AI in the Madagascar Rainforest
- AI in the Madagascar Rainforest: Server Configuration
This article details the server configuration supporting the "AI in the Madagascar Rainforest" project, a research initiative utilizing artificial intelligence to analyze biodiversity data collected from remote sensors in Madagascar's rainforests. This guide is intended for newcomers to our MediaWiki site and provides a technical overview of the infrastructure.
Project Overview
The "AI in the Madagascar Rainforest" project aims to automatically identify species from audio and visual data captured by a network of sensors deployed within the rainforest. This requires significant computational resources for both real-time data processing and model training. The server infrastructure is designed for scalability, reliability, and efficient data handling. We utilize a hybrid approach, combining on-premise servers for low-latency processing with cloud-based resources for large-scale model training. See Data Acquisition for details on the sensors used.
Server Hardware Configuration
The core of our on-premise infrastructure consists of three primary servers: a data ingestion server, a processing server, and a database server. Each server is crucial to the overall functionality of the project. Detailed specifications are outlined below:
| Server Role | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Intel Xeon Gold 6248R (24 cores) | 128 GB DDR4 ECC | 4 x 8 TB SATA HDD (RAID 10) | 10 Gigabit Ethernet | | ||||
| 2 x AMD EPYC 7763 (64 cores total) | 256 GB DDR4 ECC | 2 x 2 TB NVMe SSD (RAID 0) + 8 x 16 TB SATA HDD (RAID 6) | 25 Gigabit Ethernet | | ||||
| Intel Xeon Silver 4210 (10 cores) | 64 GB DDR4 ECC | 4 x 4 TB SATA HDD (RAID 10) | 10 Gigabit Ethernet | |
These servers are housed in a climate-controlled server room with redundant power supplies and network connectivity. Detailed information about Server Room Maintenance can be found elsewhere on the wiki.
Software Stack
The software stack is built around a Linux foundation, providing flexibility and control. The following software components are utilized:
- Operating System: Ubuntu Server 22.04 LTS
- Database: PostgreSQL 14 with PostGIS extension for geospatial data. Database Administration details the maintenance procedures.
- Programming Languages: Python 3.10, R 4.3.0
- AI Frameworks: TensorFlow 2.12, PyTorch 2.0
- Data Streaming: Apache Kafka
- Web Server: Nginx
- Monitoring: Prometheus and Grafana. See System Monitoring for configuration details.
Cloud Integration
For large-scale model training, we leverage Amazon Web Services (AWS). Specifically, we utilize the following services:
| AWS Service | Instance Type | Purpose |
|---|---|---|
| p4d.24xlarge | Model Training (GPU intensive) | | ||
| Standard | Data Storage | | ||
| Notebook Instances | Model Development & Experimentation | | ||
| - | Triggered Data Processing | |
Data is periodically synchronized between the on-premise database and AWS S3 for model training purposes. The synchronization process is automated using AWS CLI.
Network Configuration
The network is segmented to enhance security and performance. The servers are organized into three VLANs:
- VLAN 10: Data Ingestion and Processing (192.168.10.0/24)
- VLAN 20: Database (192.168.20.0/24)
- VLAN 30: Management (192.168.30.0/24)
Firewall rules are configured to restrict access between VLANs, allowing only necessary traffic. Network diagrams are available in Network Topology. We also employ a reverse proxy (Nginx) for secure remote access to the web interface.
Security Considerations
Security is paramount. The following measures are in place:
- Regular security audits. See Security Audit Procedures
- Intrusion detection and prevention systems.
- Strong password policies and multi-factor authentication.
- Data encryption at rest and in transit.
- Regular software updates and patching.
- Firewall rules restricting unauthorized access.
Future Expansion
We anticipate the need for increased computational resources as the project evolves. Future expansion plans include:
| Component | Planned Upgrade | Timeline |
|---|---|---|
| Add 2 x NVIDIA A100 GPUs | Q1 2024 | | ||
| Upgrade to 512 GB RAM | Q2 2024 | | ||
| Upgrade core switch to 40 Gigabit Ethernet | Q3 2024 | |
These upgrades will enable us to handle larger datasets and more complex AI models. Details of the upgrade process will be documented in Hardware Upgrade Procedures.
Related Pages
- Data Acquisition
- Database Administration
- System Monitoring
- Server Room Maintenance
- AWS CLI
- Network Topology
- Security Audit Procedures
- Hardware Upgrade Procedures
- Data Backup Strategy
- Disaster Recovery Plan
- Software Version Control
- User Account Management
- Incident Response Protocol
- Development Environment Setup
- API Documentation
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.* ⚠️