AI in the East Timor Rainforest
# AI in the East Timor Rainforest: Server Configuration
This document details the server configuration for the "AI in the East Timor Rainforest" project, designed to process data from a network of sensors deployed within the rainforest. This setup focuses on robust data collection, real-time analysis, and long-term storage. This guide is intended for newcomers to our MediaWiki site and outlines the key components and their configurations.
Project Overview
The project aims to leverage Artificial Intelligence (AI) to monitor biodiversity, detect illegal logging, and predict potential wildfires within the East Timor rainforest. Data is collected from various sensor types, including acoustic sensors, thermal cameras, and environmental monitors. These sensors transmit data wirelessly to a central server cluster located in Dili, East Timor. The AI models, running on these servers, analyze the incoming data in near real-time, triggering alerts when anomalies are detected. This requires a high-performance, reliable, and scalable server infrastructure. Understanding the network topology is crucial for troubleshooting.
Server Hardware Specifications
The server cluster consists of three primary server types: Data Acquisition Servers, Processing Servers, and Storage Servers. Each server type is optimized for its specific role.
| Server Type | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Data Acquisition Servers (x2) | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 4 TB NVMe SSD (RAID 1) | 10 Gbps Ethernet |
| Processing Servers (x3) | AMD EPYC 7543P (32 cores) | 128 GB DDR4 ECC | 1 TB NVMe SSD (OS) + 4 TB HDD (Data Cache) | 25 Gbps Ethernet |
| Storage Servers (x2) | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | 48 TB SAS HDD (RAID 6) | 10 Gbps Ethernet |
These specifications are based on current hardware availability and are subject to change as the project evolves. See hardware procurement for details on the purchase process. Regular server maintenance is essential.
Software Stack
The software stack is built around a Linux-based operating system, utilizing open-source tools wherever possible.
- Operating System: Ubuntu Server 22.04 LTS – chosen for its stability, security updates, and extensive community support. Refer to the OS installation guide for details.
- Database: PostgreSQL 14 – used for storing sensor data and metadata. We utilize database replication for redundancy.
- AI Framework: TensorFlow 2.10 and PyTorch 1.12 – provides the necessary tools for developing and deploying the AI models. See the AI model deployment documentation.
- Message Queue: RabbitMQ 3.9 – used for asynchronous communication between sensor data ingestion and AI processing.
- Web Server: Nginx – serves the project’s web interface for monitoring and data visualization. Nginx configuration details are available.
- Monitoring: Prometheus and Grafana – used for real-time monitoring of server performance and application health. Consult the monitoring dashboard setup instructions.
- Firewall: A robust firewall protects the server cluster from unauthorized access.
- Intrusion Detection System: A network intrusion detection system monitors network traffic for malicious activity.
- Regular Security Audits: Regular security audits are conducted to identify and address potential vulnerabilities. See the security audit schedule.
- Data Encryption: Data is encrypted both in transit and at rest.
- Access Control: Strict access control policies are enforced to limit access to sensitive data. Consult the access control matrix.
- Telegram: @powervps Servers at a discounted price
Network Configuration
The server cluster is connected to a dedicated Gigabit Ethernet network within the Dili data center. The network is segmented into three VLANs: one for the Data Acquisition Servers, one for the Processing Servers, and one for the Storage Servers. This segmentation improves security and performance. A firewall configuration document details the specific rules in place.
| VLAN ID | Subnet | Server Types | Purpose |
|---|---|---|---|
| 10 | 192.168.10.0/24 | Data Acquisition Servers | Sensor Data Ingestion |
| 20 | 192.168.20.0/24 | Processing Servers | AI Model Execution |
| 30 | 192.168.30.0/24 | Storage Servers | Data Storage & Backup |
All servers have static IP addresses assigned via DHCP reservation. The network is monitored using network intrusion detection systems.
Data Flow
The following table outlines the typical data flow within the system:
| Step | Description | Components Involved |
|---|---|---|
| 1. Data Collection | Sensors collect data (acoustic, thermal, environmental). | Acoustic Sensors, Thermal Cameras, Environmental Monitors |
| 2. Data Transmission | Sensor data is transmitted wirelessly to the Data Acquisition Servers. | Wireless Network, Data Acquisition Servers |
| 3. Data Ingestion | Data Acquisition Servers receive and pre-process the data. | Data Acquisition Servers, RabbitMQ |
| 4. AI Processing | Pre-processed data is sent to the Processing Servers for AI analysis. | RabbitMQ, Processing Servers, TensorFlow/PyTorch |
| 5. Data Storage | Analyzed data and original sensor data are stored in the Storage Servers. | Processing Servers, Storage Servers, PostgreSQL |
| 6. Data Visualization | Data is visualized through a web interface. | Web Server, PostgreSQL, Grafana |
Security Considerations
Security is paramount, given the sensitive nature of the data collected. The following measures are in place:
Future Scalability
The server architecture is designed to be scalable. Additional Processing Servers and Storage Servers can be added as needed to accommodate increasing data volumes and processing demands. The use of containerization (Docker) and orchestration (Kubernetes) will be explored to further enhance scalability and resource utilization. See the scalability plan for detailed projections.
Server documentation index Data backup procedures Troubleshooting guide Contact information
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.* ⚠️