AI in Slough
- AI in Slough: Server Configuration & Deployment
This article details the server configuration for the "AI in Slough" project, a local initiative leveraging artificial intelligence for improved urban management. This guide is intended for new members of the IT team tasked with maintaining and expanding the infrastructure. It covers hardware, software, networking, and initial security considerations. Please consult the Security Policy for a full overview of security protocols.
Project Overview
The “AI in Slough” project utilizes machine learning algorithms to analyze data from various sources, including traffic cameras, environmental sensors, and public transport systems. The goal is to optimize traffic flow, predict maintenance needs, and enhance resource allocation. This requires a robust and scalable server infrastructure. See the Project Documentation for more details on the project’s aims and functionalities. The initial deployment focuses on predictive maintenance of the Slough bus fleet, as described in the Bus Fleet Integration Document.
Hardware Configuration
The server infrastructure is housed within the Slough Data Centre, section B3. We utilize a hybrid approach, combining on-premise servers with cloud-based resources for redundancy and scalability. The core on-premise infrastructure is detailed below.
| Component | Specification | Quantity |
|---|---|---|
| CPU | Intel Xeon Gold 6248R (24 cores, 3.0 GHz) | 4 |
| RAM | 256 GB DDR4 ECC Registered 2933MHz | 4 |
| Storage (OS & Applications) | 2 x 960GB NVMe SSD (RAID 1) | 4 |
| Storage (Data) | 8 x 16TB SAS HDD (RAID 6) | 1 |
| Network Interface | Dual 10GbE SFP+ | 4 |
| Power Supply | Redundant 800W Platinum PSU | 4 |
This configuration provides sufficient processing power and storage capacity for the initial phase of the project. Future expansion will likely involve scaling the cloud resources through Cloud Provider Integration.
Software Stack
The software stack is built around a Linux foundation, utilizing open-source tools wherever possible. The primary operating system is Ubuntu Server 22.04 LTS. Detailed installation guides are available on the Internal Wiki.
| Software | Version | Purpose |
|---|---|---|
| Operating System | Ubuntu Server 22.04 LTS | Server OS |
| Python | 3.10.6 | Machine Learning & Scripting |
| TensorFlow | 2.12.0 | Deep Learning Framework |
| PyTorch | 2.0.1 | Deep Learning Framework |
| PostgreSQL | 14.7 | Database Management System |
| Nginx | 1.23.3 | Web Server & Reverse Proxy |
| Docker | 20.10.17 | Containerization Platform |
All software is managed using a combination of `apt` package manager and containerization via Docker. See the Docker Best Practices document for guidelines on container image creation and deployment. We also utilize Ansible for automated configuration management.
Networking Configuration
The servers are connected to the Slough Data Centre's internal network via dual 10GbE connections. A dedicated VLAN has been created for the “AI in Slough” project (VLAN 200). All traffic is filtered through a firewall, configured according to the Firewall Rules.
| Parameter | Value |
|---|---|
| VLAN ID | 200 |
| Subnet | 192.168.200.0/24 |
| Gateway | 192.168.200.1 |
| DNS Servers | 8.8.8.8, 8.8.4.4 |
| Firewall | pfSense 2.7.2 |
Access to the servers is restricted to authorized personnel via SSH. Multi-factor authentication is enforced for all SSH connections, as detailed in the SSH Security Guidelines. Monitoring is performed using Nagios and alerts are sent to the on-call team. The network topology diagram can be found at Network Diagram Location.
Security Considerations
Security is paramount for this project. The following are key security measures in place:
- Regular security audits are conducted by the Security Team.
- All data is encrypted at rest and in transit.
- Intrusion detection and prevention systems are in place.
- Access control is strictly enforced using role-based access control (RBAC).
- All servers are patched regularly with the latest security updates.
- See the Data Privacy Policy for information on data handling and compliance.
Future Expansion
The infrastructure is designed for scalability. Future expansion may include:
- Adding more on-premise servers to handle increased data volumes.
- Expanding the cloud-based resources for burst capacity.
- Integrating with additional data sources.
- Implementing more advanced machine learning algorithms.
- Exploring edge computing solutions for real-time data processing.
Main Page Server Maintenance Schedule Troubleshooting Guide Contact IT Support
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.* ⚠️