJSS problems that aims to improve beyond the standard GP approach while maintaining computational efficiency. The focus will be on developing approaches which can decompose complex JSS problems down to simpler subcomponents, evolving multiple heuristics to handle the subcomponents, and developing GP-HH approaches that can handle complex DJSS problems by exploiting the problem properties. This thesis is the first to develop ensemble GP approaches that evolve ensembles of dispatching rules using cooperative coevolution. In addition, the thesis also investigates different combination schemes for one of the ensemble GP approaches to combine the ensemble member outputs effectively. The results show that ensemble GP approach evolves rules that perform significantly better than the rules evolved by the benchmark GP approach. This thesis provides the first investigation into applying GP-HH to a DJSS problem with dynamic job arrivals and machine breakdowns. In addition, the thesis also develops machine breakdown GP approach to the DJSS problem by incorporating machine breakdown GP terminals. The results show that the standard GP do not generalise well over the DJSS problem. The best rules from the machine breakdown GP approach do perform better than the best rule from the standard GP approach, and the analysis shows that the rules behaviour is similar to the shortest processing time rule in certain decision situations. This thesis is the first to develop a multitask GP approach to evolve a portfolio of dispatching rules for a DJSS problem with dynamic job arrivals and machine breakdowns. The multitask GP approach improve on the standard GP approach either in terms of the effectiveness of the output rules or the computation time required to evolve the rules. The analysis shows that the difference between DJSS problem having no machine breakdowns and having machine breakdowns is a more significant factor than the difference between two DJSS problems with different frequencies of machine breakdown investigated.</p>

Recently a promising research direction of statistical learning has been advocated, i.e., the optimal margin distribution learning with the central idea that instead of the minimal margin, the margin distribution is more crucial to the generalization performance. Although the superiority of this new learning paradigm has been verified under batch learning settings, it remains open for online learning settings, in particular, the dynamic environments in which the underlying decision function varies over time. In this paper, we propose the dynamic optimal margin distribution machine and theoretically analyze its regret. Although the obtained bound has the same order with the best known one, our method can significantly relax the restrictive assumption that the function variation should be given ahead of time, resulting in better applicability in practical scenarios. We also derive an excess risk bound for the special case when the underlying decision function only evolves several discrete changes rather than varying continuously. Extensive experiments on both synthetic and real data sets demonstrate the superiority of our method.

Out-of-order execution enabled deep reinforcement learning for dynamic additive manufacturing scheduling

This paper introduces a framework to assess the performance of manufacturing systems using hybrid simulation in real time. Continuous and discrete variables of different machines are monitored to analyze performance using a virtual environment running synchronous to plant floor equipment as a reference. Data are extracted from machines using industrial Internet of Things solutions. Productivity and reliability of a physical system are compared in real time with data from a hybrid simulation. The simulation uses discrete-event systems to estimate performance metrics at a system level, and continuous dynamics at a machine level to monitor input and output variables. Simulation outputs are used as a reference to detect abnormal conditions based on deviations of real outputs in different stages of the process. This monitoring method is implemented in a fully automated manufacturing system testbed with robots and CNC machines. Machines are integrated on an Ethernet/IP control network using a programmable logic controller to coordinate actions and transfer data. Results demonstrated the capacity to perform real-time monitoring and capture performance errors within confidence intervals. Note to Practitioners —Estimating expected performance of a manufacturing system processing different parts across multiple machines is a complex problem due to the lack of closed-form equations. Existing solutions focus on monitoring stochastic variables such as production or failure rate, or machine dynamics in separate environments often running asynchronous to the real system. This paper addresses the problem of monitoring and assessing the performance of complex manufacturing systems in real time. The proposed framework uses a real-time hybrid simulation of manufacturing at a machine and system level. The hybrid approach is based on a discrete and continuous model of manufacturing equipment integrated to run synchronously with the real plant floor operation. Data from both the virtual and real environments are merged to assess performance. Deviations from expected values represent an error that can trigger a warning signal to production, maintenance, and/or manufacturing personnel at the plant regarding health and productivity of plant operations.

Cellular function requires biomolecules to undergo dynamic transitions that include folding, conformational rearrangements, and large-scale assembly. The result is a highly interdependent network of processes that is maintained by a balance of thermodynamic and kinetic factors. In molecular machines, each constituent biopolymer (i.e., a chain of residues) first folds to a low-energy configuration/ensemble. These ordered polymers can then assemble into sophisticated architectures, which undergo conformational transitions during function. In contrast to the dynamics of macroscopic machines, molecular-level processes are stochastic, where the molecular interactions that ensure structural integrity are weak (i.e., on the scale of energetic fluctuations from solvent). In this dynamic environment, biomolecules constantly fluctuate (1), and the extent of disorder is heterogeneous between residues. Inspired by this, in 2003, Miyashita et al. postulated that biomolecules may exploit disorder to accelerate functional kinetics (2). In their theoretical investigation of protein function, the authors found large levels of strain energy accumulate in isolated residues. The predicted level of strain exceeded the stability of most proteins under cellular conditions, suggesting that these highly-strained regions may locally unfold, or “crack.” By cracking, the molecule may gain configurational entropy and thereby reduce the strain-induced barrier (Fig. 1). Subsequently, many theoretical and computational investigations have found evidence of cracking during function. These studies have primarily used simplified models (3), with which millisecond-scale dynamics are computationally accessible. In contrast, simulations with explicit-solvent models are typically limited to nanoseconds, or occasionally microseconds (4, 5). Because cracking and large-scale rearrangements occur on relatively long timescales (microseconds to milliseconds), evidence of cracking with explicit-solvent models has been sparse. In PNAS, Shan et al. (6) report the most definitive evidence of cracking from explicit-solvent simulations, to date. Using a specialized computer, they performed multiple simulations of EGFR kinase in solvent for tens of microseconds and found cracking to spontaneously occur. Although open questions remain about the precise details of cracking properties, Shan et al.’s study highlights how convergent theoretical descriptions of biological dynamics are emerging as explicit-solvent simulations are pushed to longer timescales.

In a dynamic manufacturing environment, machines and machining process selection based on current part mix may need to be revised if part mix has changed or new machine tools have become available and economical. However, the costs of acquiring new machines and revising manufacturing process may exceed the benefits derived from such expansion or revision. The problem of selecting the best machining process and equipment in a dynamic manufacturing environment is studied in this paper. An integer programming model and a heuristic algorithm were developed to solve the problem of multiple time periods. Lagrangian relaxation was used to generate lower bounds of the integer programming model for testing the optimality of the heuristic solution. Numerical examples are presented to illustrate the model and the solution technique.

Recently, the intelligent and advanced IT technology such as IoT, sensor, network and computer vision developed the rotation machinery outlier detection and condition diagnosis technology from vibration sensor data for various industrial environment. However, the rotary machine consists of complex system with various parts and operates under the dynamic environment, almost anomaly detection is not focused on the in–out combined information of rotary machine. With not according to multiple information, anomaly detection doesn’t process in the fluent way and be difficult to instantaneous decision making. This paper suggests Spectrogram Power Integrated Pattern (SPIN Pattern) Outlier Detection available to detect outliers based on integrated and multiple frequency patterns of rotary machines. SPIN Pattern extracts vibration frequency patterns from spectrogram image (Spectrogram Pattern), inside vibration attributes and then rotary capacity power frequency patterns (Power Pattern) which is external information. Considering integrated vibration frequency pattern of inside information and power pattern for outside information at the same time, SPIN Pattern is to derive subdivided pattern for fluent outlier causes. After deriving SPIN Pattern, CNN multi-classification model performed outlier detection based on SPIN Pattern and resulted in 85% high accuracy which is confirmed to stable outlier detection and a cause derivation.

The efficient migration of virtual machines (VMs) is critical for optimizing resource management, ensuring service continuity, and enhancing resiliency in cloud and edge computing environments, particularly as 6G networks demand higher reliability and lower latency. This study addresses the challenges of dynamically balancing server loads while minimizing downtime and migration costs under stochastic task arrivals and variable processing times. We propose a queuing theory-based model employing continuous-time Markov chains (CTMCs) to capture the interplay between VM migration decisions, server resource constraints, and task processing dynamics. The model incorporates two migration policies—one minimizing projected post-migration server utilization and another prioritizing current utilization—to evaluate their impact on system performance. The numerical results show that the blocking probability for the first VM for Policy 1 is 2.1% times lower than for Policy 2 and the same metric for the second VM is 4.7%. The average server’s resource utilization increased up to 11.96%. The framework’s adaptability to diverse server–VM configurations and stochastic demands demonstrates its applicability to real-world cloud systems. These results highlight predictive resource allocation’s role in dynamic environments. Furthermore, the study lays the groundwork for extending this framework to multi-access edge computing (MEC) environments, which are integral to 6G networks.