AI in the New Guinean Rainforest
AI in the New Guinean Rainforest: Server Configuration
This article details the server configuration for the "AI in the New Guinean Rainforest" project, a research initiative utilizing artificial intelligence for biodiversity monitoring and conservation efforts. This documentation is intended for newcomers to our server infrastructure. We will cover hardware specifications, software stack, networking, and security considerations. Please review the Server Access Policy before attempting any configuration changes.
Project Overview
The project aims to deploy a network of low-power sensors throughout the New Guinean rainforest, collecting data on animal vocalizations, environmental conditions, and potential illegal logging activities. This data is transmitted to a central server cluster for processing using machine learning algorithms. The primary goals are species identification, population monitoring, and anomaly detection. Understanding the Data Acquisition Process is critical. See also Project Goals and Ethics.
Hardware Configuration
Our server cluster consists of three primary server types: Edge Servers, Processing Servers, and the Primary Database Server. Each has distinct hardware requirements.
Edge Server Specifications
These servers are deployed in proximity to sensor networks and perform initial data filtering and pre-processing.| Component | Specification |
|---|---|
| CPU | Intel Xeon E-2388G (8 Cores, 3.2 GHz) |
| RAM | 32 GB DDR4 ECC 3200 MHz |
| Storage | 1 TB NVMe SSD (for OS & temporary data) + 4 TB HDD (for raw data buffering) |
| Network Interface | Dual Gigabit Ethernet |
| Power Supply | 600W 80+ Platinum |
| Operating System | Ubuntu Server 22.04 LTS |
Processing Server Specifications
These servers perform the bulk of the AI model training and inference.| Component | Specification |
|---|---|
| CPU | Dual Intel Xeon Gold 6338 (32 Cores, 2.0 GHz) |
| RAM | 128 GB DDR4 ECC 3200 MHz |
| Storage | 2 x 2 TB NVMe SSD (RAID 1, for OS and model storage) + 8 x 8 TB SAS HDD (RAID 6, for large datasets) |
| GPU | 4 x NVIDIA A100 80GB |
| Network Interface | 10 Gigabit Ethernet |
| Power Supply | 1600W 80+ Titanium |
| Operating System | CentOS Stream 9 |
Primary Database Server Specifications
This server stores all processed data, model metadata, and project results.| Component | Specification |
|---|---|
| CPU | Intel Xeon Platinum 8380 (40 Cores, 2.3 GHz) |
| RAM | 256 GB DDR4 ECC 3200 MHz |
| Storage | 10 x 16 TB SAS HDD (RAID 6, with hot spare) |
| Network Interface | 10 Gigabit Ethernet |
| Power Supply | 2000W 80+ Titanium |
| Operating System | Red Hat Enterprise Linux 8 |
Software Stack
The software stack is layered to provide the necessary functionality for data ingestion, processing, and storage. Consult the Software Version Control page for the latest revisions.
- Operating Systems: As specified in the hardware section.
- Database: PostgreSQL 14 with PostGIS extension.
- Programming Languages: Python 3.9, R 4.2.
- AI Frameworks: TensorFlow 2.8, PyTorch 1.12.
- Data Streaming: Apache Kafka for real-time data ingestion.
- Data Visualization: Grafana and Jupyter Notebooks.
- Version Control: Git with GitHub for collaborative development.
- Containerization: Docker and Kubernetes for deployment and scaling.
- Network Topology: Star topology with the Primary Database Server at the center.
- IP Addressing: Static IP addresses assigned to each server.
- Firewall: iptables configured to allow only necessary traffic.
- VPN: OpenVPN for secure remote access.
- DNS: Internal DNS server for name resolution.
- Access Control: Role-based access control (RBAC) implemented using LDAP.
- Encryption: Data at rest and in transit is encrypted using TLS/SSL.
- Intrusion Detection: Snort intrusion detection system deployed.
- Regular Backups: Daily backups of all critical data stored offsite.
- Security Audits: Periodic security audits conducted by external experts.
- Physical Security: Server rooms are physically secured with access control and surveillance.
- Telegram: @powervps Servers at a discounted price
Networking Configuration
The server cluster is connected via a dedicated 10 Gigabit Ethernet network. A virtual private network (VPN) is used for secure remote access. See the Network Diagram for a visual representation.
Security Considerations
Security is paramount, given the sensitive nature of the data and the remote location of some servers. Refer to the Security Policy for detailed procedures.
Future Scalability
The architecture is designed for scalability. We anticipate adding more Processing Servers as the data volume grows. The use of Kubernetes allows for easy deployment and scaling of AI models. We are also exploring the use of Cloud Computing services for burst capacity. See Scalability Roadmap for planned upgrades.
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 configurationNeed Assistance?
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️