AI in the Laotian Rainforest
- AI in the Laotian Rainforest: Server Configuration
This article details the server configuration supporting the "AI in the Laotian Rainforest" project. This project uses artificial intelligence to analyze data collected from remote sensors deployed within the Lao People's Democratic Republic’s rainforests, focusing on biodiversity monitoring, illegal logging detection, and climate change impact assessment. This guide is intended for new contributors and system administrators assisting with maintaining the project's infrastructure. Understanding the server specifications and software stack is crucial for effective system maintenance and troubleshooting.
Project Overview
The "AI in the Laotian Rainforest" project relies on a distributed server architecture. Data is initially collected by low-power sensors and transmitted via satellite links to a central aggregation point. This data is then processed by a cluster of servers located in a secure data center in Vientiane, Laos. The processing pipeline involves data cleaning, feature extraction, and the application of machine learning models. The results are then visualized and made available to researchers and conservationists via a web-based interface. Data security is paramount given the sensitivity of the collected information. Network architecture plays a vital role in data transfer rates.
Server Hardware Specifications
The server cluster consists of four primary server types: Data Ingestion Servers, Processing Servers, Database Servers, and Web Servers. Each server type is configured with specific hardware to meet its respective workload requirements.
| Server Type | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Data Ingestion Servers (x2) | Intel Xeon Silver 4310 (12 Cores) | 64 GB DDR4 ECC | 4TB NVMe SSD (RAID 1) | 10 Gbps Ethernet |
| Processing Servers (x4) | AMD EPYC 7763 (64 Cores) | 256 GB DDR4 ECC | 8TB NVMe SSD (RAID 0) + 16TB HDD (RAID 5) | 25 Gbps Ethernet + Infiniband |
| Database Servers (x2) | Intel Xeon Gold 6338 (32 Cores) | 128 GB DDR4 ECC | 32TB SAS HDD (RAID 6) | 10 Gbps Ethernet |
| Web Servers (x2) | Intel Xeon E-2336 (8 Cores) | 32 GB DDR4 ECC | 1TB NVMe SSD | 1 Gbps Ethernet |
This configuration is regularly reviewed and updated based on project needs and available hardware advancements. Power consumption is carefully monitored to minimize operational costs and environmental impact.
Software Stack
The servers run a customized Linux distribution based on Ubuntu Server 22.04 LTS. The core software components include:
- Operating System: Ubuntu Server 22.04 LTS
- Database: PostgreSQL 14 with PostGIS extension for geospatial data.
- Programming Languages: Python 3.9, R 4.2.0
- Machine Learning Frameworks: TensorFlow 2.9, PyTorch 1.12, scikit-learn
- Web Server: Apache 2.4
- Web Framework: Django 4.0
- Data Pipeline: Apache Kafka for message queuing, Apache Spark for distributed data processing.
- Monitoring: Prometheus and Grafana for system monitoring and alerting.
- Version Control: Git for code management, hosted on a private GitLab instance.
- Containerization: Docker and Kubernetes are used for deploying and managing microservices.
Regular software updates and security patches are applied to maintain system integrity.
Network Configuration
The server cluster is connected to the internet via a redundant fiber optic connection with a bandwidth of 1 Gbps. A firewall is implemented to protect the servers from unauthorized access. The internal network is segmented to isolate different server types and enhance security. Network security is a high priority.
| Network Component | IP Address Range | Subnet Mask | Gateway |
|---|---|---|---|
| Data Ingestion Servers | 192.168.1.10 - 192.168.1.11 | 255.255.255.0 | 192.168.1.1 |
| Processing Servers | 192.168.2.10 - 192.168.2.13 | 255.255.255.0 | 192.168.2.1 |
| Database Servers | 192.168.3.10 - 192.168.3.11 | 255.255.255.0 | 192.168.3.1 |
| Web Servers | 192.168.4.10 - 192.168.4.11 | 255.255.255.0 | 192.168.4.1 |
Detailed network diagrams are available on the project’s internal wiki.
Data Storage and Backup
All data is backed up daily to an offsite location. The backup strategy includes full backups performed weekly and incremental backups performed daily. Data is encrypted both in transit and at rest. Data recovery procedures are regularly tested to ensure data integrity. The backup system utilizes rsync and borgbackup for efficient and secure data archiving. Disaster recovery plans are in place to handle potential outages.
| Backup Type | Frequency | Retention Period | Location |
|---|---|---|---|
| Full Backup | Weekly | 3 Months | Offsite Data Center |
| Incremental Backup | Daily | 1 Month | Offsite Data Center |
Future Considerations
Future upgrades will include the implementation of a GPU cluster to accelerate machine learning model training. We are also exploring the use of cloud-based storage for long-term data archiving. Scalability is a key consideration for the project’s long-term success.
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.* ⚠️