AI in Liverpool
```wiki #REDIRECT AI in Liverpool
AI in Liverpool: Server Configuration Overview
This document details the server configuration supporting the "AI in Liverpool" project, a city-wide initiative utilizing Artificial Intelligence for improved public services and research. This guide is intended for newcomers to the MediaWiki site and provides a technical overview of the hardware and software infrastructure. Understanding this configuration is crucial for system administrators, developers, and anyone contributing to the project's technical aspects.
Project Goals and Server Requirements
The "AI in Liverpool" project encompasses several key areas: traffic management, predictive policing, environmental monitoring, and healthcare data analysis. These diverse applications place significant demands on the server infrastructure, requiring high processing power, large storage capacity, and robust networking capabilities. The core requirements are:
- Scalability: The system must be able to handle increasing data volumes and user load. Scalability considerations are paramount.
- Reliability: Uptime is critical for real-time applications like traffic management. Redundancy and failover mechanisms are essential.
- Security: Protecting sensitive data (healthcare, policing) is of utmost importance. Security protocols must be rigorously enforced.
- Performance: Low latency is crucial for responsive AI models. Performance optimization is a continuous process.
- Expanding the on-premise server cluster to accommodate growing data volumes.
- Integrating additional cloud resources for burst capacity.
- Implementing advanced security measures, such as intrusion detection and prevention systems.
- Exploring new AI frameworks and technologies.
- Disaster recovery planning to ensure business continuity.
- Telegram: @powervps Servers at a discounted price
Hardware Infrastructure
The project utilizes a hybrid cloud approach, combining on-premise servers with cloud resources for flexibility and cost-effectiveness. The on-premise infrastructure consists of a cluster of high-performance servers located in a secure data center.
| Server Role | Hardware Specifications | Quantity |
|---|
| Core Processing Servers || CPU: Dual Intel Xeon Platinum 8380 (40 cores/80 threads) RAM: 512GB DDR4 ECC Registered Storage: 4 x 4TB NVMe SSD (RAID 10) || 6 |
| Data Storage Servers || CPU: Dual Intel Xeon Gold 6338 (32 cores/64 threads) RAM: 256GB DDR4 ECC Registered Storage: 24 x 16TB SAS HDD (RAID 6) || 3 |
| Network Servers || CPU: Intel Xeon E-2388G (8 cores/16 threads) RAM: 64GB DDR4 ECC Registered Network: Dual 100GbE Network Interface Cards || 2 |
| GPU Acceleration Servers || CPU: Intel Xeon Gold 6330 (28 cores/56 threads) RAM: 128GB DDR4 ECC Registered GPU: 4 x NVIDIA A100 (80GB) || 4 |
These servers are interconnected via a high-speed 100GbE network backbone. Power redundancy is provided by multiple UPS systems and a backup generator. Detailed server racking diagrams are available in the data center documentation.
Software Stack
The software stack is designed for flexibility and ease of management. A layered approach is employed, with virtualization and containerization playing key roles.
| Layer | Software | Version |
|---|
| Operating System || Ubuntu Server || 22.04 LTS |
| Virtualization || Proxmox VE || 7.4 |
| Containerization || Docker || 20.10 |
| Orchestration || Kubernetes || 1.24 |
| Database || PostgreSQL || 14 |
| AI Frameworks || TensorFlow, PyTorch || Latest Stable Releases |
The servers are virtualized using Proxmox VE, allowing for efficient resource allocation and isolation. Docker containers are used to package and deploy AI models and applications. Kubernetes orchestrates the containers, providing scalability and high availability. Database schema documentation is available separately.
Networking Configuration
The network is segmented into several VLANs to isolate different components of the system and enhance security.
| VLAN ID | Description | Subnet |
|---|
| 10 || Management Network || 192.168.10.0/24 |
| 20 || Core Application Network || 10.0.20.0/16 |
| 30 || Data Storage Network || 10.0.30.0/24 |
| 40 || GPU Acceleration Network || 10.0.40.0/24 |
A firewall is deployed at the perimeter of the network to protect against external threats. Internal firewalls are used to control traffic between VLANs. All network traffic is monitored and logged for security and auditing purposes. Refer to the network topology documentation for a visual representation of the network.
Future Considerations
The "AI in Liverpool" project is constantly evolving. Future plans include:
This document provides a snapshot of the current server configuration. Regular updates will be published to reflect changes and improvements. Please consult the project documentation portal for the latest information. For specific questions, please contact the system administration team. Troubleshooting guide is also available.
```
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 configurationNeed Assistance?
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️