skip to main content

Deploying AI at the Edge with Lenovo ThinkEdge Series Servers

Solution Brief

Home
Top
Published
27 Jun 2024
Form Number
LP1981
PDF size
6 pages, 266 KB

Edge computing challenge and a solution

The benefits of AI In today's business environment are becoming more obvious as companies strive to take advantage of the new technology. Although typically most of the AI processing tends to occur in the data center, there are many opportunities at edge or remote locations where the data is created or collected. The Lenovo ThinkEdge series provides an ideal combination of compact size with abundant storage and powerful processing. Placing ThinkEdge servers at remote locations can help offload the AI data and processing demands on the datacenter.

The ThinkEdge series servers are ideal for deployment in tight spaces. Depending on the model, they can be mounted on a wall, or ceiling, placed on a desk or mounted in a rack. These edge servers place increased processing power, storage, and network closer to where data is generated, allowing actions resulting from the analysis of that data to take place more quickly. The ThinkEdge servers are designed to handle a wide range of workloads, such as: Augmented Reality, CDN, Edge AI & MRP, Machine Learning, NFV, Online Gaming, Realtime processing, Smart surveillance, Video Analytics & Streaming.

 


Figure 1. Lenovo ThinkEdge SE455 V3

 

Lenovo ThinkEdge offerings are ideal for running applications at remote locations because of their low cost and high-performance capabilities. They are industry-standard servers providing cost effective computing and fast high-density local storage at the edge. With their smaller footprint, the ThinkEdge series servers are ideal for deployment in remote office and edge locations.

AI Edge Use Cases

A key benefit of AI and edge computing is the ability of devices to locally compute, process, and analyze data with high quality and minimal network latency from typical datacenter connections. There are many examples of edge computing use cases but here are a few popular ones.

  • Healthcare – Patient and equipment monitoring
  • Retail and grocery stores – Cashier-less payments, real-time inventory, security
  • Financial Services – Kiosk safety and fraud prevention
  • Manufacturing – Automation, smart sensors, quality assurance
  • Gas stations – Payments, security, inventory
  • Transportation – Trucking, shipping, autonomous vehicles


Figure 2. Lenovo ThinkEdge SE450

Microsoft Azure SQL Edge on ThinkEdge Systems

SQL Server is a well-known, mission-critical database system used in many customer datacenters. It is also available in an edge-sized version that runs efficiently on edge servers as a containerized application. Azure SQL Edge is a small-footprint, robust IoT database product that runs on Lenovo Edge servers to process the data locally for increased security and reduced latency.

The combination of Azure SQL Edge and Lenovo’s ThinkEdge series servers provides the ideal solution for processing data aggregated from scores of IoT devices in typical edge use cases like retail, transportation, and manufacturing. Azure SQL Edge also has Machine Learning (ML) inferencing capabilities. ML Models can be trained on-premises and deployed to the edge where AI inferencing can be done.


Figure 3. Lenovo ThinkEdge SE360 V2

Lenovo ThinkEdge Portfolio

Below is a summary of current Lenovo ThinkEdge servers and configurations available. Below are GPUs supported on the edge servers.

GPUs are important in any AI solution due to their parallel processing capability. They contain thousands of smaller cores designed for handling multiple tasks simultaneously. This is useful for AI tasks that require a large number of matrix multiplications and other parallel computations.

GPUs can also manage large volumes of data more efficiently than traditional CPUs due to their parallel architecture. After training, AI models need to make predictions or inferences. GPUs are also used to speed up the inference process, better enabling real-time AI applications.

 

System

Processor

GPU

Memory

Storage

SE455 V3 (2U)

1-socket AMD EPYC™ 8004 Series (4th Gen AMD EPYC), up to 64 cores and  200W TDP

Up to 6x single-width GPUs or 2x double-width GPUs

6x TruDDR5 slots; Maximum 576GB using 6x 96GB RDIMMs

4x 2.5-inch 15mm front drives
4x 2.5-inch 15mm internal

2x M.2 boot drives

SE450 (2U)

1-socket 3rd Gen Intel Xeon Platinum, up to 36 cores, up to 225W TDP

Up to 4x single-width GPUs or 2x double-width GPUs

10x DDR4 slots; Maximum 1TB using 8x 128GB 3DS RDIMMs

6x 2.5-inch 7mm drives; Up to 6x NVMe drives

2x M.2 boot drives

SE360 V2 (2U)

1-socket Intel Xeon D-2700, up to 16 cores

Support for NVIDIA A2, NVIDIA L4, Intel Data Center GPU Flex 140, Qualcomm Cloud AI 100

Up to 256GB in 4x slots, using 64GB DIMMs; 3200MHz TruDDR4

2x SATA/NVMe 2.5" 7mm drives; or 8x M.2 using NVMe,

2x M.2 2280 NVME boot drives

Why Lenovo

Lenovo is a US$70 billion revenue Fortune Global 500 company serving customers in 180 markets around the world. Focused on a bold vision to deliver smarter technology for all, we are developing world-changing technologies that power (through devices and infrastructure) and empower (through solutions, services, and software) millions of customers every day.

For More Information

To learn more about this Lenovo solution contact your Lenovo Business Partner or visit: https://www.lenovo.com/us/en/solutions/ai/

References

Lenovo ThinkEdge servers: Link

ThinkEdge SE455 V3: Link

ThinkEdge SE450: Link

ThinkEdge SE360 V2: Link

Lenovo Edge AI solutions: Link

Lenovo and Azure SQL Edge solution: Link

Related product families

Product families related to this document are the following:

Trademarks

Lenovo and the Lenovo logo are trademarks or registered trademarks of Lenovo in the United States, other countries, or both. A current list of Lenovo trademarks is available on the Web at https://www.lenovo.com/us/en/legal/copytrade/.

The following terms are trademarks of Lenovo in the United States, other countries, or both:
Lenovo®
ThinkEdge®
TruDDR4

The following terms are trademarks of other companies:

AMD and AMD EPYC™ are trademarks of Advanced Micro Devices, Inc.

Intel® and Xeon® are trademarks of Intel Corporation or its subsidiaries.

Microsoft®, Azure®, and SQL Server® are trademarks of Microsoft Corporation in the United States, other countries, or both.

Other company, product, or service names may be trademarks or service marks of others.