AI in the Zambezi River
- AI in the Zambezi River: Server Infrastructure Documentation
This document details the server configuration supporting the "AI in the Zambezi River" project, a research initiative utilizing artificial intelligence to monitor and analyze the health of the Zambezi River ecosystem. This guide is intended for new members of the support team and outlines the hardware, software, and network configuration. Please familiarize yourself with these details to ensure smooth operation and maintenance of the system.
Project Overview
The “AI in the Zambezi River” project uses a network of sensor buoys deployed along the Zambezi River to collect data on water quality, fish populations, and other environmental factors. This data is transmitted wirelessly to a central server farm for processing using machine learning algorithms. The goal is to create a real-time monitoring system that can detect pollution events, predict flooding, and provide insights into the long-term health of the river. See also Data Acquisition Systems and Machine Learning Algorithms.
Server Hardware Configuration
The core of the system resides in a dedicated server farm located in Lusaka, Zambia. The farm consists of three primary server types: data ingestion servers, processing servers, and database servers. Redundancy is built into the system with multiple servers of each type.
Data Ingestion Servers: These servers receive data from the sensor buoys via a LoRaWAN network.
Processing Servers: These servers run the machine learning algorithms that analyze the data.
Database Servers: These servers store the raw data, processed data, and model outputs.
The following table details the specifications for each server type:
| Server Type | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Intel Xeon Silver 4310 | 64 GB DDR4 | 2 x 2TB NVMe SSD (RAID 1) | 10GbE | ||||
| AMD EPYC 7763 | 256 GB DDR4 | 4 x 4TB NVMe SSD (RAID 10) | 10GbE | ||||
| Intel Xeon Gold 6338 | 128 GB DDR4 | 8 x 8TB SAS HDD (RAID 6) | 10GbE |
Please consult the Hardware Inventory for a complete list of individual servers and their serial numbers.
Software Stack
The software stack is built around a Linux operating system, specifically Ubuntu Server 22.04 LTS. The following software components are key to the system’s operation:
- Operating System: Ubuntu Server 22.04 LTS
- Database: PostgreSQL 14 with PostGIS extension for geospatial data. See PostgreSQL Documentation for details.
- Programming Languages: Python 3.8 with libraries such as TensorFlow, PyTorch, and scikit-learn.
- Data Ingestion: Custom Python scripts utilizing the LoRaWAN protocol. See LoRaWAN Integration Guide.
- Web Server: Nginx for serving the web interface. Refer to Nginx Configuration for details.
- Monitoring: Prometheus and Grafana for system monitoring and alerting. See Prometheus Setup and Grafana Dashboards.
Network Configuration
The server farm is connected to the internet via a dedicated fiber optic connection. The network is segmented into three VLANs:
- VLAN 10: Data Ingestion Servers
- VLAN 20: Processing Servers
- VLAN 30: Database Servers
A firewall is implemented to restrict access between VLANs and to the internet. The firewall rules are documented in Firewall Configuration. Internal communication between servers within the same VLAN is permitted. The network topology is visually represented in the Network Diagram.
The following table summarizes the key network parameters:
| Parameter | Value |
|---|---|
| Internet Connection | 1 Gbps Fiber Optic |
| Router IP Address | 192.168.1.1 |
| DNS Servers | 8.8.8.8, 8.8.4.4 |
| VLAN 10 Subnet | 10.0.10.0/24 |
| VLAN 20 Subnet | 10.0.20.0/24 |
| VLAN 30 Subnet | 10.0.30.0/24 |
Security Considerations
Security is paramount for this project. The following security measures are in place:
- Firewall: A robust firewall is configured to restrict access to the servers.
- Intrusion Detection System (IDS): An IDS is deployed to detect and prevent malicious activity. See IDS Implementation.
- Regular Security Audits: Regular security audits are conducted to identify and address vulnerabilities.
- Data Encryption: Data is encrypted both in transit and at rest.
- Access Control: Strict access control policies are enforced. See Access Control Lists.
Backup and Disaster Recovery
A comprehensive backup and disaster recovery plan is in place. Daily backups of the database are performed and stored offsite. Regular disaster recovery drills are conducted to ensure the system can be restored quickly in the event of a failure. The backup schedule is detailed in Backup Procedures.
The following table outlines the backup retention policy:
| Backup Type | Retention Period |
|---|---|
| Daily Backups | 7 days |
| Weekly Backups | 4 weeks |
| Monthly Backups | 12 months |
Future Enhancements
Planned future enhancements include:
- Scaling the Server Farm: Adding additional servers to handle increasing data volumes.
- Implementing a Distributed Database: Using a distributed database to improve scalability and availability.
- Integrating with Additional Sensor Networks: Expanding the sensor network to cover a larger area of the Zambezi River. See Sensor Network Expansion Plan.
Main Page Server Maintenance 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 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.* ⚠️