An increasing number of renewable energy-based distribution generation (DG) units are being deployed in electric distribution systems. Therefore, it is of paramount importance to optimize the installation locations as...
详细信息
As the most direct and key link to realize the supply and consumption of electric energy, distribution network is of great significance to ensure the safety, reliability and economy of power supply. However, the distr...
详细信息
Recently, the rapid development of 5G trusted communication technology has greatly contributed to economic and social progress, greatly improving production efficiency. However, the rapidly developing 5G communication...
详细信息
Recent deep learning relies on large-scale training of Deep Neural Networks (DNNs), which can be time-consuming and computationally intensive. To improve DNN training efficiency, GPU clusters have been used to perform...
详细信息
While novel power systems are developing in the direction of electrification and cleaning, there are many unstable factors in system. To alleviate the influence of random factors of external excitation on the stabilit...
详细信息
A totally asynchronous gradient algorithm, with fixed step size is proposedfor federated learning. A mathematical model is presented and a convergence result is established. The convergence result is based on the conc...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
A totally asynchronous gradient algorithm, with fixed step size is proposedfor federated learning. A mathematical model is presented and a convergence result is established. The convergence result is based on the concept of macro iterations sequence. The interest of the contribution is to show that the asynchronous federated learning method converges when gradients of loss functions are updated by workers without order nor synchronization and with possible unbounded delays.
In order to enhance the precision of ultra-short-term photovoltaic power prediction, this study introduces a novel approach grounded in a Bayes-two-Iayer XGBoost-LSTM network. The methodology commences by processing t...
详细信息
In this paper, we focus on the distributedparallel computation of tall-skinny QR factorization. Among various numerical algorithms, we evaluate the performance of four typical algorithms that have different character...
详细信息
As individuals have become overloaded with information, Recommender Systems (RS) were created to provide machine generated recommendations. Significant advancements in RS have been made thanks to Machine Learning meth...
详细信息
Scheduling problems are naturally formulated in terms of Constraint Programming (CP), yet the application of CP-based approaches for job scheduling on High-Performance computing (HPC) clusters remains underexplored. T...
详细信息
ISBN:
(纸本)9798400704437
Scheduling problems are naturally formulated in terms of Constraint Programming (CP), yet the application of CP-based approaches for job scheduling on High-Performance computing (HPC) clusters remains underexplored. This study aims to bridge this gap by analyzing the scheduling of diverse real workload traces using IBM ILOG CP Optimizer. The analysis considers not just the basic metrics Average Bounded Slowdown and Average Response Time, but also Area-Weighted Average Response Time and Level-2 Priority-Weighted Specific Time, which measure packing efficiency and fairness. For each workload trace and metric combination, schedules produced through optimizing the metric with CP Optimizer are compared against schedules generated by the variants of the list scheduling with backfilling that are most suitable for the metric. The CP-based scheduling improves scheduling quality in most of the examined cases. The analysis of the metrics that represent different scheduling goals uncovers several non-trivial insights. Presently, CP Optimizer still encounters scalability issues with large wait queues and non-linear objective functions. Nonetheless, it often demonstrates improvements in packing efficiency, which make CP techniques attractive, particularly in scenarios where high-maintenance clusters run a moderate number of large, rigid, well-characterized jobs.
暂无评论