AI in Reigate
- AI in Reigate: Server Configuration
This article details the server configuration powering the “AI in Reigate” project, a local initiative utilizing artificial intelligence for community benefit. This document is intended for system administrators and those contributing to the project’s infrastructure. Understanding this configuration is crucial for maintenance, scaling, and troubleshooting. Please refer to our Development Standards page before making any changes.
Overview
The “AI in Reigate” project relies on a cluster of servers located in a secure data center in Reigate, Surrey. These servers handle data ingestion, model training, inference, and API access. The chosen architecture prioritizes scalability, redundancy, and security. We use a hybrid cloud approach, with core processing handled on-premise and some data storage utilizing Cloud Storage Providers. This allows for cost optimization and data sovereignty compliance. Detailed information on our Data Privacy Policy is available.
Hardware Configuration
The core of the infrastructure consists of three primary server nodes, each with dedicated roles: Master Node, Worker Node 1, and Worker Node 2. Each node runs Ubuntu Server 22.04 LTS.
| Server Node | Role | CPU | RAM | Storage |
|---|---|---|---|---|
| Master Node | Orchestration, API Gateway, Database Server | Intel Xeon Gold 6248R (24 cores) | 128 GB DDR4 ECC | 2 x 1 TB NVMe SSD (RAID 1) |
| Worker Node 1 | Model Training, Data Preprocessing | AMD EPYC 7763 (64 cores) | 256 GB DDR4 ECC | 4 x 4 TB SATA HDD (RAID 10) + 1 x 500 GB NVMe SSD |
| Worker Node 2 | Model Inference, Real-time Data Analysis | Intel Xeon Platinum 8280 (28 cores) | 128 GB DDR4 ECC | 2 x 1 TB NVMe SSD (RAID 1) + 1 x 2 TB SATA HDD |
Networking is handled by a dedicated Gigabit Ethernet switch with link aggregation configured for increased bandwidth and redundancy. A separate Firewall Configuration document outlines security measures.
Software Stack
The software stack is built around Python 3.9 and utilizes several key libraries and frameworks. We use Docker for containerization and Kubernetes for orchestration.
| Software Component | Version | Purpose |
|---|---|---|
| Python | 3.9.18 | Core programming language |
| TensorFlow | 2.12.0 | Machine learning framework |
| PyTorch | 2.0.1 | Machine learning framework |
| Docker | 20.10.21 | Containerization |
| Kubernetes | 1.26.3 | Container orchestration |
| PostgreSQL | 14.8 | Database management system |
| Nginx | 1.23.3 | Reverse proxy and web server |
The Master Node also hosts a REST API built using Flask, providing access to the AI models. Further details on the API can be found in the API Documentation.
Database Configuration
A PostgreSQL database stores metadata, model parameters, and logging information. The database is configured with replication for high availability.
| Parameter | Value |
|---|---|
| Database Name | ai_reigate |
| User | ai_user |
| Replication Mode | Synchronous |
| Connection Pool Size | 50 |
| Backup Schedule | Daily |
Database backups are stored offsite using Backup Procedures. Access to the database is strictly controlled and monitored. Refer to the Database Security Policy for more details.
Monitoring and Logging
Comprehensive monitoring and logging are essential for maintaining the stability and performance of the system. We utilize Prometheus for metric collection and Grafana for visualization. Logs are aggregated using ELK Stack (Elasticsearch, Logstash, Kibana). Alerts are configured to notify administrators of critical issues. Details on the Alerting System are available.
Future Considerations
Planned upgrades include migrating to a GPU-accelerated server for faster model training, and exploring the use of Serverless Computing for specific tasks. We are also investigating the integration of more advanced Security Protocols.
Main Page AI Models Used Data Collection Methods Security Protocols API Documentation Development Standards Cloud Storage Providers Firewall Configuration REST API Flask Gigabit Ethernet Database Security Policy Backup Procedures Alerting System Serverless Computing Ubuntu Server Prometheus Grafana ELK Stack
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.* ⚠️