Server rental store

AI in Cornwall

```wiki #REDIRECT AI in Cornwall

AI in Cornwall: Server Configuration Overview

This article details the server configuration supporting the "AI in Cornwall" initiative. It aims to provide a comprehensive overview for new administrators and those seeking to understand the infrastructure. The project leverages a hybrid cloud approach, combining on-premise hardware with cloud-based services for scalability and resilience. This document will cover the core server components, network topology, and software stack. See also System Administration Guide for general MediaWiki site administration.

Core Infrastructure Components

The "AI in Cornwall" project relies on a tiered architecture. The core infrastructure consists of three primary tiers: Data Acquisition, Processing, and Delivery. Each tier has specific server requirements, outlined below. For information on Security Protocols, please see the dedicated security documentation.

Tier Purpose Server Role Key Technologies
Data Acquisition || Gathering data from sensors and external APIs || Edge Servers, Data Ingestion Servers || Python, MQTT, REST APIs, Database Schema
Processing || Performing AI/ML tasks, model training, and data analysis || GPU Servers, CPU Servers, Data Storage Servers || TensorFlow, PyTorch, CUDA, Data Analytics Tools
Delivery || Providing AI-driven insights and applications to end-users || Web Servers, Application Servers || Node.js, Flask, React, API Documentation

On-Premise Hardware Specifications

The on-premise infrastructure is housed in a dedicated data center in Truro. The following tables detail the specifications of the key server types. Refer to Hardware Inventory for a complete listing of all equipment.

GPU Servers

These servers are critical for the computationally intensive tasks of model training and inference.

Component Specification
CPU Dual Intel Xeon Gold 6248R (24 cores/48 threads per CPU)
GPU 4 x NVIDIA A100 (80GB HBM2e)
RAM 512GB DDR4 ECC Registered (3200 MHz)
Storage 2 x 4TB NVMe SSD (RAID 0) + 2 x 16TB SAS HDD (RAID 1)
Network Dual 100GbE NIC
Power Supply 2 x 2000W Redundant Power Supplies

Data Storage Servers

These servers provide high-capacity, reliable storage for datasets and model artifacts.

Component Specification
CPU Intel Xeon Silver 4210 (10 cores/20 threads)
RAM 256GB DDR4 ECC Registered (2666 MHz)
Storage 8 x 20TB SAS HDD (RAID 6) - Total usable capacity: 120TB
Network Quad 10GbE NIC
Power Supply 2 x 850W Redundant Power Supplies

Edge Servers

These servers are deployed closer to data sources (e.g., sensor networks) to perform initial data filtering and pre-processing.

Component Specification
CPU Intel Core i7-8700K (6 cores/12 threads)
RAM 32GB DDR4 (2666 MHz)
Storage 1 x 1TB NVMe SSD
Network Dual 1GbE NIC
Power Supply 1 x 650W Power Supply

Software Stack

The servers run a combination of Linux (Ubuntu Server 20.04 LTS) and containerized applications managed by Kubernetes. Key software components include:

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