WHITE PAPER
Enabling big data processing and AI-powered everything, everywhere
mrcy.com 2 mrcy.com 2
TAKING BIG DATA PROCESSING TO THE EDGE
"Business plans for the next 10,000 private sector startups
are easy to forecast: Take X and add artificial intelligence,"
said Carnegie Mellon University 's Rita Singh talking to
Signal Magazine in the fall of 2018. Ms. Singh was illustrating
that artificial intelligence (AI) and big data processing
applications are everywhere, affecting us all, and will
continue to do so. Big data processing is increasingly being
deployed in edge applications for autonomy, quick reaction
capability and untethered cognitive functionality remote
from fixed resources. Nowhere is this more pronounced
than in the rapidly emerging autonomous platform.
Machine-enabled unmanned aerial vehicle (UAV) vision
As platforms (aircraft and vehicles) become smarter and
more capable, greater on-board AI and big data processing
is required to handle the torrents of sensor data needed for
autonomous decision-making and effector control. Effectors
are the highly deterministic and reliable vetronics, avionics
and other safety- and mission-critical functions required for
platform control and mission success. As the number of smart
platforms grows, so does the need for a greatly expanded,
distributed fog layer with big data processing capability
that safely and efficiently manages the increased traffic.
EMBEDDING THE DATA CENTER IN THE APPLICATION
Big data processing is still largely confined to static
data centers running performance/cost-optimized
servers powered with the latest, AI-accelerated
processors. These server arrays are supported with
abundant storage, fast broadband switching and massive
coprocessing (GPGPU, ASIC and FPGA) resources.
Big data and AI processing across the cloud and edge
layers from an aerospace and defense perspective
To scale the data center across smarter fog and edge layers
requires the composing servers to become smaller and
resilient to harsh environments and human attempts to tamper
with them. Distributed deployment requires servers to be:
Miniaturized, while remaining well cooled
Protected from hostile environments and conditions
Secure and resilient to reverse engineering,
tampering and cyber threats
Trusted across hardware, software, middleware
and other intellectual property
Deterministic for mission- and safety-critical effector control
Supported with a long service life
Scalable, interoperable and refreshable
across cloud, fog and edge layers
Affordable by leveraging commercial IP,
IRAD and manufacturing capabilities
This paper introduces the technologies developed by Mercury Systems and Intel that
enable commercially-developed data center processing capabilities to migrate across fog
and edge layers. Required for smart, autonomous edge applications and their supportive
fog infrastructures, decentralized processing resources are enabling big data processing
and AI-powered everything, everywhere.
TACTICAL EDGE COMPUTING
ON-PLATFORM
DATA CENTER
PROCESSING CAPABILITY
AT THE TACTICAL EDGE
PROCESS DATA TRANSMIT DATA RECEIVE DATA
SENSE DATA
SENSE DATA
ACQUIRE DATA
PROCESS DATA
ON BOARD
CLOUD COMPUTING