Distribution system fault location is a crucial factor to ensure the reliability and self-healing of power supplies. Aiming at the problems of poor location accuracy and low efficiency of the existing fault zone locat...
详细信息
In modern HPC systems with deep hierarchical architectures, large-scale applications often struggle to efficiently utilize the abundant cores due to the saturation of resources such as memory. Co-allocating multiple a...
详细信息
ISBN:
(纸本)9783031488023;9783031488030
In modern HPC systems with deep hierarchical architectures, large-scale applications often struggle to efficiently utilize the abundant cores due to the saturation of resources such as memory. Co-allocating multiple applications to share compute nodes can mitigate these issues and increase system throughput. However, co-allocation may harm the performance of individual applications due to resource contention. Past research suggests that topology-aware mappings can improve the performance of parallel applications that do not share resources. In this work, we implement application-oblivious, topology-aware process-to-core mappings via different core enumerations that support the co-allocation of parallel applications. We show that these mappings have a significant impact on the available memory bandwidth. We explore how these process-to-core mappings can affect the individual application duration as well as the makespan of job schedules when they are combined with co-allocation. Our main objective is to assess whether co-allocation with a topology-aware mapping can be a viable alternative to the exclusive node allocation policies that are currently common in HPC clusters.
The rapid integration of distributed renewable energy sources and the diversification of loads have precipitated profound changes in the configuration and operation of power distribution networks in the 21st century, ...
详细信息
distributed locks are used to guarantee the distributed client-cache coherence in parallel file systems. However, they lead to poor performance in the case of parallel writes under high-contention workloads. We analyz...
详细信息
ISBN:
(纸本)9781665454445
distributed locks are used to guarantee the distributed client-cache coherence in parallel file systems. However, they lead to poor performance in the case of parallel writes under high-contention workloads. We analyze the distributed lock manager and find out that lock conflict resolution is the root cause of the poor performance, which involves frequent lock revocations and slow data flushing from client caches to data servers. We design a distributed lock manager named SeqDLM by exploiting the sequencer mechanism. SeqDLM mitigates the lock conflict resolution overhead using early grant and early revocation while keeping the same semantics as traditional distributed locks. To evaluate SeqDLM, we have implemented a parallel file system called ccPFS using both SeqDLM and traditional distributed locks. Evaluations on 96 nodes show SeqDLM outperforms the traditional distributed locks by up to 10.3x for high-contention parallel writes on a shared file with multiple stripes.
This paper deals with hash based secure chaotic steganography technique for hiding secret information, into the cover image. Hash function has been used in the proposed work for computing the Non LSB positions for hid...
详细信息
To maintain dependable and effective operation, especially in islanded microgrid situations, integrating distributed Generation (DG) units and renewable energy sources into electrical grids has required sophisticated ...
详细信息
The equivalent modeling problem of active distribution networks (ADN) has been one of the hot issues in power system-related research. When more and more distributed energy sources are connected to the grid, such prob...
详细信息
The accurate measurement methods for carbon emissions are critical in both incentivizing consumers towards energy conservation and emission reduction, as well as ensuring fairness in carbon emissions trading. The indi...
详细信息
The accurate measurement methods for carbon emissions are critical in both incentivizing consumers towards energy conservation and emission reduction, as well as ensuring fairness in carbon emissions trading. The indirect carbon emissions are generated from user's electricity consumption. The existing indirect carbon emission calculation method assumes that the carbon emissions per unit of electricity are the same at any nodes and any time in the power grid. Carbon flow calculation method could bridge this gap, however, it still need improvement when applying to large power grid. This paper proposed a practical indirect carbon emission calculation method by parallelcomputing the divided power grid, thereby significantly reducing the computational pressure. Furthermore, an effective Thevenin equivalent fitting technique is adopted to lessen the computational complexity in the transmission network. By clustering typical scenarios, the annual equivalent carbon emission intensity can be calculated for any node in the power grid. These calculated carbon emission factor can serve as substitutions for the traditional carbon emission factors. The case study proves this method for carbon emission calculation manages to strike a balance between computational complexity and acknowledging the spatio-temporal characteristics in carbon emissions.
Conventional cloud resource computing power allocation methods mainly focus on cloud resource scheduling, and the effect of computing power balanced allocation is poor. Therefore, a cloud resource computing power allo...
详细信息
This paper proposes a real-time power line loss detection technology based on information engineering drive, firstly, through the algorithmic process of real-time power line loss detection, the real-time detection met...
详细信息
暂无评论