The Embedded IoT Time Series Database for Hybrid Solid-State Storage System
نویسندگان
چکیده
IoT time series data is an important form of big data. How to improve the efficiency storage system crucial for database store and manage massive from various devices. Mixing NVM SSD effective method I/O performance systems. However, there are great differences between HDD or SSD. As a result, cannot be directly used in current effectively. We design with embedded engine device drivers hybrid solid-state consisting The software stack storing managing can shortened efficiency. Based upon intrinsic characteristics different features SSD, redundancy elimination compression fusion strategy, hierarchical management heterogeneous index designed Finally, prototype named TS-NSM implemented, YCSB-TS measure IOPS. results show that write IOPS up 243.6 times 174.3 times, respectively, compared InfluxDB OpenTSDB, read 10.1 14.4 respectively.
منابع مشابه
a time-series analysis of the demand for life insurance in iran
با توجه به تجزیه و تحلیل داده ها ما دریافتیم که سطح درامد و تعداد نمایندگیها باتقاضای بیمه عمر رابطه مستقیم دارند و نرخ بهره و بار تکفل با تقاضای بیمه عمر رابطه عکس دارند
SolID STATE DrIVE ApplIcATIonS In STorAgE AnD EmbEDDED SySTEmS
Intel® X25-E and X25-M SATA Solid-State Drives have been designed to provide high performance and capacity density for use in applications which were limited by traditional hard disk drives (HDD), input/output (I/O) performance bottlenecks, or performance density (as defined by bandwidth and I/Os/sec per gigabyte, per Rack Unit (RU), per Watt required to power, and per thermal unit waste heat. ...
متن کاملHybrid Swarm System for Time Series Forecasting
In this paper, a hybrid swarm system is presented for time series forecasting. It consists of an intelligent hybrid model composed of an Arti cial Neural Network (ANN) and a Particle Swarm Optimizer (PSO), which search the relevant time lags for a correct characterization of the time series, as well as the number of processing units in the hidden layer, the training algorithm and the modeling o...
متن کاملHybrid Storage Systems : Solid - State Memory with Magnetic Disks
My research interests are in the modeling, design, and evaluation of software critical for the performance, reliability, power-efficiency, and management of computer systems. I have studied these problems in a wide range of systems ranging from individual desktops and servers to distributed systems such as data centers and the Web. At Penn State, my research has concentrated on the management o...
متن کاملClustering Solid Models for Database Storage
Computer-Aided Design (CAD) data and Solid Models are important tools in almost all the engineering disciplines, with an estimated 30 billion CAD models in the world; however, there are few good methods to manage the growing set of models. CAD data, and the consumers of CAD data, have different requirements from traditional database media such as images, sounds, and videos. Solid models are lar...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Scientific Programming
سال: 2021
ISSN: ['1058-9244', '1875-919X']
DOI: https://doi.org/10.1155/2021/9948533