AI in the Guam Rainforest
AI in the Guam Rainforest: Server Configuration
This article details the server configuration supporting the "AI in the Guam Rainforest" project. This project utilizes artificial intelligence to analyze data collected from remote sensors deployed throughout the Guam rainforest, focusing on biodiversity monitoring and rapid environmental change detection. This document is intended for new contributors and system administrators familiar with basic Linux server administration.
Project Overview
The "AI in the Guam Rainforest" project depends on real-time data processing from a network of sensor nodes. These nodes collect data on temperature, humidity, acoustic signatures (for animal identification), and visual data (for plant species identification). This data is transmitted wirelessly to a central server cluster for analysis. The AI models, primarily convolutional neural networks (CNNs) and recurrent neural networks (RNNs), are deployed and managed on this cluster. Data Acquisition is a critical component, as is Sensor Calibration.
Server Hardware
The server cluster consists of three primary servers: a data ingestion server, a processing server, and a database server. Each server is physically located in a secure, climate-controlled facility at the University of Guam.
| Server Role | Hardware Specification | Operating System |
|---|
| Data Ingestion Server | CPU: Intel Xeon Silver 4210R RAM: 64GB DDR4 ECC Storage: 2 x 4TB SATA SSD (RAID 1) | Ubuntu Server 22.04 LTS |
| Processing Server | CPU: 2 x AMD EPYC 7763 RAM: 256GB DDR4 ECC GPU: 2 x NVIDIA A100 (80GB) Storage: 4 x 8TB SAS HDD (RAID 10) | CentOS Stream 9 |
| Database Server | CPU: Intel Xeon Gold 6248R RAM: 128GB DDR4 ECC Storage: 8 x 4TB SAS HDD (RAID 6) | Debian 11 |
Software Stack
The software stack is designed for scalability, reliability, and ease of maintenance. We rely heavily on containerization for consistent deployments. Containerization Best Practices are followed rigorously.
- Data Ingestion Server: Nginx (web server), RabbitMQ (message queue), Python 3.10 with Flask (API endpoints).
- Processing Server: Docker, NVIDIA Container Toolkit, CUDA Toolkit 11.8, TensorFlow 2.12, PyTorch 1.13.
- Database Server: PostgreSQL 14, pgAdmin 4.
- Implementing a distributed database solution for increased scalability and resilience.
- Exploring the use of edge computing to perform some data processing closer to the sensors.
- Integrating with other data sources, such as satellite imagery. Remote Sensing Data will be a valuable addition.
- Telegram: @powervps Servers at a discounted price
Network Configuration
The servers are connected via a dedicated 10 Gigabit Ethernet network. Firewall rules are configured using `iptables` to restrict access to only necessary ports. Network Security Protocols are implemented to secure data transmission. The network is segmented into three zones: public (for external access to the API), internal (for communication between servers), and management (for remote administration).
| Server | IP Address | Network Zone | Purpose |
|---|
| Data Ingestion Server | 192.168.1.10 | Internal | API Gateway & Data Receiver |
| Processing Server | 192.168.1.20 | Internal | AI Model Execution |
| Database Server | 192.168.1.30 | Internal | Data Storage |
| External API | 203.0.113.5 | Public | Public Access to Data |
AI Model Deployment
AI models are deployed as Docker containers on the Processing Server. We utilize NVIDIA's Triton Inference Server to optimize model serving and handle concurrent requests. Model Versioning is a crucial aspect of this process. The models are trained remotely on more powerful hardware and then pushed to the server cluster for inference. Continuous integration and continuous deployment (CI/CD) pipelines automate the model deployment process. CI/CD Pipeline Details are documented separately.
Database Schema
The database schema is designed to efficiently store and query the sensor data. PostgreSQL's JSONB data type is used to store the raw sensor readings. Time-series data is indexed using appropriate data types and indexes for fast retrieval.
| Table Name | Description | Key Columns |
|---|
| sensor_data | Stores raw sensor readings | sensor_id, timestamp, data (JSONB) |
| sensor_metadata | Stores metadata about each sensor | sensor_id, location, sensor_type |
| model_predictions | Stores predictions made by the AI models | sensor_id, timestamp, prediction_type, prediction_value |
Monitoring and Alerting
Server performance and application health are monitored using Prometheus and Grafana. Alerts are configured to notify administrators of any issues, such as high CPU usage, low disk space, or failed model deployments. Monitoring Dashboard Link provides access to real-time metrics. Alerting Configuration details defines the alerting thresholds.
Future Considerations
Server Administration Data Analysis AI Model Training Sensor Networks Database Management Network Troubleshooting Security Hardening System Updates Backup and Recovery Disaster Recovery Plan Performance Tuning User Management Log Analysis API Documentation
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.* ⚠️