AI in the Catalonia Rainforest
- AI in the Catalonia Rainforest: Server Configuration
This article details the server configuration utilized for the "AI in the Catalonia Rainforest" project, a research initiative focusing on biodiversity monitoring and anomaly detection using machine learning. This guide is intended for newcomers to our MediaWiki site and provides a detailed overview of the hardware and software components.
Project Overview
The "AI in the Catalonia Rainforest" project employs a network of sensors collecting data on various environmental factors, including temperature, humidity, soundscapes, and camera imagery. This data is processed locally at the edge and then transmitted to a central server farm for deeper analysis using advanced AI models. The project aims to identify and alert researchers to unusual events, such as illegal logging or the presence of invasive species. See Project Goals for more information.
Server Infrastructure
The core infrastructure consists of three primary server types: Edge Servers, Processing Servers, and Storage Servers. Each server type has a specific role and configuration, detailed below. Understanding Server Roles is crucial.
Edge Servers
Edge servers are deployed directly within the Catalonia Rainforest, close to the sensor networks. They perform initial data processing, filtering, and aggregation to reduce bandwidth requirements. They also run basic anomaly detection models for immediate alerts.
| Specification | Value |
|---|---|
| CPU | Intel Xeon E-2388G |
| RAM | 32 GB DDR4 ECC |
| Storage | 1 TB NVMe SSD |
| Operating System | Ubuntu Server 22.04 LTS |
| Network Connectivity | 4G LTE with failover to satellite |
These servers utilize a lightweight containerization solution, Docker, for deploying the edge-based AI models. Further details on Edge Server Software Stack are available.
Processing Servers
Processing servers are located in a secure data center and are responsible for running the complex AI models used for in-depth data analysis. They handle tasks such as species identification from camera imagery and soundscape classification. Data Analysis Pipeline documents the process.
| Specification | Value |
|---|---|
| CPU | Dual Intel Xeon Gold 6338 |
| RAM | 256 GB DDR4 ECC |
| Storage | 4 x 4 TB NVMe SSD (RAID 0) |
| GPU | 4 x NVIDIA A100 (40GB) |
| Operating System | CentOS Stream 9 |
| Networking | 100 Gbps Ethernet |
The processing servers utilize Kubernetes for container orchestration, enabling scalability and resilience. See Kubernetes Configuration for specifics.
Storage Servers
Storage servers provide a centralized repository for all collected data, including raw sensor readings, processed data, and AI model outputs. Data is stored redundantly to ensure data integrity. Refer to the Data Backup Strategy document.
| Specification | Value |
|---|---|
| CPU | Intel Xeon Silver 4310 |
| RAM | 128 GB DDR4 ECC |
| Storage | 60 x 16 TB SAS HDD (RAID 6) |
| Operating System | Red Hat Enterprise Linux 8 |
| Network Connectivity | 40 Gbps Ethernet |
We employ Ceph as our distributed storage system, providing scalability and high availability. See Ceph Cluster Details for further configuration information.
Software Stack
The project relies on a diverse software stack, including:
- Python: The primary programming language for AI model development.
- TensorFlow: A popular machine learning framework.
- PyTorch: Another widely used machine learning framework.
- PostgreSQL: The relational database used for storing metadata and processed data.
- InfluxDB: A time-series database for storing sensor readings.
- Grafana: A data visualization tool for monitoring system performance and data trends.
- MQTT: A lightweight messaging protocol for communication between edge servers and the central server.
- Prometheus: A system monitoring and alerting toolkit.
Networking Considerations
The network infrastructure is critical for the success of this project. We utilize a combination of technologies:
- VPN: Secure communication between edge servers and the data center.
- Firewall: Protection against unauthorized access.
- Load Balancer: Distributing traffic across processing servers.
- DNS: Managing domain names and IP addresses.
Future Enhancements
Planned future enhancements include:
- Implementing a more robust AI model for species identification.
- Developing a real-time alerting system for immediate response to critical events.
- Expanding the sensor network to cover a larger area of the Catalonia Rainforest.
- Integration with GIS mapping software for visualizing data.
Security Considerations
Security is paramount. All servers are hardened according to Security Hardening Guide. Regular security audits are performed. Access control is managed via LDAP integration.
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.* ⚠️