Research on Storage and Computation Integrated Architecture Technologies of Power Distribution Network IoT Terminal

Wang, Hongyu; Wang, Zhong; Zhang, Song; Jin, Hui; Li, Wenqiang; Tao, Jun

doi:10.1109/ispec53008.2021.9735787

Cited by 5 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only calculate the power consumption generated by weight reading and moving, excluding the power consumption generated by computing. The power consumption of traditional NDC system includes reading weights from FLASH (5.86 uJ/KB [32]), reading and writing DRAM (435.9 mW [33]). According to the size of the weight data, the energy required can be calculated as 2.0076 mJ.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A novel NVM memory file system for edge intelligence

Chen

et al. 2022

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

Edge intelligence (EI), as a combination of artificial intelligence (AI) and internet of things (IoT), is the key to realize an interconnected world of everything. EI needs to process the data collected by edge devices locally. For edge devices with insufficient computing power, a near data computing (NDC) system can provide local computing capability by adding a co-processing unit near the memory. NDC systems are extensively studied focused on the optimization of the hardware architecture but lack of universal and transparent system support. Meanwhile, we notice that non-volatile memory (NVM) plays an important role in edge intermittent computing. In this article, we propose a novel in-memory processing file system (IMPFS) based on NVM to provide general support for NDC system running on edge devices. IMPFS uses standard file system interfaces and is optimized for NVM and AI application management. To verify the IMPFS, a prototype system is designed. The results showed that the IMPFS can not only provide universal support for EI but also further improve the processing speed by reducing the redundant software overhead.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…5 The mechanism of the NDC system with IMPFS. reading weights from PCM (5.72 uJ/KB [32]). It can be calculated that the energy consumed is 1.7147 mJ, which is 14.6% lower than the original.…”

Section: Experiments and Resultsmentioning

confidence: 99%

A novel NVM memory file system for edge intelligence

Chen

et al. 2022

IEICE Electron. Express

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the deepening of the application of the IoT [5][6][7][8][9][10][11][12][13][14][15][16][17], we can see that: (1) More and more IoT applications have different levels of real-time requirements. Only relying on cloud platforms deployed in the service provision domain to provide data processing and information services will greatly increase the technical difficulty of optimizing the service performance of such IoT application systems.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, it is required that the constituent entities of the service provision domain have a certain degree of positional characteristics, which requires the service provision domain to consider the end characteristics. At the same time, the communication and computing processing capabilities of various IoT application systems are becoming stronger, and they have already possessed certain data storage capabilities [12,13]. If corresponding software function development and configuration are not carried out, these hardware capabilities will not be fully utilized, resulting in overall hardware resource waste in IoT application systems.…”

Section: Introductionmentioning

confidence: 99%

“…Part of the research on the architecture of IoT terminal systems focuses on specific software and hardware technologies and industry applications. Flamand et al [12] and Wang et al [13] conducted in-depth research on the integrated architecture technology of IoT terminal storage and computing based on phase change memory (PCRAM) technology. They analyzed its low power consumption and high energy efficiency application advantages and the technical characteristics of IoT terminal operating system storage and computing interface expansion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

IoT Terminal Architecture Model

Zhao,

Mao,

Liu

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The physical Information mapping relationship and function in the sense and control domain is described using entities such as gateway, sense, and control device in the existing IoT reference architecture. However, due to the lack of research on the IoT terminal architecture, there have been difficulties in the research and application of IoT terminal technologies. Starting from the trend analysis of application development of IoT systems, this article proposes an IoT terminal architecture reference model IoT TARM that integrates gateway and sense and control device functions. It analyses the architecture and functional characteristic enhancement acting on the IoT systems due to the IoT TARM. It summarizes the low-power, reconfigurable, lightweight, and platform characteristics of IoT TARM and expounds on the relationship between IoT TARM and the existing IoT architecture.

show abstract