Scheduling Architecture Research Articles

A multi-agent architecture for scheduling in platform-based smart manufacturing systems

During the past years, a number of smart manufacturing concepts have been proposed, such as cloud manufacturing, Industry 4.0, and Industrial Internet. One of their common aims is to optimize the collaborative resource configuration across enterprises by establishing platforms that aggregate distributed resources. In all of these concepts, a complete manufacturing system consists of distributed physical manufacturing systems and a platform containing the virtual manufacturing systems mapped from the physical ones. We call such manufacturing systems platform-based smart manufacturing systems (PSMSs). A PSMS can therefore be regarded as a huge cyber-physical system with the cyber part being the platform and the physical part being the corresponding physical manufacturing system. A significant issue for a PSMS is how to optimally schedule the aggregated resources. Multi-agent technology provides an effective approach for solving this issue. In this paper we propose a multi-agent architecture for scheduling in PSMSs, which consists of a platform-level scheduling multi-agent system (MAS) and an enterprise-level scheduling MAS. Procedures, characteristics, and requirements of scheduling in PSMSs are presented. A model for scheduling in a PSMS based on the architecture is proposed. A case study is conducted to demonstrate the effectiveness of the proposed architecture and model.

A novel four-tier architecture for delay aware scheduling and load balancing in fog environment

Fog computing paradigm is located between IoT devices and cloud paradigm that aim is to minimize the latency in terms of task scheduling and load balancing. To deal with the huge amount of data sensing from different IoT devices, in this paper we propose a four tiers architecture for delay aware scheduling and Load Balancing in the fog environment. Tier-1 is the bottom tier which consists of IoT devices. In the second tier, the applications (workloads) are categorized into two categories: High Priority (HP) and Low Priority (LP) by router based on the Dual Fuzzy Logic Algorithm. Fuzzifier considers four input metrics: task size, arrival time, minimum execution time and maximum completion time. A task with high priority is transmitted to the third tier (fog tier). In the third tier, a novel fog structure has been invoked namely Artificial Fractals consists of nodes. The fog nodes are clustered using K-means++ clustering algorithm. Each fog node is carried out several actions such as scheduling, monitoring, and communication. To schedule tasks within the fog node, we propose the Earliest Deadline First (EDF) task scheduling algorithm. The current usage of fog node is determined by Artificial Neural Network (ANN). If an IoT device does not get the required resource then the request is forwarded to the cloud tier. Our proposed work has been validated over a real-time VSOT (Video Surveillance/Object Tracking) application using iFogSim and the performance is evaluated in terms of response time, scheduling time, load balancing rate, delay, and energy consumption.

Control Aware Radio Resource Allocation in Low Latency Wireless Control Systems

We consider the problem of allocating radio resources over wireless communication links to control a series of independent wireless control systems. Low-latency transmissions are necessary in enabling time-sensitive control systems with high sampling rates to operate over wireless links. Enabling low-latency through fast data rates comes at the cost of reliability in the form of higher packet error rates due to channel noise. However, the impact of such communication link errors on the control system performance depends dynamically on the control system state. We propose a novel control-aware communication design to the low-latency resource allocation problem. In our proposed method, we incorporate both control and channel state information in scheduling transmissions across time slots, frequency bands, and data rates using the next-generation Wi-Fi scheduling architecture. Control systems that are closer to instability or further from a desired range in a given control cycle are given higher packet delivery rate targets to meet. Rather than a simple priority ranking, we derive precise adaptive packet error rate targets for each system needed to satisfy control-specific performance requirements. We use these adaptive rate targets to make scheduling decisions that reduce total transmission time. The resulting control-aware low-latency scheduling (CALLS) method is tested in numerous simulation experiments that demonstrate its effectiveness in meeting control-based goals under tight latency constraints relative to control-agnostic scheduling.

A Decentralized Energy Trading Framework for Active Distribution Networks with Multiple-Microgrids under Uncertainty

The ever-increasing need for more reliable power supply, cost-effective and environmental-friendly utilization of distributed energy resources will result in formation of multiple microgrids (MMGs) in the near future of distribution system. To achieve this prospective, a coordination among MMGs is necessary. Accordingly, this paper proposes a new non-hierarchical multilevel architecture for the optimal scheduling of active distribution network (ADN) with MMGs. The proposed model is a decentralized decision making algorithm to optimally coordinate the mutual interaction between local optimization problems of ADN and MMGs. A non-hierarchical analytical target cascading (ATC) method is presented to solve the local optimization problems in parallel. Also, underlying risks of the energy trading caused by renewable generation uncertainty are reflected in both the objective functions and the constraints of local optimization problem. The numerical results on modified IEEE 33-bus distribution test system containing two microgrids demonstrate the effectiveness and merits of proposed model.

Radio Resource Scheduling for Narrowband Internet of Things Systems: A Performance Study

In the context of the IoT, mMTC technology in 5G enables a range of new applications. The 3GPP NB-IoT introduced in Release 13 is a major enhancement toward mMTC to support devices requiring low data rate, low cost, and long battery life. Previous works suggested that NB-IoT physical channel characteristics have potential to fulfill design requirements. From the system point of view, the interaction among UEs and application data transmission procedures have to be further evaluated considering radio resource scheduling. In this article, we identify radio resource scheduling issues for NB-IoT systems and provide a comprehensive performance evaluation. We consider control plane optimization procedures with a massive number of UEs in mixed CE levels. Using a scheduling architecture verified with derived effective data rates, we show the effects of essential parameters on control channel allocation and data scheduling. Given our scheduling settings in anchor carriers, the number of transmitted data packets achieves about 65,000 per cell per hour with mixed CE levels. The results satisfy the design goal of NB-IoT data transmission in 3GPP TR 45.820.

A data-driven scheduling approach to smart manufacturing

Abstract Traditional methods of scheduling are mostly based on the use of pieces of information directly related to the performance of schedules, as for instance processing times, delivery dates, etc., assuming that the production system is operating normally. In the case of malfunctions, the literature concentrates on the ensuing corrective operations, like scheduling with machine breakdowns or under remanufacturing considerations. These event-driven approaches are mainly used in dynamic scheduling or rescheduling systems. Unlike those, Smart Manufacturing and Industry 4.0 production environments integrate the physical and decision-making aspects of manufacturing processes in order to achieve their decentralization and autonomy. On these grounds we propose a data-driven architecture for scheduling, in which the system has real time access to data. Then, scheduling decisions can be made ahead of time, on the basis of more information. This promising approach is based on the architecture of cyber-physical systems, with a data-driven engine that uses, in particular, Big Data techniques to extract vital information for Industry 4.0 systems.

GLSCH: PROGRAMADOR DE OBSERVACIONES PARA LA RED DE TELESCOPIO DE GLORIA

This paper proposes the design and development of a scheduler for the GLORIA telescope network. This network, which main objective is to make astronomy closer to citizens in general, is formed by 18 telescopes spread over four continents and both hemispheres. Part of the management of this network is made by the network scheduler. It receives the observation requests made by the GLORIA users and then sends it to the most suitable telescope. A key module of the network scheduler is the telescope decision algorithm that makes possible to choose the best telescope, and thus avoiding offering an observation to a telescope that cannot execute it. This paper shows two different telescope decision algorithms: the first one is only based on weather forecast, meanwhile the second one uses fuzzy logic and information from each network telescope. Both algorithms were deployed in the GLORIA network. The achieved results coupled with a comparative of their performance is shown. Moreover, the network scheduler architecture, based on a hybrid distributed-centralized schema, is detailed.

Computational grid scheduling architecture using MapReduce model-based non-dominated sorting genetic algorithm

Computational grid (CG) environment has a group of autonomous dissimilar distributed computing systems to provide service to user tasks. To attain the auspicious usefulness of CG resources, basically best scheduling algorithms are important. The CG service users are very cautious in time needed for task completion. To meet multiple requirements of the user, the job allocation problem in CG is designed as a multi-objective problem. Evolutionary algorithms have an efficient meta-heuristic technique for optimization problem solving. This work introduces a MapReduce model for non-dominated sorting genetic algorithm (NSGA-II) for independent job scheduling in a CG. This research work attempts to find the optimal schedules by considering makespan and flowtime minimization. A fuzzy membership function is used to analyze the efficiency of the schedule. Set of benchmark instances is used to test the algorithm. Experimental results show that MapReduce model-based NSGA-II generated finer solutions in less time than the MapReduce model-based weighted sum multi-objective genetic algorithm (WMOGA) which is also implemented in this paper.

Dynamic Scheduling of Real-Time Tasks in Heterogeneous Multicore Systems

The shift from homogeneous multicore to heterogeneous multicore introduces challenges in scheduling the tasks to the appropriate cores maintaining the time deadline. This letter studies the existing scheduling schemes in a heterogeneous multicore system and finds an approach to enhance the homogeneous system model to heterogeneous scheduling architecture. The proposed model increases the overall system utilization by accommodating almost all the tasks (low power task and high power task) into appropriate cores (big high power and small low power). It further enhances the system performance by allocating rejected jobs from small cores into the big cores through a dispatcher.

Electricity scheduling optimisation based on energy cloud for residential microgrids

Nowadays with the development of smart residential microgrid (RMG), the distributed energy storage system (DESS) can help consumers to not only balance generation and consumption but also participate in demand respond. However, the unadjustable capacity of DESS and the lack of energy sharing among users have become the major challenges to the further development of RMG. This paper proposes a novel electricity scheduling architecture based on energy cloud (EC) for RMGs and designs an electricity scheduling optimisation. The EC is used in order to link different end-users and promote coordination. In the proposed EC-based electricity scheduling architecture, the mathematical model for the RMG is provided. Moreover, considering the depreciation cost of battery, the optimisation model is established with the objective of minimising the electricity cost. Compared with the traditional RMG, simulation results show that the proposed strategy can not only allow consumers to adjust their optimal energy storage capacity but also further reduce electricity payment costs. The designed strategy provides a new and effective research perspective for electricity scheduling of RMGs.

Hierarchically distributed peer-to-peer architecture for load balancing and effective dynamic group scheduling in grid computing

The local or remote grid computing resources have been normally assigned the task of executing user jobs in a distributed environment. An important factor affecting grid processing is the network bandwidth that differs from network to network. In order to overcome this problem, a few typical algorithms are suggested keeping in view of computing grid resources based on load balancing across the grid system. These algorithms help in improving the performance to some extent, yet none of them has been found experimentally suitable to overcome the major short falls experienced in the grid computing system. A hierarchically distributed peer-to-peer (HDP2P) architecture is proposed to overcome all major problems encountered due to virtuality and heterogeneity. Results suggested that HDP2P architecture was of great use in balancing the load and allocating to the resources to the groups of jobs keeping MIPS accountability using grouping-based dynamic job scheduling algorithm (GBDJS). The proposed algorithm is compared with first come first served (FCFS) job scheduling algorithm and ant colony optimisation (ACO). There is a considerable improvement achieved in performance by using this novel architecture.

Hierarchically distributed Peer-to-Peer architecture for load balancing and effective dynamic group scheduling in Grid computing

The local or remote grid computing resources have been normally assigned the task of executing user jobs in a distributed environment. An important factor affecting grid processing is the network bandwidth that differs from network to network. In order to overcome this problem, a few typical algorithms are suggested keeping in view of computing grid resources based on load balancing across the grid system. These algorithms help in improving the performance to some extent, yet none of them has been found experimentally suitable to overcome the major short falls experienced in the grid computing system. A hierarchically distributed peer-to-peer (HDP2P) architecture is proposed to overcome all major problems encountered due to virtuality and heterogeneity. Results suggested that HDP2P architecture was of great use in balancing the load and allocating to the resources to the groups of jobs keeping MIPS accountability using grouping-based dynamic job scheduling algorithm (GBDJS). The proposed algorithm is compared with first come first served (FCFS) job scheduling algorithm and ant colony optimisation (ACO). There is a considerable improvement achieved in performance by using this novel architecture.

Limited Feedback Designs for Machine-Type Communications Exploiting User Cooperation

Multiuser multiple-input-multiple-output (MIMO) systems are a prime candidate for use in massive connection density in machine-type communication (MTC) networks. One of the key challenges of the MTC networks is to obtain accurate channel state information (CSI) at the access point (AP) so that the spectral efficiency can be improved by enabling the enhanced MIMO techniques. However, current communication mechanisms relying upon the frequency-division duplexing (FDD) might not fully support an enormous number of devices due to the rate-constrained limited feedback and the time-consuming scheduling architectures. In this paper, we propose a user cooperation-based limited feedback strategy to support high connection density in massive MTC networks. In the proposed algorithm, two close-in users share the quantized version of channel information in order to improve channel feedback accuracy. The cooperation process is performed without any transmitter interventions (i.e., in a grant-free manner) to satisfy the low-latency requirement that is vital for the MTC services. Moreover, based on the sum-rate throughput analysis, we develop an adaptive cooperation algorithm with a view to activating/deactivating the user cooperation mode according to channel and network conditions.

Multiagent and Bargaining-Game-Based Real-Time Scheduling for Internet of Things-Enabled Flexible Job Shop

With the rapid advancement and widespread applications of information technology in the manufacturing shop floor, a huge amount of real-time data is generated, providing a good opportunity to effectively respond to unpredictable exceptions so that the productivity can be improved. Thus, how to schedule the manufacturing shop floor for achieving such a goal is very challenging. This paper addresses this issue and a new multiagent-based real-time scheduling architecture is proposed for an Internet of Things-enabled flexible job shop. Differing from traditional dynamic scheduling strategies, the proposed strategy optimally assigns tasks to machines according to their real-time status. A bargaining-game-based negotiation mechanism is developed to coordinate the agents so that the problem can be efficiently solved. To demonstrate the feasibility and effectiveness of the proposed architecture and scheduling method, a proof-of-concept prototype system is implemented with Java agent development framework platform. A case study is used to test the performance and effectiveness of the proposed method. Through simulation and comparison, it is shown that the proposed method outperforms the traditional dynamic scheduling strategies in terms of makespan, critical machine workload, and total energy consumption.

Application-aware deadline constraint job scheduling mechanism on large-scale computational grid.

Recently, computational Grids have proven to be a good solution for processing large-scale, computation intensive problems. However, the heterogeneity, dynamics of resources and diversity of applications requirements have always been important factors affecting their performance. In response to these challenges, this work first builds a Grid job scheduling architecture that can dynamically monitor Grid computing center resources and make corresponding scheduling decisions. Second, a Grid job model is proposed to describe the application requirements. Third, this paper studies the characteristics of commercial interconnection networks used in Grids and forecast job transmission time. Fourth, this paper proposes an application-aware job scheduling mechanism (AJSM) that includes periodic scheduling flow and a heuristic application-aware deadline constraint job scheduling algorithm. The rigorous performance evaluation results clearly demonstrate that the proposed application-aware job scheduling mechanism can successful schedule more Grid jobs than the existing algorithms. For successful scheduled jobs, our proposed AJSM method is the best algorithm for job average processing time and makespan.

Cost-efficient reactive scheduling for real-time workflows in clouds

Workflow comprising of many tasks and data dependencies among tasks is an attractive programming paradigm for processing big data in clouds, and workflow scheduling plays essential roles in improving the cost and resource efficiency for cloud platforms. Up to now, large numbers of scheduling approaches have been proposed and improved. However, the majority of them focused on scheduling a single workflow and have not adequately exploited the idle time slots on resources to reduce the cost for executing workflow applications. To cover the above issue, we suggest to schedule tasks from different workflows in a hybrid way to take full advantage of idle time slots to improve the cost and resource efficiency, while guaranteeing the deadlines of workflows. To achieve the above idea, we first introduce a reactive scheduling architecture for real-time workflows. Then, a novel cost-efficient reactive scheduling algorithm (CERSA) is proposed to deploy multiple workflows with deadlines to cloud platforms. Finally, on the basis of real-world workflow traces, extensive experiments are conducted to compare CERSA with five existing algorithms. The experimental results demonstrate that CERSA is better than those algorithms with respect to monetary cost and resource efficiency.

Client-side straggler-aware I/O scheduler for object-based parallel file systems

Abstract Object-based parallel file systems have emerged as promising storage solutions for high-performance computing (HPC) systems. Despite the fact that object storage provides a flexible interface, scheduling highly concurrent I/O requests that access a large number of objects still remains as a challenging problem, especially in the case when stragglers (storage servers that are significantly slower than others) exist in the system. An efficient I/O scheduler needs to avoid possible stragglers to achieve low latency and high throughput. In this paper, we introduce a log-assisted straggler-aware I/O scheduling to mitigate the impact of storage server stragglers. The contribution of this study is threefold. First, we introduce a client-side, log-assisted, straggler-aware I/O scheduler architecture to tackle the storage straggler issue in HPC systems. Second, we present three scheduling algorithms that can make efficient decision for scheduling I/Os while avoiding stragglers based on such an architecture. Third, we evaluate the proposed I/O scheduler using simulations, and the simulation results have confirmed the promise of the newly introduced straggler-aware I/O scheduler.

Microservices Scheduling Model Over Heterogeneous Cloud-Edge Environments As Support for IoT Applications

Motivated by the high-interest in increasing the utilization of nongeneral purpose devices in reaching computational objectives with a reduced cost, we propose a new model for scheduling microservices over heterogeneous cloud-edge environments. Our model uses a particular mathematical formulation for describing an architecture that includes heterogeneous machines that can handle different microservices. Since any new model asks for an early risk-analysis of the solution, we improved the CloudSim simulation framework to be suitable for an experiment that includes that kind of systems. In this paper, we discuss two examples of real-life utilizations of our proposed scheduling architecture. For an objective appreciation of the first example, we also include some experimental results based on the developed simulation tool. As a result of our interpretation of the experimental results we find out that some very simple scheduling algorithms may outperform some others in given situations that are frequently present in cloud-edge environments when we are using a microservice-oriented approach.

An agent-based architecture for production scheduling in dynamic job-shop manufacturing system

Abstract In a highly competitive environment, effective production is one of the key issues which can be addressed by efficient production planning and scheduling in the manufacturing system. This paper develops an agent-based architecture which enables integration of production planning and scheduling. In addition, this architecture will facilitate real time production scheduling as well as provide a multi-agent system (MAS) platform on which multiple agents will interact to each other. A case study of job-shop manufacturing system (JMS) has been considered in this paper for implementing the concept of MAS. The modeling of JMS has been created in SimEvents which integrates an agent-based architecture developed by Stateflow to transform into dynamic JMS. Finally, the agent-based architecture is evaluated using utilization of each machine in the shop floor with respect to time.

Optimal active power dispatching of microgrid and distribution network based on model predictive control

First, a three-tier coordinated scheduling system consisting of a distribution network dispatch layer, a microgrid centralized control layer, and local control layer in the energy internet is proposed. The multi-time scale optimal scheduling of the microgrid based on Model Predictive Control (MPC) is then studied, and the optimized genetic algorithm and the microgrid multi-time rolling optimization strategy are used to optimize the datahead scheduling phase and the intra-day optimization phase. Next, based on the three-tier coordinated scheduling architecture, the operation loss model of the distribution network is solved using the improved branch current forward-generation method and the genetic algorithm. The optimal scheduling of the distribution network layer is then completed. Finally, the simulation examples are used to compare and verify the validity of the method.