AI in the Philippine Rainforest
- AI in the Philippine Rainforest: Server Configuration
This article details the server configuration used to support the "AI in the Philippine Rainforest" project, a research initiative employing artificial intelligence for biodiversity monitoring and conservation efforts. This guide is intended for newcomers to our MediaWiki site and provides a technical overview of the infrastructure powering this project.
Project Overview
The "AI in the Philippine Rainforest" project utilizes a network of remote sensors (acoustic, visual, and environmental) deployed throughout selected rainforest locations in the Philippines. Data from these sensors is transmitted to a central server cluster for processing using machine learning algorithms. These algorithms identify species, monitor population trends, and detect potential threats to the ecosystem, such as illegal logging or poaching. Data Acquisition is a critical component. Species Identification relies heavily on the server's processing power. Conservation Efforts are informed by the server's output. Rainforest Ecology provides the context for the project.
Server Infrastructure
The server infrastructure is a hybrid cloud setup, utilizing both on-premise hardware for initial data ingestion and processing, and cloud-based resources for long-term storage, model training, and computationally intensive tasks. The primary operating system is Ubuntu Server 22.04 LTS. Network Topology is documented separately. Security Protocols are vital to protecting the data.
On-Premise Servers
These servers are located in a secure facility near the research base in Palawan. They are responsible for receiving data streams from the sensor network, performing initial data validation, and pre-processing.
| Server Role | Hardware Specifications | Software |
|---|---|---|
| Data Ingestion Server | CPU: Intel Xeon Silver 4310 (12 Cores) RAM: 64GB DDR4 ECC Storage: 2 x 4TB NVMe SSD (RAID 1) |
Ubuntu Server 22.04 LTS, MQTT Broker (Mosquitto), Node-RED |
| Pre-Processing Server | CPU: AMD EPYC 7302P (16 Cores) RAM: 128GB DDR4 ECC Storage: 4 x 2TB NVMe SSD (RAID 10) GPU: NVIDIA Tesla T4 |
Ubuntu Server 22.04 LTS, Python 3.10, Pandas, NumPy, Scikit-learn |
| Database Server | CPU: Intel Xeon Gold 6248R (24 Cores) RAM: 256GB DDR4 ECC Storage: 8 x 4TB SAS HDD (RAID 6) |
Ubuntu Server 22.04 LTS, PostgreSQL 14 |
Cloud Resources
We utilize Amazon Web Services (AWS) for cloud-based resources. These resources provide scalability and cost-effectiveness for long-term data storage and model training. AWS Account Management is handled by the IT department.
| Service | Configuration | Purpose |
|---|---|---|
| Amazon S3 | Standard Storage Class, Lifecycle Policies for Archiving | Long-term storage of raw sensor data and processed datasets. Data Backup strategy is integrated with S3. |
| Amazon EC2 | p3.8xlarge instances (4 NVIDIA V100 GPUs) | Model training and hyperparameter tuning. Machine Learning Frameworks are deployed here. |
| Amazon RDS | PostgreSQL 14, Multi-AZ deployment | Backup of the on-premise database and serving as a read-replica for reporting. Database Replication is configured. |
Software Stack
The software stack is designed for flexibility and scalability. We prioritize open-source technologies wherever possible. Version Control is managed using Git.
| Component | Version | Description |
|---|---|---|
| Operating System | Ubuntu Server 22.04 LTS | Server operating system providing a stable and secure base. |
| Programming Language | Python 3.10 | Primary language for data processing, machine learning, and scripting. |
| Machine Learning Framework | TensorFlow 2.9 | Deep learning framework used for species identification and anomaly detection. |
| Data Analysis Libraries | Pandas, NumPy, Scikit-learn | Libraries for data manipulation, numerical computation, and machine learning algorithms. |
| Database System | PostgreSQL 14 | Relational database for storing sensor data, metadata, and results. |
| Message Broker | Mosquitto | Lightweight MQTT broker for real-time data ingestion. |
Future Enhancements
Planned enhancements include integrating edge computing capabilities to process data directly at the sensor locations, reducing latency and bandwidth requirements. Edge Computing Implementation is under investigation. We also plan to explore federated learning techniques to train models without centralizing sensitive data. Federated Learning Research is ongoing. Data Visualization Tools will be improved to provide more insightful reports. Power Consumption is being monitored and optimized.
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.* ⚠️