AI in the Northern Ireland Rainforest
AI in the Northern Ireland Rainforest: Server Configuration
This article details the server configuration supporting the "AI in the Northern Ireland Rainforest" project. This project utilizes artificial intelligence to monitor and analyze data collected from sensors deployed within the unique Northern Ireland rainforest environment. This documentation is aimed at newcomers to the MediaWiki site and assumes a basic understanding of server administration. See Help:Contents for general information on using this wiki.
Project Overview
The “AI in the Northern Ireland Rainforest” project aims to provide real-time data analysis on biodiversity, microclimate patterns, and potential threats to the rainforest ecosystem. Data is collected from a network of sensor nodes, transmitted wirelessly, and processed by a central server cluster. The AI models employed include machine learning algorithms for species identification (using acoustic monitoring data) and predictive modelling for identifying potential environmental changes. Understanding the data pipeline is crucial.
Server Architecture
The server infrastructure consists of three primary tiers:
1. **Ingestion Tier:** Receives and validates data from sensor nodes. 2. **Processing Tier:** Executes AI models and performs data analysis. 3. **Storage Tier:** Persists processed data and model outputs.
These tiers are implemented using a distributed architecture to ensure scalability and reliability. We utilize load balancing across multiple servers within each tier. The system is monitored using Nagios and alerts are managed through PagerDuty.
Ingestion Tier Configuration
The ingestion tier is responsible for receiving data streams from the sensor network. It’s built on a cluster of three servers running Nginx as a reverse proxy and message queueing software.
| Server Role | Operating System | CPU | Memory | Storage |
|---|---|---|---|---|
| Ingestion Server 1 | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 | 64 GB DDR4 ECC | 2 x 1 TB SSD (RAID 1) |
| Ingestion Server 2 | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 | 64 GB DDR4 ECC | 2 x 1 TB SSD (RAID 1) |
| Ingestion Server 3 | Ubuntu Server 22.04 LTS | Intel Xeon Silver 4310 | 64 GB DDR4 ECC | 2 x 1 TB SSD (RAID 1) |
Software components include:
- Nginx: Handles incoming connections and distributes load.
- RabbitMQ: A message broker for asynchronous communication. See RabbitMQ documentation for more information.
- Custom Python scripts: Validate data format and push messages to RabbitMQ. These scripts utilize the requests library.
Processing Tier Configuration
The processing tier houses the AI models and performs the core data analysis tasks. This tier utilizes GPU-accelerated servers to handle the computationally intensive machine learning workloads. We leverage Kubernetes for container orchestration.
| Server Role | Operating System | CPU | Memory | GPU | Storage |
|---|---|---|---|---|---|
| Processing Server 1 | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 | 128 GB DDR4 ECC | NVIDIA A100 (40GB) | 2 x 2 TB NVMe SSD (RAID 0) |
| Processing Server 2 | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 | 128 GB DDR4 ECC | NVIDIA A100 (40GB) | 2 x 2 TB NVMe SSD (RAID 0) |
| Processing Server 3 | Ubuntu Server 22.04 LTS | Intel Xeon Gold 6338 | 128 GB DDR4 ECC | NVIDIA A100 (40GB) | 2 x 2 TB NVMe SSD (RAID 0) |
Key software components:
- Python 3.9: The primary programming language for AI models.
- TensorFlow/PyTorch: Deep learning frameworks. See TensorFlow documentation and PyTorch documentation.
- Kubernetes: Container orchestration platform.
- Docker: Containerization technology.
- Prometheus: For monitoring resource utilization. It integrates well with Grafana.
Storage Tier Configuration
The storage tier provides persistent storage for processed data, model outputs, and historical sensor readings. It utilizes a distributed object storage system for scalability and durability.
| Server Role | Operating System | CPU | Memory | Storage |
|---|---|---|---|---|
| Storage Server 1 | CentOS Stream 9 | Intel Xeon Silver 4310 | 32 GB DDR4 ECC | 8 x 8 TB HDD (RAID 6) |
| Storage Server 2 | CentOS Stream 9 | Intel Xeon Silver 4310 | 32 GB DDR4 ECC | 8 x 8 TB HDD (RAID 6) |
| Storage Server 3 | CentOS Stream 9 | Intel Xeon Silver 4310 | 32 GB DDR4 ECC | 8 x 8 TB HDD (RAID 6) |
Software components:
- MinIO: An object storage server compatible with Amazon S3. See MinIO documentation.
- PostgreSQL: A relational database for metadata and configuration data. We utilize PostGIS for geospatial data.
- Backup system: Regularly backs up data to offsite storage. We use rsync for backups.
Network Configuration
All servers are interconnected via a dedicated Gigabit Ethernet network. A firewall is configured to restrict access to only necessary ports. We employ VLANs to segment the network for security. The network is monitored using Wireshark for troubleshooting.
Security Considerations
Security is paramount. All servers are hardened according to best practices. Regular security audits are conducted. Access control is strictly enforced. We utilize fail2ban to mitigate brute-force attacks.
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.* ⚠️