AI in the Gibraltar Rainforest
- AI in the Gibraltar Rainforest: Server Configuration
This document details the server configuration powering the "AI in the Gibraltar Rainforest" project, a research initiative utilizing artificial intelligence for ecological monitoring and species identification within the Upper Rock Nature Reserve. This guide is intended for new system administrators and developers contributing to the project.
Project Overview
The "AI in the Gibraltar Rainforest" project employs a network of sensor nodes (described in Sensor Network Deployment) collecting data on environmental conditions, audio recordings, and visual imagery. This data is processed by a centralized server cluster to identify species, detect anomalies, and provide real-time insights into the rainforest ecosystem. The project relies heavily on Machine Learning Models and Data Storage Solutions. The initial phase focuses on bird song identification using Audio Analysis Techniques.
Server Infrastructure
The server infrastructure consists of three primary server roles: Data Ingestion, Processing, and Web Interface. These roles are distributed across a cluster of physical servers housed within a secure, climate-controlled data center at the University of Gibraltar. Redundancy is built in at each layer to ensure high availability. Details on Network Topology are available in a separate document.
Data Ingestion Servers
These servers are responsible for receiving data streams from the sensor network. They perform initial data validation and buffering before passing the data to the processing servers.
| Server Name | Role | Operating System | CPU | RAM | Storage |
|---|---|---|---|---|---|
| gib-di-01 | Data Ingestion (Primary) | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 4 TB NVMe SSD (RAID 1) |
| gib-di-02 | Data Ingestion (Secondary/Failover) | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 4 TB NVMe SSD (RAID 1) |
The ingestion servers utilize Message Queueing Protocol (MQTT) for receiving data from the sensors. Security Protocols are implemented to ensure data integrity and prevent unauthorized access.
Processing Servers
These servers perform the core AI processing tasks, including data analysis, model training, and species identification. They leverage GPU acceleration for faster processing.
| Server Name | Role | Operating System | CPU | RAM | GPU | Storage |
|---|---|---|---|---|---|---|
| gib-ps-01 | AI Processing (Primary) | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | NVIDIA RTX A6000 (48 GB VRAM) | 8 TB NVMe SSD (RAID 10) |
| gib-ps-02 | AI Processing (Secondary) | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | NVIDIA RTX A6000 (48 GB VRAM) | 8 TB NVMe SSD (RAID 10) |
These servers utilize Python Libraries such as TensorFlow and PyTorch. Model Version Control is crucial for managing and deploying updated AI models.
Web Interface Server
This server hosts the web interface for visualizing data and interacting with the AI system. It provides a user-friendly dashboard for researchers and stakeholders.
| Server Name | Role | Operating System | CPU | RAM | Web Server | Storage |
|---|---|---|---|---|---|---|
| gib-wi-01 | Web Interface | Ubuntu Server 22.04 LTS | Intel Xeon E-2336 (8 cores) | 32 GB DDR4 ECC | Nginx | 2 TB SSD |
The web interface is developed using Web Development Frameworks and utilizes a RESTful API to communicate with the processing servers. User Authentication is implemented to control access to sensitive data.
Software Stack
The following software components are essential to the server configuration:
- Operating System: Ubuntu Server 22.04 LTS
- Database: PostgreSQL 14 (for storing metadata and processed data) - See Database Schema Documentation
- Message Queue: RabbitMQ (for asynchronous communication between servers)
- Web Server: Nginx
- Programming Languages: Python 3.9, JavaScript
- AI Frameworks: TensorFlow, PyTorch
- Monitoring Tools: Prometheus, Grafana – See Server Monitoring Guide
Data Flow
1. Sensor nodes transmit data to the Data Ingestion Servers via MQTT. 2. Data Ingestion Servers validate and buffer the data, then publish it to RabbitMQ. 3. Processing Servers consume data from RabbitMQ, perform AI processing, and store results in PostgreSQL. 4. The Web Interface Server retrieves data from PostgreSQL via a RESTful API and presents it to users.
Future Considerations
- Scaling the infrastructure to accommodate increasing data volumes.
- Implementing a more robust disaster recovery plan.
- Exploring the use of containerization technologies (e.g., Docker) for easier deployment and management.
- Integration with Cloud Storage Solutions for long-term data archiving.
Server Security Best Practices are regularly updated and should be reviewed by all administrators.
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.* ⚠️