Server rental store

AI in Suffolk

# AI in Suffolk: Server Configuration

This document details the server configuration supporting the "AI in Suffolk" project. It is intended for new system administrators and developers contributing to the project. This project focuses on utilizing Artificial Intelligence for agricultural optimization within the county of Suffolk.

Overview

The "AI in Suffolk" project requires significant computational resources for training machine learning models, processing sensor data from local farms, and serving prediction APIs. The infrastructure is primarily hosted on-premise for data security and low latency access to agricultural sensors. This document outlines the hardware, software, and networking configurations. We utilize a hybrid approach, with some data processing occurring on edge devices, and heavier lifting done on centralized servers. See also Data Pipeline Overview and Sensor Network Architecture.

Hardware Configuration

The core server infrastructure consists of three primary server types: Data Ingestion Servers, Model Training Servers, and API Servers. Each type is detailed below. Important consideration was given to power efficiency, as Suffolk County has a strong commitment to sustainable practices, as per the Suffolk Sustainability Plan.

Data Ingestion Servers

These servers are responsible for receiving data from various sensors deployed across farms in Suffolk County. They perform initial data validation and pre-processing before forwarding data to the model training servers.

Component Specification Quantity
CPU Intel Xeon Gold 6248R (24 cores) 2
RAM 128GB DDR4 ECC Registered 2
Storage 2 x 4TB NVMe SSD (RAID 1) 2
Network Interface 10GbE 2
Power Supply 800W Redundant 2

Model Training Servers

These servers are equipped with powerful GPUs to accelerate the training of machine learning models. They leverage distributed training frameworks to handle large datasets. These servers are crucial for the Machine Learning Model Development process.

Component Specification Quantity
CPU AMD EPYC 7763 (64 cores) 4
RAM 256GB DDR4 ECC Registered 4
GPU NVIDIA A100 80GB 8
Storage 4 x 8TB NVMe SSD (RAID 0) 4
Network Interface 100GbE 4
Power Supply 1600W Redundant 4

API Servers

These servers host the APIs that provide access to the trained machine learning models. They handle requests from farmers and other applications. These servers are designed for high availability and scalability, as documented in API Scalability Plan.

Component Specification Quantity
CPU Intel Xeon Silver 4210 (10 cores) 6
RAM 64GB DDR4 ECC Registered 6
Storage 1 x 1TB NVMe SSD 6
Network Interface 10GbE 6
Power Supply 750W Redundant 6

Software Configuration

The following software stack is used across the server infrastructure.

⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️

View full article | Back to Server rental store