Purpose – Making decisions on production and maintenance separately, as is often done in practice and research literature, may not result in overall optimization. This paper aims to propose a joint method that better integrates production planning and maintenance at the tactical level. The potential of improving the performance of the classic planning method is also explored. Design/methodology/approach – An integrated production planning and maintenance model is proposed. The production capacity losses resulted from both preventive and corrective maintenance activities are considered. Meanwhile, the reliability deterioration of the machine is considered to be operation dependent. An iterative approach is presented to find a solution for the nonlinear model through iteratively solving a sequence of mixed integer linear programming instances, accompanied by modification of some parameters prior to each iteration. Computational experiments are conducted to evaluate the performance of the proposed method compared with three other methods, including two methods based on separate planning and one integrated model. Findings – The superiority of the proposed method compared with all the other three methods is demonstrated. Thus, the values of both integrated planning and considering operation-dependent failures are testified. The advantage of the proposed method is highlighted in the cases of high capacity utilization, long maintenance durations and low maintenance costs. The performance of the two methods based on separate planning is sensitive to the system utilization, and when utilization is high, the one with an availability-sensitive objective function defined for the maintenance problem performs better. Originality/value – Few studies have been carried out to integrate decisions on production lot and maintenance. Their considerations are either incomplete or not realistic enough. A more comprehensive and realistic integrated model is proposed in this paper, along with an iterative solution algorithm for it. A potential way to improve the performance of the classic planning method with its simplicity preserved is also presented.
The increasing computational complexity of DNNs achieved unprecedented successes in various areas such as machine vision and natural language processing (NLP), e.g., the recent advanced Transformer has billions of parameters. However, as large-scale DNNs significantly exceed GPU's physical memory limit, they cannot be trained by conventional methods such as data parallelism. Pipeline parallelism that partitions a large DNN into small subnets and trains them on different GPUs is a plausible solution. Unfortunately, the layer partitioning and memory management in existing pipeline parallel systems are fixed during training, making them easily impeded by out-of-memory errors and the GPU under-utilization. These drawbacks amplify when performing neural architecture search (NAS) such as the evolved Transformer, where different network architectures of Transformer needed to be trained repeatedly. VPIPE is the first system that transparently provides dynamic layer partitioning and memory management for pipeline parallelism. VPIPE has two unique contributions, including (1) an online algorithm for searching a near-optimal layer partitioning and memory management plan, and (2) a live layer migration protocol for re-balancing the layer distribution across a training pipeline. VPIPE improved the training throughput of two notable baselines (Pipedream and GPipe) by 61.4%-463.4% and 24.8%-291.3% on various large DNNs and training settings.
Resilience functionality, including failure resilience and flow migration, is of pivotal importance in practical network function virtualization (NFV) systems. However, existing failure recovery procedures incur high packet processing delay due to heavyweight process-checkpointing, while flow migration has poor performance due to centralized control. This paper proposes NFVactor, a novel NFV system that aims to provide lightweight failure resilience and high-performance flow migration. NFVactor enables these by using actor model to provide a per-flow execution environment, so that each flow can replicate and migrate itself with improved parallelism, while the efficiency of the actor model is guaranteed by a carefully designed runtime system. Moreover, NFVactor achieves transparent resilience: once a new NF is implemented for NFVactor, the NF automatically acquires resilience support. Our evaluation result shows that NFVactor achieves 10Gbps packet processing, flow migration completion time that is 144 times faster than existing system, and packet processing delay stablized at around 20 microseconds during replication.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.