AI in the Arctic Rainforest
# AI in the Arctic Rainforest: Server Configuration
This document details the server configuration for the "AI in the Arctic Rainforest" project, a research initiative leveraging artificial intelligence to analyze data collected from remote sensor networks deployed in the boreal forests of northern regions. This guide is intended for new system administrators and developers contributing to the project. It outlines the hardware, software, and networking components crucial for successful operation.
Project Overview
The "AI in the Arctic Rainforest" project focuses on real-time analysis of environmental data – temperature, humidity, soil moisture, animal tracking, and audio recordings – to detect patterns indicative of climate change and biodiversity shifts. The server infrastructure supports data ingestion, processing, model training, and visualization. We utilize a distributed system architecture for scalability and resilience. See Data Flow Diagram for a visual representation.
Hardware Configuration
The core server infrastructure consists of three primary server types: Data Ingestion Servers, Processing/AI Servers, and a Database Server. Each server type utilizes specific hardware components optimized for its role.
| Server Type | CPU | RAM | Storage | Network Interface |
|---|
| Data Ingestion Servers | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 4 TB NVMe SSD (RAID 1) | 10 Gbps Ethernet | |
| Processing/AI Servers | AMD EPYC 7763 (64 cores) | 256 GB DDR4 ECC | 8 TB NVMe SSD (RAID 0) + 4 x NVIDIA A100 GPUs | 25 Gbps Ethernet | |
| Database Server | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | 16 TB SAS HDD (RAID 6) | 10 Gbps Ethernet | |
All servers are housed in a dedicated, climate-controlled server room with redundant power supplies and UPS backup. Detailed hardware specifications for each individual server are available on the Hardware Inventory Page. Regular hardware maintenance schedules are outlined in the Maintenance Procedures Document. We also employ a Server Monitoring System for proactive issue detection.
Software Configuration
The software stack is designed for efficient data handling, AI model training, and database management. The operating system across all servers is Ubuntu Server 22.04 LTS.
Data Ingestion Servers
These servers are responsible for receiving data from the sensor networks. They run:
- Nginx: As a reverse proxy and load balancer. See Nginx Configuration Guide.
- Fluentd: For log aggregation and forwarding.
- MQTT Broker (Mosquitto): To handle data streams from the sensors. Configuration details are found in MQTT Broker Setup.
- Python 3.10: With custom scripts for data validation and initial processing.
- CUDA Toolkit 12.2: For GPU acceleration. Installation guide at CUDA Installation.
- PyTorch 2.0: The primary deep learning framework.
- TensorFlow 2.10: Used for specific model architectures.
- Jupyter Notebook: For development and experimentation.
- Kubernetes: For container orchestration and scaling. See Kubernetes Cluster Configuration.
- PostgreSQL 15: The relational database management system. See PostgreSQL Database Administration.
- pgAdmin 4: For database administration and monitoring.
- TimescaleDB: An extension to PostgreSQL optimized for time-series data. Configuration is outlined in TimescaleDB Setup.
- Telegram: @powervps Servers at a discounted price
Processing/AI Servers
These servers perform the computationally intensive tasks of AI model training and inference. They run:
Database Server
This server stores all project data. It runs:
Networking Configuration
The server infrastructure is connected via a dedicated Gigabit Ethernet network. A separate 10 Gbps network connects the Data Ingestion and Processing/AI Servers for high-speed data transfer.
| Component | IP Address | Subnet Mask | Gateway |
|---|
| Data Ingestion Server 1 | 192.168.1.101 | 255.255.255.0 | 192.168.1.1 | |
| Data Ingestion Server 2 | 192.168.1.102 | 255.255.255.0 | 192.168.1.1 | |
| Processing/AI Server 1 | 10.0.0.101 | 255.255.255.0 | 10.0.0.1 | |
| Processing/AI Server 2 | 10.0.0.102 | 255.255.255.0 | 10.0.0.1 | |
| Database Server | 172.16.0.101 | 255.255.255.0 | 172.16.0.1 | |
Firewall rules are configured using `iptables` to restrict access to necessary ports only. Detailed firewall configuration is available at Firewall Ruleset. We utilize a VPN Configuration Guide for secure remote access to the servers. DNS resolution is handled by an internal DNS server, documented in DNS Server Configuration.
Security Considerations
Security is paramount. All servers are regularly patched with the latest security updates. Strong passwords and multi-factor authentication are enforced. Intrusion detection and prevention systems are in place. See the Security Policy Document for more detailed information. We also implement data encryption both in transit and at rest. Refer to Data Encryption Standards for specific details.
Future Expansion
We anticipate scaling the infrastructure to accommodate increasing data volumes and more complex AI models. Future plans include adding additional Processing/AI servers with more powerful GPUs and expanding the storage capacity of the Database Server. See Scalability Roadmap for details.
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.* ⚠️