AI in the Macau Rainforest
# AI in the Macau Rainforest: Server Configuration
This article details the server configuration powering the "AI in the Macau Rainforest" project. This project utilizes artificial intelligence to monitor and analyze ecological data collected from sensors deployed within the Macau Rainforest. This document is aimed at newcomers to our MediaWiki site and provides a detailed technical overview of the server infrastructure.
Overview
The "AI in the Macau Rainforest" project relies on a distributed server architecture to handle the large volume of data generated by the sensor network. Data is collected, pre-processed, analyzed by AI models, and visualized through a web interface. The system is designed for high availability, scalability, and data integrity. We utilize a combination of physical and virtual servers to optimize performance and cost-effectiveness. Server Architecture dictates this layered approach.
Hardware Specifications
The core of the system consists of three primary server types: Data Ingestion Servers, AI Processing Servers, and Web Application Servers. Each server type has specific hardware requirements to meet its designated 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 |
| AI Processing Servers | 2 x NVIDIA Tesla A100 (80GB) | 256 GB DDR4 ECC | 8 TB NVMe SSD (RAID 0) | 100 Gbps InfiniBand |
| Web Application Servers | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | 2 TB NVMe SSD (RAID 1) | 1 Gbps Ethernet |
These specifications are subject to change based on project needs and hardware availability. Regular Hardware Monitoring is crucial.
Software Stack
The software stack is built upon a Linux foundation, utilizing open-source tools and frameworks wherever possible. We prioritize security and maintainability in our software choices. Software Licensing is strictly adhered to.
Operating System
- Ubuntu Server 22.04 LTS (Long Term Support) is our standard operating system. We chose Ubuntu for its stability, security updates, and extensive package repository. Operating System Security is paramount.
- Apache Kafka is used as a distributed streaming platform to ingest data from the sensor network.
- Apache NiFi handles data flow management, preprocessing, and routing to the AI processing servers.
- PostgreSQL is used as the primary database for storing raw sensor data and metadata.
- Python 3.9 is the primary programming language for developing and deploying AI models.
- TensorFlow and PyTorch are the deep learning frameworks used for model training and inference.
- CUDA is utilized to accelerate AI computations on NVIDIA GPUs.
- Flask is a lightweight Python web framework used to build the web application.
- Nginx serves as the web server and reverse proxy.
- Docker is used for containerization and deployment of the web application and other services.
- Prometheus is used for monitoring server performance and application metrics.
- Implementing a serverless architecture for certain components.
- Exploring the use of edge computing to reduce latency and bandwidth costs.
- Integrating with Cloud Computing Platforms for increased scalability and resilience.
- Automating more aspects of server management using tools like Ansible.
- Telegram: @powervps Servers at a discounted price
Data Ingestion
AI Processing
Web Application
Network Configuration
The server network is segmented into three zones: public, DMZ (Demilitarized Zone), and private.
| Zone | Purpose | Firewall Rules |
|---|---|---|
| Public | Internet access for web application. | Allow HTTP/HTTPS traffic to web application servers. |
| DMZ | Hosts web application servers. | Limited access to private network, only necessary ports open. |
| Private | Hosts data ingestion and AI processing servers. | Strict access control, only authorized servers can communicate. |
All network traffic is encrypted using TLS/SSL. Network Security Protocols are updated regularly. We utilize a dedicated Virtual Private Network (VPN) for remote access to the private network.
Data Storage & Backup
Data is stored in a tiered storage system. Raw sensor data is stored in PostgreSQL, while pre-processed data and AI model outputs are stored in object storage using MinIO.
| Storage Tier | Type | Capacity | Redundancy |
|---|---|---|---|
| Tier 1 (Hot) | PostgreSQL | 10 TB | Replication, Backups |
| Tier 2 (Warm) | MinIO | 50 TB | Erasure Coding, Backups |
| Tier 3 (Cold) | Tape Storage | 100 TB | Offsite Storage |
Regular backups are performed and stored offsite to protect against data loss. Data Backup Procedures are documented and tested regularly. Disaster Recovery Plan details the steps to restore service in case of a major outage.
Future Considerations
We are continually evaluating new technologies to improve the performance, scalability, and security of the system. Future considerations include:
Server Maintenance is a continuous process.
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.* ⚠️