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.
- Operating System: Ubuntu Server 22.04 LTS. Refer to the Ubuntu Server Documentation.
- Programming Languages: Python 3.9, C++. See the Python Style Guide.
- AI Framework: TensorFlow 2.8.
- Data Storage: Ceph. Review the Ceph Configuration Guide.
- Containerization: Docker. The Docker Best Practices should be followed.
- Orchestration: Kubernetes. Consult the Kubernetes Tutorial.
- Monitoring: Prometheus and Grafana. See Monitoring Dashboard Setup.
- Networking: Utilizing VLAN Configuration for network segmentation.
Network Configuration
The server cluster is connected via a dedicated high-speed network. The network is segmented into different VLANs to isolate different components. Firewall rules are configured to restrict access to only necessary ports. Please review the Firewall Ruleset.
Security Considerations
Security is a paramount concern. Regular security audits are conducted, and all servers are kept up-to-date with the latest security patches. Intrusion detection systems are in place to monitor for malicious activity. The Security Incident Response Plan is regularly reviewed and updated.
Main Page Server Administration Guide Networking Protocols Project Goals Data Flow Diagram Linux Server Hardening rsync CUDA Toolkit Ubuntu Server Documentation Python Style Guide Ceph Configuration Guide Docker Best Practices Kubernetes Tutorial Monitoring Dashboard Setup VLAN Configuration Firewall Ruleset Backup Procedures Security Incident Response Plan
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️