AI in the Guernsey Rainforest
- AI in the Guernsey Rainforest: Server Configuration
This article details the server configuration supporting the "AI in the Guernsey Rainforest" project. This project utilizes machine learning to analyze audio and visual data collected from sensors deployed within the Guernsey Rainforest, aiding in biodiversity monitoring and conservation efforts. This guide is intended for new system administrators joining the team and provides a comprehensive overview of the hardware and software setup.
Project Overview
The "AI in the Guernsey Rainforest" project aims to automatically identify and classify species within the rainforest using data gathered from a network of remote sensors. These sensors capture audio recordings and low-resolution images. The data is processed locally at the edge, and then transmitted to a central server cluster for more complex analysis and long-term storage. This server cluster is the focus of this document. The project relies heavily on Semantic MediaWiki for data organization and querying.
Server Hardware Specifications
The server cluster consists of three primary server nodes: a database server, an application server, and a processing/inference server. Each node is built with redundancy in mind.
| Server Role | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Database Server | Intel Xeon Gold 6248R (24 cores) | 256 GB DDR4 ECC | 4 x 4TB NVMe SSD (RAID 10) | 10 Gigabit Ethernet |
| Application Server | AMD EPYC 7763 (64 cores) | 128 GB DDR4 ECC | 2 x 2TB NVMe SSD (RAID 1) + 8TB HDD | 10 Gigabit Ethernet |
| Processing/Inference Server | 2 x NVIDIA Tesla A100 GPUs, Intel Xeon Gold 6338 (32 cores) | 512 GB DDR4 ECC | 1 x 2TB NVMe SSD | 100 Gigabit Ethernet |
All servers run on a dedicated VLAN for security and network isolation. Power redundancy is achieved through dual power supplies and a UPS system. See Server Room Infrastructure for more details.
Software Stack
The software stack is built around open-source components to minimize licensing costs and maximize flexibility. The operating system of choice is Ubuntu Server 22.04 LTS.
Database Server
The database server hosts the project's primary data store: a PostgreSQL database.
| Component | Version | Configuration Notes |
|---|---|---|
| Operating System | Ubuntu Server 22.04 LTS | Standard security hardening applied |
| PostgreSQL | 14.7 | Configured with WAL archiving and regular backups. Database Backup Procedures document details the process. |
| pgAdmin 4 | 4.16 | Used for database administration and monitoring. |
The database schema is designed to efficiently store and query sensor data, species classifications, and related metadata. Refer to the Database Schema Documentation for a complete description.
Application Server
The application server runs the core application logic, providing an API for data access and management. It's built using Python with the Flask web framework.
| Component | Version | Configuration Notes |
|---|---|---|
| Operating System | Ubuntu Server 22.04 LTS | Standard security hardening applied |
| Python | 3.10 | Virtual environment managed with venv. |
| Flask | 2.2.2 | Deployed using Gunicorn as a WSGI server. |
| Nginx | 1.22.1 | Used as a reverse proxy and load balancer. See Nginx Configuration Guide |
The application server interacts with the database server to retrieve and store data. It also communicates with the processing/inference server to request species classifications.
Processing/Inference Server
This server is responsible for running the machine learning models used to classify species. It utilizes the TensorFlow framework and is optimized for GPU acceleration.
- Operating System: Ubuntu Server 22.04 LTS
- CUDA Toolkit: 11.7
- cuDNN: 8.4.0
- TensorFlow: 2.10.0
- Python: 3.10
The models are periodically updated and deployed using a CI/CD pipeline. See Model Deployment Process for detailed instructions. GPU utilization is monitored using NVIDIA System Management Interface (nvidia-smi).
Network Configuration
All servers reside within a dedicated VLAN (192.168.10.0/24). Firewall rules are configured to restrict access to only necessary ports. DNS resolution is provided by an internal DNS server. The servers are also accessible via a secure VPN connection for remote administration. Refer to Network Diagram for a visual representation of the network topology.
Security Considerations
Security is paramount. All servers are regularly patched and updated. Intrusion detection and prevention systems are in place. Access control is strictly enforced. Data is encrypted both in transit and at rest. See Security Policy for a comprehensive overview of the project's security measures. Regular security audits are conducted by Security Team.
Future Expansion
As the project evolves, we anticipate scaling the server cluster to handle increased data volumes and processing demands. This may involve adding more processing/inference servers or migrating to a cloud-based infrastructure. Scalability Planning document details the proposed expansion strategies.
Main Page Technical Documentation Sensor Network Configuration Data Pipeline Machine Learning Models API Documentation Monitoring and Alerting Troubleshooting Guide Backup and Recovery User Access Control System Logs Performance Tuning Software Updates Contact Information
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.* ⚠️