AI in the Sint Eustatius Rainforest
AI in the Sint Eustatius Rainforest: Server Configuration
This article details the server configuration supporting the “AI in the Sint Eustatius Rainforest” project. This project leverages artificial intelligence to monitor and analyze biodiversity within the rainforest ecosystem of Sint Eustatius. This document is intended for new system administrators and developers joining the project, providing a comprehensive overview of the server infrastructure.
Project Overview
The “AI in the Sint Eustatius Rainforest” project utilizes a network of sensor nodes deployed throughout the rainforest, collecting data on audio, visual, and environmental conditions. This data is transmitted to a central server cluster for processing and analysis using machine learning algorithms. The primary goals are species identification, population monitoring, and early detection of ecological changes. See also Data Acquisition Pipeline and Machine Learning Models. Understanding the Sensor Network Topology is critical for troubleshooting.
Server Infrastructure
The server infrastructure is hosted within a secure, climate-controlled data center located in St. Eustatius. The core components consist of three primary server roles: Data Ingestion, Processing/AI, and Data Storage. These are all running on bare metal servers for performance and security reasons. We avoid virtual machines due to the real-time processing demands. See Security Protocols for details on data center security.
Data Ingestion Servers
These servers are responsible for receiving data streams from the sensor network. They perform initial data validation and buffering before forwarding the data to the processing cluster. These servers run a custom-built ingestion service written in Python. Refer to the Ingestion Service Documentation for details.
| Server Name | Role | Operating System | CPU | RAM | Network Interface |
|---|---|---|---|---|---|
| statia-ingest-01 | Data Ingestion | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 10 Gbps Ethernet |
| statia-ingest-02 | Data Ingestion (Backup) | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 10 Gbps Ethernet |
Processing/AI Servers
These servers are the heart of the project, performing the computationally intensive tasks of machine learning model training and inference. They utilize GPUs to accelerate these processes. These servers run a containerized environment using Docker and Kubernetes for scalability and manageability. See the Kubernetes Configuration document.
| Server Name | Role | Operating System | CPU | RAM | GPU | Storage |
|---|---|---|---|---|---|---|
| statia-ai-01 | AI Processing | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | NVIDIA A100 (80GB) | 4 TB NVMe SSD |
| statia-ai-02 | AI Processing | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | NVIDIA A100 (80GB) | 4 TB NVMe SSD |
| statia-ai-03 | AI Processing | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | NVIDIA A100 (80GB) | 4 TB NVMe SSD |
Data Storage Servers
These servers provide persistent storage for the raw sensor data, processed data, and model artifacts. They utilize a distributed file system for redundancy and scalability. We use Ceph as our distributed filesystem. See Ceph Cluster Configuration for details.
| Server Name | Role | Operating System | CPU | RAM | Storage |
|---|---|---|---|---|---|
| statia-storage-01 | Data Storage | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 96 GB DDR4 ECC | 16 TB HDD (RAID6) |
| statia-storage-02 | Data Storage | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 96 GB DDR4 ECC | 16 TB HDD (RAID6) |
| statia-storage-03 | Data Storage | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 96 GB DDR4 ECC | 16 TB HDD (RAID6) |
Networking
All servers are connected via a dedicated 10 Gbps network. A firewall protects the network from external threats. Internal communication between servers is secured using TLS/SSL. See Network Diagram for a visual representation of the network topology. Network monitoring is handled by Nagios Monitoring System.
Software Stack
- **Operating System:** Ubuntu Server 22.04 LTS
- **Programming Languages:** Python, C++
- **Machine Learning Frameworks:** TensorFlow, PyTorch
- **Containerization:** Docker
- **Orchestration:** Kubernetes
- **Database:** PostgreSQL (for metadata) – see PostgreSQL Configuration
- **Distributed File System:** Ceph
- **Monitoring:** Nagios, Prometheus, Grafana
Future Considerations
Future upgrades will include expanding the GPU cluster with newer generation hardware and exploring the use of edge computing to perform initial data processing closer to the sensor nodes. We will also investigate integrating a more robust alerting system based on Alertmanager Configuration.
Data Acquisition Sensor Calibration Data Validation Procedures Model Training Pipeline Deployment Strategies System Backup Procedures Disaster Recovery Plan Security Audit Logs Performance Tuning Guide API Documentation Troubleshooting Guide Software Version Control Collaboration Guidelines 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.* ⚠️