Server rental store

AI in the Tasman Sea

# AI in the Tasman Sea: Server Configuration

This article details the server infrastructure supporting the "AI in the Tasman Sea" project, a research initiative focused on real-time marine mammal detection and classification using artificial intelligence. It's designed for new contributors to our MediaWiki site and aims to provide a clear understanding of the hardware and software components. Please read this in conjunction with our Server Administration Guide and Networking Protocols documentation.

Project Overview

The "AI in the Tasman Sea" project utilizes a network of underwater acoustic sensors deployed throughout the Tasman Sea. Data is streamed to a central server cluster for processing. The AI models, primarily Deep Neural Networks (DNNs), analyze the acoustic data to identify the presence and species of marine mammals. This data is then used for population monitoring and conservation efforts. Refer to the Project Goals page for more information. Understanding the Data Flow Diagram is crucial before reviewing the server configuration.

Server Cluster Architecture

The server cluster is based on a distributed architecture, comprising several key components. These include: data ingestion servers, processing servers (GPU-accelerated), storage servers, and a management server. Each component has a specific role and is configured for optimal performance. The system relies heavily on Linux Server Hardening best practices.

Data Ingestion Servers

These servers are responsible for receiving data streams from the underwater acoustic sensors. They perform initial data validation and buffering before forwarding the data to the processing servers. They utilize rsync for reliable data transfer.

Data Ingestion Server Specs Value
Server Model Dell PowerEdge R750
CPU Intel Xeon Gold 6338 (2 x 32 cores)
RAM 256 GB DDR4 ECC
Network Interface Dual 10 Gigabit Ethernet
Storage 4 TB NVMe SSD (RAID 1)

Processing Servers

These servers perform the computationally intensive task of running the AI models. They are equipped with high-end GPUs for accelerated processing. They use CUDA Toolkit for GPU programming.

Processing Server Specs Value
Server Model Supermicro SYS-220P-HNR
CPU AMD EPYC 7763 (2 x 64 cores)
RAM 512 GB DDR4 ECC
GPU 4 x NVIDIA A100 (80GB)
Network Interface Dual 100 Gigabit Ethernet
Storage 2 x 8 TB NVMe SSD (RAID 0)

Storage Servers

These servers provide long-term storage for the processed data and AI model checkpoints. They utilize a distributed file system for scalability and redundancy. See the Backup Procedures documentation.

Storage Server Specs Value
Server Model HP ProLiant DL380 Gen10
CPU Intel Xeon Silver 4310 (12 cores)
RAM 128 GB DDR4 ECC
Network Interface Quad 25 Gigabit Ethernet
Storage 16 x 16 TB SAS HDD (RAID 6)

Software Stack

The software stack is built on a foundation of open-source technologies.

⚠️ *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