Edge computing in space: Field programmable gate array-based solutions for spectral and probabilistic analysis of time series.

This paper addresses the problem of performing time series analysis on-board a spacecraft, where the number of constraints is much bigger than for applications running in regular (i.e., ground-based) environments. An objective of modern spacecraft technologies designed for space exploration is to perform on-board data processing tasks, in order to increase the amount of data available for scientific analysis. Field Programmable Gate Array (FPGA) devices are considered as good candidates for hardware implementations of such systems. In order to optimize the usage of on-board resources, FPGAs share their resources between several digital signal processing (DSP) algorithms. In this paper, we describe the design and implementation of such an optimized design where two DSP algorithms are implemented on the same FPGA: (1) the power spectral density and (2) the multiscale probability distribution functions. The entire implementation process is described in detail, including a discussion about the main architectural choices. The proposed solutions focus on optimization of area, speed, and power. The tests performed, on both synthetic and real data, demonstrate the feasibility of our approach and constitute the first step toward porting the design on space-grade FPGAs.

[1]  Christoph Hagleitner,et al.  An architecture for near-data processing systems , 2016, Conf. Computing Frontiers.

[2]  L. Burlaga.  Intermittent turbulence in the solar wind , 1991 .

[3]  Wang Qian,et al.  A new spectrum measurement trigging method and its implementation , 2013, 2013 International Conference on Computational Problem-Solving (ICCP).

[4]  Teruo Higashino,et al.  Edge-centric Computing: Vision and Challenges , 2015, CCRV.

[5]  Maciej Wielgosz,et al.  FPGA Implementaton of Strongly Parallel Histogram Equalization , 2007, 2007 IEEE Design and Diagnostics of Electronic Circuits and Systems.

[6]  Florent de Dinechin,et al.  Designing Custom Arithmetic Data Paths with FloPoCo , 2011, IEEE Design & Test of Computers.

[7]  C. R. Subrahmanya,et al.  High Performance Power Spectrum Analysis Using a FPGA Based Reconfigurable Computing Platform , 2006, 2006 IEEE International Conference on Reconfigurable Computing and FPGA's (ReConFig 2006).

[8]  Rainer Buchty,et al.  Data-Centric Computing Frontiers: A Survey On Processing-In-Memory , 2016, MEMSYS.

[9]  K. Mursula,et al.  Effect of data gaps: comparison of different spectral analysis methods , 2016 .

[10]  Lei Shu,et al.  Survey of Fog Computing: Fundamental, Network Applications, and Research Challenges , 2018, IEEE Communications Surveys & Tutorials.

[11]  D. Sornette.  Critical Phenomena in Natural Sciences: Chaos, Fractals, Selforganization and Disorder: Concepts and Tools , 2000 .

[12]  Franz Franchetti,et al.  Computer Generation of Hardware for Linear Digital Signal Processing Transforms , 2012, TODE.

[13]  P. Daly,et al.  Analysis methods for multi-spacecraft data , 1998 .

[14]  Stephan Wong,et al.  FPGA Implementation of Parallel Histogram Computation , 2022 .

[15]  H. Lamy,et al.  Multi-point observations of intermittency in the cusp regions , 2007 .

[16]  Guangwen Yang,et al.  A fully pipelined probability density function engine for Gaussian Copula model , 2014, Tsinghua Science and Technology.

[17]  Jing Wang,et al.  Edge-Oriented Computing Paradigms , 2018, ACM Comput. Surv..

[18]  Vladimir Vlassov,et al.  Identifying the potential of near data processing for apache spark , 2017, MEMSYS.

[19]  Suhaib A. Fahmy.  Histogram-based probability density function estimation on FPGAs , 2010, 2010 International Conference on Field-Programmable Technology.

[20]  R. Abiad,et al.  Instrument Data Processing Unit for THEMIS , 2008 .

[21]  J. Richardson,et al.  MHD turbulence in Saturn's magnetosheath downstream of a quasi‐parallel bow shock , 2000 .

[22]  Wolfgang Baumjohann,et al.  The Magnetospheric Multiscale Magnetometers , 2016 .

[23]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[24]  Valentin Stanciu,et al.  FPGA implementation for power spectral estimation using grouped B-Spline windows , 2014, 2014 11th International Symposium on Electronics and Telecommunications (ISETC).

[25]  Johannes Brendel,et al.  Model-based implementation for the calculation of Power Spectral Density in an FPGA system , 2013, 2013, 7th International Conference on Signal Processing and Communication Systems (ICSPCS).

[26]  Per-Arne Lindqvist,et al.  The Axial Double Probe and Fields Signal Processing for the MMS Mission , 2016 .

[27]  Luis Lino Ferreira,et al.  Probability Distribution Functions , 2007 .

[28]  Marius Echim,et al.  Edge computing for space applications: Field programmable gate array-based implementation of multiscale probability distribution functions. , 2018, The Review of scientific instruments.

[29]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[30]  Eckart Marsch,et al.  Non-Gaussian probability distributions of solar wind fluctuations , 1994 .