AI in Dorset
```wiki
- REDIRECT AI in Dorset
AI in Dorset: Server Configuration & Technical Overview
This article details the server configuration supporting the "AI in Dorset" project, a local initiative focused on applying artificial intelligence to issues facing Dorset County. This documentation is intended for new system administrators and developers contributing to the project. It outlines the hardware, software, and network configuration.
Project Overview
The "AI in Dorset" project utilizes machine learning models to analyze local data sources, including weather patterns, traffic flow, and demographic information. The goal is to provide insights for improved resource allocation, disaster preparedness, and economic development. The server infrastructure is designed for scalability, reliability, and security. See Data Security Policy for more details on data handling.
Hardware Specification
The core server infrastructure consists of three primary servers, each with a specific role. The following table details the hardware configuration for each:
| Server Role | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Intel Xeon Gold 6248R (24 cores) | 128GB DDR4 ECC | 2 x 2TB NVMe SSD (RAID 1) | 10Gbps Ethernet | ||||
| AMD EPYC 7763 (64 cores) | 256GB DDR4 ECC | 4 x 4TB SAS HDD (RAID 10) | 10Gbps Ethernet | ||||
| 2 x NVIDIA Tesla A100 GPUs | 512GB DDR4 ECC | 2 x 8TB NVMe SSD (RAID 0) | 25Gbps Ethernet & 10Gbps Ethernet |
All servers are housed in a dedicated, climate-controlled server room at the Dorset County Council IT facility. Power redundancy is provided by dual power supplies and a UPS system. Refer to the Server Room Access Policy for physical access procedures.
Software Stack
The software stack is built around a Linux operating system, providing a stable and flexible platform.
| Component | Version | Function | ||||
|---|---|---|---|---|---|---|
| Ubuntu Server 22.04 LTS | Server OS | Apache 2.4 | Hosting the web application | PostgreSQL 14 | Data storage and management | Python 3.10 | Backend logic and model integration | TensorFlow 2.12 | Model training and inference | Docker 24.0 | Application deployment & isolation | Kubernetes 1.27 | Container management and scaling |
The application server hosts the web-based user interface and API endpoints. The database server manages all project data. The model training server is responsible for training and updating the machine learning models. See Software Licensing Information for details on software licenses.
Network Configuration
The servers are connected to the Dorset County Council network via a dedicated VLAN. Security is paramount, and access is restricted based on the principle of least privilege.
| Parameter | Value | Description | ||
|---|---|---|---|---|
| 100 | Dedicated VLAN for the AI in Dorset project | 255.255.255.0 | Network subnet | 192.168.100.1 | Default gateway | 8.8.8.8, 8.8.4.4 | Public DNS servers | iptables | Network firewall |
The firewall is configured to allow only necessary traffic to and from the servers. Regular security audits are conducted to identify and address potential vulnerabilities. Review the Network Security Guidelines for detailed network security information. Connectivity to external data sources is managed through a secure VPN connection as defined in the VPN Configuration Guide.
Security Considerations
Security is a critical aspect of the "AI in Dorset" project. All data is encrypted at rest and in transit. Access control is enforced through strong authentication and authorization mechanisms. Regular vulnerability scans are performed to identify and mitigate potential security risks. See the Incident Response Plan for procedures to follow in the event of a security incident.
Future Scalability
The infrastructure is designed to be scalable to accommodate future growth. Kubernetes allows for easy scaling of the application and model training components. Additional servers can be added to the cluster as needed. We anticipate utilizing Cloud Computing Resources for burst capacity during peak demand. See the Capacity Planning Document for long-term scalability projections.
Related Documentation
- Data Security Policy
- Server Room Access Policy
- Software Licensing Information
- Network Security Guidelines
- VPN Configuration Guide
- Incident Response Plan
- Cloud Computing Resources
- Capacity Planning Document
- Database Backup Procedures
- Application Deployment Process
- Monitoring and Alerting System
- Troubleshooting Guide
- API Documentation
- User Access Management
- Change Management Process
```
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.* ⚠️