Server rental store

AI in the Red Sea

AI in the Red Sea: Server Configuration Documentation

This document details the server configuration for the "AI in the Red Sea" project, a research initiative focusing on underwater data analysis using artificial intelligence. This guide is intended for new team members and system administrators tasked with maintaining the project's infrastructure. It covers hardware, software, networking, and security considerations. Please review this document thoroughly before making any changes to the server environment. Refer to the System Administration Policy for overarching guidelines.

Overview

The "AI in the Red Sea" project relies on a distributed server architecture to process the large volumes of data collected from underwater sensors and remotely operated vehicles (ROVs). The system is designed for high throughput, low latency, and scalability. Data is initially ingested into a staging area, then processed by AI models, and finally archived for long-term storage. This process is outlined in the Data Flow Diagram. This documentation focuses on the core server components. For details on the data acquisition systems, see Sensor Network Configuration.

Hardware Specifications

The server infrastructure consists of three primary tiers: ingestion, processing, and storage. Each tier utilizes specialized hardware optimized for its respective tasks.

Ingestion Servers

These servers handle the initial intake of data from the ROVs and sensor networks. They require high network bandwidth and fast storage for temporary buffering.

Component Specification Quantity
CPU Intel Xeon Gold 6248R (24 cores) 2
RAM 256 GB DDR4 ECC Reg. 2
Storage (Temporary) 4 x 2TB NVMe SSD (RAID 0) 2
Network Interface Dual 100 Gbps Ethernet 2
Power Supply 1600W Redundant 2

Processing Servers

These servers execute the AI models for data analysis. They are equipped with high-performance GPUs for accelerated computation.

Component Specification Quantity
CPU AMD EPYC 7763 (64 cores) 4
RAM 512 GB DDR4 ECC Reg. 4
GPU NVIDIA A100 (80GB) 8
Storage (Local) 2 x 4TB NVMe SSD (RAID 1) 4
Network Interface Dual 100 Gbps Ethernet 4
Power Supply 2000W Redundant 4

Storage Servers

These servers provide long-term archival storage for processed data. Capacity and data integrity are the primary concerns.

Component Specification Quantity
CPU Intel Xeon Silver 4210 (10 cores) 6
RAM 64 GB DDR4 ECC Reg. 6
Storage (Archival) 12 x 16TB SAS HDD (RAID 6) 6
Network Interface Dual 25 Gbps Ethernet 6
Power Supply 1200W Redundant 6

Software Configuration

All servers run Ubuntu Server 22.04 LTS. The following software components are installed and configured:

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