AI in the Bering Sea
- AI in the Bering Sea: Server Configuration
This article details the server configuration used to support the "AI in the Bering Sea" project, a research initiative utilizing artificial intelligence to analyze real-time data from sensors deployed in the Bering Sea. This document is designed for new server engineers joining the team and assumes a basic understanding of Linux server administration and networking. We will cover hardware, software, networking, and data storage.
Project Overview
The "AI in the Bering Sea" project involves continuous data streams from various sensors (hydrophones, temperature probes, salinity sensors, current meters, and satellite imagery) monitoring marine mammal populations, oceanographic conditions, and climate change effects. The data is processed in real-time using machine learning models to identify patterns, predict events, and provide insights to researchers. This requires a robust, scalable, and reliable server infrastructure. See also Data Acquisition Systems and Machine Learning Algorithms.
Hardware Configuration
The core of the server infrastructure consists of three primary server types: Data Ingestion Servers, Processing Servers, and Database Servers. The specifications for each are outlined below.
| Server Type | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Intel Xeon Gold 6248R (24 cores) | 128 GB DDR4 ECC | 4 x 4TB NVMe SSD (RAID 10) | 10 Gbps Ethernet | | ||||
| AMD EPYC 7763 (64 cores) | 256 GB DDR4 ECC | 8 x 8TB NVMe SSD (RAID 10) + 2 x 16TB HDD (Backup) | 25 Gbps Ethernet | | ||||
| Intel Xeon Platinum 8280 (28 cores) | 512 GB DDR4 ECC | 12 x 4TB NVMe SSD (RAID 6) | 10 Gbps Ethernet | |
These servers are housed in a dedicated, climate-controlled server room with redundant power supplies and UPS backup. See also Server Room Requirements and Redundancy Planning.
Software Stack
The software stack is built around a Linux base, utilizing containerization for application deployment and management.
- Operating System: Ubuntu Server 22.04 LTS (Long Term Support)
- Containerization: Docker and Kubernetes are used for application deployment and orchestration. See Docker Basics and Kubernetes Tutorial.
- Programming Languages: Python 3.9 is the primary language used for data processing and machine learning. R is used for statistical analysis.
- Machine Learning Frameworks: TensorFlow and PyTorch are used for developing and deploying machine learning models. See TensorFlow Installation and PyTorch Setup.
- Database: PostgreSQL 14 with the PostGIS extension is used for storing and managing spatial and temporal data. See PostgreSQL Administration.
- Monitoring: Prometheus and Grafana are used for system monitoring and alerting. See Prometheus Configuration and Grafana Dashboards.
Networking Configuration
The server infrastructure is connected to the internet via a dedicated 1 Gbps fiber optic connection. Internal networking is handled by a VLAN-configured network switch.
| VLAN ID | Subnet | Description |
|---|---|---|
| 192.168.10.0/24 | Data Ingestion Servers | | ||
| 192.168.20.0/24 | Processing Servers | | ||
| 192.168.30.0/24 | Database Servers | | ||
| 192.168.40.0/24 | Management Network | |
Firewall rules are configured using `iptables` to restrict access to the servers. Regular security audits are conducted. See Firewall Configuration and Network Security Best Practices. A reverse proxy (Nginx) is used to provide secure access to web-based interfaces. See Nginx Configuration.
Data Storage and Backup
Data is stored on NVMe SSDs in a RAID configuration for performance and redundancy. Regular backups are performed to a separate offsite storage location.
| Backup Type | Frequency | Retention Period | Storage Location |
|---|---|---|---|
| Weekly | 6 Months | Offsite Cloud Storage | | |||
| Daily | 1 Month | Local NAS | | |||
| Hourly | 7 Days | Local NAS | |
Backup procedures are documented and tested regularly. Data encryption is used both in transit and at rest. See Backup and Recovery Procedures and Data Encryption Standards. Consider utilizing Data Archiving Strategies for long-term data preservation.
Security Considerations
Security is paramount. All servers are hardened according to industry best practices. Regular vulnerability scans are performed. Access to the servers is restricted based on the principle of least privilege. Multi-factor authentication is required for all administrative access. See Server Hardening Guide and Security Audit Checklist. We also utilize intrusion detection systems (IDS) and intrusion prevention systems (IPS). See IDS/IPS Implementation.
Future Expansion
As the project grows, the server infrastructure will be scaled accordingly. Future expansion plans include adding more Processing Servers and increasing the storage capacity. We are also exploring the use of cloud-based services for certain workloads. See Scalability Planning and Cloud Integration Strategies.
Server Maintenance Troubleshooting Guide System Documentation Change Management Process Monitoring Alerts Capacity Planning
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.* ⚠️