Protecting Critical Infrastructure Using Network Edge AI Platform

This blog post was originally published at Lanner Electronics’ website. It is reprinted here with the permission of Lanner Electronics.

Background

Forest fires may have a variety of origins and causes but early detection and warning methods used to limit the extent of their damage are largely the same. Now, cutting-edge AI technology is enabling more rapid detection to facilitate greater advance warning.

One application of this is the physical protection of critical infrastructure, particularly for electrical power distribution. In addition, such AI technology also facilitates protection from cyber attacks. This type of system also enables the implementation of an Advanced Forest Fire Detection System for Public Safety Power Shutoff. Where conditions create a high risk of wildfire, control systems can initiate a temporary shutdown of power transmission to prevent transmission cables from becoming a source of ignition.

Requirements

An Edge AI innovator in the U.S. approached Lanner seeking to establish cooperation by using their AI-enhanced software to work seamlessly with Lanner’s network edge servers. This joint solution met the following requirements:

  • AI accelerated Network Appliance – The AI Edge Server is an NGC-Ready and hyper-converged appliance with dual Nvidia T4 GPU accelerated video computational engines providing enhanced performance for video analytics.
  • Two full-size PCIe slots for AI expansion and computation offloading for video analytics.
  • Dual 2nd Generation Scalable Xeon (Cascade Lake) CPU sockets for virtualization computing.
  • Edge Server with twelve 3.5” NVMe high-performance SSD storage connectors and two 2.5” SATA 6Gb/s at the rear.
  • Extensive network I/O connectivity – four 10G SFP, and six GbE RJ-45 with Intelligent Platform Management Interface (IPMI).

Solution

The Edge uCPE connects high-precision sensors and cameras, leveraging the advantage of Artificial Intelligence in smoke detection using video analytics to monitor forests and provide alerts of suspicious events to wildfire control centers.

The FX-3420 offers security, high-performance, and high storage density in just a 2RU form factor for next-generation Lanner HCI appliances. It can support up to 768GB of memory using multiple DDR4 2,666 MHz REG DIMM modules and has twelve 3.5” SATA hot-swappable disk drive bays. The FX-3420 is an optimal choice for Edge AI platforms and VDI servers where performance and storage are critical.

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top