Adaptive Scheduling System Research Articles

Design and Implementation of Simulation-Based Scheduling System with Reinforcement Learning for Re-Entrant Production Lines

Recently, manufacturing companies have been making efforts to increase resource utilization while ensuring the flexibility of production lines to respond to rapidly changing market environments and customer demand. In the high-tech manufacturing industry, which requires expensive manufacturing facilities and is capital-intensive, re-entrant production lines are used for efficient production with limited resources. In such a production system, a part visits a specific station repeatedly during the production period. However, a re-entrant production line requires an appropriate scheduling system because other parts with different processing requirements are processed at the same station. In this study, a re-entrant production line was modeled as a manufacturing environment via simulation, and an adaptive scheduling system was developed to improve its operational performance by applying deep reinforcement learning (DRL). To achieve this, a software architecture for integrating DRL with the simulation was developed and the states, actions, and rewards of the reinforcement learning (RL) agent were defined. Moreover, a discrete-event simulation control module was designed to collect data from the simulation model and evaluate the policy network trained via DRL. Finally, the applicability and effectiveness of the developed scheduling system were verified by conducting experiments on a hypothetical re-entrant production line.

Adaptive Context-Aware Energy Optimization for Services on Mobile Devices with Use of Machine Learning

In this paper we present an original adaptive task scheduling system, which optimizes the energy consumption of mobile devices using machine learning mechanisms and context information. The system learns how to allocate resources appropriately: how to schedule services/tasks optimally between the device and the cloud, which is especially important in mobile systems. Decisions are made taking the context into account (e.g. network connection type, location, potential time and cost of executing the application or service). In this study, a supervised learning agent architecture and service selection algorithm are proposed to solve this problem. Adaptation is performed online, on a mobile device. Information about the context, task description, the decision made and its results such as power consumption are stored and constitute training data for a supervised learning algorithm, which updates the knowledge used to determine the optimal location for the execution of a given type of task. To verify the solution proposed, appropriate software has been developed and a series of experiments have been conducted. Results show that as a result of the experience gathered and the learning process performed, the decision module has become more efficient in assigning the task to either the mobile device or cloud resources.

Resilience in the Surgical Scheduling to Support Adaptive Scheduling System.

Operating Room (OR) managers frequently encounter uncertainties related to real-time scheduling, especially on the day of surgery. It is necessary to enable earlier identification of uncertainties occurring in the perioperative environment. This study aims to propose a framework for resilient surgical scheduling by identifying uncertainty factors affecting the real-time surgical scheduling through a mixed-methods study. We collected the pre- and post-surgical scheduling data for twenty days and a one-day observation data in a top-tier general university hospital in South Korea. Data were compared and analyzed for any changes related to the dimensions of uncertainty. The observations in situ of surgical scheduling were performed to confirm our findings from the quantitative data. Analysis was divided into two phases of fundamental uncertainties categorization (conceptual, technical and personal) and uncertainties leveling for effective decision-making strategies. Pre- and post-surgical scheduling data analysis showed that unconfirmed patient medical conditions and emergency cases are the main causes of frequent same-day surgery schedule changes, with derived factors that affect the scheduling pattern (time of surgery, overtime surgery, surgical procedure changes and surgery duration). The observation revealed how the OR manager controlled the unexpected events to prevent overtime surgeries. In conclusion, integrating resilience approach to identifying uncertainties and managing event changes can minimize potential risks that may compromise the surgical personnel and patients’ safety, thereby promoting higher resilience in the current system. Furthermore, this strategy may improve coordination among personnel and increase surgical scheduling efficiency.

A decision support flexible scheduling system for continuous galvanization lines using genetic algorithm

An important, complex problem for logistic optimization in the steel manufacturing plants is obtaining a flexible and adaptive scheduling system for a continuous galvanization line (CGL). The problem tackled in this work involves several constraints and characteristics inspired by real-life manufacturing goals. Given the complexity of the problem, which belongs to the class of NP-hard problems, a genetic algorithm (GA) methodology was developed, combining a penalty procedure defined for constraints with assigned weights for different characteristics of coils. By enlisting the ability and flexibility of GAs, a set of parameters are analyzed to achieve the best results for practical applications. This scheduling solution predicts a CGL sequences with a minimum number of coil transitions, to improve productivity and reduce costs.

Enhanced Retention Performance Modeling for Intelligent Tutoring System

The aim of Personalized Adaptive Scheduling System is not only to maximize learning, but also to minimize the tendency to forget. Empirical studies from psychology and cognitive theory of memory indicate that repetition with gradually increasing spacing interval is necessary to promote optimal long-term retention. While all individuals differ in their capacity to learn and retain information, the existing personalized systems attempt to model student retention performance based on learning capabilities only. The present study aims to investigate the extent to which individual differences in learning and forgetfulness help in predicting retention performance, which is essential for designing personalized retrieval practice schedules for a student. This study was conducted using data from Personalized Adaptive Scheduling System in ASSISTments, an adaptive mathematical tutor. The results illustrate the importance of student learning and forgetfulness features in predicting retention performance of a new skill, the proposed prediction model showed a significant improvement from an R of 0.2975 with an existing baseline model to an R value of 0.3989. In addition the newly identified features are used to predict the retention interval of a student, since ideal personalized retention schedules should be roughly equal to the retention interval of the student. The predictive accuracy of the linear regression model thus obtained was found to be statistically significant with an R value of 0.413.

Deadline Constrained Adaptive Multilevel Scheduling System in Cloud Environment

In cloud, everything can be provided as a service wherein a large number of users submit their jobs and wait for their services. Thus, scheduling plays major role for providing the resources efficiently to the submitted jobs. The brainwave of the proposed work is to improve user satisfaction, to balance the load efficiently and to bolster the resource utilization. Hence, this paper proposes an Adaptive Multilevel Scheduling System (AMSS) which will process the jobs in a multileveled fashion. The first level contains Preprocessing Jobs with Multi-Criteria (PJMC) which will preprocess the jobs to elevate the user satisfaction and to mitigate the jobs violation. In the second level, a Deadline Based Dynamic Priority Scheduler (DBDPS) is proposed which will dynamically prioritize the jobs for evading starvation. At the third level, Contest Mapping Jobs with Virtual Machine (CMJVM) is proposed that will map the job to suitable Virtual Machine (VM). In the last level, VM Scheduler is introduced in the two-tier VM architecture that will efficiently schedule the jobs and increase the resource utilization. These contributions will mitigate job violations, avoid starvation, increase throughput and maximize resource utilization. Experimental results show that the performance of AMSS is better than other algorithms.

Fuzzy rule generation for adaptive scheduling in a dynamic manufacturing environment

This paper proposes a fuzzy rule-based system for an adaptive scheduling, which dynamically selects and applies the most suitable strategy according to the current state of the scheduling environment. The adaptive scheduling problem is generally considered as a classification task since the performance of the adaptive scheduling system depends on the effectiveness of the mapping knowledge between system states and the best rules for the states. A rule base for this mapping is built and evolved by the proposed fuzzy dynamic learning classifier based on the training data cumulated by a simulation method. Distributed fuzzy sets approach, which uses multiple fuzzy numbers simultaneously, is adopted to recognize the system states. The developed fuzzy rules may readily be interpreted, adopted and, when necessary, modified by human experts. An application of the proposed method to a job-dispatching problem in a hypothetical flexible manufacturing system (FMS) shows that the method can develop more effective and robust rules than the traditional job-dispatching rules and a neural network approach.

An adaptive scheduling system with genetic algorithms for arranging employee training programs

An outstanding human resources system is one of the important competitive factors in modern enterprises. Employee training is a frequently used method for promoting the working capabilities for better human resources. Employee training programs cultivate personnel capabilities for enterprise operation. The training effect can be dramatically enhanced if curriculum is well designed and arranged. However, arranging curriculum is a difficult and lengthy task which enterprises traditionally devote a large amount of human and material resources to. We improved the process by proposing an optimal curriculum arrangement model in maintenance personnel training programs, and utilizing genetic algorithms as solution procedures. An adaptive computer aided training system for maintenance representative training was also developed to facilitate personnel training for machine tool industry.

The adaptive layer-based scheduling system for embedded real-time transmission on scalable multimedia stream

With the recent development in compression and network technology, stream media has been adopted in internet and intranet. Application of stream media technology will play a key role in future development of fast networks. Original video/audio data will be stored in the devices for storage after having been pre-compressed by a video/audio compression algorithm. When clients have requirements, the stream server retrieves the video/audio data from the storage devices through the network. This paper discusses a simple and effective real-time scheduling algorithm, adaptive Layer-Based Least-Laxity-First (LB-LLF) scheduling algorithm, to improve the output quality of video/audio on a network and to achieve synchronised playback effect. The proposed algorithm considered real-time constraint, unequal priorities of scalable media stream in different layers, and a good tradeoff between coding efficiency and drifting error. This guarantees the effective usage of available channel bandwidth and the better quality of playback in client.

An enhanced knowledge representation for decision-tree based learning adaptive scheduling

The classical decision tree (DT) learning approach to constructing DT knowledge bases is usually not considered if there exist some irrelevant and redundant attributes in the problem domain. Since the essential attributes are uncertain in manufacturing systems, how to select important manufacturing attributes to improve the generalization ability of knowledge bases and avoid overfitting training data in DT-based learning is a crucial research issue for the adaptive scheduling problem domain. In this study, we will first develop an attribute selection algorithm based on the weights of artificial neural networks (ANNs) to identify the importance of system attributes. Next, we will use the C4.5 DT learning algorithm to learn the whole set of training examples with important attributes in order to enhance knowledge representation. This hybrid ANN/DT approach is called an attribute selection DT (ASDT) based learning adaptive scheduling system. The results from the case study show that the use of an attribute selection algorithm to build scheduling knowledge bases delivers better generalization ability than in the absence of the attribute selection procedure in terms of the size of DTs under various performance criteria. Consistent conclusions are drawn from the resulting prediction accuracy of unseen data. The resulting prediction accuracy of unseen data also reveals that scheduling knowledge bases by the proposed attribute selection approach to constructing DTs can avoid overfitting the training data compared with the classical DT learning approach.

Attribute Selection for Neural Network-Based Adaptive Scheduling Systems in Flexible Manufacturing Systems

System attribute selection is an integral part of adaptive scheduling systems. Owing to the existence of irrelevant and redundant attributes in manufacturing systems, by selecting the important attributes, better performance or accuracy in prediction can be expected in scheduling knowledge bases. In this study, we first propose an attribute selection algorithm based on the weights of neural networks to measure the importance of system attributes in a neural network-based adaptive scheduling (NNAS) system. Next, the NNAS system is combined with the attribute selection algorithm to build scheduling knowledge bases. This hybrid approach is called an attribute selection neural network-based adaptive scheduling (ASNNAS) system. The experimental results show that the proposed ASNNAS system works very well, when measured by a variety of performance criteria, as opposed to the traditional NNAS system and a single dispatching strategy. Furthermore, the scheduling knowledge bases in the ASNNAS system can provide a stronger generalisation ability compared with NNAS systems under various performance criteria.

Generating interpretable fuzzy rules for adaptive job dispatching

Adaptive scheduling is an approach that selects and applies the most suitable strategy considering the current state of the system. The performance of an adaptive scheduling system relies on the effectiveness of the mapping knowledge between system states and the best rules in the states. This study proposes a new fuzzy adaptive scheduling method and an automated knowledge acquisition method to acquire and continuously update the required knowledge. In this method, the criteria for scheduling priority are selected to correspond to the performance measures of interest. The decisions are made by rules that reflect those criteria with appropriate weights that are determined according to the system states. A situated rule base for this mapping is built by an automated knowledge acquisition method based on system simulation. Distributed fuzzy sets are used for evaluating the criteria and recognizing the system states. The combined method is distinctive in its similarity to the way human schedulers accumulate and adjust their expertise: qualitatively establishing meaningful criteria and quantitatively optimizing the use of them. As a result, the developed rules may readily be interpreted, adopted and, when necessary, modified by human experts. An application of the proposed method to a job-dispatching problem in a hypothetical flexible manufacturing system (FMS) shows that the method can develop effective and robust rules.

Fuzzy adaptive scheduling and control systems

In order to achieve the goal of fully automated manufacturing systems, novel techniques and tools in many aspects of manufacturing, including scheduling and control, need to be developed. These novel techniques can be recognised by their capabilities to adapt to complex situations, which conventional approaches have not as yet been able to handle properly. This paper proposes a new approach to provide a suitable framework for the design and development of adaptive scheduling and control systems, by incorporating concepts and techniques from fuzzy set theory, control theory, and optimisation theory. This is achieved by the mathematical modelling and simulation of a real-time fuzzy adaptive scheduling and control system for a fully automated manufacturing system.

群ロボットの作業分担のための適応スケジューリングシステムの開発

An adaptive multirobot scheduling system was studied in order to introduce intelligent robots in a plant and to maintain the plant effectively. Necessary information for the plat maintenance tasks was classified by character that are a variable and a fixed information. In order to assign maintenance tasks to the robots, the scheduling system uses the fixed information of own databases, and gathers the variable information from the robots and a human operator adaptively. From numerical experiments it has been confirmed that the adaptive scheduling system could perform its original idea of adjusting the scheduling of maintenance operation even when an accident occurred in the plant or when a robot was disabled.

Control-flow versus data-flow-based scheduling: combining both approaches in an adaptive scheduling system

As high-level synthesis techniques gain acceptance among designers, it is important to be able to provide a robust system which can handle large designs in short execution times, producing high-quality results. Scheduling is one of the most complex tasks in high-level synthesis, and although many algorithms exist for solving the scheduling problem, it remains a main source of inefficiency by either not producing high-quality results, not taking into account realistic design requirements, or requiring unacceptable execution times. One of the main problems in scheduling is the dichotomy between control and data. Many algorithms to date have been able to provide scheduling solutions by looking only at either the data part or the control part of the design. This has been done in order to simplify the problem; however, it has resulted in many algorithms unable to handle efficiently large designs with complex control and data functionality. This paper presents algorithms for combining dataflow and control-flow techniques into a robust scheduling system. The main characteristics of this system are as follows: 1) it uses path-based techniques for efficient handling of control and mutual exclusiveness (for resource sharing), 2) it allows operation reordering and parallelism extraction within the context of path-based scheduling, 3) it contains a control partitioning algorithm for design space exploration as well as for reducing the number of control paths, and 4) it combines the above algorithms into an adaptive scheduling system which is capable of trading optimality for execution time on-the-fly. Results involving billions of paths are presented and analyzed.