AI in the Palau Rainforest
AI in the Palau Rainforest: Server Configuration
This document details the server configuration for the "AI in the Palau Rainforest" project, outlining the hardware, software, and network setup used to support the real-time data processing and analysis of sensor data collected within the Palau rainforest environment. This guide is intended for new system administrators and engineers joining the project. Understanding this setup is crucial for maintenance, troubleshooting, and future scalability. See also System Administration Guide for general server management procedures.
Project Overview
The "AI in the Palau Rainforest" project utilizes a network of sensor nodes deployed throughout the rainforest to collect data on biodiversity, climate conditions, and ecosystem health. This data is streamed back to a central server cluster for processing using machine learning algorithms. The primary goals of the AI processing are species identification from audio recordings, anomaly detection in temperature and humidity data, and predictive modeling of rainforest health. Refer to the Project Goals page for more details. Data storage and access are governed by the Data Management Policy.
Hardware Configuration
The server cluster consists of three primary server types: Data Intake Servers, Processing Servers, and Database Servers. Each type is described below with detailed specifications.
Data Intake Servers
These servers are responsible for receiving data streams from the sensor nodes. They perform initial data validation and buffering before forwarding data to the processing servers. Two Data Intake Servers are currently in operation for redundancy.
| Specification | Value |
|---|---|
| Server Model | Dell PowerEdge R750 |
| CPU | 2 x Intel Xeon Gold 6338 (32 cores/64 threads per CPU) |
| RAM | 128 GB DDR4 ECC Registered |
| Storage | 2 x 1TB NVMe SSD (RAID 1) for OS and buffering |
| Network Interface | 2 x 10 GbE Ethernet |
| Operating System | Ubuntu Server 22.04 LTS |
These servers utilize a custom data intake script written in Python to manage the incoming data streams. See Data Intake Script Documentation for details.
Processing Servers
These servers execute the machine learning algorithms and perform data analysis. We currently have four processing servers, optimized for GPU-accelerated computation.
| Specification | Value |
|---|---|
| Server Model | Supermicro SYS-220M-CT |
| CPU | 2 x AMD EPYC 7763 (64 cores/128 threads per CPU) |
| RAM | 256 GB DDR4 ECC Registered |
| GPU | 4 x NVIDIA A100 (40GB) |
| Storage | 1 x 2TB NVMe SSD (OS) + 4 x 4TB SATA HDD (Data Storage) |
| Network Interface | 2 x 10 GbE Ethernet |
| Operating System | CentOS Stream 9 |
Machine learning models are developed and deployed using TensorFlow and PyTorch. See Model Deployment Guide for instructions.
Database Servers
These servers store processed data, metadata, and model outputs. We employ a clustered PostgreSQL database for high availability and scalability.
| Specification | Value |
|---|---|
| Server Model | HP ProLiant DL380 Gen10 |
| CPU | 2 x Intel Xeon Silver 4310 (12 cores/24 threads per CPU) |
| RAM | 128 GB DDR4 ECC Registered |
| Storage | 8 x 4TB SAS HDD (RAID 6) |
| Network Interface | 2 x 10 GbE Ethernet |
| Operating System | Debian 11 |
| Database | PostgreSQL 14 |
Database backups are performed nightly and stored offsite. Refer to the Backup and Recovery Plan for details. Data schemas are detailed in the Database Schema Documentation.
Software Configuration
All servers utilize a centralized logging system based on Elasticsearch, Logstash, and Kibana (the ELK stack). This allows for efficient monitoring and troubleshooting. Servers are provisioned using Ansible for automated configuration management. The version control system used for all code and configuration files is Git, hosted on a private GitLab instance. Security is managed using Firewall Configuration and regular vulnerability scanning.
Network Configuration
The server cluster is located within a dedicated VLAN on the research network. Each server has a static IP address. A load balancer distributes traffic to the Data Intake Servers. The network topology is illustrated in the Network Diagram. All communication between servers is encrypted using TLS. Network monitoring is performed using Nagios.
Future Considerations
Future plans include upgrading the Processing Server GPUs to the latest generation and exploring the use of a distributed file system like Hadoop for larger datasets. We are also investigating the integration of a real-time data visualization dashboard using Grafana. Further details about these plans can be found in the Future Development Roadmap.
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.* ⚠️